@article{Chiba2015, author = {Chiba, H. and Nishide, H. and Uchiyama, I.}, title = {{Construction of an ortholog database using the semantic web technology for integrative analysis of genomic data}}, journal = {PLOS ONE}, year = {2015}, volume = {10}, number = {4}, pages = {e0122802}, doi = {10.1371/journal.pone.0122802}, url = {https://www.ncbi.nlm.nih.gov/pubmed/25875762}, abstract = {Recently, various types of biological data, including genomic sequences, have been rapidly accumulating. To discover biological knowledge from such growing heterogeneous data, a flexible framework for data integration is necessary. Ortholog information is a central resource for interlinking corresponding genes among different organisms, and the Semantic Web provides a key technology for the flexible integration of heterogeneous data. We have constructed an ortholog database using the Semantic Web technology, aiming at the integration of numerous genomic data and various types of biological information. To formalize the structure of the ortholog information in the Semantic Web, we have constructed the Ortholog Ontology (OrthO). While the OrthO is a compact ontology for general use, it is designed to be extended to the description of database-specific concepts. On the basis of OrthO, we described the ortholog information from our Microbial Genome Database for Comparative Analysis (MBGD) in the form of Resource Description Framework (RDF) and made it available through the SPARQL endpoint, which accepts arbitrary queries specified by users. In this framework based on the OrthO, the biological data of different organisms can be integrated using the ortholog information as a hub. Besides, the ortholog information from different data sources can be compared with each other using the OrthO as a shared ontology. Here we show some examples demonstrating that the ortholog information described in RDF can be used to link various biological data such as taxonomy information and Gene Ontology. Thus, the ortholog database using the Semantic Web technology can contribute to biological knowledge discovery through integrative data analysis.}, } @article{Queralt2016, author={Queralt-Rosinach, N. and Pinero, J. and Bravo, {\`A}lex and Sanz, F. and Furlong, L. I.}, title={{DisGeNET-RDF: harnessing the innovative power of the Semantic Web to explore the genetic basis of diseases}}, journal={Bioinformatics}, year={2016}, volume={32}, number={14}, pages={2236--2238}, doi={10.1093/bioinformatics/btw214}, } @PhdThesis{ByrdPhD, author = {William E. Byrd}, advisor = {Friedman, Daniel P.}, title = {Relational Programming in miniKanren: Techniques, Applications, and Implementations}, school = {Indiana University}, year = {2009}, OPTkey = {}, OPTtype = {}, address = {Bloomington, IN, USA}, OPTmonth = {}, OPTnote = {}, OPTannote = {} } @book{ReasonedSchemer, title={The Reasoned Schemer}, author={Friedman, D. P. and Byrd, W. E. and Kiselyov, O.}, isbn={9780262562140}, lccn={2005051092}, series={The MIT Press}, url={https://books.google.com/books?id=\_xciAQAAIAAJ}, year={2005}, publisher={MIT Press} } @book{reasoned2nd, Address = {Cambridge, MA, USA}, Author = {Daniel P. Friedman and William E. Byrd and Oleg Kiselyov and Jason Hemann}, Isbn = {9780262535519}, Publisher = {MIT Press}, Edition = {second edition}, Title = {{T}he {R}easoned {S}chemer}, Year = 2018} @article{WielemakerBHO15, author = {Jan Wielemaker and Wouter Beek and Michiel Hildebrand and Jacco van Ossenbruggen}, title = {ClioPatria: {A} {SWI-P}rolog infrastructure for the {S}emantic {W}eb}, journal = {Semantic Web}, volume = {7}, number = {5}, pages = {529--541}, year = {2016}, url = {http://dx.doi.org/10.3233/SW-150191}, doi = {10.3233/SW-150191}, timestamp = {Mon, 12 Dec 2016 16:21:50 +0100}, biburl = {http://dblp2.uni-trier.de/rec/bib/journals/semweb/WielemakerBHO15}, bibsource = {dblp computer science bibliography, http://dblp.org} } @article{Bolleman2016, author = {Bolleman, J. T. and Mungall, C. J. and Strozzi, F. and Baran, J. and Dumontier, M. and Bonnal, R. J. and Buels, R. and Hoehndorf, R. and Fujisawa, T. and Katayama, T. and Cock, P. J.}, title = {{FALDO: a semantic standard for describing the location of nucleotide and protein feature annotation}}, journal = {J Biomed Semantics}, year = {2016}, volume = {7}, pages = {39}, doi = {10.1186/s13326-016-0067-z}, url = {http://www.ncbi.nlm.nih.gov/pubmed/27296299}, abstract = {BACKGROUND: Nucleotide and protein sequence feature annotations are essential to understand biology on the genomic, transcriptomic, and proteomic level. Using Semantic Web technologies to query biological annotations, there was no standard that described this potentially complex location information as subject-predicate-object triples. DESCRIPTION: We have developed an ontology, the Feature Annotation Location Description Ontology (FALDO), to describe the positions of annotated features on linear and circular sequences. FALDO can be used to describe nucleotide features in sequence records, protein annotations, and glycan binding sites, among other features in coordinate systems of the aforementioned "omics" areas. Using the same data format to represent sequence positions that are independent of file formats allows us to integrate sequence data from multiple sources and data types. The genome browser JBrowse is used to demonstrate accessing multiple SPARQL endpoints to display genomic feature annotations, as well as protein annotations from UniProt mapped to genomic locations. CONCLUSIONS: Our ontology allows users to uniformly describe - and potentially merge - sequence annotations from multiple sources. Data sources using FALDO can prospectively be retrieved using federalised SPARQL queries against public SPARQL endpoints and/or local private triple stores.}, }