references.bib

% Generated by Paperpile. Check out https://paperpile.com for more information.
% BibTeX export options can be customized via Settings -> BibTeX.

@MANUAL{R_Development_Core_Team2008-gd,
  title        = "R: a language and environment for statistical computing",
  author       = "{R Development Core Team}",
  year         =  2008,
  keywords     = "Holo-Omics",
  organization = "Vienna, Austria"
}

@ARTICLE{Kircher2012-vy,
  title    = "Double indexing overcomes inaccuracies in multiplex sequencing on
              the Illumina platform",
  author   = "Kircher, Martin and Sawyer, Susanna and Meyer, Matthias",
  abstract = "Due to the increasing throughput of current DNA sequencing
              instruments, sample multiplexing is necessary for making
              economical use of available sequencing capacities. A widely used
              multiplexing strategy for the Illumina Genome Analyzer utilizes
              sample-specific indexes, which are embedded in one of the library
              adapters. However, this and similar multiplex approaches come
              with a risk of sample misidentification. By introducing indexes
              into both library adapters (double indexing), we have developed a
              method that reveals the rate of sample misidentification within
              current multiplex sequencing experiments. With ~0.3\% these rates
              are orders of magnitude higher than expected and may severely
              confound applications in cancer genomics and other fields
              requiring accurate detection of rare variants. We identified the
              occurrence of mixed clusters on the flow as the predominant
              source of error. The accuracy of sample identification is further
              impaired if indexed oligonucleotides are cross-contaminated or if
              indexed libraries are amplified in bulk. Double-indexing
              eliminates these problems and increases both the scope and
              accuracy of multiplex sequencing on the Illumina platform.",
  journal  = "Nucleic Acids Res.",
  volume   =  40,
  number   =  1,
  pages    = "e3",
  month    =  jan,
  year     =  2012,
  keywords = "Holo-Omics",
  language = "en"
}

@ARTICLE{Jones2015-bk,
  title    = "Library preparation methodology can influence genomic and
              functional predictions in human microbiome research",
  author   = "Jones, Marcus B and Highlander, Sarah K and Anderson, Ericka L
              and Li, Weizhong and Dayrit, Mark and Klitgord, Niels and Fabani,
              Martin M and Seguritan, Victor and Green, Jessica and Pride,
              David T and Yooseph, Shibu and Biggs, William and Nelson, Karen E
              and Venter, J Craig",
  abstract = "Observations from human microbiome studies are often conflicting
              or inconclusive. Many factors likely contribute to these issues
              including small cohort sizes, sample collection, and handling and
              processing differences. The field of microbiome research is
              moving from 16S rDNA gene sequencing to a more comprehensive
              genomic and functional representation through whole-genome
              sequencing (WGS) of complete communities. Here we performed
              quantitative and qualitative analyses comparing WGS metagenomic
              data from human stool specimens using the Illumina Nextera XT and
              Illumina TruSeq DNA PCR-free kits, and the KAPA Biosystems Hyper
              Prep PCR and PCR-free systems. Significant differences in
              taxonomy are observed among the four different next-generation
              sequencing library preparations using a DNA mock community and a
              cell control of known concentration. We also revealed biases in
              error profiles, duplication rates, and loss of reads representing
              organisms that have a high \%G+C content that can significantly
              impact results. As with all methods, the use of benchmarking
              controls has revealed critical differences among methods that
              impact sequencing results and later would impact study
              interpretation. We recommend that the community adopt
              PCR-free-based approaches to reduce PCR bias that affects
              calculations of abundance and to improve assemblies for accurate
              taxonomic assignment. Furthermore, the inclusion of a known-input
              cell spike-in control provides accurate quantitation of organisms
              in clinical samples.",
  journal  = "Proc. Natl. Acad. Sci. U. S. A.",
  volume   =  112,
  number   =  45,
  pages    = "14024--14029",
  month    =  nov,
  year     =  2015,
  keywords = "genomics; microbiome; sequencing;Holo-Omics",
  language = "en"
}

@ARTICLE{Simao2015-ex,
  title     = "{BUSCO}: assessing genome assembly and annotation completeness
               with single-copy orthologs",
  author    = "Sim{\~a}o, Felipe A and Waterhouse, Robert M and Ioannidis,
               Panagiotis and Kriventseva, Evgenia V and Zdobnov, Evgeny M",
  abstract  = "MOTIVATION: Genomics has revolutionized biological research, but
               quality assessment of the resulting assembled sequences is
               complicated and remains mostly limited to technical measures
               like N50. RESULTS: We propose a measure for quantitative
               assessment of genome assembly and annotation completeness based
               on evolutionarily informed expectations of gene content. We
               implemented the assessment procedure in open-source software,
               with sets of Benchmarking Universal Single-Copy Orthologs, named
               BUSCO. AVAILABILITY AND IMPLEMENTATION: Software implemented in
               Python and datasets available for download from
               http://busco.ezlab.org. CONTACT: evgeny.zdobnov@unige.ch
               SUPPLEMENTARY INFORMATION: Supplementary data are available at
               Bioinformatics online.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  31,
  number    =  19,
  pages     = "3210--3212",
  month     =  oct,
  year      =  2015,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Limborg2018-tf,
  title    = "Applied Hologenomics: Feasibility and Potential in Aquaculture",
  author   = "Limborg, Morten T and Alberdi, Antton and Kodama, Miyako and
              Roggenbuck, Michael and Kristiansen, Karsten and Gilbert, M
              Thomas P",
  abstract = "Aquaculture will play an essential role in feeding a growing
              human population, but several biological challenges impede
              sustainable growth of production. Emerging evidence across all
              areas of life has revealed the importance of the intimate
              biological interactions between animals and their associated gut
              microbiota. Based on challenges in aquaculture, we leverage
              current knowledge in molecular biology and host microbiota
              interactions to propose an applied holo-omic framework that
              integrates molecular data including genomes, transcriptomes,
              epigenomes, proteomes, and metabolomes for analyzing fish and
              their gut microbiota as interconnected and coregulated systems.
              With an eye towards aquaculture, we discuss the feasibility and
              potential of our holo-omic framework to improve growth, health,
              and sustainability in any area of food production, including
              livestock and agriculture.",
  journal  = "Trends Biotechnol.",
  volume   =  36,
  number   =  3,
  pages    = "252--264",
  month    =  mar,
  year     =  2018,
  keywords = "aquaculture; holo-omic analysis; holobiont; hologenome;
              sustainable production;Holo-Omics",
  language = "en"
}

@ARTICLE{Theis2016-dc,
  title    = "Getting the Hologenome Concept Right: an {Eco-Evolutionary}
              Framework for Hosts and Their Microbiomes",
  author   = "Theis, Kevin R and Dheilly, Nolwenn M and Klassen, Jonathan L and
              Brucker, Robert M and Baines, John F and Bosch, Thomas C G and
              Cryan, John F and Gilbert, Scott F and Goodnight, Charles J and
              Lloyd, Elisabeth A and Sapp, Jan and Vandenkoornhuyse, Philippe
              and Zilber-Rosenberg, Ilana and Rosenberg, Eugene and
              Bordenstein, Seth R",
  abstract = "Given the complexity of host-microbiota symbioses, scientists and
              philosophers are asking questions at new biological levels of
              hierarchical organization-what is a holobiont and hologenome?
              When should this vocabulary be applied? Are these concepts a null
              hypothesis for host-microbe systems or limited to a certain
              spectrum of symbiotic interactions such as host-microbial
              coevolution? Critical discourse is necessary in this nascent
              area, but productive discourse requires that skeptics and
              proponents use the same lexicon. For instance, critiquing the
              hologenome concept is not synonymous with critiquing coevolution,
              and arguing that an entity is not a primary unit of selection
              dismisses the fact that the hologenome concept has always
              embraced multilevel selection. Holobionts and hologenomes are
              incontrovertible, multipartite entities that result from
              ecological, evolutionary, and genetic processes at various
              levels. They are not restricted to one special process but
              constitute a wider vocabulary and framework for host biology in
              light of the microbiome.",
  journal  = "mSystems",
  volume   =  1,
  number   =  2,
  month    =  mar,
  year     =  2016,
  keywords = "ecology; evolution; hologenome; microbiome;Holo-Omics",
  language = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@BOOK{Rosenberg2013-dc,
  title     = "The Hologenome Concept: Human, Animal and Plant Microbiota",
  author    = "Rosenberg, Eugene and Zilber-Rosenberg, Ilana",
  abstract  = "\copyright{} Springer International Publishing Switzerland 2013
               This work is subject to copyright. All rights are reserved by
               the Publisher, whether the whole or part of the material is
               concerned, specifically the rights of translation, reprinting,
               reuse of illustrations, recitation, broadcasting, reproduction
               on microfilms or in any other physical way, and transmission or
               information storage and retrieval, electronic adaptation,
               computer software, or by similar or dissimilar methodology now
               known or hereafter developed. Exempted from this legal
               reservation are brief excerpts in connection …",
  publisher = "Springer, Cham",
  year      =  2013,
  keywords  = "Holo-Omics"
}

@ARTICLE{Bowers2017-kj,
  title    = "Minimum information about a single amplified genome ({MISAG}) and
              a metagenome-assembled genome ({MIMAG}) of bacteria and archaea",
  author   = "Bowers, Robert M and Kyrpides, Nikos C and Stepanauskas, Ramunas
              and Harmon-Smith, Miranda and Doud, Devin and Reddy, T B K and
              Schulz, Frederik and Jarett, Jessica and Rivers, Adam R and
              Eloe-Fadrosh, Emiley A and Tringe, Susannah G and Ivanova,
              Natalia N and Copeland, Alex and Clum, Alicia and Becraft, Eric D
              and Malmstrom, Rex R and Birren, Bruce and Podar, Mircea and
              Bork, Peer and Weinstock, George M and Garrity, George M and
              Dodsworth, Jeremy A and Yooseph, Shibu and Sutton, Granger and
              Gl{\"o}ckner, Frank O and Gilbert, Jack A and Nelson, William C
              and Hallam, Steven J and Jungbluth, Sean P and Ettema, Thijs J G
              and Tighe, Scott and Konstantinidis, Konstantinos T and Liu,
              Wen-Tso and Baker, Brett J and Rattei, Thomas and Eisen, Jonathan
              A and Hedlund, Brian and McMahon, Katherine D and Fierer, Noah
              and Knight, Rob and Finn, Rob and Cochrane, Guy and
              Karsch-Mizrachi, Ilene and Tyson, Gene W and Rinke, Christian and
              {Genome Standards Consortium} and Lapidus, Alla and Meyer, Folker
              and Yilmaz, Pelin and Parks, Donovan H and Eren, A M and Schriml,
              Lynn and Banfield, Jillian F and Hugenholtz, Philip and Woyke,
              Tanja",
  abstract = "We present two standards developed by the Genomic Standards
              Consortium (GSC) for reporting bacterial and archaeal genome
              sequences. Both are extensions of the Minimum Information about
              Any (x) Sequence (MIxS). The standards are the Minimum
              Information about a Single Amplified Genome (MISAG) and the
              Minimum Information about a Metagenome-Assembled Genome (MIMAG),
              including, but not limited to, assembly quality, and estimates of
              genome completeness and contamination. These standards can be
              used in combination with other GSC checklists, including the
              Minimum Information about a Genome Sequence (MIGS), Minimum
              Information about a Metagenomic Sequence (MIMS), and Minimum
              Information about a Marker Gene Sequence (MIMARKS).
              Community-wide adoption of MISAG and MIMAG will facilitate more
              robust comparative genomic analyses of bacterial and archaeal
              diversity.",
  journal  = "Nat. Biotechnol.",
  volume   =  35,
  number   =  8,
  pages    = "725--731",
  month    =  aug,
  year     =  2017,
  keywords = "Holo-Omics",
  language = "en"
}

@ARTICLE{Sieber2018-fp,
  title    = "Recovery of genomes from metagenomes via a dereplication,
              aggregation and scoring strategy",
  author   = "Sieber, Christian M K and Probst, Alexander J and Sharrar,
              Allison and Thomas, Brian C and Hess, Matthias and Tringe,
              Susannah G and Banfield, Jillian F",
  abstract = "Microbial communities are critical to ecosystem function. A key
              objective of metagenomic studies is to analyse organism-specific
              metabolic pathways and reconstruct community interaction
              networks. This requires accurate assignment of assembled genome
              fragments to genomes. Existing binning methods often fail to
              reconstruct a reasonable number of genomes and report many bins
              of low quality and completeness. Furthermore, the performance of
              existing algorithms varies between samples and biotopes. Here, we
              present a dereplication, aggregation and scoring strategy, DAS
              Tool, that combines the strengths of a flexible set of
              established binning algorithms. DAS Tool applied to a constructed
              community generated more accurate bins than any automated method.
              Indeed, when applied to environmental and host-associated samples
              of different complexity, DAS Tool recovered substantially more
              near-complete genomes, including previously unreported lineages,
              than any single binning method alone. The ability to reconstruct
              many near-complete genomes from metagenomics data will greatly
              advance genome-centric analyses of ecosystems.",
  journal  = "Nat Microbiol",
  volume   =  3,
  number   =  7,
  pages    = "836--843",
  month    =  jul,
  year     =  2018,
  keywords = "Holo-Omics",
  language = "en"
}

@ARTICLE{Nyholm2020-ua,
  title    = "{Holo-Omics}: Integrated {Host-Microbiota} Multi-omics for Basic
              and Applied Biological Research",
  author   = "Nyholm, Lasse and Koziol, Adam and Marcos, Sofia and Botnen,
              Amanda Bolt and Aizpurua, Ostaizka and Gopalakrishnan, Shyam and
              Limborg, Morten T and Gilbert, M Thomas P and Alberdi, Antton",
  abstract = "From ontogenesis to homeostasis, the phenotypes of complex
              organisms are shaped by the bidirectional interactions between
              the host organisms and their associated microbiota. Current
              technology can reveal many such interactions by combining
              multi-omic data from both hosts and microbes. However, exploring
              the full extent of these interactions requires careful
              consideration of study design for the efficient generation and
              optimal integration of data derived from (meta)genomics,
              (meta)transcriptomics, (meta)proteomics, and (meta)metabolomics.
              In this perspective, we introduce the holo-omic approach that
              incorporates multi-omic data from both host and microbiota
              domains to untangle the interplay between the two. We revisit the
              recent literature on biomolecular host-microbe interactions and
              discuss the implementation and current limitations of the
              holo-omic approach. We anticipate that the application of this
              approach can contribute to opening new research avenues and
              discoveries in biomedicine, biotechnology, agricultural and
              aquacultural sciences, nature conservation, as well as basic
              ecological and evolutionary research.",
  journal  = "iScience",
  volume   =  23,
  number   =  8,
  pages    = "101414",
  month    =  aug,
  year     =  2020,
  keywords = "Evolutionary Biology; Microbiome;Holo-Omics",
  language = "en"
}

@ARTICLE{Eren2015-tt,
  title     = "Anvi'o: an advanced analysis and visualization platform for
               'omics data",
  author    = "Eren, A Murat and Esen, {\"O}zcan C and Quince, Christopher and
               Vineis, Joseph H and Morrison, Hilary G and Sogin, Mitchell L
               and Delmont, Tom O",
  abstract  = "Advances in high-throughput sequencing and 'omics technologies
               are revolutionizing studies of naturally occurring microbial
               communities. Comprehensive investigations of microbial
               lifestyles require the ability to interactively organize and
               visualize genetic information and to incorporate subtle
               differences that enable greater resolution of complex data. Here
               we introduce anvi'o, an advanced analysis and visualization
               platform that offers automated and human-guided characterization
               of microbial genomes in metagenomic assemblies, with interactive
               interfaces that can link 'omics data from multiple sources into
               a single, intuitive display. Its extensible visualization
               approach distills multiple dimensions of information about each
               contig, offering a dynamic and unified work environment for data
               exploration, manipulation, and reporting. Using anvi'o, we
               re-analyzed publicly available datasets and explored temporal
               genomic changes within naturally occurring microbial populations
               through de novo characterization of single nucleotide
               variations, and linked cultivar and single-cell genomes with
               metagenomic and metatranscriptomic data. Anvi'o is an
               open-source platform that empowers researchers without extensive
               bioinformatics skills to perform and communicate in-depth
               analyses on large 'omics datasets.",
  journal   = "PeerJ",
  publisher = "peerj.com",
  volume    =  3,
  pages     = "e1319",
  month     =  oct,
  year      =  2015,
  keywords  = "Assembly; Genome binning; Metagenomics; Metatranscriptomics; SNP
               profiling; Visualization;Holo-Omics",
  language  = "en"
}

@ARTICLE{Zhang2018-ty,
  title    = "Deep {Learning-Based} {Multi-Omics} Data Integration Reveals Two
              Prognostic Subtypes in {High-Risk} Neuroblastoma",
  author   = "Zhang, Li and Lv, Chenkai and Jin, Yaqiong and Cheng, Ganqi and
              Fu, Yibao and Yuan, Dongsheng and Tao, Yiran and Guo, Yongli and
              Ni, Xin and Shi, Tieliu",
  abstract = "High-risk neuroblastoma is a very aggressive disease, with
              excessive tumor growth and poor outcomes. A proper stratification
              of the high-risk patients by prognostic outcome is important for
              treatment. However, there is still a lack of survival
              stratification for the high-risk neuroblastoma. To fill the gap,
              we adopt a deep learning algorithm, Autoencoder, to integrate
              multi-omics data, and combine it with K-means clustering to
              identify two subtypes with significant survival differences. By
              comparing the Autoencoder with PCA, iCluster, and DGscore about
              the classification based on multi-omics data integration,
              Autoencoder-based classification outperforms the alternative
              approaches. Furthermore, we also validated the classification in
              two independent datasets by training machine-learning
              classification models, and confirmed its robustness. Functional
              analysis revealed that MYCN amplification was more frequently
              occurred in the ultra-high-risk subtype, in accordance with the
              overexpression of MYC/MYCN targets in this subtype. In summary,
              prognostic subtypes identified by deep learning-based multi-omics
              integration could not only improve our understanding of molecular
              mechanism, but also help the clinicians make decisions.",
  journal  = "Front. Genet.",
  volume   =  9,
  pages    = "477",
  month    =  oct,
  year     =  2018,
  keywords = "MYCN amplification; deep learning; high-risk neuroblastoma;
              machine learning; multi-omics data integration;machine
              learning;autoencoder;Holo-Omics",
  language = "en"
}

@ARTICLE{Mushegian2019-md,
  title     = "Environmental Sources of Bacteria and Genetic Variation in
               Behavior Influence {Host-Associated} Microbiota",
  author    = "Mushegian, Alexandra A and Arbore, Roberto and Walser,
               Jean-Claude and Ebert, Dieter",
  abstract  = "ABSTRACT In many organisms, host-associated microbial
               communities are acquired horizontally after birth. This process
               is believed to be shaped by a combination of environmental and
               host genetic factors. We examined whether genetic variation in
               animal behavior could affect the composition of the animal's
               microbiota in different environments. The freshwater crustacean
               Daphnia magna is primarily planktonic but exhibits variation in
               the degree to which it browses in benthic sediments. We
               performed an experiment with clonal lines of D. magna showing
               different levels of sediment-browsing intensity exposed to
               either bacteria-rich or bacteria-poor sediment or whose access
               to sediments was prevented. We found that the bacterial
               composition of the environment and genotype-specific browsing
               intensity together influence the composition of the
               Daphnia-associated bacterial community. Exposure to more diverse
               bacteria did not lead to a more diverse microbiome, but greater
               abundances of environment-specific bacteria were found
               associated with host genotypes that exhibited greater browsing
               behavior. Our results indicate that, although there is a great
               deal of variation between individuals, behavior can mediate
               genotype-by-environment interaction effects on microbiome
               composition.IMPORTANCE An animal's behavior can affect its risk
               of infection, but it is not well understood how behavior affects
               microbiome composition. The aquatic crustacean Daphnia exhibits
               genetic variation in the extent to which it browses in the
               sediment at the bottoms of ponds. We show that this behavior
               affects the Daphnia microbiome, indicating that genetic
               variation among individuals may affect microbiome composition
               and the movement of bacteria in different environments.",
  journal   = "Appl. Environ. Microbiol.",
  publisher = "American Society for Microbiology",
  volume    =  85,
  number    =  8,
  month     =  apr,
  year      =  2019,
  keywords  = "Holo-Omics",
  language  = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Argelaguet2018-dl,
  title     = "{Multi-Omics} Factor Analysis---a framework for unsupervised
               integration of multi-omics data sets",
  author    = "Argelaguet, Ricard and Velten, Britta and Arnol, Damien and
               Dietrich, Sascha and Zenz, Thorsten and Marioni, John C and
               Buettner, Florian and Huber, Wolfgang and Stegle, Oliver",
  abstract  = "Multi ‐ omics studies promise the improved characterization of
               biological processes across molecular layers. However, methods
               for the unsupervised integration of the resulting heterogeneous
               data sets are lacking. We present Multi ‐ Omics Factor Analysis
               (MOFA), a …",
  journal   = "Mol. Syst. Biol.",
  publisher = "embopress.org",
  volume    =  14,
  number    =  6,
  pages     = "e8124",
  year      =  2018,
  keywords  = "Holo-Omics"
}

@ARTICLE{Fiedorova2019-yk,
  title     = "The Impact of {DNA} Extraction Methods on Stool Bacterial and
               Fungal Microbiota Community Recovery",
  author    = "Fiedorov{\'a}, Krist{\'y}na and Radvansk{\'y}, Mat{\v e}j and
               N{\v e}mcov{\'a}, Eva and Grombi{\v r}{\'\i}kov{\'a}, Hana and
               Bos{\'a}k, Juraj and {\v C}ernochov{\'a}, Michaela and Lexa,
               Matej and {\v S}majs, David and Freiberger, Tom{\'a}{\v s}",
  abstract  = "Our understanding of human gut microbiota in health and disease
               depends on accurate and reproducible microbial data acquisition.
               The critical step in this process is to apply an appropriate
               methodology to extract microbial DNA, since biases introduced
               during the DNA extraction process may result in inaccurate
               microbial representation. In this study, we attempted to find a
               DNA extraction protocol which could be effectively used to
               analyze both the bacterial and fungal community. We evaluated
               the effect of five DNA extraction methods (QIAamp DNA Stool Mini
               Kit, PureLinkTM Microbiome DNA Purification Kit, ZR Fecal DNA
               MiniPrepTM Kit, NucleoSpin\textregistered{} DNA Stool Kit, and
               IHMS protocol Q) on bacterial and fungal gut microbiome recovery
               using (i) a defined system of germ-free mice feces spiked with
               bacterial or fungal strains, and (ii) non-spiked human feces. In
               our experimental setup, we confirmed that the examined methods
               significantly differed in efficiency and quality, which affected
               the identified stool microbiome composition. In addition, our
               results indicated that fungal DNA extraction might be prone to
               be affected by reagent/kit contamination, and thus an
               appropriate blank control should be included in mycobiome
               research. Overall, standardized IHMS protocol Q, recommended by
               the International Human Microbiome Consortium, performed the
               best when considering all the parameters analyzed, and thus
               could be applied not only in bacterial, but also in fungal
               microbiome research.",
  journal   = "Front. Microbiol.",
  publisher = "frontiersin.org",
  volume    =  10,
  pages     = "821",
  month     =  apr,
  year      =  2019,
  keywords  = "16S rDNA; DNA extraction method; ITS rDNA; fungal microbiota;
               gut microbiome; gut microbiota; gut mycobiome; gut
               mycobiota;Holo-Omics",
  language  = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Prezza2020-ln,
  title     = "Improved bacterial {RNA-seq} by Cas9-based depletion of
               ribosomal {RNA} reads",
  author    = "Prezza, Gianluca and Heckel, Tobias and Dietrich, Sascha and
               Homberger, Christina and Westermann, Alexander J and Vogel,
               J{\"o}rg",
  abstract  = "A major challenge for RNA-seq analysis of gene expression is to
               achieve sufficient coverage of informative nonribosomal
               transcripts. In eukaryotic samples, this is typically achieved
               by selective oligo(dT)-priming of messenger RNAs to exclude
               ribosomal RNA (rRNA) during cDNA synthesis. However, this
               strategy is not compatible with prokaryotes in which functional
               transcripts are generally not polyadenylated. To overcome this,
               we adopted DASH (depletion of abundant sequences by
               hybridization), initially developed for eukaryotic cells, to
               improve both the sensitivity and depth of bacterial RNA-seq.
               DASH uses the Cas9 nuclease to remove unwanted cDNA sequences
               prior to library amplification. We report the design,
               evaluation, and optimization of DASH experiments for standard
               bacterial short-read sequencing approaches, including software
               for automated guide RNA (gRNA) design for Cas9-mediated cleavage
               in bacterial rDNA sequences. Using these gRNA pools, we
               effectively removed rRNA reads (56\%-86\%) in RNA-seq libraries
               from two different model bacteria, the Gram-negative pathogen
               Salmonella enterica and the anaerobic gut commensal Bacteroides
               thetaiotaomicron DASH works robustly, even with subnanogram
               amounts of input RNA. Its efficiency, high sensitivity, ease of
               implementation, and low cost (∼\$5 per sample) render DASH an
               attractive alternative to rRNA removal protocols, in particular
               for material-constrained studies where conventional
               ribodepletion techniques fail.",
  journal   = "RNA",
  publisher = "rnajournal.cshlp.org",
  volume    =  26,
  number    =  8,
  pages     = "1069--1078",
  month     =  aug,
  year      =  2020,
  keywords  = "Bacteroides; CRISPR; Cas9; DASH; Salmonella; bacterial RNA-seq;
               ribosomal RNA;Holo-Omics",
  language  = "en"
}

@ARTICLE{Shaffer2020-kp,
  title     = "{DRAM} for distilling microbial metabolism to automate the
               curation of microbiome function",
  author    = "Shaffer, Michael and Borton, Mikayla A and McGivern, Bridget B
               and Zayed, Ahmed A and La Rosa, Sabina Leanti and Solden,
               Lindsey M and Liu, Pengfei and Narrowe, Adrienne B and
               Rodr{\'\i}guez-Ramos, Josu{\'e} and Bolduc, Benjamin and
               Gazit{\'u}a, M Consuelo and Daly, Rebecca A and Smith, Garrett J
               and Vik, Dean R and Pope, Phil B and Sullivan, Matthew B and
               Roux, Simon and Wrighton, Kelly C",
  abstract  = "Microbial and viral communities transform the chemistry of
               Earth's ecosystems, yet the specific reactions catalyzed by
               these biological engines are hard to decode due to the absence
               of a scalable, metabolically resolved, annotation software.
               Here, we present DRAM (Distilled and Refined Annotation of
               Metabolism), a framework to translate the deluge of
               microbiome-based genomic information into a catalog of microbial
               traits. To demonstrate the applicability of DRAM across
               metabolically diverse genomes, we evaluated DRAM performance on
               a defined, in silico soil community and previously published
               human gut metagenomes. We show that DRAM accurately assigned
               microbial contributions to geochemical cycles and automated the
               partitioning of gut microbial carbohydrate metabolism at
               substrate levels. DRAM-v, the viral mode of DRAM, established
               rules to identify virally-encoded auxiliary metabolic genes
               (AMGs), resulting in the metabolic categorization of thousands
               of putative AMGs from soils and guts. Together DRAM and DRAM-v
               provide critical metabolic profiling capabilities that decipher
               mechanisms underpinning microbiome function.",
  journal   = "Nucleic Acids Res.",
  publisher = "academic.oup.com",
  volume    =  48,
  number    =  16,
  pages     = "8883--8900",
  month     =  sep,
  year      =  2020,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Nguyen2019-pv,
  title     = "{PINSPlus}: a tool for tumor subtype discovery in integrated
               genomic data",
  author    = "Nguyen, Hung and Shrestha, Sangam and Draghici, Sorin and
               Nguyen, Tin",
  abstract  = "SUMMARY: Since cancer is a heterogeneous disease, tumor
               subtyping is crucial for improved treatment and prognosis. We
               have developed a subtype discovery tool, called PINSPlus, that
               is: (i) robust against noise and unstable quantitative assays,
               (ii) able to integrate multiple types of omics data in a single
               analysis and (iii) dramatically superior to established
               approaches in identifying known subtypes and novel subgroups
               with significant survival differences. Our validation on 12,158
               samples from 44 datasets shows that PINSPlus vastly outperforms
               other approaches. The software is easy-to-use and can partition
               hundreds of patients in a few minutes on a personal computer.
               AVAILABILITY AND IMPLEMENTATION: The package is available at
               https://cran.r-project.org/package=PINSPlus. Data and R script
               used in this manuscript are available at
               https://bioinformatics.cse.unr.edu/software/PINSPlus/.
               SUPPLEMENTARY INFORMATION: Supplementary data are available at
               Bioinformatics online.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  35,
  number    =  16,
  pages     = "2843--2846",
  month     =  aug,
  year      =  2019,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Lock2013-uq,
  title     = "Bayesian consensus clustering",
  author    = "Lock, Eric F and Dunson, David B",
  abstract  = "MOTIVATION: In biomedical research a growing number of platforms
               and technologies are used to measure diverse but related
               information, and the task of clustering a set of objects based
               on multiple sources of data arises in several applications. Most
               current approaches to multisource clustering either
               independently determine a separate clustering for each data
               source or determine a single 'joint' clustering for all data
               sources. There is a need for more flexible approaches that
               simultaneously model the dependence and the heterogeneity of the
               data sources. RESULTS: We propose an integrative statistical
               model that permits a separate clustering of the objects for each
               data source. These separate clusterings adhere loosely to an
               overall consensus clustering, and hence they are not
               independent. We describe a computationally scalable Bayesian
               framework for simultaneous estimation of both the consensus
               clustering and the source-specific clusterings. We demonstrate
               that this flexible approach is more robust than joint clustering
               of all data sources, and is more powerful than clustering each
               data source independently. We present an application to subtype
               identification of breast cancer tumor samples using publicly
               available data from The Cancer Genome Atlas. AVAILABILITY: R
               code with instructions and examples is available at
               http://people.duke.edu/\%7Eel113/software.html.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  29,
  number    =  20,
  pages     = "2610--2616",
  month     =  oct,
  year      =  2013,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Olm2017-nx,
  title     = "dRep: a tool for fast and accurate genomic comparisons that
               enables improved genome recovery from metagenomes through
               de-replication",
  author    = "Olm, Matthew R and Brown, Christopher T and Brooks, Brandon and
               Banfield, Jillian F",
  abstract  = "The number of microbial genomes sequenced each year is expanding
               rapidly, in part due to genome-resolved metagenomic studies that
               routinely recover hundreds of draft-quality genomes. Rapid
               algorithms have been developed to comprehensively compare large
               genome sets, but they are not accurate with draft-quality
               genomes. Here we present dRep, a program that reduces the
               computational time for pairwise genome comparisons by
               sequentially applying a fast, inaccurate estimation of genome
               distance, and a slow, accurate measure of average nucleotide
               identity. dRep achieves a 28 $\times$ increase in speed with
               perfect recall and precision when benchmarked against previously
               developed algorithms. We demonstrate the use of dRep for genome
               recovery from time-series datasets. Each metagenome was
               assembled separately, and dRep was used to identify groups of
               essentially identical genomes and select the best genome from
               each replicate set. This resulted in recovery of significantly
               more and higher-quality genomes compared to the set recovered
               using co-assembly.",
  journal   = "ISME J.",
  publisher = "nature.com",
  volume    =  11,
  number    =  12,
  pages     = "2864--2868",
  month     =  dec,
  year      =  2017,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Orakov2021-pt,
  title     = "{GUNC}: detection of chimerism and contamination in prokaryotic
               genomes",
  author    = "Orakov, Askarbek and Fullam, Anthony and Coelho, Luis Pedro and
               Khedkar, Supriya and Szklarczyk, Damian and Mende, Daniel R and
               Schmidt, Thomas S B and Bork, Peer",
  abstract  = "Genomes are critical units in microbiology, yet ascertaining
               quality in prokaryotic genome assemblies remains a formidable
               challenge. We present GUNC (the Genome UNClutterer), a tool that
               accurately detects and quantifies genome chimerism based on the
               lineage homogeneity of individual contigs using a genome's full
               complement of genes. GUNC complements existing approaches by
               targeting previously underdetected types of contamination: we
               conservatively estimate that 5.7\% of genomes in GenBank, 5.2\%
               in RefSeq, and 15-30\% of pre-filtered ``high-quality''
               metagenome-assembled genomes in recent studies are undetected
               chimeras. GUNC provides a fast and robust tool to substantially
               improve prokaryotic genome quality.",
  journal   = "Genome Biol.",
  publisher = "Springer",
  volume    =  22,
  number    =  1,
  pages     = "178",
  month     =  jun,
  year      =  2021,
  keywords  = "Bioinformatics; Genome contamination; Genome quality;
               Metagenome-assembled genomes; Metagenomics;Holo-Omics",
  language  = "en"
}

@ARTICLE{Uritskiy2018-my,
  title     = "{MetaWRAP---a} flexible pipeline for genome-resolved metagenomic
               data analysis",
  author    = "Uritskiy, Gherman V and DiRuggiero, Jocelyne and Taylor, James",
  abstract  = "The study of microbiomes using whole-metagenome shotgun
               sequencing enables the analysis of uncultivated microbial
               populations that may have important roles in their environments.
               Extracting individual draft genomes (bins) facilitates
               metagenomic analysis at the single genome level. Software and
               pipelines for such analysis have become diverse and
               sophisticated, resulting in a significant burden for biologists
               to access and use them. Furthermore, while bin extraction
               algorithms are rapidly improving, there is still a lack of tools
               for their evaluation and visualization. To address these
               challenges, we present metaWRAP, a modular pipeline software for
               shotgun metagenomic data analysis. MetaWRAP deploys
               state-of-the-art software to handle metagenomic data processing
               starting from raw sequencing reads and ending in metagenomic
               bins and their analysis. MetaWRAP is flexible enough to give
               investigators control over the analysis, while still being
               easy-to-install and easy-to-use. It includes hybrid algorithms
               that leverage the strengths of a variety of software to extract
               and refine high-quality bins from metagenomic data through bin
               consolidation and reassembly. MetaWRAP's hybrid bin extraction
               algorithm outperforms individual binning approaches and other
               bin consolidation programs in both synthetic and real data sets.
               Finally, metaWRAP comes with numerous modules for the analysis
               of metagenomic bins, including taxonomy assignment, abundance
               estimation, functional annotation, and visualization. MetaWRAP
               is an easy-to-use modular pipeline that automates the core tasks
               in metagenomic analysis, while contributing significant
               improvements to the extraction and interpretation of
               high-quality metagenomic bins. The bin refinement and reassembly
               modules of metaWRAP consistently outperform other binning
               approaches. Each module of metaWRAP is also a standalone
               component, making it a flexible and versatile tool for tackling
               metagenomic shotgun sequencing data. MetaWRAP is open-source
               software available at https://github.com/bxlab/metaWRAP .",
  journal   = "Microbiome",
  publisher = "BioMed Central",
  volume    =  6,
  number    =  1,
  pages     = "1--13",
  month     =  sep,
  year      =  2018,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Parks2022-zl,
  title     = "{GTDB}: an ongoing census of bacterial and archaeal diversity
               through a phylogenetically consistent, rank normalized and
               complete genome-based taxonomy",
  author    = "Parks, Donovan H and Chuvochina, Maria and Rinke, Christian and
               Mussig, Aaron J and Chaumeil, Pierre-Alain and Hugenholtz,
               Philip",
  abstract  = "The Genome Taxonomy Database (GTDB; https://gtdb.ecogenomic.org)
               provides a phylogenetically consistent and rank normalized
               genome-based taxonomy for prokaryotic genomes sourced from the
               NCBI Assembly database. GTDB R06-RS202 spans 254 090 bacterial
               and 4316 archaeal genomes, a 270\% increase since the
               introduction of the GTDB in November, 2017. These genomes are
               organized into 45 555 bacterial and 2339 archaeal species
               clusters which is a 200\% increase since the integration of
               species clusters into the GTDB in June, 2019. Here, we explore
               prokaryotic diversity from the perspective of the GTDB and
               highlight the importance of metagenome-assembled genomes in
               expanding available genomic representation. We also discuss
               improvements to the GTDB website which allow tracking of
               taxonomic changes, easy assessment of genome assembly quality,
               and identification of genomes assembled from type material or
               used as species representatives. Methodological updates and
               policy changes made since the inception of the GTDB are then
               described along with the procedure used to update species
               clusters in the GTDB. We conclude with a discussion on the use
               of average nucleotide identities as a pragmatic approach for
               delineating prokaryotic species.",
  journal   = "Nucleic Acids Res.",
  publisher = "academic.oup.com",
  volume    =  50,
  number    = "D1",
  pages     = "D785--D794",
  month     =  jan,
  year      =  2022,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Alberdi2022-ay,
  title    = "Disentangling host-microbiota complexity through hologenomics",
  author   = "Alberdi, Antton and Andersen, Sandra B and Limborg, Morten T and
              Dunn, Robert R and Gilbert, M Thomas P",
  abstract = "Research on animal-microbiota interactions has become a central
              topic in biological sciences because of its relevance to basic
              eco-evolutionary processes and applied questions in agriculture
              and health. However, animal hosts and their associated microbial
              communities are still seldom studied in a systemic fashion.
              Hologenomics, the integrated study of the genetic features of a
              eukaryotic host alongside that of its associated microbes, is
              becoming a feasible - yet still underexploited - approach that
              overcomes this limitation. Acknowledging the biological and
              genetic properties of both hosts and microbes, along with the
              advantages and disadvantages of implemented techniques, is
              essential for designing optimal studies that enable some of the
              major questions in biology to be addressed.",
  journal  = "Nat. Rev. Genet.",
  volume   =  23,
  number   =  5,
  pages    = "281--297",
  month    =  may,
  year     =  2022,
  keywords = "Holo-Omics",
  language = "en"
}

@ARTICLE{Poirion2020-cn,
  title    = "Multi-omics-based pan-cancer prognosis prediction using an
              ensemble of deep-learning and machine-learning models",
  author   = "Poirion, O B and Chaudhary, K and Huang, S and Garmire, L X",
  journal  = "medRxiv",
  year     =  2020,
  keywords = "Holo-Omics"
}

@ARTICLE{Rhie2021-cf,
  title     = "Towards complete and error-free genome assemblies of all
               vertebrate species",
  author    = "Rhie, Arang and McCarthy, Shane A and Fedrigo, Olivier and
               Damas, Joana and Formenti, Giulio and Koren, Sergey and
               Uliano-Silva, Marcela and Chow, William and Fungtammasan,
               Arkarachai and Kim, Juwan and Lee, Chul and Ko, Byung June and
               Chaisson, Mark and Gedman, Gregory L and Cantin, Lindsey J and
               Thibaud-Nissen, Francoise and Haggerty, Leanne and Bista, Iliana
               and Smith, Michelle and Haase, Bettina and Mountcastle,
               Jacquelyn and Winkler, Sylke and Paez, Sadye and Howard, Jason
               and Vernes, Sonja C and Lama, Tanya M and Grutzner, Frank and
               Warren, Wesley C and Balakrishnan, Christopher N and Burt, Dave
               and George, Julia M and Biegler, Matthew T and Iorns, David and
               Digby, Andrew and Eason, Daryl and Robertson, Bruce and Edwards,
               Taylor and Wilkinson, Mark and Turner, George and Meyer, Axel
               and Kautt, Andreas F and Franchini, Paolo and Detrich, 3rd, H
               William and Svardal, Hannes and Wagner, Maximilian and Naylor,
               Gavin J P and Pippel, Martin and Malinsky, Milan and Mooney,
               Mark and Simbirsky, Maria and Hannigan, Brett T and Pesout,
               Trevor and Houck, Marlys and Misuraca, Ann and Kingan, Sarah B
               and Hall, Richard and Kronenberg, Zev and Sovi{\'c}, Ivan and
               Dunn, Christopher and Ning, Zemin and Hastie, Alex and Lee,
               Joyce and Selvaraj, Siddarth and Green, Richard E and Putnam,
               Nicholas H and Gut, Ivo and Ghurye, Jay and Garrison, Erik and
               Sims, Ying and Collins, Joanna and Pelan, Sarah and Torrance,
               James and Tracey, Alan and Wood, Jonathan and Dagnew, Robel E
               and Guan, Dengfeng and London, Sarah E and Clayton, David F and
               Mello, Claudio V and Friedrich, Samantha R and Lovell, Peter V
               and Osipova, Ekaterina and Al-Ajli, Farooq O and Secomandi,
               Simona and Kim, Heebal and Theofanopoulou, Constantina and
               Hiller, Michael and Zhou, Yang and Harris, Robert S and Makova,
               Kateryna D and Medvedev, Paul and Hoffman, Jinna and Masterson,
               Patrick and Clark, Karen and Martin, Fergal and Howe, Kevin and
               Flicek, Paul and Walenz, Brian P and Kwak, Woori and Clawson,
               Hiram and Diekhans, Mark and Nassar, Luis and Paten, Benedict
               and Kraus, Robert H S and Crawford, Andrew J and Gilbert, M
               Thomas P and Zhang, Guojie and Venkatesh, Byrappa and Murphy,
               Robert W and Koepfli, Klaus-Peter and Shapiro, Beth and Johnson,
               Warren E and Di Palma, Federica and Marques-Bonet, Tomas and
               Teeling, Emma C and Warnow, Tandy and Graves, Jennifer Marshall
               and Ryder, Oliver A and Haussler, David and O'Brien, Stephen J
               and Korlach, Jonas and Lewin, Harris A and Howe, Kerstin and
               Myers, Eugene W and Durbin, Richard and Phillippy, Adam M and
               Jarvis, Erich D",
  abstract  = "High-quality and complete reference genome assemblies are
               fundamental for the application of genomics to biology, disease,
               and biodiversity conservation. However, such assemblies are
               available for only a few non-microbial species1-4. To address
               this issue, the international Genome 10K (G10K) consortium5,6
               has worked over a five-year period to evaluate and develop
               cost-effective methods for assembling highly accurate and nearly
               complete reference genomes. Here we present lessons learned from
               generating assemblies for 16 species that represent six major
               vertebrate lineages. We confirm that long-read sequencing
               technologies are essential for maximizing genome quality, and
               that unresolved complex repeats and haplotype heterozygosity are
               major sources of assembly error when not handled correctly. Our
               assemblies correct substantial errors, add missing sequence in
               some of the best historical reference genomes, and reveal
               biological discoveries. These include the identification of many
               false gene duplications, increases in gene sizes, chromosome
               rearrangements that are specific to lineages, a repeated
               independent chromosome breakpoint in bat genomes, and a
               canonical GC-rich pattern in protein-coding genes and their
               regulatory regions. Adopting these lessons, we have embarked on
               the Vertebrate Genomes Project (VGP), an international effort to
               generate high-quality, complete reference genomes for all of the
               roughly 70,000 extant vertebrate species and to help to enable a
               new era of discovery across the life sciences.",
  journal   = "Nature",
  publisher = "nature.com",
  volume    =  592,
  number    =  7856,
  pages     = "737--746",
  month     =  apr,
  year      =  2021,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Reel2021-wb,
  title     = "Using machine learning approaches for multi-omics data analysis:
               A review",
  author    = "Reel, Parminder S and Reel, Smarti and Pearson, Ewan and Trucco,
               Emanuele and Jefferson, Emily",
  abstract  = "With the development of modern high-throughput omic measurement
               platforms, it has become essential for biomedical studies to
               undertake an integrative (combined) approach to fully utilise
               these data to gain insights into biological systems. Data from
               various omics sources such as genetics, proteomics, and
               metabolomics can be integrated to unravel the intricate working
               of systems biology using machine learning-based predictive
               algorithms. Machine learning methods offer novel techniques to
               integrate and analyse the various omics data enabling the
               discovery of new biomarkers. These biomarkers have the potential
               to help in accurate disease prediction, patient stratification
               and delivery of precision medicine. This review paper explores
               different integrative machine learning methods which have been
               used to provide an in-depth understanding of biological systems
               during normal physiological functioning and in the presence of a
               disease. It provides insight and recommendations for
               interdisciplinary professionals who envisage employing machine
               learning skills in multi-omics studies.",
  journal   = "Biotechnol. Adv.",
  publisher = "Elsevier",
  volume    =  49,
  pages     = "107739",
  month     =  jul,
  year      =  2021,
  keywords  = "Machine Learning; Multi-omics; Predictive Modelling; Supervised
               Learning; Systems Biology; Unsupervised Learning;Holo-Omics",
  language  = "en"
}

@ARTICLE{Ritchie2015-qe,
  title     = "Methods of integrating data to uncover genotype--phenotype
               interactions",
  author    = "Ritchie, Marylyn D and Holzinger, Emily R and Li, Ruowang and
               Pendergrass, Sarah A and Kim, Dokyoon",
  abstract  = "Integrating multiple data types can be substantially more
               informative than analysing data sets separately, and methods to
               combine data sets are now emerging. This Review outlines the
               current approaches for data integration and the various
               strengths and weaknesses of these strategies. The analytical
               challenges that emerge with data sets of this magnitude are also
               described, and the authors provide their perspective on how such
               systems genomic analyses might develop in the future. Recent
               technological advances have expanded the breadth of available
               omic data, from whole-genome sequencing data, to extensive
               transcriptomic, methylomic and metabolomic data. A key goal of
               analyses of these data is the identification of effective models
               that predict phenotypic traits and outcomes, elucidating
               important biomarkers and generating important insights into the
               genetic underpinnings of the heritability of complex traits.
               There is still a need for powerful and advanced analysis
               strategies to fully harness the utility of these comprehensive
               high-throughput data, identifying true associations and reducing
               the number of false associations. In this Review, we explore the
               emerging approaches for data integration --- including
               meta-dimensional and multi-staged analyses --- which aim to
               deepen our understanding of the role of genetics and genomics in
               complex outcomes. With the use and further development of these
               approaches, an improved understanding of the relationship
               between genomic variation and human phenotypes may be revealed.",
  journal   = "Nat. Rev. Genet.",
  publisher = "Nature Publishing Group",
  volume    =  16,
  number    =  2,
  pages     = "85--97",
  month     =  jan,
  year      =  2015,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Fischer2017-wa,
  title     = "Metabolite exchange between microbiome members produces
               compounds that influence Drosophila behavior",
  author    = "Fischer, Caleb N and Trautman, Eric P and Crawford, Jason M and
               Stabb, Eric V and Handelsman, Jo and Broderick, Nichole A",
  abstract  = "Animals host multi-species microbial communities (microbiomes)
               whose properties may result from inter-species interactions;
               however, current understanding of host-microbiome interactions
               derives mostly from studies in which elucidation of
               microbe-microbe interactions is difficult. In exploring how
               Drosophila melanogaster acquires its microbiome, we found that a
               microbial community influences Drosophila olfactory and
               egg-laying behaviors differently than individual members.
               Drosophila prefers a Saccharomyces-Acetobacter co-culture to the
               same microorganisms grown individually and then mixed, a
               response mainly due to the conserved olfactory receptor, Or42b.
               Acetobacter metabolism of Saccharomyces-derived ethanol was
               necessary, and acetate and its metabolic derivatives were
               sufficient, for co-culture preference. Preference correlated
               with three emergent co-culture properties: ethanol catabolism, a
               distinct volatile profile, and yeast population decline.
               Egg-laying preference provided a context-dependent fitness
               benefit to larvae. We describe a molecular mechanism by which a
               microbial community affects animal behavior. Our results support
               a model whereby emergent metabolites signal a beneficial
               multispecies microbiome.",
  journal   = "Elife",
  publisher = "elifesciences.org",
  volume    =  6,
  month     =  jan,
  year      =  2017,
  keywords  = "D. melanogaster; S. cerevisiae; ecology; host-microbe
               interactions; infectious disease; metabolism; microbe-microbe
               interactions; microbiology; microbiota; olfaction;Holo-Omics",
  language  = "en"
}

@ARTICLE{Wu2012-jt,
  title     = "The role of gut microbiota in immune homeostasis and
               autoimmunity",
  author    = "Wu, Hsin-Jung and Wu, Eric",
  abstract  = "Keeping a delicate balance in the immune system by eliminating
               invading pathogens, while still maintaining self-tolerance to
               avoid autoimmunity, is critical for the body's health. The gut
               microbiota that resides in the gastrointestinal tract provides
               essential health benefits to its host, particularly by
               regulating immune homeostasis. Moreover, it has recently become
               obvious that alterations of these gut microbial communities can
               cause immune dysregulation, leading to autoimmune disorders.
               Here we review the advances in our understanding of how the gut
               microbiota regulates innate and adaptive immune homeostasis,
               which in turn can affect the development of not only intestinal
               but also systemic autoimmune diseases. Exploring the interaction
               of gut microbes and the host immune system will not only allow
               us to understand the pathogenesis of autoimmune diseases but
               will also provide us new foundations for the design of novel
               immuno- or microbe-based therapies.",
  journal   = "Gut Microbes",
  publisher = "Taylor \& Francis",
  volume    =  3,
  number    =  1,
  pages     = "4--14",
  month     =  jan,
  year      =  2012,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Kivioja2011-fe,
  title     = "Counting absolute numbers of molecules using unique molecular
               identifiers",
  author    = "Kivioja, Teemu and V{\"a}h{\"a}rautio, Anna and Karlsson, Kasper
               and Bonke, Martin and Enge, Martin and Linnarsson, Sten and
               Taipale, Jussi",
  abstract  = "Counting individual RNA or DNA molecules is difficult because
               they are hard to copy quantitatively for detection. To overcome
               this limitation, we applied unique molecular identifiers (UMIs),
               which make each molecule in a population distinct, to
               genome-scale human karyotyping and mRNA sequencing in Drosophila
               melanogaster. Use of this method can improve accuracy of almost
               any next-generation sequencing method, including chromatin
               immunoprecipitation-sequencing, genome assembly, diagnostics and
               manufacturing-process control and monitoring.",
  journal   = "Nat. Methods",
  publisher = "nature.com",
  volume    =  9,
  number    =  1,
  pages     = "72--74",
  month     =  nov,
  year      =  2011,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Schroeder2006-dn,
  title     = "The {RIN}: an {RNA} integrity number for assigning integrity
               values to {RNA} measurements",
  author    = "Schroeder, Andreas and Mueller, Odilo and Stocker, Susanne and
               Salowsky, Ruediger and Leiber, Michael and Gassmann, Marcus and
               Lightfoot, Samar and Menzel, Wolfram and Granzow, Martin and
               Ragg, Thomas",
  abstract  = "BACKGROUND: The integrity of RNA molecules is of paramount
               importance for experiments that try to reflect the snapshot of
               gene expression at the moment of RNA extraction. Until recently,
               there has been no reliable standard for estimating the integrity
               of RNA samples and the ratio of 28S:18S ribosomal RNA, the
               common measure for this purpose, has been shown to be
               inconsistent. The advent of microcapillary electrophoretic RNA
               separation provides the basis for an automated high-throughput
               approach, in order to estimate the integrity of RNA samples in
               an unambiguous way. METHODS: A method is introduced that
               automatically selects features from signal measurements and
               constructs regression models based on a Bayesian learning
               technique. Feature spaces of different dimensionality are
               compared in the Bayesian framework, which allows selecting a
               final feature combination corresponding to models with high
               posterior probability. RESULTS: This approach is applied to a
               large collection of electrophoretic RNA measurements recorded
               with an Agilent 2100 bioanalyzer to extract an algorithm that
               describes RNA integrity. The resulting algorithm is a
               user-independent, automated and reliable procedure for
               standardization of RNA quality control that allows the
               calculation of an RNA integrity number (RIN). CONCLUSION: Our
               results show the importance of taking characteristics of several
               regions of the recorded electropherogram into account in order
               to get a robust and reliable prediction of RNA integrity,
               especially if compared to traditional methods.",
  journal   = "BMC Mol. Biol.",
  publisher = "bmcmolbiol.biomedcentral.com",
  volume    =  7,
  pages     = "3",
  month     =  jan,
  year      =  2006,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Huang2020-xf,
  title     = "Scalable and cost-effective ribonuclease-based {rRNA} depletion
               for transcriptomics",
  author    = "Huang, Yiming and Sheth, Ravi U and Kaufman, Andrew and Wang,
               Harris H",
  abstract  = "Bacterial RNA sequencing (RNA-seq) is a powerful approach for
               quantitatively delineating the global transcriptional profiles
               of microbes in order to gain deeper understanding of their
               physiology and function. Cost-effective bacterial RNA-seq
               requires efficient physical removal of ribosomal RNA (rRNA),
               which otherwise dominates transcriptomic reads. However, current
               methods to effectively deplete rRNA of diverse non-model
               bacterial species are lacking. Here, we describe a probe and
               ribonuclease based strategy for bacterial rRNA removal. We
               implemented the method using either chemically synthesized
               oligonucleotides or amplicon-based single-stranded DNA probes
               and validated the technique on three novel gut microbiota
               isolates from three distinct phyla. We further showed that
               different probe sets can be used on closely related species. We
               provide a detailed methods protocol, probe sets for >5000 common
               microbes from RefSeq, and an online tool to generate custom
               probe libraries. This approach lays the groundwork for
               large-scale and cost-effective bacterial transcriptomics
               studies.",
  journal   = "Nucleic Acids Res.",
  publisher = "academic.oup.com",
  volume    =  48,
  number    =  4,
  pages     = "e20",
  month     =  feb,
  year      =  2020,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Gu2016-yf,
  title     = "Depletion of Abundant Sequences by Hybridization ({DASH)}: using
               Cas9 to remove unwanted high-abundance species in sequencing
               libraries and molecular counting applications",
  author    = "Gu, W and Crawford, E D and O'Donovan, B D and Wilson, M R and
               Chow, E D and Retallack, H and DeRisi, J L",
  abstract  = "Next-generation sequencing has generated a need for a broadly
               applicable method to remove unwanted high-abundance species
               prior to sequencing. We introduce DASH (Depletion of Abundant
               Sequences by Hybridization). Sequencing libraries are 'DASHed'
               with recombinant Cas9 protein complexed with a library of guide
               RNAs targeting unwanted species for cleavage, thus preventing
               them from consuming sequencing space. We demonstrate a more than
               99 \% reduction of mitochondrial rRNA in HeLa cells, and
               enrichment of pathogen sequences in patient samples. We also
               demonstrate an application of DASH in cancer. This simple method
               can be adapted for any sample type and increases sequencing
               yield without additional cost.",
  journal   = "Genome Biol.",
  publisher = "Springer",
  volume    =  17,
  pages     = "41",
  month     =  mar,
  year      =  2016,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Kraus2019-fq,
  title     = "Efficient and specific oligo-based depletion of {rRNA}",
  author    = "Kraus, Amelie J and Brink, Benedikt G and Siegel, T Nicolai",
  abstract  = "In most organisms, ribosomal RNA (rRNA) contributes to >85\% of
               total RNA. Thus, to obtain useful information from
               RNA-sequencing (RNA-seq) analyses at reasonable sequencing
               depth, typically, mature polyadenylated transcripts are enriched
               or rRNA molecules are depleted. Targeted depletion of rRNA is
               particularly useful when studying transcripts lacking a poly(A)
               tail, such as some non-coding RNAs (ncRNAs), most bacterial RNAs
               and partially degraded or immature transcripts. While several
               commercially available kits allow effective rRNA depletion,
               their efficiency relies on a high degree of sequence homology
               between oligonucleotide probes and the target RNA. This
               restricts the use of such kits to a limited number of organisms
               with conserved rRNA sequences. In this study we describe the use
               of biotinylated oligos and streptavidin-coated paramagnetic
               beads for the efficient and specific depletion of trypanosomal
               rRNA. Our approach reduces the levels of the most abundant rRNA
               transcripts to less than 5\% with minimal off-target effects. By
               adjusting the sequence of the oligonucleotide probes, our
               approach can be used to deplete rRNAs or other abundant
               transcripts independent of species. Thus, our protocol provides
               a useful alternative for rRNA removal where enrichment of
               polyadenylated transcripts is not an option and commercial kits
               for rRNA are not available.",
  journal   = "Sci. Rep.",
  publisher = "nature.com",
  volume    =  9,
  number    =  1,
  pages     = "12281",
  month     =  aug,
  year      =  2019,
  keywords  = "Holo-Omics",
  language  = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Lee2021-th,
  title     = "Comparability of reference-based and reference-free
               transcriptome analysis approaches at the gene expression level",
  author    = "Lee, Sung-Gwon and Na, Dokyun and Park, Chungoo",
  abstract  = "BACKGROUND: Lately, high-throughput RNA sequencing has been
               extensively used to elucidate the transcriptome landscape and
               dynamics of cell types of different species. In particular, for
               most non-model organisms lacking complete reference genomes with
               high-quality annotation of genetic information, reference-free
               (RF) de novo transcriptome analyses, rather than reference-based
               (RB) approaches, are widely used, and RF analyses have
               substantially contributed toward understanding the mechanisms
               regulating key biological processes and functions. To date,
               numerous bioinformatics studies have been conducted for
               assessing the workflow, production rate, and completeness of
               transcriptome assemblies within and between RF and RB datasets.
               However, the degree of consistency and variability of results
               obtained by analyzing gene expression levels through these two
               different approaches have not been adequately documented.
               RESULTS: In the present study, we evaluated the differences in
               expression profiles obtained with RF and RB approaches and
               revealed that the former tends to be satisfactorily replaced by
               the latter with respect to transcriptome repertoires, as well as
               from a gene expression quantification perspective. In addition,
               we urge cautious interpretation of these findings. Several genes
               that are lowly expressed, have long coding sequences, or belong
               to large gene families must be validated carefully, whenever
               gene expression levels are calculated using the RF method.
               CONCLUSIONS: Our empirical results indicate important
               contributions toward addressing transcriptome-related biological
               questions in non-model organisms.",
  journal   = "BMC Bioinformatics",
  publisher = "bmcbioinformatics.biomedcentral …",
  volume    =  22,
  number    = "Suppl 11",
  pages     = "310",
  month     =  oct,
  year      =  2021,
  keywords  = "Quantification of gene expression; RNA-seq; Reference-based
               assembly; Reference-free assembly; Transcriptome
               analysis;Holo-Omics",
  language  = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Yan2017-xh,
  title     = "A comparison of graph- and kernel-based --omics data integration
               algorithms for classifying complex traits",
  author    = "Yan, Kang K and Zhao, Hongyu and Pang, Herbert",
  abstract  = "High-throughput sequencing data are widely collected and
               analyzed in the study of complex diseases in quest of improving
               human health. Well-studied algorithms mostly deal with single
               data source, and cannot fully utilize the potential of these
               multi-omics data sources. In order to provide a holistic
               understanding of human health and diseases, it is necessary to
               integrate multiple data sources. Several algorithms have been
               proposed so far, however, a comprehensive comparison of data
               integration algorithms for classification of binary traits is …",
  journal   = "BMC Bioinformatics",
  publisher = "Springer Science and Business Media LLC",
  volume    =  18,
  number    =  1,
  month     =  dec,
  year      =  2017,
  keywords  = "Holo-Omics",
  copyright = "http://creativecommons.org/licenses/by/4.0/",
  language  = "en"
}

@ARTICLE{Holzinger2014-mn,
  title     = "{ATHENA}: the analysis tool for heritable and environmental
               network associations",
  author    = "Holzinger, Emily R and Dudek, Scott M and Frase, Alex T and
               Pendergrass, Sarah A and Ritchie, Marylyn D",
  abstract  = "MOTIVATION: Advancements in high-throughput technology have
               allowed researchers to examine the genetic etiology of complex
               human traits in a robust fashion. Although genome-wide
               association studies have identified many novel variants
               associated with hundreds of traits, a large proportion of the
               estimated trait heritability remains unexplained. One hypothesis
               is that the commonly used statistical techniques and study
               designs are not robust to the complex etiology that may underlie
               these human traits. This etiology could include non-linear gene
               $\times$ gene or gene $\times$ environment interactions.
               Additionally, other levels of biological regulation may play a
               large role in trait variability. RESULTS: To address the need
               for computational tools that can explore enormous datasets to
               detect complex susceptibility models, we have developed a
               software package called the Analysis Tool for Heritable and
               Environmental Network Associations (ATHENA). ATHENA combines
               various variable filtering methods with machine learning
               techniques to analyze high-throughput categorical (i.e. single
               nucleotide polymorphisms) and quantitative (i.e. gene expression
               levels) predictor variables to generate multivariable models
               that predict either a categorical (i.e. disease status) or
               quantitative (i.e. cholesterol levels) outcomes. The goal of
               this article is to demonstrate the utility of ATHENA using
               simulated and biological datasets that consist of both single
               nucleotide polymorphisms and gene expression variables to
               identify complex prediction models. Importantly, this method is
               flexible and can be expanded to include other types of
               high-throughput data (i.e. RNA-seq data and biomarker
               measurements). AVAILABILITY: ATHENA is freely available for
               download. The software, user manual and tutorial can be
               downloaded from http://ritchielab.psu.edu/ritchielab/software.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  30,
  number    =  5,
  pages     = "698--705",
  month     =  mar,
  year      =  2014,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Tan2020-lq,
  title     = "A multi-omics supervised autoencoder for pan-cancer clinical
               outcome endpoints prediction",
  author    = "Tan, Kaiwen and Huang, Weixian and Hu, Jinlong and Dong, Shoubin",
  abstract  = "BACKGROUND: With the rapid development of sequencing
               technologies, collecting diverse types of cancer omics data
               become more cost-effective. Many computational methods attempted
               to represent and fuse multiple omics into a comprehensive view
               of cancer. However, different types of omics are related and
               heterogeneous. Most of the existing methods do not consider the
               difference between omics, so the biological knowledge of
               individual omics may not be fully excavated. And for a given
               task (e.g. predicting overall survival), these methods prefer to
               use sample similarity or domain knowledge to learn a more
               reasonable representation of omics, but it's not enough.
               METHODS: For the purpose of learning more useful representation
               for individual omics and fusing them to improve the prediction
               ability, we proposed an autoencoder-based method named MOSAE
               (Multi-omics Supervised Autoencoder). In our method, a specific
               autoencoder were designed for each omics according to their size
               of dimension to generate omics-specific representations. Then, a
               supervised autoencoder was constructed based on specific
               autoencoder by using labels to enforce each specific autoencoder
               to learn both omics-specific and task-specific representations.
               Finally, representations of different omics that generate from
               supervised autoencoders were fused in a traditional but powerful
               way, and the fused representation was used for subsequent
               predictive tasks. RESULTS: We applied our method over TCGA
               Pan-Cancer dataset to predict four different clinical outcome
               endpoints (OS, PFI, DFI, and DSS). Compared with traditional and
               state-of-the-art methods, MOSAE achieved better predictive
               performance. We also tested the effects of each improvement,
               which all have a positive effect on predictive performance.
               CONCLUSIONS: Predicting clinical outcome endpoints are very
               important for precision medicine and personalized medicine. And
               multi-omics fusion is an effective way to solve this problem.
               MOSAE is a powerful multi-omics fusion method, which can
               generate both omics-specific and task-specific representation
               for given endpoint predictive tasks and improve the predictive
               performance.",
  journal   = "BMC Med. Inform. Decis. Mak.",
  publisher = "Springer",
  volume    =  20,
  number    = "Suppl 3",
  pages     = "129",
  month     =  jul,
  year      =  2020,
  keywords  = "Autoencoder; Endpoints; Fusion; Multic-omics; Pan-Cancer;
               Representation;Holo-Omics",
  language  = "en"
}

@ARTICLE{Zhang2021-sn,
  title    = "Impact of {Bead-Beating} Intensity on the Genus- and
              {Species-Level} Characterization of the Gut Microbiome Using
              Amplicon and Complete {16S} {rRNA} Gene Sequencing",
  author   = "Zhang, Bo and Brock, Matthew and Arana, Carlos and Dende,
              Chaitanya and van Oers, Nicolai Stanislas and Hooper, Lora V and
              Raj, Prithvi",
  abstract = "Bead-beating within a DNA extraction protocol is critical for
              complete microbial cell lysis and accurate assessment of the
              abundance and composition of the microbiome. While the impact of
              bead-beating on the recovery of OTUs at the phylum and class
              level have been studied, its influence on species-level
              microbiome recovery is not clear. Recent advances in sequencing
              technology has allowed species-level resolution of the microbiome
              using full length 16S rRNA gene sequencing instead of smaller
              amplicons that only capture a few hypervariable regions of the
              gene. We sequenced the v3-v4 hypervariable region as well as the
              full length 16S rRNA gene in mouse and human stool samples and
              discovered major clusters of gut bacteria that exhibit different
              levels of sensitivity to bead-beating treatment. Full length 16S
              rRNA gene sequencing unraveled vast species diversity in the
              mouse and human gut microbiome and enabled characterization of
              several unclassified OTUs in amplicon data. Many species of major
              gut commensals such as Bacteroides, Lactobacillus, Blautia,
              Clostridium, Escherichia, Roseburia, Helicobacter, and
              Ruminococcus were identified. Interestingly, v3-v4 amplicon data
              classified about 50\% of Ruminococcus reads as Ruminococcus
              gnavus species which showed maximum abundance in a 9 min beaten
              sample. However, the remaining 50\% of reads could not be
              assigned to any species. Full length 16S rRNA gene sequencing
              data showed that the majority of the unclassified reads were
              Ruminococcus albus species which unlike R. gnavus showed maximum
              recovery in the unbeaten sample instead. Furthermore, we found
              that the Blautia hominis and Streptococcus parasanguinis species
              were differently sensitive to bead-beating treatment than the
              rest of the species in these genera. Thus, the present study
              demonstrates species level variations in sensitivity to
              bead-beating treatment that could only be resolved with full
              length 16S rRNA sequencing. This study identifies species of
              common gut commensals and potential pathogens that require
              minimum (0-1 min) or extensive (4-9 min) bead-beating for their
              maximal recovery.",
  journal  = "Front. Cell. Infect. Microbiol.",
  volume   =  11,
  pages    = "678522",
  month    =  oct,
  year     =  2021,
  keywords = "16S; DNA extraction; bead-beating; long-read; microbiome;
              sequencing; short-read;Holo-Omics",
  language = "en"
}

@ARTICLE{Goussarov2022-ih,
  title     = "Introduction to the principles and methods underlying the
               recovery of metagenome-assembled genomes from metagenomic data",
  author    = "Goussarov, Gleb and Mysara, Mohamed and Vandamme, Peter and Van
               Houdt, Rob",
  abstract  = "The rise of metagenomics offers a leap forward for understanding
               the genetic diversity of microorganisms in many different
               complex environments by providing a platform that can identify
               potentially unlimited numbers of known and novel microorganisms.
               As such, it is impossible to imagine new major initiatives
               without metagenomics. Nevertheless, it represents a relatively
               new discipline with various levels of complexity and demands on
               bioinformatics. The underlying principles and methods used in
               metagenomics are often seen as common knowledge and often not
               detailed or fragmented. Therefore, we reviewed these to guide
               microbiologists in taking the first steps into metagenomics. We
               specifically focus on a workflow aimed at reconstructing
               individual genomes, that is, metagenome-assembled genomes,
               integrating DNA sequencing, assembly, binning, identification
               and annotation.",
  journal   = "Microbiologyopen",
  publisher = "Wiley",
  volume    =  11,
  number    =  3,
  pages     = "e1298",
  month     =  jun,
  year      =  2022,
  keywords  = "annotation; assembly; binning; metagenome-assembled genome;
               metagenomics; sequencing;Holo-Omics",
  copyright = "http://creativecommons.org/licenses/by/4.0/",
  language  = "en"
}

@ARTICLE{Evans2020-hs,
  title     = "To dereplicate or not to dereplicate?",
  author    = "Evans, Jacob T and Denef, Vincent J",
  abstract  = "Metagenome-assembled genomes (MAGs) expand our understanding of
               microbial diversity, evolution, and ecology. Concerns have been
               raised on how sequencing, assembly, binning, and quality
               assessment tools may result in MAGs that do not reflect single
               populations in nature. Here, we reflect on another issue, i.e.,
               how to handle highly similar MAGs assembled from independent
               data sets. Obtaining multiple genomic representatives for a
               species is highly valuable, as it allows for population genomic
               analyses; however, when retaining genomes of closely related
               populations, it complicates MAG quality assessment and abundance
               inferences. We show that (i) published data sets contain a large
               fraction of MAGs sharing >99\% average nucleotide identity, (ii)
               different software packages and parameters used to resolve this
               redundancy remove very different numbers of MAGs, and (iii) the
               removal of closely related genomes leads to losses of
               population-specific auxiliary genes. Finally, we highlight some
               approaches that can infer strain-specific dynamics across a
               sample series without dereplication.",
  journal   = "mSphere",
  publisher = "American Society for Microbiology",
  volume    =  5,
  number    =  3,
  month     =  may,
  year      =  2020,
  keywords  = "MAG; binning; dereplication; metagenomics; population genomics;
               software;Holo-Omics",
  copyright = "https://creativecommons.org/licenses/by/4.0/",
  language  = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Chaumeil2022-jr,
  title     = "{GTDB-Tk} v2: memory friendly classification with the genome
               taxonomy database",
  author    = "Chaumeil, Pierre-Alain and Mussig, Aaron J and Hugenholtz,
               Philip and Parks, Donovan H",
  abstract  = "SUMMARY: The Genome Taxonomy Database (GTDB) and associated
               taxonomic classification toolkit (GTDB-Tk) have been widely
               adopted by the microbiology community. However, the growing size
               of the GTDB bacterial reference tree has resulted in GTDB-Tk
               requiring substantial amounts of memory (∼320 GB) which limits
               its adoption and ease of use. Here, we present an update to
               GTDB-Tk that uses a divide-and-conquer approach where user
               genomes are initially placed into a bacterial reference tree
               with family-level representatives followed by placement into an
               appropriate class-level subtree comprising species
               representatives. This substantially reduces the memory
               requirements of GTDB-Tk while having minimal impact on
               classification. AVAILABILITY AND IMPLEMENTATION: GTDB-Tk is
               implemented in Python and licenced under the GNU General Public
               Licence v3.0. Source code and documentation are available at:
               https://github.com/ecogenomics/gtdbtk. SUPPLEMENTARY
               INFORMATION: Supplementary data are available at Bioinformatics
               online.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  38,
  number    =  23,
  pages     = "5315--5316",
  month     =  nov,
  year      =  2022,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Tanizawa2017-uy,
  title     = "{DFAST}: a flexible prokaryotic genome annotation pipeline for
               faster genome publication",
  author    = "Tanizawa, Yasuhiro and Fujisawa, Takatomo and Nakamura, Yasukazu",
  abstract  = "AbstractSummary. We developed a prokaryotic genome annotation
               pipeline, DFAST, that also supports genome submission to public
               sequence databases. DFAST was orig",
  journal   = "Bioinformatics",
  publisher = "Oxford Academic",
  volume    =  34,
  number    =  6,
  pages     = "1037--1039",
  month     =  nov,
  year      =  2017,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Speicher2015-sv,
  title     = "Integrating different data types by regularized unsupervised
               multiple kernel learning with application to cancer subtype
               discovery",
  author    = "Speicher, Nora K and Pfeifer, Nico",
  abstract  = "MOTIVATION: Despite ongoing cancer research, available therapies
               are still limited in quantity and effectiveness, and making
               treatment decisions for individual patients remains a hard
               problem. Established subtypes, which help guide these decisions,
               are mainly based on individual data types. However, the analysis
               of multidimensional patient data involving the measurements of
               various molecular features could reveal intrinsic
               characteristics of the tumor. Large-scale projects accumulate
               this kind of data for various cancer types, but we still lack
               the computational methods to reliably integrate this information
               in a meaningful manner. Therefore, we apply and extend current
               multiple kernel learning for dimensionality reduction
               approaches. On the one hand, we add a regularization term to
               avoid overfitting during the optimization procedure, and on the
               other hand, we show that one can even use several kernels per
               data type and thereby alleviate the user from having to choose
               the best kernel functions and kernel parameters for each data
               type beforehand. RESULTS: We have identified biologically
               meaningful subgroups for five different cancer types. Survival
               analysis has revealed significant differences between the
               survival times of the identified subtypes, with P values
               comparable or even better than state-of-the-art methods.
               Moreover, our resulting subtypes reflect combined patterns from
               the different data sources, and we demonstrate that input kernel
               matrices with only little information have less impact on the
               integrated kernel matrix. Our subtypes show different responses
               to specific therapies, which could eventually assist in
               treatment decision making. AVAILABILITY AND IMPLEMENTATION: An
               executable is available upon request.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  31,
  number    =  12,
  pages     = "i268--75",
  month     =  jun,
  year      =  2015,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Tepeli2021-as,
  title     = "{PAMOGK}: a pathway graph kernel-based multiomics approach for
               patient clustering",
  author    = "Tepeli, Yasin Ilkagan and {\"U}nal, Ali Burak and Akdemir,
               Furkan Mustafa and Tastan, Oznur",
  abstract  = "MOTIVATION: Accurate classification of patients into molecular
               subgroups is critical for the development of effective
               therapeutics and for deciphering what drives these subgroups to
               cancer. The availability of multiomics data catalogs for large
               cohorts of cancer patients provides multiple views into the
               molecular biology of the tumors with unprecedented resolution.
               RESULTS: We develop Pathway-based MultiOmic Graph Kernel
               clustering (PAMOGK) that integrates multiomics patient data with
               existing biological knowledge on pathways. We develop a novel
               graph kernel that evaluates patient similarities based on a
               single molecular alteration type in the context of a pathway. To
               corroborate multiple views of patients evaluated by hundreds of
               pathways and molecular alteration combinations, we use multiview
               kernel clustering. Applying PAMOGK to kidney renal clear cell
               carcinoma (KIRC) patients results in four clusters with
               significantly different survival times (P-value =1.24e-11). When
               we compare PAMOGK to eight other state-of-the-art multiomics
               clustering methods, PAMOGK consistently outperforms these in
               terms of its ability to partition KIRC patients into groups with
               different survival distributions. The discovered patient
               subgroups also differ with respect to other clinical parameters
               such as tumor stage and grade, and primary tumor and metastasis
               tumor spreads. The pathways identified as important are highly
               relevant to KIRC. AVAILABILITY AND IMPLEMENTATION:
               github.com/tastanlab/pamogk. SUPPLEMENTARY INFORMATION:
               Supplementary data are available at Bioinformatics online.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  36,
  number    =  21,
  pages     = "5237--5246",
  month     =  jan,
  year      =  2021,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Rappoport2019-zn,
  title     = "{NEMO}: cancer subtyping by integration of partial multi-omic
               data",
  author    = "Rappoport, Nimrod and Shamir, Ron",
  abstract  = "MOTIVATION: Cancer subtypes were usually defined based on
               molecular characterization of single omic data. Increasingly,
               measurements of multiple omic profiles for the same cohort are
               available. Defining cancer subtypes using multi-omic data may
               improve our understanding of cancer, and suggest more precise
               treatment for patients. RESULTS: We present NEMO (NEighborhood
               based Multi-Omics clustering), a novel algorithm for multi-omics
               clustering. Importantly, NEMO can be applied to partial datasets
               in which some patients have data for only a subset of the omics,
               without performing data imputation. In extensive testing on ten
               cancer datasets spanning 3168 patients, NEMO achieved results
               comparable to the best of nine state-of-the-art multi-omics
               clustering algorithms on full data and showed an improvement on
               partial data. On some of the partial data tests, PVC, a
               multi-view algorithm, performed better, but it is limited to two
               omics and to positive partial data. Finally, we demonstrate the
               advantage of NEMO in detailed analysis of partial data of AML
               patients. NEMO is fast and much simpler than existing
               multi-omics clustering algorithms, and avoids iterative
               optimization. AVAILABILITY AND IMPLEMENTATION: Code for NEMO and
               for reproducing all NEMO results in this paper is in github:
               https://github.com/Shamir-Lab/NEMO. SUPPLEMENTARY INFORMATION:
               Supplementary data are available at Bioinformatics online.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  35,
  number    =  18,
  pages     = "3348--3356",
  month     =  sep,
  year      =  2019,
  keywords  = "Holo-Omics",
  language  = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@MISC{Tipping2001-tj,
  title        = "Sparse Bayesian learning and the relevance vector machine",
  author       = "Tipping, Michael E",
  abstract     = "… While the range of models of the type (1) that we can
                  address is extremely broad, we concentrate here on a
                  specialisation that we denote the ' relevance vector machine
                  ' (RVM), …",
  publisher    = "jmlr.org",
  year         =  2001,
  howpublished = "\url{https://www.jmlr.org/papers/volume1/tipping01a/tipping01a.pdf?ref=https://githubhelp.com}",
  note         = "Accessed: 2023-4-18",
  keywords     = "Holo-Omics"
}

@ARTICLE{Lanckriet2004-kw,
  title     = "A statistical framework for genomic data fusion",
  author    = "Lanckriet, Gert R G and De Bie, Tijl and Cristianini, Nello and
               Jordan, Michael I and Noble, William Stafford",
  abstract  = "MOTIVATION: During the past decade, the new focus on genomics
               has highlighted a particular challenge: to integrate the
               different views of the genome that are provided by various types
               of experimental data. RESULTS: This paper describes a
               computational framework for integrating and drawing inferences
               from a collection of genome-wide measurements. Each dataset is
               represented via a kernel function, which defines generalized
               similarity relationships between pairs of entities, such as
               genes or proteins. The kernel representation is both flexible
               and efficient, and can be applied to many different types of
               data. Furthermore, kernel functions derived from different types
               of data can be combined in a straightforward fashion. Recent
               advances in the theory of kernel methods have provided efficient
               algorithms to perform such combinations in a way that minimizes
               a statistical loss function. These methods exploit semidefinite
               programming techniques to reduce the problem of finding
               optimizing kernel combinations to a convex optimization problem.
               Computational experiments performed using yeast genome-wide
               datasets, including amino acid sequences, hydropathy profiles,
               gene expression data and known protein-protein interactions,
               demonstrate the utility of this approach. A statistical learning
               algorithm trained from all of these data to recognize particular
               classes of proteins--membrane proteins and ribosomal
               proteins--performs significantly better than the same algorithm
               trained on any single type of data. AVAILABILITY: Supplementary
               data at http://noble.gs.washington.edu/proj/sdp-svm",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  20,
  number    =  16,
  pages     = "2626--2635",
  month     =  nov,
  year      =  2004,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Seoane2014-as,
  title     = "A pathway-based data integration framework for prediction of
               disease progression",
  author    = "Seoane, Jos{\'e} A and Day, Ian N M and Gaunt, Tom R and
               Campbell, Colin",
  abstract  = "MOTIVATION: Within medical research there is an increasing trend
               toward deriving multiple types of data from the same individual.
               The most effective prognostic prediction methods should use all
               available data, as this maximizes the amount of information
               used. In this article, we consider a variety of learning
               strategies to boost prediction performance based on the use of
               all available data. IMPLEMENTATION: We consider data integration
               via the use of multiple kernel learning supervised learning
               methods. We propose a scheme in which feature selection by
               statistical score is performed separately per data type and by
               pathway membership. We further consider the introduction of a
               confidence measure for the class assignment, both to remove some
               ambiguously labeled datapoints from the training data and to
               implement a cautious classifier that only makes predictions when
               the associated confidence is high. RESULTS: We use the METABRIC
               dataset for breast cancer, with prediction of survival at 2000
               days from diagnosis. Predictive accuracy is improved by using
               kernels that exclusively use those genes, as features, which are
               known members of particular pathways. We show that yet further
               improvements can be made by using a range of additional kernels
               based on clinical covariates such as Estrogen Receptor (ER)
               status. Using this range of measures to improve prediction
               performance, we show that the test accuracy on new instances is
               nearly 80\%, though predictions are only made on 69.2\% of the
               patient cohort. AVAILABILITY: https://github.com/jseoane/FSMKL
               CONTACT: J.Seoane@bristol.ac.uk SUPPLEMENTARY INFORMATION:
               Supplementary data are available at Bioinformatics online.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  30,
  number    =  6,
  pages     = "838--845",
  month     =  mar,
  year      =  2014,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Cheng2021-nh,
  title     = "Haplotype-resolved de novo assembly using phased assembly graphs
               with hifiasm",
  author    = "Cheng, Haoyu and Concepcion, Gregory T and Feng, Xiaowen and
               Zhang, Haowen and Li, Heng",
  abstract  = "Haplotype-resolved de novo assembly is the ultimate solution to
               the study of sequence variations in a genome. However, existing
               algorithms either collapse heterozygous alleles into one
               consensus copy or fail to cleanly separate the haplotypes to
               produce high-quality phased assemblies. Here we describe
               hifiasm, a de novo assembler that takes advantage of long
               high-fidelity sequence reads to faithfully represent the
               haplotype information in a phased assembly graph. Unlike other
               graph-based assemblers that only aim to maintain the contiguity
               of one haplotype, hifiasm strives to preserve the contiguity of
               all haplotypes. This feature enables the development of a graph
               trio binning algorithm that greatly advances over standard trio
               binning. On three human and five nonhuman datasets, including
               California redwood with a ~30-Gb hexaploid genome, we show that
               hifiasm frequently delivers better assemblies than existing
               tools and consistently outperforms others on haplotype-resolved
               assembly.",
  journal   = "Nat. Methods",
  publisher = "nature.com",
  volume    =  18,
  number    =  2,
  pages     = "170--175",
  month     =  feb,
  year      =  2021,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Shin2010-rj,
  title     = "Graph sharpening",
  author    = "Shin, Hyunjung and Hill, N Jeremy and Lisewski, Andreas Martin
               and Park, Joon-Sang",
  abstract  = "In many graph-based semi-supervised learning algorithms, edge
               weights are assumed to be fixed and determined by the data
               points' (often symmetric) relationships in input space, without
               considering directionality. However, relationships may be more
               informative in one direction (e.g. from labelled to unlabelled)
               than in the reverse direction, and some relationships (e.g.
               strong weights between oppositely labelled points) are unhelpful
               in either direction. Undesirable edges may reduce the amount of
               influence an informative point can propagate to its neighbours
               -- the point and its outgoing edges have been ``blunted.'' We
               present an approach to ``sharpening'' in which weights are
               adjusted to meet an optimization criterion wherever they are
               directed towards labelled points. This principle can be applied
               to a wide variety of algorithms. In this paper, we present one
               solution satisfying the principle, in order to show that it can
               improve performance on a number of publicly available bench-mark
               data sets. When tested on a real-world problem, protein function
               classification with four vastly different molecular similarity
               graphs, sharpening improved ROC scores by 16\% on average, at
               negligible computational cost.",
  journal   = "Expert Syst. Appl.",
  publisher = "Elsevier",
  volume    =  37,
  number    =  12,
  pages     = "7870--7879",
  month     =  dec,
  year      =  2010,
  keywords  = "Machine learning; Semi-supervised learning;Holo-Omics"
}

@ARTICLE{Kim2015-kx,
  title     = "Knowledge boosting: a graph-based integration approach with
               multi-omics data and genomic knowledge for cancer clinical
               outcome prediction",
  author    = "Kim, Dokyoon and Joung, Je-Gun and Sohn, Kyung-Ah and Shin,
               Hyunjung and Park, Yu Rang and Ritchie, Marylyn D and Kim, Ju
               Han",
  abstract  = "OBJECTIVE: Cancer can involve gene dysregulation via multiple
               mechanisms, so no single level of genomic data fully elucidates
               tumor behavior due to the presence of numerous genomic
               variations within or between levels in a biological system. We
               have previously proposed a graph-based integration approach that
               combines multi-omics data including copy number alteration,
               methylation, miRNA, and gene expression data for predicting
               clinical outcome in cancer. However, genomic features likely
               interact with other genomic features in complex signaling or
               regulatory networks, since cancer is caused by alterations in
               pathways or complete processes. METHODS: Here we propose a new
               graph-based framework for integrating multi-omics data and
               genomic knowledge to improve power in predicting clinical
               outcomes and elucidate interplay between different levels. To
               highlight the validity of our proposed framework, we used an
               ovarian cancer dataset from The Cancer Genome Atlas for
               predicting stage, grade, and survival outcomes. RESULTS:
               Integrating multi-omics data with genomic knowledge to construct
               pre-defined features resulted in higher performance in clinical
               outcome prediction and higher stability. For the grade outcome,
               the model with gene expression data produced an area under the
               receiver operating characteristic curve (AUC) of 0.7866.
               However, models of the integration with pathway, Gene Ontology,
               chromosomal gene set, and motif gene set consistently
               outperformed the model with genomic data only, attaining AUCs of
               0.7873, 0.8433, 0.8254, and 0.8179, respectively. CONCLUSIONS:
               Integrating multi-omics data and genomic knowledge to improve
               understanding of molecular pathogenesis and underlying biology
               in cancer should improve diagnostic and prognostic indicators
               and the effectiveness of therapies.",
  journal   = "J. Am. Med. Inform. Assoc.",
  publisher = "academic.oup.com",
  volume    =  22,
  number    =  1,
  pages     = "109--120",
  month     =  jan,
  year      =  2015,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Wang2021-wb,
  title     = "{MOGONET} integrates multi-omics data using graph convolutional
               networks allowing patient classification and biomarker
               identification",
  author    = "Wang, Tongxin and Shao, Wei and Huang, Zhi and Tang, Haixu and
               Zhang, Jie and Ding, Zhengming and Huang, Kun",
  abstract  = "To fully utilize the advances in omics technologies and achieve
               a more comprehensive understanding of human diseases, novel
               computational methods are required for integrative analysis of
               multiple types of omics data. Here, we present a novel
               multi-omics integrative method named Multi-Omics Graph
               cOnvolutional NETworks (MOGONET) for biomedical classification.
               MOGONET jointly explores omics-specific learning and cross-omics
               correlation learning for effective multi-omics data
               classification. We demonstrate that MOGONET outperforms other
               state-of-the-art supervised multi-omics integrative analysis
               approaches from different biomedical classification applications
               using mRNA expression data, DNA methylation data, and microRNA
               expression data. Furthermore, MOGONET can identify important
               biomarkers from different omics data types related to the
               investigated biomedical problems.",
  journal   = "Nat. Commun.",
  publisher = "nature.com",
  volume    =  12,
  number    =  1,
  pages     = "3445",
  month     =  jun,
  year      =  2021,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Mostafavi2010-aa,
  title     = "Fast integration of heterogeneous data sources for predicting
               gene function with limited annotation",
  author    = "Mostafavi, Sara and Morris, Quaid",
  abstract  = "MOTIVATION: Many algorithms that integrate multiple functional
               association networks for predicting gene function construct a
               composite network as a weighted sum of the individual networks
               and then use the composite network to predict gene function. The
               weight assigned to an individual network represents the
               usefulness of that network in predicting a given gene function.
               However, because many categories of gene function have a small
               number of annotations, the process of assigning these network
               weights is prone to overfitting. RESULTS: Here, we address this
               problem by proposing a novel approach to combining multiple
               functional association networks. In particular, we present a
               method where network weights are simultaneously optimized on
               sets of related function categories. The method is simpler and
               faster than existing approaches. Further, we show that it
               produces composite networks with improved function prediction
               accuracy using five example species (yeast, mouse, fly,
               Esherichia coli and human). AVAILABILITY: Networks and code are
               available from: http://morrislab.med.utoronto.ca/sara/SW",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  26,
  number    =  14,
  pages     = "1759--1765",
  month     =  jul,
  year      =  2010,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Wu2010-jd,
  title     = "Prediction of human functional genetic networks from
               heterogeneous data using {RVM-based} ensemble learning",
  author    = "Wu, Chia-Chin and Asgharzadeh, Shahab and Triche, Timothy J and
               D'Argenio, David Z",
  abstract  = "MOTIVATION: Three major problems confront the construction of a
               human genetic network from heterogeneous genomics data using
               kernel-based approaches: definition of a robust gold-standard
               negative set, large-scale learning and massive missing data
               values. RESULTS: The proposed graph-based approach generates a
               robust GSN for the training process of genetic network
               construction. The RVM-based ensemble model that combines
               AdaBoost and reduced-feature yields improved performance on
               large-scale learning problems with massive missing values in
               comparison to Na{\"\i}ve Bayes. CONTACT: dargenio@bmsr.usc.edu
               SUPPLEMENTARY INFORMATION: Supplementary material is available
               at Bioinformatics online.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  26,
  number    =  6,
  pages     = "807--813",
  month     =  mar,
  year      =  2010,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Kim2017-ao,
  title     = "Erratum to: Meta-analytic support vector machine for integrating
               multiple omics data",
  author    = "Kim, Sunghwan and Jhong, Jae-Hwan and Lee, Jungjun and Koo,
               Ja-Yong",
  abstract  = "[This corrects the article DOI: 10.1186/s13040-017-0126-8.].",
  journal   = "BioData Min.",
  publisher = "Springer",
  volume    =  10,
  pages     = "8",
  month     =  feb,
  year      =  2017,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Hristoskova2014-pj,
  title     = "A formal concept analysis approach to consensus clustering of
               multi-experiment expression data",
  author    = "Hristoskova, Anna and Boeva, Veselka and Tsiporkova, Elena",
  abstract  = "BACKGROUND: Presently, with the increasing number and complexity
               of available gene expression datasets, the combination of data
               from multiple microarray studies addressing a similar biological
               question is gaining importance. The analysis and integration of
               multiple datasets are expected to yield more reliable and robust
               results since they are based on a larger number of samples and
               the effects of the individual study-specific biases are
               diminished. This is supported by recent studies suggesting that
               important biological signals are often preserved or enhanced by
               multiple experiments. An approach to combining data from
               different experiments is the aggregation of their clusterings
               into a consensus or representative clustering solution which
               increases the confidence in the common features of all the
               datasets and reveals the important differences among them.
               RESULTS: We propose a novel generic consensus clustering
               technique that applies Formal Concept Analysis (FCA) approach
               for the consolidation and analysis of clustering solutions
               derived from several microarray datasets. These datasets are
               initially divided into groups of related experiments with
               respect to a predefined criterion. Subsequently, a consensus
               clustering algorithm is applied to each group resulting in a
               clustering solution per group.These solutions are pooled
               together and further analysed by employing FCA which allows
               extracting valuable insights from the data and generating a gene
               partition over all the experiments. In order to validate the
               FCA-enhanced approach two consensus clustering algorithms are
               adapted to incorporate the FCA analysis. Their performance is
               evaluated on gene expression data from multi-experiment study
               examining the global cell-cycle control of fission yeast. The
               FCA results derived from both methods demonstrate that, although
               both algorithms optimize different clustering characteristics,
               FCA is able to overcome and diminish these differences and
               preserve some relevant biological signals. CONCLUSIONS: The
               proposed FCA-enhanced consensus clustering technique is a
               general approach to the combination of clustering algorithms
               with FCA for deriving clustering solutions from multiple gene
               expression matrices. The experimental results presented herein
               demonstrate that it is a robust data integration technique able
               to produce good quality clustering solution that is
               representative for the whole set of expression matrices.",
  journal   = "BMC Bioinformatics",
  publisher = "Springer",
  volume    =  15,
  pages     = "151",
  month     =  may,
  year      =  2014,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Bonnet2015-ff,
  title     = "Integrative multi-omics module network inference with
               {Lemon-Tree}",
  author    = "Bonnet, Eric and Calzone, Laurence and Michoel, Tom",
  abstract  = "Module network inference is an established statistical method to
               reconstruct co-expression modules and their upstream regulatory
               programs from integrated multi-omics datasets measuring the
               activity levels of various cellular components across different
               individuals, experimental conditions or time points of a dynamic
               process. We have developed Lemon-Tree, an open-source,
               platform-independent, modular, extensible software package
               implementing state-of-the-art ensemble methods for module
               network inference. We benchmarked Lemon-Tree using large-scale
               tumor datasets and showed that Lemon-Tree algorithms compare
               favorably with state-of-the-art module network inference
               software. We also analyzed a large dataset of somatic
               copy-number alterations and gene expression levels measured in
               glioblastoma samples from The Cancer Genome Atlas and found that
               Lemon-Tree correctly identifies known glioblastoma oncogenes and
               tumor suppressors as master regulators in the inferred module
               network. Novel candidate driver genes predicted by Lemon-Tree
               were validated using tumor pathway and survival analyses.
               Lemon-Tree is available from http://lemon-tree.googlecode.com
               under the GNU General Public License version 2.0.",
  journal   = "PLoS Comput. Biol.",
  publisher = "journals.plos.org",
  volume    =  11,
  number    =  2,
  pages     = "e1003983",
  month     =  feb,
  year      =  2015,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Wang2014-jz,
  title     = "Similarity network fusion for aggregating data types on a
               genomic scale",
  author    = "Wang, Bo and Mezlini, Aziz M and Demir, Feyyaz and Fiume, Marc
               and Tu, Zhuowen and Brudno, Michael and Haibe-Kains, Benjamin
               and Goldenberg, Anna",
  abstract  = "Recent technologies have made it cost-effective to collect
               diverse types of genome-wide data. Computational methods are
               needed to combine these data to create a comprehensive view of a
               given disease or a biological process. Similarity network fusion
               (SNF) solves this problem by constructing networks of samples
               (e.g., patients) for each available data type and then
               efficiently fusing these into one network that represents the
               full spectrum of underlying data. For example, to create a
               comprehensive view of a disease given a cohort of patients, SNF
               computes and fuses patient similarity networks obtained from
               each of their data types separately, taking advantage of the
               complementarity in the data. We used SNF to combine mRNA
               expression, DNA methylation and microRNA (miRNA) expression data
               for five cancer data sets. SNF substantially outperforms single
               data type analysis and established integrative approaches when
               identifying cancer subtypes and is effective for predicting
               survival.",
  journal   = "Nat. Methods",
  publisher = "nature.com",
  volume    =  11,
  number    =  3,
  pages     = "333--337",
  month     =  mar,
  year      =  2014,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Bavafaye_Haghighi2019-ee,
  title     = "Hierarchical Classification of Cancers of Unknown Primary Using
               {Multi-Omics} Data",
  author    = "Bavafaye Haghighi, Elham and Knudsen, Michael and Elmedal
               Laursen, Britt and Besenbacher, S{\o}ren",
  abstract  = "A cancer of unknown primary (CUP) is a metastatic cancer for
               which standard diagnostic tests fail to locate the primary
               cancer. As standard treatments are based on the cancer type,
               such cases are hard to treat and have very poor prognosis. Using
               molecular data from the metastatic cancer to predict the primary
               site can make treatment choice easier and enable targeted
               therapy. In this article, we first examine the ability to
               predict cancer type using different types of omics data.
               Methylation data lead to slightly better prediction than gene
               expression and both these are superior to classification using
               somatic mutations. After using 3 data types independently, we
               notice some differences between the classes that tend to be
               misclassified, suggesting that integrating the data might
               improve accuracy. In light of the different levels of
               information provided by different omics types and to be able to
               handle missing data, we perform multi-omics classification by
               hierarchically combining the classifiers. The proposed
               hierarchical method first classifies based on the most
               informative type of omics data and then uses the other types of
               omics data to classify samples that did not get a high
               confidence classification in the first step. The resulting
               hierarchical classifier has higher accuracy than any of the
               single omics classifiers and thus proves that the combination of
               different data types is beneficial. Our results show that using
               multi-omics data can improve the classification of cancer types.
               We confirm this by testing our method on metastatic cancers from
               the MET500 dataset.",
  journal   = "Cancer Inform.",
  publisher = "journals.sagepub.com",
  volume    =  18,
  pages     = "1176935119872163",
  month     =  aug,
  year      =  2019,
  keywords  = "Cancer of unknown primary; gene expression; hierarchical
               classification; methylation; multi-omics data; somatic
               variation; targeted therapy;Holo-Omics",
  language  = "en"
}

@ARTICLE{Ma2020-ce,
  title     = "Integrative Methods and Practical Challenges for {Single-Cell}
               Multi-omics",
  author    = "Ma, Anjun and McDermaid, Adam and Xu, Jennifer and Chang, Yuzhou
               and Ma, Qin",
  abstract  = "Fast-developing single-cell multimodal omics (scMulti-omics)
               technologies enable the measurement of multiple modalities, such
               as DNA methylation, chromatin accessibility, RNA expression,
               protein abundance, gene perturbation, and spatial information,
               from the same cell. scMulti-omics can comprehensively explore
               and identify cell characteristics, while also presenting
               challenges to the development of computational methods and tools
               for integrative analyses. Here, we review these integrative
               methods and summarize the existing tools for studying a variety
               of scMulti-omics data. The various functionalities and practical
               challenges in using the available tools in the public domain are
               explored through several case studies. Finally, we identify
               remaining challenges and future trends in scMulti-omics modeling
               and analyses.",
  journal   = "Trends Biotechnol.",
  publisher = "Elsevier",
  volume    =  38,
  number    =  9,
  pages     = "1007--1022",
  month     =  sep,
  year      =  2020,
  keywords  = "analysis tools; integrative methods; single-cell multi-modality;
               single-cell sequencing technology;Holo-Omics",
  language  = "en"
}

@ARTICLE{Draghici2003-ht,
  title     = "Predicting {HIV} drug resistance with neural networks",
  author    = "Dr{\u a}ghici, Sorin and Potter, R Brian",
  abstract  = "MOTIVATION: Drug resistance is a very important factor
               influencing the failure of current HIV therapies. The ability to
               predict the drug resistance of HIV protease mutants may be
               useful in developing more effective and longer lasting treatment
               regimens. METHODS: The HIV resistance is predicted to two
               current protease inhibitors, Indinavir and Saquinavir. The
               problem was approached from two perspectives. First, a predictor
               was constructed based on the structural features of the HIV
               protease-drug inhibitor complex. A particular structure was
               represented by its list of contacts between the inhibitor and
               the protease. Next, a classifier was constructed based on the
               sequence data of various drug resistant mutants. In both cases,
               self-organizing maps were first used to extract the important
               features and cluster the patterns in an unsupervised manner.
               This was followed by subsequent labelling based on the known
               patterns in the training set. RESULTS: The prediction
               performance of the classifiers was measured by cross-validation.
               The classifier using the structure information correctly
               classified previously unseen mutants with an accuracy of between
               60 and 70\%. Several architectures were tested on the more
               abundant sequence data. The best single classifier provided an
               accuracy of 68\% and a coverage of 69\%. Multiple networks were
               then combined into various majority voting schemes. The best
               combination yielded an average of 85\% coverage and 78\%
               accuracy on previously unseen data. This is more than two times
               better than the 33\% accuracy expected from a random classifier.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  19,
  number    =  1,
  pages     = "98--107",
  month     =  jan,
  year      =  2003,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Zhang2012-nb,
  title     = "Discovery of multi-dimensional modules by integrative analysis
               of cancer genomic data",
  author    = "Zhang, Shihua and Liu, Chun-Chi and Li, Wenyuan and Shen, Hui
               and Laird, Peter W and Zhou, Xianghong Jasmine",
  abstract  = "Recent technology has made it possible to simultaneously perform
               multi-platform genomic profiling (e.g. DNA methylation (DM) and
               gene expression (GE)) of biological samples, resulting in
               so-called 'multi-dimensional genomic data'. Such data provide
               unique opportunities to study the coordination between
               regulatory mechanisms on multiple levels. However, integrative
               analysis of multi-dimensional genomics data for the discovery of
               combinatorial patterns is currently lacking. Here, we adopt a
               joint matrix factorization technique to address this challenge.
               This method projects multiple types of genomic data onto a
               common coordinate system, in which heterogeneous variables
               weighted highly in the same projected direction form a
               multi-dimensional module (md-module). Genomic variables in such
               modules are characterized by significant correlations and likely
               functional associations. We applied this method to the DM, GE,
               and microRNA expression data of 385 ovarian cancer samples from
               the The Cancer Genome Atlas project. These md-modules revealed
               perturbed pathways that would have been overlooked with only a
               single type of data, uncovered associations between different
               layers of cellular activities and allowed the identification of
               clinically distinct patient subgroups. Our study provides an
               useful protocol for uncovering hidden patterns and their
               biological implications in multi-dimensional 'omic' data.",
  journal   = "Nucleic Acids Res.",
  publisher = "academic.oup.com",
  volume    =  40,
  number    =  19,
  pages     = "9379--9391",
  month     =  oct,
  year      =  2012,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Lock2013-rq,
  title     = "{JOINT} {AND} {INDIVIDUAL} {VARIATION} {EXPLAINED} ({JIVE})
               {FOR} {INTEGRATED} {ANALYSIS} {OF} {MULTIPLE} {DATA} {TYPES}",
  author    = "Lock, Eric F and Hoadley, Katherine A and Marron, J S and Nobel,
               Andrew B",
  abstract  = "Research in several fields now requires the analysis of datasets
               in which multiple high-dimensional types of data are available
               for a common set of objects. In particular, The Cancer Genome
               Atlas (TCGA) includes data from several diverse genomic
               technologies on the same cancerous tumor samples. In this paper
               we introduce Joint and Individual Variation Explained (JIVE), a
               general decomposition of variation for the integrated analysis
               of such datasets. The decomposition consists of three terms: a
               low-rank approximation capturing joint variation across data
               types, low-rank approximations for structured variation
               individual to each data type, and residual noise. JIVE
               quantifies the amount of joint variation between data types,
               reduces the dimensionality of the data, and provides new
               directions for the visual exploration of joint and individual
               structure. The proposed method represents an extension of
               Principal Component Analysis and has clear advantages over
               popular two-block methods such as Canonical Correlation Analysis
               and Partial Least Squares. A JIVE analysis of gene expression
               and miRNA data on Glioblastoma Multiforme tumor samples reveals
               gene-miRNA associations and provides better characterization of
               tumor types.",
  journal   = "Ann. Appl. Stat.",
  publisher = "ncbi.nlm.nih.gov",
  volume    =  7,
  number    =  1,
  pages     = "523--542",
  month     =  mar,
  year      =  2013,
  keywords  = "Data fusion; Data integration; Multi-block data; Principal
               Component Analysis;Holo-Omics",
  language  = "en"
}

@ARTICLE{Ray2014-mn,
  title     = "Bayesian joint analysis of heterogeneous genomics data",
  author    = "Ray, Priyadip and Zheng, Lingling and Lucas, Joseph and Carin,
               Lawrence",
  abstract  = "SUMMARY: A non-parametric Bayesian factor model is proposed for
               joint analysis of multi-platform genomics data. The approach is
               based on factorizing the latent space (feature space) into a
               shared component and a data-specific component with the
               dimensionality of these components (spaces) inferred via a
               beta-Bernoulli process. The proposed approach is demonstrated by
               jointly analyzing gene expression/copy number variations and
               gene expression/methylation data for ovarian cancer patients,
               showing that the proposed model can potentially uncover key
               drivers related to cancer. AVAILABILITY AND IMPLEMENTATION: The
               source code for this model is written in MATLAB and has been
               made publicly available at
               https://sites.google.com/site/jointgenomics/. CONTACT:
               catherine.ll.zheng@gmail.com SUPPLEMENTARY INFORMATION:
               Supplementary data are available at Bioinformatics online.",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  30,
  number    =  10,
  pages     = "1370--1376",
  month     =  may,
  year      =  2014,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Shen2009-xr,
  title     = "Integrative clustering of multiple genomic data types using a
               joint latent variable model with application to breast and lung
               cancer subtype analysis",
  author    = "Shen, Ronglai and Olshen, Adam B and Ladanyi, Marc",
  abstract  = "MOTIVATION: The molecular complexity of a tumor manifests itself
               at the genomic, epigenomic, transcriptomic and proteomic levels.
               Genomic profiling at these multiple levels should allow an
               integrated characterization of tumor etiology. However, there is
               a shortage of effective statistical and bioinformatic tools for
               truly integrative data analysis. The standard approach to
               integrative clustering is separate clustering followed by manual
               integration. A more statistically powerful approach would
               incorporate all data types simultaneously and generate a single
               integrated cluster assignment. METHODS: We developed a joint
               latent variable model for integrative clustering. We call the
               resulting methodology iCluster. iCluster incorporates flexible
               modeling of the associations between different data types and
               the variance-covariance structure within data types in a single
               framework, while simultaneously reducing the dimensionality of
               the datasets. Likelihood-based inference is obtained through the
               Expectation-Maximization algorithm. RESULTS: We demonstrate the
               iCluster algorithm using two examples of joint analysis of copy
               number and gene expression data, one from breast cancer and one
               from lung cancer. In both cases, we identified subtypes
               characterized by concordant DNA copy number changes and gene
               expression as well as unique profiles specific to one or the
               other in a completely automated fashion. In addition, the
               algorithm discovers potentially novel subtypes by combining weak
               yet consistent alteration patterns across data types.
               AVAILABILITY: R code to implement iCluster can be downloaded at
               http://www.mskcc.org/mskcc/html/85130.cfm",
  journal   = "Bioinformatics",
  publisher = "academic.oup.com",
  volume    =  25,
  number    =  22,
  pages     = "2906--2912",
  month     =  nov,
  year      =  2009,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Mo2013-jj,
  title     = "Pattern discovery and cancer gene identification in integrated
               cancer genomic data",
  author    = "Mo, Qianxing and Wang, Sijian and Seshan, Venkatraman E and
               Olshen, Adam B and Schultz, Nikolaus and Sander, Chris and
               Powers, R Scott and Ladanyi, Marc and Shen, Ronglai",
  abstract  = "Large-scale integrated cancer genome characterization efforts
               including the cancer genome atlas and the cancer cell line
               encyclopedia have created unprecedented opportunities to study
               cancer biology in the context of knowing the entire catalog of
               genetic alterations. A clinically important challenge is to
               discover cancer subtypes and their molecular drivers in a
               comprehensive genetic context. Curtis et al. [Nature (2012)
               486(7403):346-352] has recently shown that integrative
               clustering of copy number and gene expression in 2,000 breast
               tumors reveals novel subgroups beyond the classic expression
               subtypes that show distinct clinical outcomes. To extend the
               scope of integrative analysis for the inclusion of somatic
               mutation data by massively parallel sequencing, we propose a
               framework for joint modeling of discrete and continuous
               variables that arise from integrated genomic, epigenomic, and
               transcriptomic profiling. The core idea is motivated by the
               hypothesis that diverse molecular phenotypes can be predicted by
               a set of orthogonal latent variables that represent distinct
               molecular drivers, and thus can reveal tumor subgroups of
               biological and clinical importance. Using the cancer cell line
               encyclopedia dataset, we demonstrate our method can accurately
               group cell lines by their cell-of-origin for several cancer
               types, and precisely pinpoint their known and potential cancer
               driver genes. Our integrative analysis also demonstrates the
               power for revealing subgroups that are not lineage-dependent,
               but consist of different cancer types driven by a common genetic
               alteration. Application of the cancer genome atlas colorectal
               cancer data reveals distinct integrated tumor subtypes,
               suggesting different genetic pathways in colon cancer
               progression.",
  journal   = "Proc. Natl. Acad. Sci. U. S. A.",
  publisher = "National Acad Sciences",
  volume    =  110,
  number    =  11,
  pages     = "4245--4250",
  month     =  mar,
  year      =  2013,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Meng2016-hv,
  title     = "moCluster: Identifying Joint Patterns Across Multiple Omics Data
               Sets",
  author    = "Meng, Chen and Helm, Dominic and Frejno, Martin and Kuster,
               Bernhard",
  abstract  = "Increasingly, multiple omics approaches are being applied to
               understand the complexity of biological systems. Yet,
               computational approaches that enable the efficient integration
               of such data are not well developed. Here, we describe a novel
               algorithm, termed moCluster, which discovers joint patterns
               among multiple omics data. The method first employs a multiblock
               multivariate analysis to define a set of latent variables
               representing joint patterns across input data sets, which is
               further passed to an ordinary clustering algorithm in order to
               discover joint clusters. Using simulated data, we show that
               moCluster's performance is not compromised by issues present in
               iCluster/iCluster+ (notably, the nondeterministic solution) and
               that it operates 100$\times$ to 1000$\times$ faster than
               iCluster/iCluster+. We used moCluster to cluster proteomic and
               transcriptomic data from the NCI-60 cell line panel. The
               resulting cluster model revealed different phenotypes across
               cellular subtypes, such as doubling time and drug response.
               Applying moCluster to methylation, mRNA, and protein data from a
               large study on colorectal cancer patients identified four
               molecular subtypes, including one characterized by
               microsatellite instability and high expression of genes/proteins
               involved in immunity, such as PDL1, a target of multiple drugs
               currently in development. The other three subtypes have not been
               discovered before using single data sets, which clearly
               illustrates the molecular complexity of oncogenesis and the need
               for holistic, multidata analysis strategies.",
  journal   = "J. Proteome Res.",
  publisher = "ACS Publications",
  volume    =  15,
  number    =  3,
  pages     = "755--765",
  month     =  mar,
  year      =  2016,
  keywords  = "Multiple omics data; cancer; clustering; data analysis;
               stratification;Holo-Omics",
  language  = "en"
}

@ARTICLE{Wu2015-qf,
  title     = "Fast dimension reduction and integrative clustering of
               multi-omics data using low-rank approximation: application to
               cancer molecular classification",
  author    = "Wu, Dingming and Wang, Dongfang and Zhang, Michael Q and Gu, Jin",
  abstract  = "BACKGROUND: One major goal of large-scale cancer omics study is
               to identify molecular subtypes for more accurate cancer
               diagnoses and treatments. To deal with high-dimensional cancer
               multi-omics data, a promising strategy is to find an effective
               low-dimensional subspace of the original data and then cluster
               cancer samples in the reduced subspace. However, due to
               data-type diversity and big data volume, few methods can
               integrative and efficiently find the principal low-dimensional
               manifold of the high-dimensional cancer multi-omics data.
               RESULTS: In this study, we proposed a novel low-rank
               approximation based integrative probabilistic model to fast find
               the shared principal subspace across multiple data types: the
               convexity of the low-rank regularized likelihood function of the
               probabilistic model ensures efficient and stable model fitting.
               Candidate molecular subtypes can be identified by unsupervised
               clustering hundreds of cancer samples in the reduced
               low-dimensional subspace. On testing datasets, our method
               LRAcluster (low-rank approximation based multi-omics data
               clustering) runs much faster with better clustering performances
               than the existing method. Then, we applied LRAcluster on
               large-scale cancer multi-omics data from TCGA. The pan-cancer
               analysis results show that the cancers of different tissue
               origins are generally grouped as independent clusters, except
               squamous-like carcinomas. While the single cancer type analysis
               suggests that the omics data have different subtyping abilities
               for different cancer types. CONCLUSIONS: LRAcluster is a very
               useful method for fast dimension reduction and unsupervised
               clustering of large-scale multi-omics data. LRAcluster is
               implemented in R and freely available via
               http://bioinfo.au.tsinghua.edu.cn/software/lracluster/ .",
  journal   = "BMC Genomics",
  publisher = "bmcgenomics.biomedcentral.com",
  volume    =  16,
  pages     = "1022",
  month     =  dec,
  year      =  2015,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Mo2018-ty,
  title     = "A fully Bayesian latent variable model for integrative
               clustering analysis of multi-type omics data",
  author    = "Mo, Qianxing and Shen, Ronglai and Guo, Cui and Vannucci, Marina
               and Chan, Keith S and Hilsenbeck, Susan G",
  abstract  = "Identification of clinically relevant tumor subtypes and omics
               signatures is an important task in cancer translational research
               for precision medicine. Large-scale genomic profiling studies
               such as The Cancer Genome Atlas (TCGA) Research Network have
               generated vast amounts of genomic, transcriptomic, epigenomic,
               and proteomic data. While these studies have provided great
               resources for researchers to discover clinically relevant tumor
               subtypes and driver molecular alterations, there are few
               computationally efficient methods and tools for integrative
               clustering analysis of these multi-type omics data. Therefore,
               the aim of this article is to develop a fully Bayesian latent
               variable method (called iClusterBayes) that can jointly model
               omics data of continuous and discrete data types for
               identification of tumor subtypes and relevant omics features.
               Specifically, the proposed method uses a few latent variables to
               capture the inherent structure of multiple omics data sets to
               achieve joint dimension reduction. As a result, the tumor
               samples can be clustered in the latent variable space and
               relevant omics features that drive the sample clustering are
               identified through Bayesian variable selection. This method
               significantly improve on the existing integrative clustering
               method iClusterPlus in terms of statistical inference and
               computational speed. By analyzing TCGA and simulated data sets,
               we demonstrate the excellent performance of the proposed method
               in revealing clinically meaningful tumor subtypes and driver
               omics features.",
  journal   = "Biostatistics",
  publisher = "academic.oup.com",
  volume    =  19,
  number    =  1,
  pages     = "71--86",
  month     =  jan,
  year      =  2018,
  keywords  = "Bayesian variable selection; Integrative clustering; Latent
               variable model; Multi-type omics data; iCluster; iClusterBayes;
               iClusterPlus;Holo-Omics",
  language  = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Acharjee2016-uc,
  title     = "Integration of multi-omics data for prediction of phenotypic
               traits using random forest",
  author    = "Acharjee, Animesh and Kloosterman, Bjorn and Visser, Richard G F
               and Maliepaard, Chris",
  abstract  = "BACKGROUND: In order to find genetic and metabolic pathways
               related to phenotypic traits of interest, we analyzed gene
               expression data, metabolite data obtained with GC-MS and LC-MS,
               proteomics data and a selected set of tuber quality phenotypic
               data from a diploid segregating mapping population of potato. In
               this study we present an approach to integrate these ~ omics
               data sets for the purpose of predicting phenotypic traits. This
               gives us networks of relatively small sets of interrelated ~
               omics variables that can predict, with higher accuracy, a
               quality trait of interest. RESULTS: We used Random Forest
               regression for integrating multiple ~ omics data for prediction
               of four quality traits of potato: tuber flesh colour, DSC onset,
               tuber shape and enzymatic discoloration. For tuber flesh colour
               beta-carotene hydroxylase and zeaxanthin epoxidase were ranked
               first and forty-fourth respectively both of which have
               previously been associated with flesh colour in potato tubers.
               Combining all the significant genes, LC-peaks, GC-peaks and
               proteins, the variation explained was 75 \%, only slightly more
               than what gene expression or LC-MS data explain by themselves
               which indicates that there are correlations among the variables
               across data sets. For tuber shape regressed on the gene
               expression, LC-MS, GC-MS and proteomics data sets separately,
               only gene expression data was found to explain significant
               variation. For DSC onset, we found 12 significant gene
               expression, 5 metabolite levels (GC) and 2 proteins that are
               associated with the trait. Using those 19 significant variables,
               the variation explained was 45 \%. Expression QTL (eQTL)
               analyses showed many associations with genomic regions in
               chromosome 2 with also the highest explained variation compared
               to other chromosomes. Transcriptomics and metabolomics analysis
               on enzymatic discoloration after 5 min resulted in 420
               significant genes and 8 significant LC metabolites, among which
               two were putatively identified as caffeoylquinic acid methyl
               ester and tyrosine. CONCLUSIONS: In this study, we made a
               strategy for selecting and integrating multiple ~ omics data
               using random forest method and selected representative
               individual peaks for networks based on eQTL, mQTL or pQTL
               information. Network analysis was done to interpret how a
               particular trait is associated with gene expression, metabolite
               and protein data.",
  journal   = "BMC Bioinformatics",
  publisher = "bmcbioinformatics.biomedcentral …",
  volume    = "17 Suppl 5",
  number    = "Suppl 5",
  pages     = "180",
  month     =  jun,
  year      =  2016,
  keywords  = "Data integration; Genetical genomics; Networks; Random
               forest;Holo-Omics",
  language  = "en"
}

@ARTICLE{Li2017-qk,
  title     = "Complex integrated analysis of {lncRNAs-miRNAs-mRNAs} in oral
               squamous cell carcinoma",
  author    = "Li, Simin and Chen, Xiujie and Liu, Xiangqiong and Yu, Yang and
               Pan, Hongying and Haak, Rainer and Schmidt, Jana and Ziebolz,
               Dirk and Schmalz, Gerhard",
  abstract  = "OBJECTIVES: This study aims to reveal regulatory network of
               lncRNAs-miRNAs-mRNAs in oral squamous cell carcinoma (OSCC)
               through gene expression data. MATERIAL AND METHODS:
               Differentially expressed lncRNAs, miRNAs and mRNAs (cut-off:
               False discovery rate (FDR)1.5) were unveiled by package edgeR of
               R. Cox regression analysis was performed to screen prognostic
               factors in OSCC related with overall survival (OS) and
               relapse-free survival (RFS). Protein-protein interaction (PPI)
               network was constructed for differentially expressed mRNAs using
               BioGRID, HPRD and DIP. Key hub genes were identified from top
               100 differentially expressed mRNAs ranked by betweenness
               centrality using recursive feature elimination. LncRNA-miRNA and
               miRNA-mRNA regulatory network were constructed and combined into
               ceRNAs regulatory network. Gene ontology biological terms and
               Kyoto Encyclopedia of Genes and Genomes pathways were identified
               using Fisher's exact test. RESULTS: A total of 929
               differentially expressed mRNAs, 23 differentially expressed
               lncRNAs and 29 differentially expressed miRNAs were identified.
               59 mRNAs, 6 miRNAs (hsa-mir-133a-1, hsa-mir-1-2, hsa-mir-486,
               hsa-mir-135b, hsa-mir-196b, hsa-mir-193b) and 6 lncRNAs
               (C10orf91, C2orf48, SFTA1P, FLJ41941,PART1,TTTY14) were related
               with OS; and 52 mRNAs, 4 miRNAs (hsa-mir-133a-1, hsa-mir-135b,
               hsa-mir-196b, hsa-mir-193b) and 2 lncRNAs (PART1, TTTY14) were
               associated with RFS. A support vector machine (SVM) classifier
               containing 37 key hub genes was obtained. A ceRNA regulatory
               network containing 417 nodes and 696 edges was constructed.
               ECM-receptor interaction, cytokine-cytokine receptor
               interaction, focal adhesion, arachidonic acid metabolism, and
               p53 signaling pathway were significantly enriched in the
               network. CONCLUSION: These findings uncover the pathogenesis of
               OSCC and might provide potential therapeutic targets.",
  journal   = "Oral Oncol.",
  publisher = "Elsevier",
  volume    =  73,
  pages     = "1--9",
  month     =  oct,
  year      =  2017,
  keywords  = "Biomarker; OSCC; Oral cancer; Prognosis; Regulatory network;
               ceRNA; lncRNA; mRNA; miRNA;Holo-Omics",
  language  = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Lee2017-bv,
  title     = "Identifying subtype-specific associations between gene
               expression and {DNA} methylation profiles in breast cancer",
  author    = "Lee, Garam and Bang, Lisa and Kim, So Yeon and Kim, Dokyoon and
               Sohn, Kyung-Ah",
  abstract  = "BACKGROUND: Breast cancer is a complex disease in which
               different genomic patterns exists depending on different
               subtypes. Recent researches present that multiple subtypes of
               breast cancer occur at different rates, and play a crucial role
               in planning treatment. To better understand underlying
               biological mechanisms on breast cancer subtypes, investigating
               the specific gene regulatory system via different subtypes is
               desirable. METHODS: Gene expression, as an intermediate
               phenotype, is estimated based on methylation profiles to
               identify the impact of epigenomic features on transcriptomic
               changes in breast cancer. We propose a kernel weighted
               l1-regularized regression model to incorporate tumor subtype
               information and further reveal gene regulations affected by
               different breast cancer subtypes. For the proper control of
               subtype-specific estimation, samples from different breast
               cancer subtype are learned at different rate based on target
               estimates. Kolmogorov Smirnov test is conducted to determine
               learning rate of each sample from different subtype. RESULTS: It
               is observed that genes that might be sensitive to breast cancer
               subtype show prediction improvement when estimated using our
               proposed method. Comparing to a standard method, overall
               performance is also enhanced by incorporating tumor subtypes. In
               addition, we identified subtype-specific network structures
               based on the associations between gene expression and DNA
               methylation. CONCLUSIONS: In this study, kernel weighted lasso
               model is proposed for identifying subtype-specific associations
               between gene expressions and DNA methylation profiles.
               Identification of subtype-specific gene expression associated
               with epigenomic changes might be helpful for better planning
               treatment and developing new therapies.",
  journal   = "BMC Med. Genomics",
  publisher = "bmcmedgenomics.biomedcentral …",
  volume    =  10,
  number    = "Suppl 1",
  pages     = "28",
  month     =  may,
  year      =  2017,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Ranallo-Benavidez2020-am,
  title     = "{GenomeScope} 2.0 and Smudgeplot for reference-free profiling of
               polyploid genomes",
  author    = "Ranallo-Benavidez, T Rhyker and Jaron, Kamil S and Schatz,
               Michael C",
  abstract  = "An important assessment prior to genome assembly and related
               analyses is genome profiling, where the k-mer frequencies within
               raw sequencing reads are analyzed to estimate major genome
               characteristics such as size, heterozygosity, and
               repetitiveness. Here we introduce GenomeScope 2.0
               (https://github.com/tbenavi1/genomescope2.0), which applies
               combinatorial theory to establish a detailed mathematical model
               of how k-mer frequencies are distributed in heterozygous and
               polyploid genomes. We describe and evaluate a practical
               implementation of the polyploid-aware mixture model that quickly
               and accurately infers genome properties across thousands of
               simulated and several real datasets spanning a broad range of
               complexity. We also present a method called Smudgeplot
               (https://github.com/KamilSJaron/smudgeplot) to visualize and
               estimate the ploidy and genome structure of a genome by
               analyzing heterozygous k-mer pairs. We successfully apply the
               approach to systems of known variable ploidy levels in the
               Meloidogyne genus and the extreme case of octoploid Fragaria
               $\times$ ananassa.",
  journal   = "Nat. Commun.",
  publisher = "nature.com",
  volume    =  11,
  number    =  1,
  pages     = "1432",
  month     =  mar,
  year      =  2020,
  keywords  = "Holo-Omics",
  language  = "en"
}

@ARTICLE{Wang2020-fj,
  title         = "Estimation of genome size using k-mer frequencies from
                   corrected long reads",
  author        = "Wang, Hengchao and Liu, Bo and Zhang, Yan and Jiang, Fan and
                   Ren, Yuwei and Yin, Lijuan and Liu, Hangwei and Wang, Sen
                   and Fan, Wei",
  abstract      = "The third-generation long reads sequencing technologies,
                   such as PacBio and Nanopore, have great advantages over
                   second-generation Illumina sequencing in de novo assembly
                   studies. However, due to the inherent low base accuracy,
                   third-generation sequencing data cannot be used for k-mer
                   counting and estimating genomic profile based on k-mer
                   frequencies. Thus, in current genome projects,
                   second-generation data is also necessary for accurately
                   determining genome size and other genomic characteristics.
                   We show that corrected third-generation data can be used to
                   count k-mer frequencies and estimate genome size reliably,
                   in replacement of using second-generation data. Therefore,
                   future genome projects can depend on only one sequencing
                   technology to finish both assembly and k-mer analysis, which
                   will largely decrease sequencing cost in both time and
                   money. Moreover, we present a fast light-weight tool
                   kmerfreq and use it to perform all the k-mer counting tasks
                   in this work. We have demonstrated that corrected
                   third-generation sequencing data can be used to estimate
                   genome size and developed a new open-source C/C++ k-mer
                   counting tool, kmerfreq, which is freely available at
                   https://github.com/fanagislab/kmerfreq.",
  month         =  mar,
  year          =  2020,
  keywords      = "Holo-Omics",
  archivePrefix = "arXiv",
  primaryClass  = "q-bio.GN",
  eprint        = "2003.11817"
}

@ARTICLE{Rhie2020-hw,
  title     = "Merqury: reference-free quality, completeness, and phasing
               assessment for genome assemblies",
  author    = "Rhie, Arang and Walenz, Brian P and Koren, Sergey and Phillippy,
               Adam M",
  abstract  = "Recent long-read assemblies often exceed the quality and
               completeness of available reference genomes, making validation
               challenging. Here we present Merqury, a novel tool for
               reference-free assembly evaluation based on efficient k-mer set
               operations. By comparing k-mers in a de novo assembly to those
               found in unassembled high-accuracy reads, Merqury estimates
               base-level accuracy and completeness. For trios, Merqury can
               also evaluate haplotype-specific accuracy, completeness, phase
               block continuity, and switch errors. Multiple visualizations,
               such as k-mer spectrum plots, can be generated for evaluation.
               We demonstrate on both human and plant genomes that Merqury is a
               fast and robust method for assembly validation.",
  journal   = "Genome Biol.",
  publisher = "genomebiology.biomedcentral.com",
  volume    =  21,
  number    =  1,
  pages     = "245",
  month     =  sep,
  year      =  2020,
  keywords  = "Assembly validation; Benchmarking; Genome assembly; Haplotype
               phasing; K-mers; Trio binning;Holo-Omics",
  language  = "en"
}