bmc_article.bib

% bmc_article.bib
% 
%  An example of bibtex entries.
%  Entries taken from BMC instructions for authors page.

% uncomment next line to make author-year bibliography
% @settings{label, options="nameyear"}

%%%%%%%%
% Webpage Link / URL
%
@webpage{mouse,
    title = {The Mouse Tumor Biology Database},
    url = {http://tumor.informatics.jax.org/cancer\_links.html}
}

@article{Jupp2014,
    abstract = {MOTIVATION Resource description framework (RDF) is an emerging technology for describing, publishing and linking life science data. As a major provider of bioinformatics data and services, the European Bioinformatics Institute (EBI) is committed to making data readily accessible to the community in ways that meet existing demand. The EBI RDF platform has been developed to meet an increasing demand to coordinate RDF activities across the institute and provides a new entry point to querying and exploring integrated resources available at the EBI.},
    author = {Jupp, Simon and Malone, James and Bolleman, Jerven and Brandizi, Marco and Davies, Mark and Garcia, Leyla and Gaulton, Anna and Gehant, Sebastien and Laibe, Camille and Redaschi, Nicole and Wimalaratne, Sarala M. and Martin, Maria and { Le Nov { \` { e } } re } , Nicolas and Parkinson, Helen and Birney, Ewan and Jenkinson, Andrew M. and { Le Novere } , N. and Parkinson, Helen and Birney, Ewan and Jenkinson, Andrew M.},
    doi = {10.1093/bioinformatics/btt765},
    file = {:Users/cthoyt/ownCloud/Mendeley/2014/The EBI RDF platform Linked open data for the life sciences - 2014 - Jupp et al.pdf:pdf;:Users/cthoyt/ownCloud/Mendeley/2014/The EBI RDF platform Linked open data for the life sciences - 2014 - Jupp et al(2).pdf:pdf},
    isbn = {1367-4811 (Electronic)},
    issn = {14602059},
    journal = {Bioinformatics},
    keywords = {Folder - RDF and Semantic Web},
    language = {en},
    mendeley-groups = {Bio2BEL Manuscript References},
    mendeley-tags = {Folder - RDF and Semantic Web},
    month = {may},
    number = {9},
    pages = {1338--1339},
    pmid = {24413672},
    shorttitle = {The EBI RDF platform},
    title = {{ The EBI RDF platform: Linked open data for the life sciences }},
    url = {http://bioinformatics.oxfordjournals.org/cgi/doi/10.1093/bioinformatics/btt765},
    volume = {30},
    year = {2014}
}
@article{Fan2019,
    abstract = {Long non-coding RNAs play an important role in human complex diseases. Identification of lncRNA-disease associations will gain insight into disease-related lncRNAs and benefit disease diagnoses and treatment. However, using experiments to explore the lncRNA-disease associations is expensive and time consuming. In this study, we developed a novel method to identify potential lncRNA-disease associations by Integrating Diverse Heterogeneous Information sources with positive pointwise Mutual Information and Random Walk with restart algorithm (namely IDHI-MIRW). IDHI-MIRW first constructs multiple lncRNA similarity networks and disease similarity networks from diverse lncRNA-related and disease-related datasets, then implements the random walk with restart algorithm on these similarity networks for extracting the topological similarities which are fused with positive pointwise mutual information to build a large-scale lncRNA-disease heterogeneous network. Finally, IDHI-MIRW implemented random walk with restart algorithm on the lncRNA-disease heterogeneous network to infer potential lncRNA-disease associations. Compared with other state-of-the-art methods, IDHI-MIRW achieves the best prediction performance. In case studies of breast cancer, stomach cancer, and colorectal cancer, 36/45 (80 { \% } ) novel lncRNA-disease associations predicted by IDHI-MIRW are supported by recent literatures. Furthermore, we found lncRNA LINC01816 is associated with the survival of colorectal cancer patients. IDHI-MIRW is freely available at
    https://github.com/NWPU-903PR/IDHI-MIRW

    .},
    author = {Fan, Xiao-Nan and Zhang, Shao-Wu and Zhang, Song-Yao and Zhu, Kunju and Lu, Songjian},
    doi = {10.1186/s12859-019-2675-y},
    file = {:Users/cthoyt/ownCloud/Mendeley/2019/Prediction of lncRNA-disease associations by integrating diverse heterogeneous information sources with RWR algorithm and positive point.pdf:pdf},
    issn = {1471-2105},
    journal = {BMC Bioinformatics},
    keywords = {Algorithms,Bioinformatics,Computational Biology/Bioinformatics,Computer Appl. in Life Sciences,Microarrays},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {1},
    pages = {87},
    publisher = {BMC Bioinformatics},
    title = {{ Prediction of lncRNA-disease associations by integrating diverse heterogeneous information sources with RWR algorithm and positive pointwise mutual information }},
    url = {https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-019-2675-y},
    volume = {20},
    year = {2019}
}
@article{Carbon2017,
    abstract = {The Gene Ontology (GO) is a comprehensive re-source of computable knowledge regarding the func-tions of genes and gene products. As such, it is ex-tensively used by the biomedical research commu-nity for the analysis of -omics and related data. Our continued focus is on improving the quality and util-ity of the GO resources, and we welcome and encour-age input from researchers in all areas of biology. In this update, we summarize the current contents of the GO knowledgebase, and present several new fea-tures and improvements that have been made to the ontology, the annotations and the tools. Among the highlights are 1) developments that facilitate access to, and application of, the GO knowledgebase, and 2) extensions to the resource as well as increasing support for descriptions of causal models of biologi-cal systems and network biology. To learn more, visit http://geneontology.org/.},
    author = {Carbon, S. and Dietze, H. and Lewis, S. E. and Mungall, C. J. and Munoz-Torres, M. C. and Basu, S. and Chisholm, R. L. and Dodson, R. J. and Fey, P. and Thomas, Paul D. and Mi, H. and Muruganujan, A. and Huang, X. and Poudel, S. and Hu, J. C. and Aleksander, S. A. and McIntosh, B. K. and Renfro, D. P. and Siegele, D. A. and Antonazzo, G. and Attrill, H. and Brown, N. H. and Marygold, S. J. and Mc-Quilton, P. and Ponting, L. and Millburn, G. H. and Rey, A. J. and Stefancsik, R. and Tweedie, S. and Falls, K. and Schroeder, A. J. and Courtot, M. and Osumi-Sutherland, D. and Parkinson, H. and Roncaglia, P. and Lovering, R. C. and Foulger, R. E. and Huntley, R. P. and Denny, P. and Campbell, N. H. and Kramarz, B. and Patel, S. and Buxton, J. L. and Umrao, Z. and Deng, A. T. and Alrohaif, H. and Mitchell, K. and Ratnaraj, F. and Omer, W. and Rodr { \' { i } } guez-L { \' { o } } pez, M. and { C. Chibucos } , M. and Giglio, M. and Nadendla, S. and Duesbury, M. J. and Koch, M. and Meldal, B. H.M. and Melidoni, A. and Porras, P. and Orchard, S. and Shrivastava, A. and Chang, H. Y. and Finn, R. D. and Fraser, M. and Mitchell, A. L. and Nuka, G. and Potter, S. and Rawlings, N. D. and Richardson, L. and Sangrador-Vegas, A. and Young, S. Y. and Blake, J. A. and Christie, K. R. and Dolan, M. E. and Drabkin, H. J. and Hill, D. P. and Ni, L. and Sitnikov, D. and Harris, M. A. and Hayles, J. and Oliver, S. G. and Rutherford, K. and Wood, V. and Bahler, J. and Lock, A. and { De Pons } , J. and Dwinell, M. and Shimoyama, M. and Laulederkind, S. and Hayman, G. T. and Tutaj, M. and Wang, S. J. and D'Eustachio, P. and Matthews, L. and Balhoff, J. P. and Balakrishnan, R. and Binkley, G. and Cherry, J. M. and Costanzo, M. C. and Engel, S. R. and Miyasato, S. R. and Nash, R. S. and Simison, M. and Skrzypek, M. S. and Weng, S. and Wong, E. D. and Feuermann, M. and Gaudet, P. and Berardini, T. Z. and Li, D. and Muller, B. and Reiser, L. and Huala, E. and Argasinska, J. and Arighi, C. and Auchincloss, A. and Axelsen, K. and Argoud-Puy, G. and Bateman, A. and Bely, B. and Blatter, M. C. and Bonilla, C. and Bougueleret, L. and Boutet, E. and Breuza, L. and Bridge, A. and Britto, R. and { Hye- A-Bye } , H. and Casals, C. and Cibrian-Uhalte, E. and Coudert, E. and Cusin, I. and Duek-Roggli, P. and Estreicher, A. and Famiglietti, L. and Gane, P. and Garmiri, P. and Georghiou, G. and Gos, A. and Gruaz-Gumowski, N. and Hatton-Ellis, E. and Hinz, U. and Holmes, A. and Hulo, C. and Jungo, F. and Keller, G. and Laiho, K. and Lemercier, P. and Lieberherr, D. and { Mac- Dougall } , A. and Magrane, M. and Martin, M. J. and Masson, P. and Natale, D. A. and O'Donovan, C. and Pedruzzi, I. and Pichler, K. and Poggioli, D. and Poux, S. and Rivoire, C. and Roechert, B. and Sawford, T. and Schneider, M. and Speretta, E. and Shypitsyna, A. and Stutz, A. and Sundaram, S. and Tognolli, M. and Wu, C. and Xenarios, I. and Yeh, L. S. and Chan, J. and Gao, S. and Howe, K. and Kishore, R. and Lee, R. and Li, Y. and Lomax, J. and Muller, H. M. and Raciti, D. and { Van Auken } , K. and Berriman, M. and { Stein, Paul Kersey } , L. and { W. Sternberg } , P. and Howe, D. and Westerfield, M.},
    doi = {10.1093/nar/gkw1108},
    file = {:Users/cthoyt/ownCloud/Mendeley/2017/Expansion of the gene ontology knowledgebase and resources The gene ontology consortium - 2017 - Carbon et al(2).pdf:pdf},
    isbn = {13624962 (Electronic)},
    issn = {13624962},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {D1},
    pages = {D331--D338},
    pmid = {27899567},
    title = {{ Expansion of the gene ontology knowledgebase and resources: The gene ontology consortium }},
    volume = {45},
    year = {2017}
}
@article{Sun2014,
    abstract = {The growing body of transcriptomic, proteomic, metabolomic and genomic data generated from disease states provides a great opportunity to improve our current understanding of the molecular mechanisms driving diseases and shared between diseases. The use of both clinical and molecular phenotypes will lead to better disease understanding and classification. In this study, we set out to gain novel insights into diseases and their relationships by utilising knowledge gained from system-level molecular data. We integrated different types of biological data including genome-wide association studies data, disease–chemical associations, biological pathways and Gene Ontology annotations into an Integrated Disease Network (IDN), a heterogeneous network where nodes are bio-entities and edges between nodes represent their associations. We also introduced a novel disease similarity measure to infer disease–disease associations from the IDN. Our predicted associations were systemically evaluated against the Medical Subject Heading classification and a statistical measure of disease co-occurrence in PubMed. The strong correlation between our predictions and co-occurrence associations indicated the ability of our approach to recover known disease associations. Furthermore, we presented a case study of Crohn's disease. We demonstrated that our approach not only identified well-established connections between Crohn's disease and other diseases, but also revealed new, interesting connections consistent with emerging literature. Our approach also enabled ready access to the knowledge supporting these new connections, making this a powerful approach for exploring connections between diseases.},
    author = {Sun, Kai and Pr { \v { z } } ulj, Nata { \v { s } } a and Buchan, Natalie and Larminie, Chris},
    doi = {10.1039/c4ib00122b},
    issn = {1757-9708},
    journal = {Integrative Biology},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {aug},
    number = {11},
    pages = {1069--1079},
    title = {{ The integrated disease network }},
    url = {https://doi.org/10.1039/c4ib00122b},
    volume = {6},
    year = {2014}
}
@article{Demir2010,
    abstract = {Biological Pathway Exchange (BioPAX) is a standard language to represent biological pathways at the molecular and cellular level and to facilitate the exchange of pathway data. The rapid growth of the volume of pathway data has spurred the development of databases and computational tools to aid interpretation; however, use of these data is hampered by the current fragmentation of pathway information across many databases with incompatible formats. BioPAX, which was created through a community process, solves this problem by making pathway data substantially easier to collect, index, interpret and share. BioPAX can represent metabolic and signaling pathways, molecular and genetic interactions and gene regulation networks. Using BioPAX, millions of interactions, organized into thousands of pathways, from many organisms are available from a growing number of databases. This large amount of pathway data in a computable form will support visualization, analysis and biological discovery.},
    author = {Demir, Emek and Cary, Michael P and Paley, Suzanne and Fukuda, Ken and Lemer, Christian and Vastrik, Imre and Wu, Guanming and D'Eustachio, Peter and Schaefer, Carl and Luciano, Joanne and Schacherer, Frank and Martinez-Flores, Irma and Hu, Zhenjun and Jimenez-Jacinto, Veronica and Joshi-Tope, Geeta and Kandasamy, Kumaran and Lopez-Fuentes, Alejandra C and Mi, Huaiyu and Pichler, Elgar and Rodchenkov, Igor and Splendiani, Andrea and Tkachev, Sasha and Zucker, Jeremy and Gopinath, Gopal and Rajasimha, Harsha and Ramakrishnan, Ranjani and Shah, Imran and Syed, Mustafa and Anwar, Nadia and Babur, { \" { O } } zg { \" { u } } n and Blinov, Michael and Brauner, Erik and Corwin, Dan and Donaldson, Sylva and Gibbons, Frank and Goldberg, Robert and Hornbeck, Peter and Luna, Augustin and Murray-Rust, Peter and Neumann, Eric and Reubenacker, Oliver and Samwald, Matthias and van Iersel, Martijn and Wimalaratne, Sarala and Allen, Keith and Braun, Burk and Whirl-Carrillo, Michelle and Cheung, Kei-Hoi and Dahlquist, Kam and Finney, Andrew and Gillespie, Marc and Glass, Elizabeth and Gong, Li and Haw, Robin and Honig, Michael and Hubaut, Olivier and Kane, David and Krupa, Shiva and Kutmon, Martina and Leonard, Julie and Marks, Debbie and Merberg, David and Petri, Victoria and Pico, Alex and Ravenscroft, Dean and Ren, Liya and Shah, Nigam and Sunshine, Margot and Tang, Rebecca and Whaley, Ryan and Letovksy, Stan and Buetow, Kenneth H and Rzhetsky, Andrey and Schachter, Vincent and Sobral, Bruno S and Dogrusoz, Ugur and McWeeney, Shannon and Aladjem, Mirit and Birney, Ewan and Collado-Vides, Julio and Goto, Susumu and Hucka, Michael and Nov { \` { e } } re, Nicolas Le and Maltsev, Natalia and Pandey, Akhilesh and Thomas, Paul and Wingender, Edgar and Karp, Peter D and Sander, Chris and Bader, Gary D},
    doi = {10.1038/nbt1210-1308c},
    file = {:Users/cthoyt/ownCloud/Mendeley/2010/The BioPAX community standard for pathway data sharing - 2010 - Demir et al.pdf:pdf},
    isbn = {1546-1696 (Electronic)$\backslash$r1087-0156 (Linking)},
    issn = {1087-0156},
    journal = {Nature Biotechnology},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {12},
    pages = {1308--1308},
    pmid = {20829833},
    title = {{ The BioPAX community standard for pathway data sharing }},
    url = {http://www.nature.com/doifinder/10.1038/nbt1210-1308c},
    volume = {28},
    year = {2010}
}
@article{Alanis-Lobato2017,
    author = {Alanis-Lobato, Gregorio and Andrade-Navarro, Miguel A. and Schaefer, Martin H},
    doi = {10.1093/nar/gkw985},
    file = {:Users/cthoyt/ownCloud/Mendeley/2017/HIPPIE v2.0 enhancing meaningfulness and reliability of protein–protein interaction networks - 2017 - Alanis-Lobato, Andrade-Navarro,.pdf:pdf},
    issn = {0305-1048},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {jan},
    number = {D1},
    pages = {D408--D414},
    title = {{ HIPPIE v2.0: enhancing meaningfulness and reliability of protein–protein interaction networks }},
    url = {https://academic.oup.com/nar/article-lookup/doi/10.1093/nar/gkw985},
    volume = {45},
    year = {2017}
}
@inproceedings{mckinney-proc-scipy-2010,
    author = {McKinney, Wes},
    booktitle = {Proceedings of the 9th Python in Science Conference},
    editor = {van der Walt, St { \' { e } } fan and Millman, Jarrod},
    mendeley-groups = {Bio2BEL Manuscript References},
    pages = {51--56},
    title = {{ Data Structures for Statistical Computing in Python }},
    year = {2010}
}
@inproceedings{Abadi:2016:TSL:3026877.3026899,
    address = {Berkeley, CA, USA},
    author = {Abadi, Mart { \' { i } } n and Barham, Paul and Chen, Jianmin and Chen, Zhifeng and Davis, Andy and Dean, Jeffrey and Devin, Matthieu and Ghemawat, Sanjay and Irving, Geoffrey and Isard, Michael and Kudlur, Manjunath and Levenberg, Josh and Monga, Rajat and Moore, Sherry and Murray, Derek G and Steiner, Benoit and Tucker, Paul and Vasudevan, Vijay and Warden, Pete and Wicke, Martin and Yu, Yuan and Zheng, Xiaoqiang},
    booktitle = {Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation},
    isbn = {978-1-931971-33-1},
    mendeley-groups = {Bio2BEL Manuscript References},
    pages = {265--283},
    publisher = {USENIX Association},
    series = {OSDI'16},
    title = {{ TensorFlow: A System for Large-scale Machine Learning }},
    url = {http://dl.acm.org/citation.cfm?id=3026877.3026899},
    year = {2016}
}
@article{Laibe2007,
    abstract = {BACKGROUND The Minimal Information Requested In the Annotation of biochemical Models (MIRIAM) is a set of guidelines for the annotation and curation processes of computational models, in order to facilitate their exchange and reuse. An important part of the standard consists in the controlled annotation of model components, based on Uniform Resource Identifiers. In order to enable interoperability of this annotation, the community has to agree on a set of standard URIs, corresponding to recognised data types. MIRIAM Resources are being developed to support the use of those URIs. RESULTS MIRIAM Resources are a set of on-line services created to catalogue data types, their URIs and the corresponding physical URLs (or resources), whether data types are controlled vocabularies or primary data resources. MIRIAM Resources are composed of several components: MIRIAM Database stores the information, MIRIAM Web Services allows to programmatically access the database, MIRIAM Library provides an access to the Web Services and MIRIAM Web Application is a way to access the data (human browsing) and also to edit or add entries. CONCLUSIONS The project MIRIAM Resources allows an easy access to MIRIAM URIs and the associated information and is therefore crucial to foster a general use of MIRIAM annotations in computational models of biological processes.},
    author = {Laibe, Camille and { Le Nov { \` { e } } re } , Nicolas},
    doi = {10.1186/1752-0509-1-58},
    file = {:Users/cthoyt/ownCloud/Mendeley/2007/MIRIAM Resources tools to generate and resolve robust cross-references in Systems Biology. - 2007 - Laibe, Le Nov { \` { e } } re.pdf:pdf},
    isbn = {1752-0509},
    issn = {1752-0509},
    journal = {BMC systems biology},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {dec},
    pages = {58},
    pmid = {18078503},
    title = {{ MIRIAM Resources: tools to generate and resolve robust cross-references in Systems Biology. }},
    url = {http://www.ncbi.nlm.nih.gov/pubmed/18078503 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC2259379},
    volume = {1},
    year = {2007}
}
@article{Fabregat2018,
    abstract = {The Reactome Knowledgebase (https://reactome.org) provides molecular details of signal transduction, transport, DNA replication, metabolism, and other cellular processes as an ordered network of molecular transformations-an extended version of a classic metabolic map, in a single consistent data model. Reactome functions both as an archive of biological processes and as a tool for discovering unexpected functional relationships in data such as gene expression profiles or somatic mutation catalogues from tumor cells. To support the continued brisk growth in the size and complexity of Reactome, we have implemented a graph database, improved performance of data analysis tools, and designed new data structures and strategies to boost diagram viewer performance. To make our website more accessible to human users, we have improved pathway display and navigation by implementing interactive Enhanced High Level Diagrams (EHLDs) with an associated icon library, and subpathway highlighting and zooming, in a simplified and reorganized web site with adaptive design. To encourage re-use of our content, we have enabled export of pathway diagrams as 'PowerPoint' files.},
    archivePrefix = {arXiv},
    arxivId = {NIHMS150003},
    author = {Fabregat, Antonio and Jupe, Steven and Matthews, Lisa and Sidiropoulos, Konstantinos and Gillespie, Marc and Garapati, Phani and Haw, Robin and Jassal, Bijay and Korninger, Florian and May, Bruce and Milacic, Marija and Roca, Corina Duenas and Rothfels, Karen and Sevilla, Cristoffer and Shamovsky, Veronica and Shorser, Solomon and Varusai, Thawfeek and Viteri, Guilherme and Weiser, Joel and Wu, Guanming and Stein, Lincoln and Hermjakob, Henning and D'Eustachio, Peter},
    doi = {10.1093/nar/gkx1132},
    eprint = {NIHMS150003},
    file = {:Users/cthoyt/ownCloud/Mendeley/2018/The Reactome Pathway Knowledgebase - 2018 - Fabregat et al.pdf:pdf},
    isbn = {1362-4962 (Electronic)$\backslash$n0305-1048 (Linking)},
    issn = {0305-1048},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {jan},
    number = {D1},
    pages = {D649--D655},
    pmid = {29145629},
    publisher = {Oxford University Press},
    title = {{ The Reactome Pathway Knowledgebase }},
    url = {http://academic.oup.com/nar/article/46/D1/D649/4626770},
    volume = {46},
    year = {2018}
}
@article{Cote2006a,
    abstract = {BACKGROUND: With the vast amounts of biomedical data being generated by high-throughput analysis methods, controlled vocabularies and ontologies are becoming increasingly important to annotate units of information for ease of search and retrieval. Each scientific community tends to create its own locally available ontology. The interfaces to query these ontologies tend to vary from group to group. We saw the need for a centralized location to perform controlled vocabulary queries that would offer both a lightweight web-accessible user interface as well as a consistent, unified SOAP interface for automated queries. RESULTS: The Ontology Lookup Service (OLS) was created to integrate publicly available biomedical ontologies into a single database. All modified ontologies are updated daily. A list of currently loaded ontologies is available online. The database can be queried to obtain information on a single term or to browse a complete ontology using AJAX. Auto-completion provides a user-friendly search mechanism. An AJAX-based ontology viewer is available to browse a complete ontology or subsets of it. A programmatic interface is available to query the webservice using SOAP. The service is described by a WSDL descriptor file available online. A sample Java client to connect to the webservice using SOAP is available for download from SourceForge. All OLS source code is publicly available under the open source Apache Licence. CONCLUSION: The OLS provides a user-friendly single entry point for publicly available ontologies in the Open Biomedical Ontology (OBO) format. It can be accessed interactively or programmatically at http://www.ebi.ac.uk/ontology-lookup/.},
    author = {Cote, RG and Jones, P and Apweiler, R and Hermjakob, H},
    doi = {10.1186/1471-2105-7-97},
    file = {:Users/cthoyt/ownCloud/Mendeley/2006/The Ontology Lookup Service, a lightweight cross-platform tool for controlled vocabulary queries. - 2006 - Cote et al(2).pdf:pdf},
    issn = {1471-2105},
    journal = {BMC Bioinformatics},
    mendeley-groups = {Bio2BEL Manuscript References},
    pages = {1--7},
    pmid = {16507094},
    title = {{ The Ontology Lookup Service, a lightweight cross-platform tool for controlled vocabulary queries. }},
    volume = {7},
    year = {2006}
}
@article{Perfetto2016,
    abstract = {Assembly of large biochemical networks can be achieved by confronting new cell-specific experimental data with an interaction subspace constrained by prior literature evidence. The SIGnaling Network Open Resource, SIGNOR (available on line at http://signor.uniroma2.it), was developed to support such a strategy by providing a scaffold of prior experimental evidence of causal relationships between biological entities. The core of SIGNOR is a collection of approximately 12 000 manually-annotated causal relationships between over 2800 human proteins participating in signal transduction. Other entities annotated in SIGNOR are complexes, chemicals, phenotypes and stimuli. The information captured in SIGNOR can be represented as a signed directed graph illustrating the activation/inactivation relationships between signalling entities. Each entry is associated to the post-translational modifications that cause the activation/inactivation of the target proteins. More than 4900 modified residues causing a change in protein concentration or activity have been curated and linked to the modifying enzymes (about 351 human kinases and 94 phosphatases). Additional modifications such as ubiquitinations, sumoylations, acetylations and their effect on the modified target proteins are also annotated. This wealth of structured information can support experimental approaches based on multi-parametric analysis of cell systems after physiological or pathological perturbations and to assemble large logic models.},
    author = {Perfetto, Livia and Briganti, Leonardo and Calderone, Alberto and Perpetuini, Andrea Cerquone and Iannuccelli, Marta and Langone, Francesca and Licata, Luana and Marinkovic, Milica and Mattioni, Anna and Pavlidou, Theodora and Peluso, Daniele and Petrilli, Lucia Lisa and Pirr { \' { o } } , Stefano and Posca, Daniela and Santonico, Elena and Silvestri, Alessandra and Spada, Filomena and Castagnoli, Luisa and Cesareni, Gianni},
    doi = {10.1093/nar/gkv1048},
    file = {:Users/cthoyt/ownCloud/Mendeley/2016/SIGNOR A database of causal relationships between biological entities - 2016 - Perfetto et al.pdf:pdf},
    isbn = {13624962 (Electronic)},
    issn = {13624962},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {D1},
    pages = {D548--D554},
    pmid = {26467481},
    title = {{ SIGNOR: A database of causal relationships between biological entities }},
    volume = {44},
    year = {2016}
}
@article{Gyori2017,
    abstract = {Word models (natural language descriptions of molecular mechanisms) are a common currency in spoken and written communication in biomedicine but are of limited use in predicting the behavior of complex biological networks. We present an approach to building computational models directly from natural language using automated assembly. Molecular mechanisms described in simple English are read by natural language processing algorithms, converted into an intermediate representation, and assembled into executable or network models. We have implemented this approach in the Integrated Network and Dynamical Reasoning Assembler (INDRA), which draws on existing natural language processing systems as well as pathway information in Pathway Commons and other online resources. We demonstrate the use of INDRA and natural language to model three biological processes of increasing scope: (i) p53 dynamics in response to DNA damage, (ii) adaptive drug resistance in BRAF-V600E-mutant melanomas, and (iii) the RAS signaling pathway. The use of natural language makes the task of developing a model more efficient and it increases model transparency, thereby promoting collaboration with the broader biology community.},
    author = {Gyori, Benjamin M and Bachman, John A and Subramanian, Kartik and Muhlich, Jeremy L and Galescu, Lucian and Sorger, Peter K},
    doi = {10.15252/msb.20177651},
    file = {:Users/cthoyt/ownCloud/Mendeley/2017/From word models to executable models of signaling networks using automated assembly - 2017 - Gyori et al(3).pdf:pdf},
    isbn = {17444292 (Electronic)},
    issn = {1744-4292},
    journal = {Molecular Systems Biology},
    keywords = {computational modeling,natural language processing,signaling},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {11},
    pages = {954},
    pmid = {29175850},
    title = {{ From word models to executable models of signaling networks using automated assembly }},
    url = {http://msb.embopress.org/lookup/doi/10.15252/msb.20177651},
    volume = {13},
    year = {2017}
}
@article{Hoyt2019,
    abstract = {The rapid accumulation of new biomedical literature not only causes curated knowledge graphs to become outdated and incomplete, but also makes manual curation an impractical and unsustainable solution. Automated or semi-automated workflows are necessary to assist in prioritizing and curating the literature to update and enrich knowledge graphs. We have developed two workflows: one for re-curating a given knowledge graph to assure its syntactic and semantic quality and another for rationally enriching it by manually revising automatically extracted relations for nodes with low information density. We applied these workflows to the knowledge graphs encoded in Biological Expression Language from the NeuroMMSig database using content that was pre-extracted from MEDLINE abstracts and PubMed Central full text articles using text mining output integrated by INDRA. We have made this workflow freely available at https://github.com/bel-enrichment.},
    author = {Hoyt, Charles and Domingo-Fernandez, Daniel and Aldisi, Rana and Xu, Lingling and Kolpeja, Kristian and Spalek, Sandra and Wollert, Esther and Bachman, John and Gyori, Benjamin and Greene, Patrick and Hofmann-Apitius, Martin},
    doi = {10.1101/536409},
    journal = {bioRxiv},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {jan},
    pages = {536409},
    title = {{ Re-curation and Rational Enrichment of Knowledge Graphs in Biological Expression Language }},
    url = {http://biorxiv.org/content/early/2019/01/31/536409.abstract},
    year = {2019}
}
@article{Iyappan2016,
    author = {Iyappan, Anandhi and Kawalia, Shweta Bagewadi and Raschka, Tamara and Hofmann-Apitius, Martin and Senger, Philipp},
    doi = {10.1186/s13326-016-0079-8},
    file = {:Users/cthoyt/ownCloud/Mendeley/2016/NeuroRDF semantic integration of highly curated data to prioritize biomarker candidates in Alzheimer's disease - 2016 - Iyappan et al.pdf:pdf},
    isbn = {20411480 (Electronic)},
    issn = {2041-1480},
    journal = {Journal of Biomedical Semantics},
    keywords = {RDF,Semantic web,Data integration,Data curation,Da,alzheimer,bagewadi,correspondence,data curation,data harmonization,data integration,de,disease modeling,fraunhofer,neurodegenerative diseases,rdf,s disease,scai,semantic web,shweta},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {1},
    pages = {45},
    pmid = {27392431},
    publisher = {Journal of Biomedical Semantics},
    title = {{ NeuroRDF: semantic integration of highly curated data to prioritize biomarker candidates in Alzheimer's disease }},
    url = {http://jbiomedsem.biomedcentral.com/articles/10.1186/s13326-016-0079-8},
    volume = {7},
    year = {2016}
}
@article{Ali2019,
    abstract = {SUMMARY Knowledge graph embeddings (KGEs) have received significant attention in other domains due to their ability to predict links and create dense representations for graphs' nodes and edges. However, the software ecosystem for their application to bioinformatics remains limited and inaccessible for users without expertise in programming and machine learning. Therefore, we developed BioKEEN (Biological KnowlEdge EmbeddiNgs) and PyKEEN (Python KnowlEdge EmbeddiNgs) to facilitate their easy use through an interactive command line interface. Finally, we present a case study in which we used a novel biological pathway mapping resource to predict links that represent pathway crosstalks and hierarchies. AVAILABILITY BioKEEN and PyKEEN are open source Python packages publicly available under the MIT License at https://github.com/SmartDataAnalytics/BioKEEN and https://github.com/SmartDataAnalytics/PyKEEN. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.},
    author = {Ali, Mehdi and Hoyt, Charles Tapley and Domingo-Fern { \' { a } } ndez, Daniel and Lehmann, Jens and Jabeen, Hajira},
    doi = {10.1093/bioinformatics/btz117},
    editor = {Wren, Jonathan},
    issn = {1367-4811},
    journal = {Bioinformatics (Oxford, England)},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {feb},
    pmid = {30768158},
    title = {{ BioKEEN: A library for learning and evaluating biological knowledge graph embeddings. }},
    url = {https://dx.doi.org/10.1093/bioinformatics/btz117 https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/btz117/5320556 http://www.ncbi.nlm.nih.gov/pubmed/30768158},
    year = {2019}
}
@article{Saqi2018,
    abstract = {Large amounts of data emerging from experiments in molecular medicine are leading to the identification of molecular signatures associated with disease subtypes. The contextualization of these patterns is important for obtaining mechanistic insight into the aberrant processes associated with a disease, and this typically involves the integration of multiple heterogeneous types of data. In this review, we discuss knowledge representations that can be useful to explore the biological context of molecular signatures, in particular three main approaches, namely, pathway mapping approaches, molecular network centric approaches and approaches that represent biological statements as knowledge graphs. We discuss the utility of each of these paradigms, illustrate how they can be leveraged with selected practical examples and identify ongoing challenges for this field of research.},
    author = {Saqi, Mansoor and Lysenko, Artem and Guo, Yi-Ke and Tsunoda, Tatsuhiko and Auffray, Charles},
    doi = {10.1093/bib/bby025},
    file = {:Users/cthoyt/ownCloud/Mendeley/2018/Navigating the disease landscape knowledge representations for contextualizing molecular signatures. - 2018 - Saqi et al.pdf:pdf},
    isbn = {14774054 (Electronic)},
    issn = {1477-4054},
    journal = {Briefings in bioinformatics},
    keywords = {1,10,1093,15,2018,bby025,bib,doi,efings in bioinformatics},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {apr},
    number = {May},
    pages = {1--15},
    pmid = {29684165},
    title = {{ Navigating the disease landscape: knowledge representations for contextualizing molecular signatures. }},
    url = {https://academic.oup.com/bib/advance-article/doi/10.1093/bib/bby025/4978142 http://www.ncbi.nlm.nih.gov/pubmed/29684165},
    year = {2018}
}
@article{Ward2012,
    abstract = {The resolution of genome-wide association studies (GWAS) is limited by the linkage disequilibrium (LD) structure of the population being studied. Selecting the most likely causal variants within an LD block is relatively straightforward within coding sequence, but is more difficult when all variants are intergenic. Predicting functional non-coding sequence has been recently facilitated by the availability of conservation and epigenomic information. We present HaploReg, a tool for exploring annotations of the non-coding genome among the results of published GWAS or novel sets of variants. Using LD information from the 1000 Genomes Project, linked SNPs and small indels can be visualized along with their predicted chromatin state in nine cell types, conservation across mammals and their effect on regulatory motifs. Sets of SNPs, such as those resulting from GWAS, are analyzed for an enrichment of cell type-specific enhancers. HaploReg will be useful to researchers developing mechanistic hypotheses of the impact of non-coding variants on clinical phenotypes and normal variation. The HaploReg database is available at http://compbio.mit.edu/HaploReg.},
    author = {Ward, Lucas D. and Kellis, Manolis},
    doi = {10.1093/nar/gkr917},
    file = {:Users/cthoyt/ownCloud/Mendeley/2012/HaploReg A resource for exploring chromatin states, conservation, and regulatory motif alterations within sets of genetically linked var.pdf:pdf},
    isbn = {1362-4962 (Electronic)$\backslash$r0305-1048 (Linking)},
    issn = {03051048},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {D1},
    pages = {930--934},
    pmid = {22064851},
    title = {{ HaploReg: A resource for exploring chromatin states, conservation, and regulatory motif alterations within sets of genetically linked variants }},
    volume = {40},
    year = {2012}
}
@article{Moret2018,
    abstract = {Libraries of highly annotated small molecules have many uses in chemical genetics, drug discovery and drug repurposing. Many such libraries have become available, but few data-driven approaches exist to compare these libraries and design new ones. In this paper, we describe such an approach that makes use of data on binding selectivity, target coverage and induced cellular phenotypes as well as chemical structure and stage of clinical development. We implement the approach as R software and a Web-accessible tool (http://www.smallmoleculesuite.org) that uses incomplete and often confounded public data in combination with user preferences to score and create libraries. Analysis of six kinase inhibitor libraries using our approach reveals dramatic differences among them, leading us to design a new LSP-OptimalKinase library that outperforms all previous collections in terms of target coverage and compact size. We also assemble a mechanism of action library that optimally covers 1852 targets of the liganded genome. Using our tools, individual research groups and companies can quickly analyze private compound collections and public libraries can be progressively improved using the latest data.},
    author = {Moret, Nienke and Clark, Nicholas and Hafner, Marc and Wang, Yuan and Lounkine, Eugen and Medvedovic, Mario and Wang, Jinhua and Gray, Nathanael and Jenkins, Jeremy and Sorger, Peter},
    doi = {10.1101/358978},
    file = {:Users/cthoyt/ownCloud/Mendeley/2018/Cheminformatics tools for analyzing and designing optimized small molecule libraries - 2018 - Moret et al.pdf:pdf},
    journal = {bioRxiv},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {617},
    pages = {358978},
    title = {{ Cheminformatics tools for analyzing and designing optimized small molecule libraries }},
    url = {https://www.biorxiv.org/content/early/2018/06/29/358978},
    year = {2018}
}
@article{Turei2016,
    author = {T { \" { u } } rei, D { \' { e } } nes and Korcsm { \' { a } } ros, Tam { \' { a } } s and Saez-Rodriguez, Julio},
    doi = {10.1038/nmeth.4077},
    issn = {1548-7091},
    journal = {Nature Methods},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {dec},
    number = {12},
    pages = {966--967},
    title = {{ OmniPath: guidelines and gateway for literature-curated signaling pathway resources }},
    url = {http://www.nature.com/articles/nmeth.4077},
    volume = {13},
    year = {2016}
}
@article{Domingo-Fernandez2019,
    abstract = {The complexity of representing biological systems is compounded by an ever-expanding body of knowledge emerging from multi-omics experiments. A number of pathway databases have facilitated pathway-centric approaches that assist in the interpretation of molecular signatures yielded by these experiments. However, the lack of interoperability between pathway databases has hindered the ability to harmonize these resources and to exploit their consolidated knowledge. Such a unification of pathway knowledge is imperative in enhancing the comprehension and modeling of biological abstractions.},
    author = {Domingo-Fern { \' { a } } ndez, Daniel and Mubeen, Sarah and Mar { \' { i } } n-Lla { \' { o } } , Josep and Hoyt, Charles Tapley and Hofmann-Apitius, Martin},
    doi = {10.1186/s12859-019-2863-9},
    file = {:Users/cthoyt/ownCloud/Mendeley/2019/PathMe merging and exploring mechanistic pathway knowledge - 2019 - Domingo-Fern { \' { a } } ndez et al.pdf:pdf},
    issn = {1471-2105},
    journal = {BMC Bioinformatics},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {1},
    pages = {243},
    title = {{ PathMe: merging and exploring mechanistic pathway knowledge }},
    url = {https://doi.org/10.1186/s12859-019-2863-9},
    volume = {20},
    year = {2019}
}
@article{Courtot2011,
    abstract = {The use of computational modeling to describe and analyze biological systems is at the heart of systems biology. Model structures, simulation descriptions and numerical results can be encoded in structured formats, but there is an increasing need to provide an additional semantic layer. Semantic information adds meaning to components of structured descriptions to help identify and interpret them unambiguously. Ontologies are one of the tools frequently used for this purpose. We describe here three ontologies created specifically to address the needs of the systems biology community. The Systems Biology Ontology (SBO) provides semantic information about the model components. The Kinetic Simulation Algorithm Ontology (KiSAO) supplies information about existing algorithms available for the simulation of systems biology models, their characterization and interrelationships. The Terminology for the Description of Dynamics (TEDDY) categorizes dynamical features of the simulation results and general systems behavior. The provision of semantic information extends a model's longevity and facilitates its reuse. It provides useful insight into the biology of modeled processes, and may be used to make informed decisions on subsequent simulation experiments.},
    author = {Courtot, M { \' { e } } lanie and Juty, Nick and Kn { \" { u } } pfer, Christian and Waltemath, Dagmar and Zhukova, Anna and Dr { \" { a } } ger, Andreas and Dumontier, Michel and Finney, Andrew and Golebiewski, Martin and Hastings, Janna and Hoops, Stefan and Keating, Sarah and Kell, Douglas B. and Kerrien, Samuel and Lawson, James and Lister, Allyson and Lu, James and MacHne, Rainer and Mendes, Pedro and Pocock, Matthew and Rodriguez, Nicolas and Villeger, Alice and Wilkinson, Darren J. and Wimalaratne, Sarala and Laibe, Camille and Hucka, Michael and { Le Nov { \` { e } } re } , Nicolas},
    doi = {10.1038/msb.2011.77},
    file = {:Users/cthoyt/ownCloud/Mendeley/2011/Controlled vocabularies and semantics in systems biology - 2011 - Courtot et al.pdf:pdf},
    isbn = {1744-4292 (Linking)},
    issn = {17444292},
    journal = {Molecular Systems Biology},
    keywords = {dynamics,kinetics,model,ontology,simulation},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {543},
    pmid = {22027554},
    title = {{ Controlled vocabularies and semantics in systems biology }},
    volume = {7},
    year = {2011}
}
@article{Hoyt2018,
    abstract = {The rapid accumulation of knowledge in the field of systems and networks biology during recent years requires complex, but user-friendly and accessible web applications that allow from visualization to complex algorithmic analysis. While several web applications exist with various focuses on creation, revision, curation, storage, integration, collaboration, exploration, visualization and analysis, many of these services remain disjoint and have yet to be packaged into a cohesive environment.Here, we present BEL Commons: an integrative knowledge discovery environment for networks encoded in the Biological Expression Language (BEL). Users can upload files in BEL to be parsed, validated, compiled and stored with fine granular permissions. After, users can summarize, explore and optionally shared their networks with the scientific community. We have implemented a query builder wizard to help users find the relevant portions of increasingly large and complex networks and a visualization interface that allows them to explore their resulting networks. Finally, we have included a dedicated analytical service for performing data-driven analysis of knowledge networks to support hypothesis generation.},
    archivePrefix = {arXiv},
    arxivId = {1611.06654},
    author = {Hoyt, Charles Tapley and Domingo-Fern { \' { a } } ndez, Daniel and Hofmann-Apitius, Martin},
    doi = {10.1093/database/bay126},
    eprint = {1611.06654},
    file = {:Users/cthoyt/ownCloud/Mendeley/2018/BEL Commons an environment for exploration and analysis of networks encoded in Biological Expression Language - 2018 - Hoyt, Domingo-Fer.pdf:pdf},
    isbn = {2076792171},
    issn = {1758-0463},
    journal = {Database : the journal of biological databases and curation},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {jan},
    number = {3},
    pages = {1--11},
    pmid = {30576488},
    title = {{ BEL Commons: an environment for exploration and analysis of networks encoded in Biological Expression Language. }},
    url = {http://fdslive.oup.com/www.oup.com/pdf/production { \_ } in { \_ } progress.pdf http://www.ncbi.nlm.nih.gov/pubmed/30576488},
    volume = {2018},
    year = {2018}
}
@article{Iyappan2017,
    author = {Iyappan, Anandhi and Younesi, Erfan and Redolfi, Alberto and Vrooman, Henri and Khanna, Shashank and Frisoni, Giovanni B. and Hofmann-Apitius, Martin},
    doi = {10.3233/jad-161148},
    file = {:Users/cthoyt/ownCloud/Mendeley/2017/Neuroimaging Feature Terminology A Controlled Terminology for the Annotation of Brain Imaging Features - 2017 - Iyappan et al.pdf:pdf;:Users/cthoyt/ownCloud/Mendeley/2017/Neuroimaging Feature Terminology A Controlled Terminology for the Annotation of Brain Imaging Features - 2017 - Iyappan et al(2).pdf:pdf},
    issn = {13872877},
    journal = {Journal of Alzheimer's Disease},
    keywords = {alzheimer,annotation,brain,neuroimaging,s disease,terminology},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {4},
    pages = {1153--1169},
    title = {{ Neuroimaging Feature Terminology: A Controlled Terminology for the Annotation of Brain Imaging Features }},
    volume = {59},
    year = {2017}
}
@article{Curk2005,
    abstract = {Summary: Visual programming offers an intuitive means of combining known analysis and visualization methods into powerful applications. The system presented here enables users who are not programmers to manage microarray and genomic data flow and to customize their analyses by combining common data analysis tools to fit their needs.Availability:http://www.ailab.si/supp/bi-visprogContact:blaz.zupan@fri.uni-lj.siSupplementary information:http://www.ailab.si/supp/bi-visprog},
    author = {Curk, Tomaz and Demsar, Janez and Xu, Qikai and Leban, Gregor and Petrovic, Uros and Bratko, Ivan and Shaulsky, Gad and Zupan, Blaz},
    doi = {10.1093/bioinformatics/bth474},
    issn = {1367-4803},
    journal = {Bioinformatics},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {feb},
    number = {3},
    pages = {396--398},
    title = {{ Microarray data mining with visual programming }},
    url = {https://dx.doi.org/10.1093/bioinformatics/bth474 https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/bth474},
    volume = {21},
    year = {2005}
}
@article{Wanichthanarak2015,
    abstract = {Robust interpretation of experimental results measuring discreet biological domains remains a significant challenge in the face of complex biochemical regulation processes such as organismal versus tissue versus cellular metabolism, epigenetics, and protein post-translational modification. Integration of analyses carried out across multiple measurement or omic platforms is an emerging approach to help address these challenges. This review focuses on select methods and tools for the integration of metabolomic with genomic and proteomic data using a variety of approaches including biochemical pathway-, ontology-, network-, and empirical-correlation-based methods.},
    author = {Wanichthanarak, Kwanjeera and Fahrmann, Johannes F. and Grapov, Dmitry},
    doi = {10.4137/BMI.S29511},
    file = {:Users/cthoyt/ownCloud/Mendeley/2015/Genomic, proteomic, and metabolomic data integration strategies - 2015 - Wanichthanarak, Fahrmann, Grapov.pdf:pdf},
    issn = {11772719},
    journal = {Biomarker Insights},
    keywords = {Bioinformatics,Data analysis,Data integration,Genomics,Metabolomics,Networks,Omics,Proteomics},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {Table 1},
    pages = {1--6},
    pmid = {26396492},
    title = {{ Genomic, proteomic, and metabolomic data integration strategies }},
    volume = {10},
    year = {2015}
}
@article{Cokelaer2013,
    abstract = {Motivation: Web interfaces provide access to numerous biological databases. Many can be accessed to in a programmatic way thanks to Web Services. Building applications that combine several of them would benefit from a single framework.Results: BioServices is a comprehensive Python framework that provides programmatic access to major bioinformatics Web Services (e.g. KEGG, UniProt, BioModels, ChEMBLdb). Wrapping additional Web Services based either on Representational State Transfer or Simple Object Access Protocol/Web Services Description Language technologies is eased by the usage of object-oriented programming.Availability and implementation: BioServices releases and documentation are available at http://pypi.python.org/pypi/bioservices under a GPL-v3 license.Contact:cokelaer@ebi.ac.uk or bioservices@googlegroups.comSupplementary information:Supplementary data are available at Bioinformatics online.},
    author = {Cokelaer, Thomas and Pultz, Dennis and Harder, Lea M and Serra-Musach, Jordi and Saez-Rodriguez, Julio},
    doi = {10.1093/bioinformatics/btt547},
    issn = {1460-2059},
    journal = {Bioinformatics},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {dec},
    number = {24},
    pages = {3241--3242},
    title = {{ BioServices: a common Python package to access biological Web Services programmatically }},
    url = {https://dx.doi.org/10.1093/bioinformatics/btt547 https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/btt547},
    volume = {29},
    year = {2013}
}
@article{Xin2016a,
    abstract = {Efficient tools for data management and integration are essential for many aspects of high-throughput biology. In particular, annotations of genes and human genetic variants are commonly used but highly fragmented across many resources. Here, we describe MyGene.info and MyVariant.info, high-performance web services for querying gene and variant annotation information. These web services are currently accessed more than three million times permonth. They also demonstrate a generalizable cloud-based model for organizing and querying biological annotation information. MyGene.info and MyVariant.info are provided as high-performance web services, accessible at $\backslash$r$\backslash$n http://mygene.info$\backslash$r$\backslash$n $\backslash$r$\backslash$n and $\backslash$r$\backslash$n http://myvariant.info$\backslash$r$\backslash$n $\backslash$r$\backslash$n . Both are offered free of charge to the research community.},
    author = {Xin, Jiwen and Mark, Adam and Afrasiabi, Cyrus and Tsueng, Ginger and Juchler, Moritz and Gopal, Nikhil and Stupp, Gregory S. and Putman, Timothy E. and Ainscough, Benjamin J. and Griffith, Obi L. and Torkamani, Ali and Whetzel, Patricia L. and Mungall, Christopher J. and Mooney, Sean D. and Su, Andrew I. and Wu, Chunlei},
    doi = {10.1186/s13059-016-0953-9},
    file = {:Users/cthoyt/ownCloud/Mendeley/2016/High-performance web services for querying gene and variant annotation - 2016 - Xin et al.pdf:pdf},
    isbn = {1474760X (Electronic)},
    issn = {1474760X},
    journal = {Genome Biology},
    keywords = {API,Annotation,Cloud,Database,Gene,Repository,Variant},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {1},
    pages = {1--7},
    pmid = {27154141},
    publisher = {Genome Biology},
    title = {{ High-performance web services for querying gene and variant annotation }},
    url = {http://dx.doi.org/10.1186/s13059-016-0953-9},
    volume = {17},
    year = {2016}
}
@article{Davidson1995,
    abstract = {Scientific data of importance to biologists reside in a number of different data sources, such as GenBank, GSDB, SWISS-PROT, EMBL, and OMIM, among many others. Some of these data sources are conventional databases implemented using database management systems (DBMSs) and others are structured files maintained in a number of different formats (e.g., ASN.1 and ACE). In addition, software packages such as sequence analysis packages (e.g., BLAST and FASTA) produce data and can therefore be viewed as data sources. To counter the increasing dispersion and heterogeneity of data, different approaches to integrating these data sources are appearing throughout the bioinformatics community. This paper surveys the technical challenges to integration, classifies the approaches, and critiques the available tools and methodologies.},
    author = {Davidson, S B and Overton, C and Buneman, P},
    doi = {10.1089/cmb.1995.2.557},
    issn = {1066-5277 (Print)},
    journal = {Journal of computational biology : a journal of computational molecular cell biology},
    keywords = {Chromosomes, Artificial, Yeast,Data Interpretation, Statistical,Database Management Systems,Databases, Factual,Humans,Mathematics,Models, Genetic,Molecular Biology,Polymerase Chain Reaction,Repetitive Sequences, Nucleic Acid,Sequence Tagged Sites,Software},
    language = {eng},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {4},
    pages = {557--572},
    pmid = {8634908},
    title = {{ Challenges in integrating biological data sources. }},
    volume = {2},
    year = {1995}
}
@article{Chatr-Aryamontri2017,
    abstract = {The Biological General Repository for Interaction Datasets (BioGRID: https://thebiogrid.org) is an open access database dedicated to the annotation and archival of protein, genetic and chemical interac- tions for all major model organism species and hu- mans. As of September 2016 (build 3.4.140), the Bi- oGRID contains 1 072 173 genetic and protein in- teractions, and 38 559 post-translational modifica- tions, as manually annotated from 48 114 publica- tions. This dataset represents interaction records for 66 model organisms and represents a 30 { \% } increase compared to the previous 2015 BioGRID update. Bi- oGRID curates the biomedical literature for major model organism species, including humans, with a recent emphasis on central biological processes and specific human diseases. To facilitate network-based approaches to drug discovery, BioGRID nowincorpo- rates 27 501 chemical–protein interactions forhuman drug targets, as drawn fromthe DrugBank database. A newdynamic interaction network viewer allows the easy navigation and filtering of all genetic and pro- tein interaction data, as well as for bioactive com- pounds and their established targets. BioGRID data are directly downloadable without restriction in a variety of standardized formats and are freely dis- tributed through partner model organism databases and meta-databases.},
    author = {Chatr-Aryamontri, Andrew and Oughtred, Rose and Boucher, Lorrie and Rust, Jennifer and Chang, Christie and Kolas, Nadine K. and O'Donnell, Lara and Oster, Sara and Theesfeld, Chandra and Sellam, Adnane and Stark, Chris and Breitkreutz, Bobby Joe and Dolinski, Kara and Tyers, Mike},
    doi = {10.1093/nar/gkw1102},
    file = {:Users/cthoyt/ownCloud/Mendeley/2017/The BioGRID interaction database 2017 update - 2017 - Chatr-Aryamontri et al.pdf:pdf},
    isbn = {1362-4962 (Electronic)$\backslash$r0305-1048 (Linking)},
    issn = {13624962},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {D1},
    pages = {D369--D379},
    pmid = {25428363},
    title = {{ The BioGRID interaction database: 2017 update }},
    volume = {45},
    year = {2017}
}
@article{Redaschi2009,
    author = {Redaschi, Nicole and Consortium, UniProt},
    doi = {10.1038/npre.2009.3193.1},
    issn = {1756-0357},
    journal = {Nature Precedings},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {apr},
    title = {{ UniProt in RDF: Tackling Data Integration and Distributed Annotation with the Semantic Web }},
    url = {http://precedings.nature.com/doifinder/10.1038/npre.2009.3193.1},
    year = {2009}
}
@article{Domingo-Fernandez2018,
    abstract = {Although pathways are widely used for the analysis and representation of biological systems, their lack of clear boundaries, their dispersion across numerous databases, and the lack of interoperability impedes the evaluation of the coverage, agreements, and discrepancies between them. Here, we present ComPath, an ecosystem that supports curation of pathway mappings between databases and fosters the exploration of pathway knowledge through several novel visualizations. We have curated mappings between three of the major pathway databases and present a case study focusing on Parkinson's disease that illustrates how ComPath can generate new biological insights by identifying pathway modules, clusters, and cross-talks with these mappings. The ComPath source code and resources are available at https://github.com/ComPathand the web application can be accessed at https://compath.scai.fraunhofer.de/.},
    author = {Domingo-Fernandez, Daniel and Hoyt, Charles Tapley and Alvarez, Carlos Bobis and Marin-Llao, Josep and Hofmann-Apitius, Martin and Domingo-Fern { \' { a } } ndez, Daniel and Hoyt, Charles Tapley and Bobis- { \' { A } } lvarez, Carlos and Mar { \' { i } } n-Lla { \' { o } } , Josep and Hofmann-Apitius, Martin},
    doi = {10.1038/s41540-018-0078-8},
    file = {:Users/cthoyt/ownCloud/Mendeley/2018/ComPath An ecosystem for exploring, analyzing, and curating pathway databases - 2018 - Domingo-Fernandez et al.pdf:pdf},
    issn = {2056-7189},
    journal = {npj Systems Biology and Applications},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {1},
    pages = {3},
    publisher = {Springer US},
    title = {{ ComPath: an ecosystem for exploring, analyzing, and curating mappings across pathway databases }},
    url = {https://doi.org/10.1038/s41540-018-0078-8 https://www.biorxiv.org/content/early/2018/06/21/353235},
    volume = {5},
    year = {2018}
}
@article{Warde-Farley2010,
    abstract = {GeneMANIA (http://www.genemania.org) is a flexible, user-friendly web interface for generating hypotheses about gene function, analyzing gene lists and prioritizing genes for functional assays. Given a query list, GeneMANIA extends the list with functionally similar genes that it identifies using available genomics and proteomics data. GeneMANIA also reports weights that indicate the predictive value of each selected data set for the query. Six organisms are currently supported (Arabidopsis thaliana, Caenorhabditis elegans, Drosophila melanogaster, Mus musculus, Homo sapiens and Saccharomyces cerevisiae) and hundreds of data sets have been collected from GEO, BioGRID, Pathway Commons and I2D, as well as organism-specific functional genomics data sets. Users can select arbitrary subsets of the data sets associated with an organism to perform their analyses and can upload their own data sets to analyze. The GeneMANIA algorithm performs as well or better than other gene function prediction methods on yeast and mouse benchmarks. The high accuracy of the GeneMANIA prediction algorithm, an intuitive user interface and large database make GeneMANIA a useful tool for any biologist.},
    author = {Warde-Farley, David and Donaldson, Sylva L. and Comes, Ovi and Zuberi, Khalid and Badrawi, Rashad and Chao, Pauline and Franz, Max and Grouios, Chris and Kazi, Farzana and Lopes, Christian Tannus and Maitland, Anson and Mostafavi, Sara and Montojo, Jason and Shao, Quentin and Wright, George and Bader, Gary D. and Morris, Quaid},
    doi = {10.1093/nar/gkq537},
    file = {:Users/cthoyt/ownCloud/Mendeley/2010/The GeneMANIA prediction server Biological network integration for gene prioritization and predicting gene function - 2010 - Warde-Farle.pdf:pdf},
    issn = {03051048},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {SUPPL. 2},
    pages = {214--220},
    title = {{ The GeneMANIA prediction server: Biological network integration for gene prioritization and predicting gene function }},
    volume = {38},
    year = {2010}
}
@article{Stelzer2016,
    abstract = {GeneCards, the human gene compendium, enables researchers to effectively navigate and inter-relate the wide universe of human genes, diseases, variants, proteins, cells, and biological pathways. Our recently launched Version 4 has a revamped infrastructure facilitating faster data updates, better-targeted data queries, and friendlier user experience. It also provides a stronger foundation for the GeneCards suite of companion databases and analysis tools. Improved data unification includes gene-disease links via MalaCards and merged biological pathways via PathCards, as well as drug information and proteome expression. VarElect, another suite member, is a phenotype prioritizer for next-generation sequencing, leveraging the GeneCards and MalaCards knowledgebase. It automatically infers direct and indirect scored associations between hundreds or even thousands of variant-containing genes and disease phenotype terms. VarElect's capabilities, either independently or within TGex, our comprehensive variant analysis pipeline, help prepare for the challenge of clinical projects that involve thousands of exome/genome NGS analyses. { \textcopyright } 2016 by John Wiley { \& } Sons, Inc.},
    author = {Stelzer, Gil and Rosen, Naomi and Plaschkes, Inbar and Zimmerman, Shahar and Twik, Michal and Fishilevich, Simon and { Iny Stein } , Tsippi and Nudel, Ron and Lieder, Iris and Mazor, Yaron and Kaplan, Sergey and Dahary, Dvir and Warshawsky, David and Guan-Golan, Yaron and Kohn, Asher and Rappaport, Noa and Safran, Marilyn and Lancet, Doron},
    doi = {10.1002/cpbi.5},
    file = {:Users/cthoyt/ownCloud/Mendeley/2016/The GeneCards suite From gene data mining to disease genome sequence analyses - 2016 - Stelzer et al.pdf:pdf},
    issn = {1934340X},
    journal = {Current Protocols in Bioinformatics},
    keywords = {Bioinformatics,Biological database,Diseases,Gene prioritization,Genecards,Human genes,Integrated information retrieval,Next generation sequencing,VarElect},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {June},
    pages = {1.30.1--1.30.33},
    title = {{ The GeneCards suite: From gene data mining to disease genome sequence analyses }},
    volume = {2016},
    year = {2016}
}
@article{Queralt-Rosinach2016,
    abstract = {Motivation: DisGeNET-RDF makes available knowledge on the genetic basis of human diseases in the Semantic Web. Gene-disease associations (GDAs) and their provenance metadata are published as human-readable and machine-processable web resources. The information on GDAs included in DisGeNET-RDF is interlinked to other biomedical databases to support the development of bioinformatics approaches for translational research through evidence-based exploitation of a rich and fully interconnected linked open data.Availability and implementation:http://rdf.disgenet.org/Contact:support@disgenet.org},
    author = {Queralt-Rosinach, N { \' { u } } ria and Pi { \~ { n } } ero, Janet and Bravo, { \` { A } } lex and Sanz, Ferran and Furlong, Laura I},
    doi = {10.1093/bioinformatics/btw214},
    issn = {1367-4803},
    journal = {Bioinformatics},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {jul},
    number = {14},
    pages = {2236--2238},
    title = {{ DisGeNET-RDF: harnessing the innovative power of the Semantic Web to explore the genetic basis of diseases }},
    url = {https://dx.doi.org/10.1093/bioinformatics/btw214 https://academic.oup.com/bioinformatics/article-lookup/doi/10.1093/bioinformatics/btw214},
    volume = {32},
    year = {2016}
}
@article{VanDam2014,
    abstract = {BACKGROUND: Different methods have been developed to infer regulatory networks from heterogeneous omics datasets and to construct co-expression networks. Each algorithm produces different networks and efforts have been devoted to automatically integrate them into consensus sets. However each separate set has an intrinsic value that is diluted and partly lost when building a consensus network. Here we present a methodology to generate co-expression networks and, instead of a consensus network, we propose an integration framework where the different networks are kept and analysed with additional tools to efficiently combine the information extracted from each network.$\backslash$n$\backslash$nRESULTS: We developed a workflow to efficiently analyse information generated by different inference and prediction methods. Our methodology relies on providing the user the means to simultaneously visualise and analyse the coexisting networks generated by different algorithms, heterogeneous datasets, and a suite of analysis tools. As a show case, we have analysed the gene co-expression networks of Mycobacterium tuberculosis generated using over 600 expression experiments. Regarding DNA damage repair, we identified SigC as a key control element, 12 new targets for LexA, an updated LexA binding motif, and a potential mismatch repair system. We expanded the DevR regulon with 27 genes while identifying 9 targets wrongly assigned to this regulon. We discovered 10 new genes linked to zinc uptake and a new regulatory mechanism for ZuR. The use of co-expression networks to perform system level analysis allows the development of custom made methodologies. As show cases we implemented a pipeline to integrate ChIP-seq data and another method to uncover multiple regulatory layers.$\backslash$n$\backslash$nCONCLUSIONS: Our workflow is based on representing the multiple types of information as network representations and presenting these networks in a synchronous framework that allows their simultaneous visualization while keeping specific associations from the different networks. By simultaneously exploring these networks and metadata, we gained insights into regulatory mechanisms in M. tuberculosis that could not be obtained through the separate analysis of each data type.},
    author = {van Dam, Jesse CJ J and Schaap, Peter J and { Martins dos Santos } , Vitor AP P and Su { \' { a } } rez-Diez, Mar { \' { i } } a},
    doi = {10.1186/s12918-014-0111-5},
    file = {:Users/cthoyt/ownCloud/Mendeley/2014/Integration of heterogeneous molecular networks to unravel gene-regulation in Mycobacterium tuberculosis. - 2014 - van Dam et al.pdf:pdf},
    issn = {1752-0509},
    journal = {BMC systems biology},
    keywords = {Algorithms,Bacterial,Bacterial: genetics,Bacterial: physiology,Biological,Chromatin Immunoprecipitation,Folder - Data Integration,Gene Expression Regulation,Gene Regulatory Networks,Gene Regulatory Networks: genetics,Gene Regulatory Networks: physiology,Models,Mycobacterium tuberculosis,Mycobacterium tuberculosis: genetics,Mycobacterium tuberculosis: metabolism,RNA,Sequence Analysis},
    language = {en},
    mendeley-groups = {Bio2BEL Manuscript References},
    mendeley-tags = {Folder - Data Integration},
    month = {dec},
    number = {1},
    pages = {111},
    pmid = {25279447},
    title = {{ Integration of heterogeneous molecular networks to unravel gene-regulation in Mycobacterium tuberculosis. }},
    url = {http://www.biomedcentral.com/1752-0509/8/111},
    volume = {8},
    year = {2014}
}
@article{Naz2016,
    abstract = {The work we present here is based on the recent extension of the syntax of the Biological Expression Language (BEL), which now allows for the representation of genetic variation information in cause-and-effect models. In our article, we describe, how genetic variation information can be used to identify candidate disease mechanisms in diseases with complex aetiology such as Alzheimer's disease and Parkinson's disease. In those diseases, we have to assume that many genetic variants contribute moderately to the overall dysregulation that in the case of neurodegenerative diseases has such a long incubation time until the first clinical symptoms are detectable. Owing to the multilevel nature of dysregulation events, systems biomedicine modelling approaches need to combine mechanistic information from various levels, including gene expression, microRNA (miRNA) expression, protein-protein interaction, genetic variation and pathway. OpenBEL, the open source version of BEL, has recently been extended to match this requirement, and we demonstrate in our article, how candidate mechanisms for early dysregulation events in Alzheimer's disease can be identified based on an integrative mining approach that identifies 'chains of causation' that include single nucleotide polymorphism information in BEL models.},
    author = {Naz, Mufassra and Kodamullil, Alpha Tom and Hofmann-Apitius, Martin},
    doi = {10.1093/bib/bbv063},
    file = {:Users/cthoyt/ownCloud/Mendeley/2016/Reasoning over genetic variance information in cause-and-effect models of neurodegenerative diseases. - 2016 - Naz, Kodamullil, Hofmann-.pdf:pdf},
    issn = {1477-4054},
    journal = {Briefings in bioinformatics},
    keywords = {Alzheimer's disease,BEL model,GWAS,causal reasoning,cause-and-effect,genetic variants},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {3},
    pages = {505--16},
    pmid = {26249223},
    title = {{ Reasoning over genetic variance information in cause-and-effect models of neurodegenerative diseases. }},
    url = {http://bib.oxfordjournals.org/lookup/doi/10.1093/bib/bbv063 { \% } 5Cnhttp://www.ncbi.nlm.nih.gov/pubmed/26249223 http://www.ncbi.nlm.nih.gov/pubmed/26249223 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC4870396},
    volume = {17},
    year = {2016}
}
@article{Gautier2004,
    abstract = {MOTIVATION The processing of the Affymetrix GeneChip data has been a recent focus for data analysts. Alternatives to the original procedure have been proposed and some of these new methods are widely used. RESULTS The affy package is an R package of functions and classes for the analysis of oligonucleotide arrays manufactured by Affymetrix. The package is currently in its second release, affy provides the user with extreme flexibility when carrying out an analysis and make it possible to access and manipulate probe intensity data. In this paper, we present the main classes and functions in the package and demonstrate how they can be used to process probe-level data. We also demonstrate the importance of probe-level analysis when using the Affymetrix GeneChip platform.},
    author = {Gautier, Laurent and Cope, Leslie and Bolstad, Benjamin M. and Irizarry, Rafael A.},
    doi = {10.1093/bioinformatics/btg405},
    file = {:Users/cthoyt/ownCloud/Mendeley/2004/Affy - Analysis of Affymetrix GeneChip data at the probe level - 2004 - Gautier et al.pdf:pdf},
    isbn = {1367-4803 (Print)$\backslash$r1367-4803 (Linking)},
    issn = {13674803},
    journal = {Bioinformatics},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {3},
    pages = {307--315},
    pmid = {14960456},
    title = {{ Affy - Analysis of Affymetrix GeneChip data at the probe level }},
    volume = {20},
    year = {2004}
}
@article{Paszke2017,
    abstract = {In this article, we describe an automatic differentiation module of PyTorch — a library designed to enable rapid research on machine learning models. It builds upon a few projects, most notably Lua Torch, Chainer, and HIPS Autograd, and provides a high performance environment with easy access to automatic differentiation of models executed on different devices (CPU and GPU). To make prototyping easier, PyTorch does not follow the symbolic approach used in many other deep learning frameworks, but focuses on differentiation of purely imperative programs, with a focus on extensibility and low overhead. Note that this preprint is a draft of certain sections from an upcoming paper covering all PyTorch features.},
    archivePrefix = {arXiv},
    arxivId = {arXiv:1011.1669v3},
    author = {Paszke, Adam and Chanan, Gregory and Lin, Zeming and Gross, Sam and Yang, Edward and Antiga, Luca and Devito, Zachary},
    doi = {10.1017/CBO9781107707221.009},
    eprint = {arXiv:1011.1669v3},
    file = {:Users/cthoyt/ownCloud/Mendeley/2017/Automatic differentiation in PyTorch - 2017 - Paszke et al.pdf:pdf},
    isbn = {9788578110796},
    issn = {1098-6596},
    journal = {31st Conference on Neural Information Processing Systems},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {Nips},
    pages = {1--4},
    pmid = {25246403},
    title = {{ Automatic differentiation in PyTorch }},
    year = {2017}
}
@article{Nickel2016,
    abstract = {Relational machine learning studies methods for the statistical analysis of relational, or graph-structured, data. In this paper, we provide a review of how such statistical models can be "trained" on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges in the graph). In particular, we discuss two fundamentally different kinds of statistical relational models, both of which can scale to massive datasets. The first is based on latent feature models such as tensor factorization and multiway neural networks. The second is based on mining observable patterns in the graph. We also show how to combine these latent and observable models to get improved modeling power at decreased computational cost. Finally, we discuss how such statistical models of graphs can be combined with text-based information extraction methods for automatically constructing knowledge graphs from the Web. To this end, we also discuss Google's Knowledge Vault project as an example of such combination.},
    author = {Nickel, Maximilian and Murphy, Kevin and Tresp, Volker and Gabrilovich, Evgeniy},
    doi = {10.1109/JPROC.2015.2483592},
    file = {:Users/cthoyt/ownCloud/Mendeley/2016/A Review of Relational Machine Learning for Knowledge Graphs - 2016 - Nickel et al.pdf:pdf},
    issn = {0018-9219},
    journal = {Proceedings of the IEEE},
    keywords = {graph-based models,knowledge extraction,knowledge graphs,latent feature models,statistical relational},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {jan},
    number = {1},
    pages = {11--33},
    title = {{ A Review of Relational Machine Learning for Knowledge Graphs }},
    url = {http://arxiv.org/abs/1503.00759 https://ieeexplore.ieee.org/document/7358050/},
    volume = {104},
    year = {2016}
}
@article{Emon2017,
    abstract = {Neurodegenerative diseases including Alzheimer's disease are complex to tackle because of the complexity of the brain, both in structure and function. Such complexity is reflected by the involvement of various brain regions and multiple pathways in the etiology of neurodegenerative diseases that render single drug target approaches ineffective. Particularly in the area of neurodegeneration, attention has been drawn to repurposing existing drugs with proven efficacy and safety profiles. However, there is a lack of systematic analysis of the brain chemical space to predict the feasibility of repurposing strategies. Using a mechanism-based, drug-target interaction modeling approach, we have identified promising drug candidates for repositioning. Mechanistic cause-and-effect models consolidate relevant prior knowledge on drugs, targets, and pathways from the scientific literature and integrate insights derived from experimental data. We demonstrate the power of this approach by predicting two repositioning candidates for Alzheimer's disease and one for amyotrophic lateral sclerosis.},
    author = {Emon, Mohammad Asif Emran Khan and Kodamullil, Alpha Tom and Karki, Reagon and Younesi, Erfan and Hofmann-Apitius, Martin},
    doi = {10.3233/JAD-160222},
    file = {:Users/cthoyt/ownCloud/Mendeley/2017/Using Drugs as Molecular Probes A Computational Chemical Biology Approach in Neurodegenerative Diseases - 2017 - Emon et al.pdf:pdf},
    issn = {13872877},
    journal = {Journal of Alzheimer's Disease},
    keywords = {alzheimer disease,amyotrophic lateral sclerosis,biological expression language,disease-drug modeling,drug repositioning,neurodegenerative diseases},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {2},
    pages = {677--686},
    pmid = {28035920},
    title = {{ Using Drugs as Molecular Probes: A Computational Chemical Biology Approach in Neurodegenerative Diseases }},
    url = {http://www.medra.org/servlet/aliasResolver?alias=iospress { \& } doi=10.3233/JAD-160222},
    volume = {56},
    year = {2017}
}
@article{Chen2010,
    author = {Chen, B and Dong, X and Jiao, D and Wang, H and Zhu, Q and Ding, Y and Wild, DJ},
    file = {:Users/cthoyt/ownCloud/Mendeley/2010/Chem2Bio2RDF a sematic framework for linking and data mining chemogenomic and systems chemical biology data - 2010 - Chen et al.pdf:pdf},
    journal = {BMC Bioinformatics},
    mendeley-groups = {Bio2BEL Manuscript References},
    pages = {255},
    title = {{ Chem2Bio2RDF: a sematic framework for linking and data mining chemogenomic and systems chemical biology data }},
    volume = {11},
    year = {2010}
}
@article{Kanehisa2017,
    abstract = {KEGG (http://www.kegg.jp/ or http://www.genome.jp/kegg/) is an encyclopedia of genes and genomes. Assigning functional meanings to genes and genomes both at the molecular and higher levels is the primary objective of the KEGG database project. Molecular-level functions are stored in the KO (KEGG Orthology) database, where each KO is defined as a functional ortholog of genes and proteins. Higher-level functions are represented by networks of molecular interactions, reactions and relations in the forms of KEGG pathway maps, BRITE hierarchies and KEGG modules. In the past the KO database was developed for the purpose of defining nodes of molecular networks, but now the content has been expanded and the quality improved irrespective of whether or not the KOs appear in the three molecular network databases. The newly introduced addendum category of the GENES database is a collection of individual proteins whose functions are experimentally characterized and from which an increasing number of KOs are defined. Furthermore, the DISEASE and DRUG databases have been improved by systematic analysis of drug labels for better integration of diseases and drugs with the KEGG molecular networks. KEGG is moving towards becoming a comprehensive knowledge base for both functional interpretation and practical application of genomic information.},
    archivePrefix = {arXiv},
    arxivId = {1611.06654},
    author = {Kanehisa, Minoru and Furumichi, Miho and Tanabe, Mao and Sato, Yoko and Morishima, Kanae},
    doi = {10.1093/nar/gkw1092},
    eprint = {1611.06654},
    file = {:Users/cthoyt/ownCloud/Mendeley/2017/KEGG New perspectives on genomes, pathways, diseases and drugs - 2017 - Kanehisa et al.pdf:pdf},
    isbn = {2076792171},
    issn = {13624962},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {D1},
    pages = {D353--D361},
    pmid = {27899565},
    title = {{ KEGG: New perspectives on genomes, pathways, diseases and drugs }},
    volume = {45},
    year = {2017}
}
@article{Meldal2015,
    abstract = {The IntAct molecular interaction database has created a new, free, open-source, manually curated resource, the Complex Portal (www.ebi.ac.uk/intact/complex), through which protein complexes from major model organisms are being collated and made available for search, viewing and download. It has been built in close collaboration with other bioinformatics services and populated with data from ChEMBL, MatrixDB, PDBe, Reactome and UniProtKB. Each entry contains information about the participating molecules (including small molecules and nucleic acids), their stoichiometry, topology and structural assembly. Complexes are annotated with details about their function, properties and complex-specific Gene Ontology (GO) terms. Consistent nomenclature is used throughout the resource with systematic names, recommended names and a list of synonyms all provided. The use of the Evidence Code Ontology allows us to indicate for which entries direct experimental evidence is available or if the complex has been inferred based on homology or orthology. The data are searchable using standard identifiers, such as UniProt, ChEBI and GO IDs, protein, gene and complex names or synonyms. This reference resource will be maintained and grow to encompass an increasing number of organisms. Input from groups and individuals with specific areas of expertise is welcome.},
    author = {Meldal, Birgit H.M. and Forner-Martinez, Oscar and Costanzo, Maria C. and Dana, Jose and Demeter, Janos and Dumousseau, Marine and Dwight, Selina S. and Gaulton, Anna and Licata, Luana and Melidoni, Anna N. and Ricard-Blum, Sylvie and Roechert, Bernd and Skyzypek, Marek S. and Tiwari, Manu and Velankar, Sameer and Wong, Edith D. and Hermjakob, Henning and Orchard, Sandra},
    doi = {10.1093/nar/gku975},
    file = {:Users/cthoyt/ownCloud/Mendeley/2015/The complex portal - An encyclopaedia of macromolecular complexes - 2015 - Meldal et al.pdf:pdf},
    isbn = {1362-4962 (Electronic)$\backslash$r0305-1048 (Linking)},
    issn = {13624962},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {D1},
    pages = {D479--D484},
    pmid = {25313161},
    title = {{ The complex portal - An encyclopaedia of macromolecular complexes }},
    volume = {43},
    year = {2015}
}
@article{Wishart2018,
    abstract = {DrugBank (www.drugbank.ca) is a web-enabled database containing comprehensive molecular information about drugs, their mechanisms, their interactions and their targets. First described in 2006, DrugBank has continued to evolve over the past 12 years in response to marked improvements to web standards and changing needs for drug research and development. This year's update, DrugBank 5.0, represents the most significant upgrade to the database in more than 10 years. In many cases, existing data content has grown by 100 { \% } or more over the last update. For instance, the total number of investigational drugs in the database has grown by almost 300 { \% } , the number of drug-drug interactions has grown by nearly 600 { \% } and the number of SNP-associated drug effects has grown more than 3000 { \% } . Significant improvements have been made to the quantity, quality and consistency of drug indications, drug binding data as well as drug-drug and drug-food interactions. A great deal of brand new data have also been added to DrugBank 5.0. This includes information on the influence of hundreds of drugs on metabolite levels (pharmacometabolomics), gene expression levels (pharmacotranscriptomics) and protein expression levels (pharmacoprotoemics). New data have also been added on the status of hundreds of new drug clinical trials and existing drug repurposing trials. Many other important improvements in the content, interface and performance of the DrugBank website have been made and these should greatly enhance its ease of use, utility and potential applications in many areas of pharmacological research, pharmaceutical science and drug education.},
    author = {Wishart, David S and Feunang, Yannick D and Guo, An C and Lo, Elvis J and Marcu, Ana and Grant, Jason R and Sajed, Tanvir and Johnson, Daniel and Li, Carin and Sayeeda, Zinat and Assempour, Nazanin and Iynkkaran, Ithayavani and Liu, Yifeng and Maciejewski, Adam and Gale, Nicola and Wilson, Alex and Chin, Lucy and Cummings, Ryan and Le, Diana and Pon, Allison and Knox, Craig and Wilson, Michael},
    doi = {10.1093/nar/gkx1037},
    file = {:Users/cthoyt/ownCloud/Mendeley/2018/DrugBank 5.0 a major update to the DrugBank database for 2018. - 2018 - Wishart et al.pdf:pdf},
    issn = {1362-4962},
    journal = {Nucleic acids research},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {jan},
    number = {D1},
    pages = {D1074--D1082},
    pmid = {29126136},
    title = {{ DrugBank 5.0: a major update to the DrugBank database for 2018. }},
    url = {http://www.ncbi.nlm.nih.gov/pubmed/29126136 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC5753335},
    volume = {46},
    year = {2018}
}
@article{Belleau2008,
    author = {Belleau, Fran { \c { c } } ois and Nolin, Marc-Alexandre and Tourigny, Nicole and Rigault, Philippe and Morissette, Jean},
    doi = {10.1016/j.jbi.2008.03.004},
    file = {:Users/cthoyt/ownCloud/Mendeley/2008/Bio2RDF Towards a mashup to build bioinformatics knowledge systems - 2008 - Belleau et al.pdf:pdf},
    issn = {15320464},
    journal = {Journal of Biomedical Informatics},
    keywords = {Data Integration,Folder - RDF and Semantic Web,Linked Biological Data,RDF},
    language = {en},
    mendeley-groups = {Bio2BEL Manuscript References},
    mendeley-tags = {Data Integration,Folder - RDF and Semantic Web,Linked Biological Data,RDF},
    month = {oct},
    number = {5},
    pages = {706--716},
    shorttitle = {Bio2RDF},
    title = {{ Bio2RDF: Towards a mashup to build bioinformatics knowledge systems }},
    url = {http://linkinghub.elsevier.com/retrieve/pii/S1532046408000415},
    volume = {41},
    year = {2008}
}
@article{Yates2017,
    abstract = {The HUGO Gene Nomenclature Committee (HGNC) based at the European Bioinformatics Institute (EMBL-EBI) assigns unique symbols and names to human genes. Currently the HGNC database contains almost 40 000 approved gene symbols, over 19 000 of which represent protein-coding genes. In addition to naming genomic loci we manually curate genes into family sets based on shared characteristics such as homology, function or phenotype. We have recently updated our gene family resources and introduced new improved visualizations which can be seen alongside our gene symbol reports on our primary website http://www.genenames.org In 2016 we expanded our remit and formed the Vertebrate Gene Nomenclature Committee (VGNC) which is responsible for assigning names to vertebrate species lacking a dedicated nomenclature group. Using the chimpanzee genome as a pilot project we have approved symbols and names for over 14 500 protein-coding genes in chimpanzee, and have developed a new website http://vertebrate.genenames.org to distribute these data. Here, we review our online data and resources, focusing particularly on the improvements and new developments made during the last two years.},
    author = {Yates, Bethan and Braschi, Bryony and Gray, Kristian A. and Seal, Ruth L. and Tweedie, Susan and Bruford, Elspeth A.},
    doi = {10.1093/nar/gkw1033},
    file = {:Users/cthoyt/ownCloud/Mendeley/2017/Genenames.org The HGNC and VGNC resources in 2017 - 2017 - Yates et al.pdf:pdf},
    isbn = {13624962 (Electronic)},
    issn = {13624962},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {D1},
    pages = {D619--D625},
    pmid = {27799471},
    title = {{ Genenames.org: The HGNC and VGNC resources in 2017 }},
    volume = {45},
    year = {2017}
}
@article{Cerami2011,
    abstract = {Pathway Commons (http://www.pathwaycommons.org) is a collection of publicly available pathway data from multiple organisms. Pathway Commons provides a web-based interface that enables biologists to browse and search a comprehensive collection of pathways from multiple sources represented in a common language, a download site that provides integrated bulk sets of pathway information in standard or convenient formats and a web service that software developers can use to conveniently query and access all data. Database providers can share their pathway data via a common repository. Pathways include biochemical reactions, complex assembly, transport and catalysis events and physical interactions involving proteins, DNA, RNA, small molecules and complexes. Pathway Commons aims to collect and integrate all public pathway data available in standard formats. Pathway Commons currently contains data from nine databases with over 1400 pathways and 687,000 interactions and will be continually expanded and updated.},
    author = {Cerami, Ethan G. and Gross, Benjamin E. and Demir, Emek and Rodchenkov, Igor and Babur, { \" { O } } zg { \" { u } } n and Anwar, Nadia and Schultz, Nikolaus and Bader, Gary D. and Sander, Chris},
    doi = {10.1093/nar/gkq1039},
    file = {:Users/cthoyt/ownCloud/Mendeley/2011/Pathway Commons, a web resource for biological pathway data - 2011 - Cerami et al.pdf:pdf},
    isbn = {1362-4962 (Electronic)$\backslash$r0305-1048 (Linking)},
    issn = {03051048},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {SUPPL. 1},
    pages = {685--690},
    pmid = {21071392},
    title = {{ Pathway Commons, a web resource for biological pathway data }},
    volume = {39},
    year = {2011}
}
@article{Schriml2018,
    abstract = {The Human Disease Ontology (DO) (http://www.disease-ontology.org), database has undergone significant expansion in the past three years. The DO disease classification includes specific formal semantic rules to express meaningful disease models and has expanded from a single asserted classification to include multiple-inferred mechanistic disease classifications, thus providing novel perspectives on related diseases. Expansion of disease terms, alternative anatomy, cell type and genetic disease classifications and workflow automation highlight the updates for the DO since 2015. The enhanced breadth and depth of the DO's knowledgebase has expanded the DO's utility for exploring the multi-etiology of human disease, thus improving the capture and communication of health-related data across biomedical databases, bioinformatics tools, genomic and cancer resources and demonstrated by a 6.6× growth in DO's user community since 2015. The DO's continual integration of human disease knowledge, evidenced by the more than 200 SVN/GitHub releases/revisions, since previously reported in our DO 2015 NAR paper, includes the addition of 2650 new disease terms, a 30 { \% } increase of textual definitions, and an expanding suite of disease classification hierarchies constructed through defined logical axioms.},
    author = {Schriml, Lynn M and Mitraka, Elvira and Munro, James and Tauber, Becky and Schor, Mike and Nickle, Lance and Felix, Victor and Jeng, Linda and Bearer, Cynthia and Lichenstein, Richard and Bisordi, Katharine and Campion, Nicole and Hyman, Brooke and Kurland, David and Oates, Connor Patrick and Kibbey, Siobhan and Sreekumar, Poorna and Le, Chris and Giglio, Michelle and Greene, Carol},
    doi = {10.1093/nar/gky1032},
    file = {:Users/cthoyt/ownCloud/Mendeley/2019/Human Disease Ontology 2018 update classification, content and workflow expansion. - 2019 - Schriml et al.pdf:pdf},
    isbn = {13624962 (Electronic)},
    issn = {1362-4962},
    journal = {Nucleic acids research},
    keywords = {automation,bioinformatics,cancer,causality,community,disease models,disorder classification,genetic disorder,genome,knowledge bases,semantics,workflow},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {jan},
    number = {D1},
    pages = {D955--D962},
    pmid = {30407550},
    publisher = {Oxford University Press},
    title = {{ Human Disease Ontology 2018 update: classification, content and workflow expansion. }},
    url = {https://academic.oup.com/nar/advance-article/doi/10.1093/nar/gky1032/5165342 http://www.ncbi.nlm.nih.gov/pubmed/30407550 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC6323977},
    volume = {47},
    year = {2019}
}
@article{Zhou2014,
    abstract = {In the post-genomic era, the elucidation of the relationship between the molecular origins of diseases and their resulting phenotypes is a crucial task for medical research. Here, we use a large-scale biomedical literature database to construct a symptom-based human disease network and investigate the connection between clinical manifestations of diseases and their underlying molecular interactions. We find that the symptom-based similarity of two diseases correlates strongly with the number of shared genetic associations and the extent to which their associated proteins interact. Moreover, the diversity of the clinical manifestations of a disease can be related to the connectivity patterns of the underlying protein interaction network. The comprehensive, high-quality map of disease-symptom relations can further be used as a resource helping to address important questions in the field of systems medicine, for example, the identification of unexpected associations between diseases, disease etiology research or drug design.},
    author = {Zhou, Xuezhong and Menche, J { \" { o } } rg and Barab { \' { a } } si, Albert-L { \' { a } } szl { \' { o } } and Sharma, Amitabh},
    doi = {10.1038/ncomms5212},
    file = {:Users/cthoyt/ownCloud/Mendeley/2014/Human symptoms-disease network. - 2014 - Zhou et al.pdf:pdf},
    issn = {2041-1723},
    journal = {Nature communications},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {jun},
    number = {May},
    pages = {4212},
    pmid = {24967666},
    title = {{ Human symptoms-disease network. }},
    url = {http://www.ncbi.nlm.nih.gov/pubmed/24967666},
    volume = {5},
    year = {2014}
}
@article{Wadi2016,
    abstract = {Pathway-based interpretation of gene lists is a staple of genome analysis. It depends on frequently updated gene annotation databases. We analyzed the evolution of gene annotations over the past seven years and found that the vocabulary of pathways and processes has doubled. This strongly impacts practical analysis of genes: 80 { \% } of publications we surveyed in 2015 used outdated software that only captured 20 { \% } of pathway enrichments apparent in current annotations.},
    author = {Wadi, Lina and Meyer, Mona and Weiser, Joel and Stein, Lincoln D. and Reimand, J { \" { u } } ri},
    doi = {10.1038/nmeth.3963},
    file = {:Users/cthoyt/ownCloud/Mendeley/2016/Impact of outdated gene annotations on pathway enrichment analysis - 2016 - Wadi et al.pdf:pdf},
    isbn = {9781607614289},
    issn = {15487105},
    journal = {Nature Methods},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {9},
    pages = {705--706},
    pmid = {15708109},
    title = {{ Impact of outdated gene annotations on pathway enrichment analysis }},
    volume = {13},
    year = {2016}
}
@article{Slater2014,
    author = {Slater, Ted},
    doi = {10.1016/j.drudis.2013.12.011},
    file = {:Users/cthoyt/ownCloud/Mendeley/2014/Recent advances in modeling languages for pathway maps and computable biological networks - 2014 - Slater.pdf:pdf},
    issn = {13596446},
    journal = {Drug Discovery Today},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {feb},
    number = {2},
    pages = {193--198},
    title = {{ Recent advances in modeling languages for pathway maps and computable biological networks }},
    url = {http://linkinghub.elsevier.com/retrieve/pii/S1359644614000063},
    volume = {19},
    year = {2014}
}
@article{Himmelstein2017,
    abstract = {The ability to computationally predict whether a compound treats a disease would improve the economy and success rate of drug approval. This study describes Project Rephetio to systematically model drug efficacy based on 755 existing treatments. First, we constructed Hetionet (neo4j.het.io), an integrative network encoding knowledge from millions of biomedical studies. Hetionet v1.0 consists of 47,031 nodes of 11 types and 2,250,197 relationships of 24 types. Data were integrated from 29 public resources to connect compounds, diseases, genes, anatomies, pathways, biological processes, molecular functions, cellular components, pharmacologic classes, side effects, and symptoms. Next, we identified network patterns that distinguish treatments from non-treatments. Then, we predicted the probability of treatment for 209,168 compound-disease pairs (het.io/repurpose). Our predictions validated on two external sets of treatment and provided pharmacological insights on epilepsy, suggesting they will help prioritize drug repurposing candidates. This study was entirely open and received realtime feedback from 40 community members.},
    author = {Himmelstein, Daniel Scott and Lizee, Antoine and Hessler, Christine and Brueggeman, Leo and Chen, Sabrina L and Hadley, Dexter and Green, Ari and Khankhanian, Pouya and Baranzini, Sergio E},
    doi = {10.7554/eLife.26726},
    file = {:Users/cthoyt/ownCloud/Mendeley/2017/Systematic integration of biomedical knowledge prioritizes drugs for repurposing. - 2017 - Himmelstein et al.pdf:pdf},
    issn = {2050-084X},
    journal = {eLife},
    keywords = {computational biology,drug repurposing,heterogeneous networks,human,machine learning,systems biology},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {sep},
    pmid = {28936969},
    title = {{ Systematic integration of biomedical knowledge prioritizes drugs for repurposing. }},
    url = {http://www.ncbi.nlm.nih.gov/pubmed/28936969 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC5640425},
    volume = {6},
    year = {2017}
}
@article{Szklarczyk2015,
    abstract = {The many functional partnerships and interactions that occur between proteins are at the core of cellular processing and their systematic characterization helps to provide context in molecular systems biology. However, known and predicted interactions are scattered over multiple resources, and the available data exhibit notable differences in terms of quality and completeness. The STRING database (http://string-db.org) aims to provide a critical assessment and integration of protein-protein interactions, including direct (physical) as well as indirect (functional) associations. The new version 10.0 of STRING covers more than 2000 organisms, which has necessitated novel, scalable algorithms for transferring interaction information between organisms. For this purpose, we have introduced hierarchical and self-consistent orthology annotations for all interacting proteins, grouping the proteins into families at various levels of phylogenetic resolution. Further improvements in version 10.0 include a completely redesigned prediction pipeline for inferring protein-protein associations from co-expression data, an API interface for the R computing environment and improved statistical analysis for enrichment tests in user-provided networks.},
    author = {Szklarczyk, Damian and Franceschini, Andrea and Wyder, Stefan and Forslund, Kristoffer and Heller, Davide and Huerta-Cepas, Jaime and Simonovic, Milan and Roth, Alexander and Santos, Alberto and Tsafou, Kalliopi P. and Kuhn, Michael and Bork, Peer and Jensen, Lars J. and { Von Mering } , Christian},
    doi = {10.1093/nar/gku1003},
    file = {:Users/cthoyt/ownCloud/Mendeley/2015/STRING v10 Protein-protein interaction networks, integrated over the tree of life - 2015 - Szklarczyk et al.pdf:pdf},
    isbn = {13624962 (Electronic)},
    issn = {13624962},
    journal = {Nucleic Acids Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {D1},
    pages = {D447--D452},
    pmid = {25352553},
    title = {{ STRING v10: Protein-protein interaction networks, integrated over the tree of life }},
    volume = {43},
    year = {2015}
}
@article{ROGERS1963,
    author = {Rogers, F B},
    file = {:Users/cthoyt/ownCloud/Mendeley/1963/Medical subject headings. - 1963 - Rogers.pdf:pdf},
    issn = {0025-7338},
    journal = {Bulletin of the Medical Library Association},
    keywords = {LIBRARIES,MEDICAL,SUBJECT HEADINGS},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {jan},
    pages = {114--6},
    pmid = {13982385},
    title = {{ Medical subject headings. }},
    url = {http://www.ncbi.nlm.nih.gov/pubmed/13982385 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC197951},
    volume = {51},
    year = {1963}
}
@article{Liberzon2015,
    abstract = {The Molecular Signatures Database (MSigDB) is one of the most widely used and comprehensive databases of gene sets for performing gene set enrichment analysis. Since its creation, MSigDB has grown beyond its roots in metabolic disease and cancer to include { \textgreater } 10,000 gene sets. These better represent a wider range of biological processes and diseases, but the utility of the database is reduced by increased redundancy across, and heterogeneity within, gene sets. To address this challenge, here we use a combination of automated approaches and expert curation to develop a collection of “hallmark” gene sets as part of MSigDB. Each hallmark in this collection consists of a “refined” gene set, derived from multiple “founder” sets, that conveys a specific biological state or process and displays coherent expression. The hallmarks effectively summarize most of the relevant information of the original founder sets and, by reducing both variation and redundancy, provide more refined and concise inputs for gene set enrichment analysis.},
    author = {Liberzon, Arthur and Birger, Chet and Thorvaldsd { \' { o } } ttir, Helga and Ghandi, Mahmoud and Mesirov, Jill P. and Tamayo, Pablo},
    doi = {10.1016/J.CELS.2015.12.004},
    file = {:Users/cthoyt/ownCloud/Mendeley/2015/The Molecular Signatures Database Hallmark Gene Set Collection - 2015 - Liberzon et al.pdf:pdf},
    issn = {2405-4712},
    journal = {Cell Systems},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {dec},
    number = {6},
    pages = {417--425},
    publisher = {Cell Press},
    title = {{ The Molecular Signatures Database Hallmark Gene Set Collection }},
    url = {https://www.sciencedirect.com/science/article/pii/S2405471215002185},
    volume = {1},
    year = {2015}
}
@article{Alocci2015,
    abstract = {Resource description framework (RDF) and Property Graph databases are emerging technologies that are used for storing graph-structured data. We compare these technologies through a molecular biology use case: glycan substructure search. Glycans are branched tree-like molecules composed of building blocks linked together by chemical bonds. The molecular structure of a glycan can be encoded into a direct acyclic graph where each node represents a building block and each edge serves as a chemical linkage between two building blocks. In this context, Graph databases are possible software solutions for storing glycan structures and Graph query languages, such as SPARQL and Cypher, can be used to perform a substructure search. Glycan substructure searching is an important feature for querying structure and experimental glycan databases and retrieving biologically meaningful data. This applies for example to identifying a region of the glycan recognised by a glycan binding protein (GBP). In this study, 19,404 glycan structures were selected from GlycomeDB (www.glycome-db.org) and modelled for being stored into a RDF triple store and a Property Graph. We then performed two different sets of searches and compared the query response times and the results from both technologies to assess performance and accuracy. The two implementations produced the same results, but interestingly we noted a difference in the query response times. Qualitative measures such as portability were also used to define further criteria for choosing the technology adapted to solving glycan substructure search and other comparable issues.},
    author = {Alocci, Davide and Mariethoz, Julien and Horlacher, Oliver and Bolleman, Jerven T. and Campbell, Matthew P. and Lisacek, Frederique},
    doi = {10.1371/journal.pone.0144578},
    file = {:Users/cthoyt/ownCloud/Mendeley/2015/Property Graph vs RDF triple store A comparison on glycan substructure search - 2015 - Alocci et al.PDF:PDF},
    issn = {19326203},
    journal = {PLoS ONE},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {12},
    pages = {1--17},
    title = {{ Property Graph vs RDF triple store: A comparison on glycan substructure search }},
    volume = {10},
    year = {2015}
}
@article{Irin2015,
    abstract = {Neurodegenerative as well as autoimmune diseases have unclear aetiologies, but an increasing number of evidences report for a combination of genetic and epigenetic alterations that predispose for the development of disease. This review examines the major milestones in epigenetics research in the context of diseases and various computational approaches developed in the last decades to unravel new epigenetic modifications. However, there are limited studies that systematically link genetic and epigenetic alterations of DNA to the aetiology of diseases. In this work, we demonstrate how disease-related epigenetic knowledge can be systematically captured and integrated with heterogeneous information into a functional context using Biological Expression Language (BEL). This novel methodology, based on BEL, enables us to integrate epigenetic modifications such as DNA methylation or acetylation of histones into a specific disease network. As an example, we depict the integration of epigenetic and genetic factors in a functional context specific to Parkinson's disease (PD) and Multiple Sclerosis (MS).},
    author = {{ Khanam Irin } , Afroza and { Tom Kodamullil } , Alpha and G { \" { u } } ndel, Michaela and Hofmann-Apitius, Martin},
    doi = {10.1155/2015/737168},
    file = {:Users/cthoyt/ownCloud/Mendeley/2015/Computational Modelling Approaches on Epigenetic Factors in Neurodegenerative and Autoimmune Diseases and Their Mechanistic Analysis - 2.pdf:pdf},
    issn = {2314-8861},
    journal = {Journal of Immunology Research},
    mendeley-groups = {Bio2BEL Manuscript References},
    pages = {1--10},
    pmid = {26636108},
    title = {{ Computational Modelling Approaches on Epigenetic Factors in Neurodegenerative and Autoimmune Diseases and Their Mechanistic Analysis }},
    url = {http://www.ncbi.nlm.nih.gov/pubmed/26636108 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC4655260 http://www.hindawi.com/journals/jir/2015/737168/},
    volume = {2015},
    year = {2015}
}
@article{Menche2015,
    abstract = {According to the disease module hypothesis, the cellular components associated with a disease segregate in the same neighborhood of the human interactome, the map of biologically relevant molecular interactions. Yet, given the incompleteness of the interactome and the limited knowledge of disease-associated genes, it is not obvious if the available data have sufficient coverage to map out modules associated with each disease. Here we derive mathematical conditions for the identifiability of disease modules and show that the network-based location of each disease module determines its pathobiological relationship to other diseases. For example, diseases with overlapping network modules show significant coexpression patterns, symptom similarity, and comorbidity, whereas diseases residing in separated network neighborhoods are phenotypically distinct. These tools represent an interactome-based platform to predict molecular commonalities between phenotypically related diseases, even if they do not share primary disease genes.},
    archivePrefix = {arXiv},
    arxivId = {15334406},
    author = {Menche, J { \" { o } } rg and Sharma, Amitabh and Kitsak, Maksim and Ghiassian, Susan Dina and Vidal, Marc and Loscalzo, Joseph and Barab { \' { a } } si, Albert-L { \' { a } } szl { \' { o } }},
    doi = {10.1126/science.1257601},
    eprint = {15334406},
    file = {:Users/cthoyt/ownCloud/Mendeley/2015/Disease networks. Uncovering disease-disease relationships through the incomplete interactome. - 2015 - Menche et al(2).pdf:pdf;:Users/cthoyt/ownCloud/Mendeley/2015/Disease networks. Uncovering disease-disease relationships through the incomplete interactome. - 2015 - Menche et al.pdf:pdf},
    isbn = {1223326500},
    issn = {1095-9203},
    journal = {Science (New York, N.Y.)},
    mendeley-groups = {Bio2BEL Manuscript References},
    month = {feb},
    number = {6224},
    pages = {1257601},
    pmid = {25700523},
    title = {{ Disease networks. Uncovering disease-disease relationships through the incomplete interactome. }},
    url = {http://www.ncbi.nlm.nih.gov/pubmed/25700523 http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC4435741},
    volume = {347},
    year = {2015}
}
@article{Sales2019,
    abstract = {Metabolomics is an emerging 'omics' science involving the characterization of metabolites and metabolism in biological systems. Few bioinformatic tools have been developed for the visualization, exploration and analysis of metabolomic data within the context of metabolic pathways: some of them became rapidly obsolete and are no longer supported, others are based on a single database. A systematic collection of existing annotations has the potential of considerably boosting the investigation and contextualization of metabolomic measurements.},
    author = {Sales, Gabriele and Calura, Enrica and Romualdi, Chiara},
    doi = {10.1093/bioinformatics/bty719},
    file = {:Users/cthoyt/ownCloud/Mendeley/2018/meta Graphite - a new layer of pathway annotation to get metabolite networks - 2018 - Sales, Calura, Romualdi.pdf:pdf},
    issn = {14602059},
    journal = {Bioinformatics},
    mendeley-groups = {Bio2BEL Manuscript References},
    number = {7},
    pages = {1258--1260},
    title = {{ Meta Graphite-a new layer of pathway annotation to get metabolite networks }},
    volume = {35},
    year = {2019}
}

@article{Williams2012,
abstract = {Open PHACTS is a public-private partnership between academia, publishers, small and medium sized enterprises and pharmaceutical companies. The goal of the project is to deliver and sustain an 'open pharmacological space' using and enhancing state-of-the-art semantic web standards and technologies. It is focused on practical and robust applications to solve specific questions in drug discovery research. OPS is intended to facilitate improvements in drug discovery in academia and industry and to support open innovation and in-house non-public drug discovery research. This paper lays out the challenges and how the Open PHACTS project is hoping to address these challenges technically and socially. {\textcopyright} 2012 Elsevier Ltd.},
author = {Williams, Antony J. and Harland, Lee and Groth, Paul and Pettifer, Stephen and Chichester, Christine and Willighagen, Egon L. and Evelo, Chris T. and Blomberg, Niklas and Ecker, Gerhard and Goble, Carole and Mons, Barend},
doi = {10.1016/j.drudis.2012.05.016},
file = {:Users/cthoyt/ownCloud/Mendeley/2012/Open PHACTS semantic interoperability for drug discovery - 2012 - Williams et al.pdf:pdf},
isbn = {1878-5832 (Electronic)$\backslash$r1359-6446 (Linking)},
issn = {13596446},
journal = {Drug Discovery Today},
month = {nov},
number = {21-22},
pages = {1188--1198},
pmid = {22683805},
publisher = {Elsevier Ltd},
title = {{Open PHACTS: semantic interoperability for drug discovery}},
url = {http://dx.doi.org/10.1016/j.drudis.2012.05.016 http://linkinghub.elsevier.com/retrieve/pii/S1359644612001936},
volume = {17},
year = {2012}
}