Supplementary Information CROssBAR: Comprehensive Resource of Biomedical Relations with Deep Learning Applications and Knowledge Graph Representations Tunca Doğan1,2,3,4*, Heval Atas3, Vishal Joshi4, Ahmet Atakan5, Ahmet Sureyya Rifaioglu5,6, Esra Nalbat3, Andrew Nightingale4, Rabie Saidi4, Vladimir Volynkin4, Hermann Zellner4, Rengul Cetin-Atalay3,7, Maria Martin4, Volkan Atalay5. 1Department of Computer Engineering, Hacettepe University, 06800 Ankara, Turkey 2Institute of Informatics, Hacettepe University, 06800 Ankara, Turkey 3Cancer Systems Biology Laboratory, Graduate School of Informatics, METU, 06800 Ankara, Turkey 4European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL–EBI), Hinxton, Cambridgeshire, CB10 1SD, UK 5Department of Computer Engineering, METU, 06800 Ankara, Turkey 6Department of Computer Engineering, İskenderun Technical University, 31200 Hatay, Turkey 7Section of Pulmonary and Critical Care Medicine, the University of Chicago, Chicago IL 60637, USA *To whom correspondence should be addressed, e-mail:
[email protected] 1. Background Work There are numerous studies, tools and resources that integrate biological data (either from other data sources or by direct curation) and communicate it via textual or visual representations. One of the most commonly used resources in this sense are biological pathway databases such as Reactome1, KEGG2 and WikiPathways3, where the interactions/reactions are communicated via network representations. STRING and STITCH databases are two well-known molecular interaction services, in which protein-protein and protein-chemical interactions are integrated from various resources, including both experimentally proven and electronically predicted data points, and presented to users as pre-computed networks4, 5. GeneMANIA is an online platform for exploring the relationships between genes over network representations generated by utilizing large-scale genomics and proteomics data, for gene prioritization and function prediction6.