Rengul Cetin-Atalay1, Deniz Cansen Kahraman2, Esra Nalbat3, Ahmet Sureyya Rifaioglu4,5, Ahmet Atakan5,6, Ataberk Donmez5,7, Heval Atas3, M Volkan Atalay3,5, Aybar C Acar3, Tunca Doğan8,9. 1. Section of Pulmonary and Critical Care Medicine, University of Chicago, Chicago, IL, 60637, USA. rengul@uchicago.edu. 2. Cancer Systems Biology Laboratory, Graduate School of Informatics, METU, Ankara, 06800, Turkey. cansen@metu.edu.tr. 3. Cancer Systems Biology Laboratory, Graduate School of Informatics, METU, Ankara, 06800, Turkey. 4. Department of Computer Engineering, Iskenderun Technical University, Iskenderun, Hatay, 31200, Turkey. 5. Department of Computer Engineering, METU, Ankara, 06800, Turkey. 6. Department of Computer Engineering, EBYU, Ankara, 24002, Turkey. 7. Department of Computer Science, University of Maryland, College Park, MD, 20742, USA. 8. Cancer Systems Biology Laboratory, Graduate School of Informatics, METU, Ankara, 06800, Turkey. tuncadogan@hacettepe.edu.tr. 9. Department of Computer Engineering, Hacettepe University, Ankara, 06800, Turkey. tuncadogan@hacettepe.edu.tr.
Abstract
PURPOSE: Computational approaches have been used at different stages of drug development with the purpose of decreasing the time and cost of conventional experimental procedures. Lately, techniques mainly developed and applied in the field of artificial intelligence (AI), have been transferred to different application domains such as biomedicine. METHODS: In this study, we conducted an investigative analysis via data-driven evaluation of potential hepatocellular carcinoma (HCC) therapeutics in the context of AI-assisted drug discovery/repurposing. First, we discussed basic concepts, computational approaches, databases, modeling approaches, and featurization techniques in drug discovery/repurposing. In the analysis part, we automatically integrated HCC-related biological entities such as genes/proteins, pathways, phenotypes, drugs/compounds, and other diseases with similar implications, and represented these heterogeneous relationships via a knowledge graph using the CROssBAR system. RESULTS: Following the system-level evaluation and selection of critical genes/proteins and pathways to target, our deep learning-based drug/compound-target protein interaction predictors DEEPScreen and MDeePred have been employed for predicting new bioactive drugs and compounds for these critical targets. Finally, we embedded ligands of selected HCC-associated proteins which had a significant enrichment with the CROssBAR system into a 2-D space to identify and repurpose small molecule inhibitors as potential drug candidates based on their molecular similarities to known HCC drugs. CONCLUSIONS: We expect that these series of data-driven analyses can be used as a roadmap to propose early-stage potential inhibitors (from database-scale sets of compounds) to both HCC and other complex diseases, which may subsequently be analyzed with more targeted in silico and experimental approaches.
PURPOSE: Computational approaches have been used at different stages of drug development with the purpose of decreasing the time and cost of conventional experimental procedures. Lately, techniques mainly developed and applied in the field of artificial intelligence (AI), have been transferred to different application domains such as biomedicine. METHODS: In this study, we conducted an investigative analysis via data-driven evaluation of potential hepatocellular carcinoma (HCC) therapeutics in the context of AI-assisted drug discovery/repurposing. First, we discussed basic concepts, computational approaches, databases, modeling approaches, and featurization techniques in drug discovery/repurposing. In the analysis part, we automatically integrated HCC-related biological entities such as genes/proteins, pathways, phenotypes, drugs/compounds, and other diseases with similar implications, and represented these heterogeneous relationships via a knowledge graph using the CROssBAR system. RESULTS: Following the system-level evaluation and selection of critical genes/proteins and pathways to target, our deep learning-based drug/compound-target protein interaction predictors DEEPScreen and MDeePred have been employed for predicting new bioactive drugs and compounds for these critical targets. Finally, we embedded ligands of selected HCC-associated proteins which had a significant enrichment with the CROssBAR system into a 2-D space to identify and repurpose small molecule inhibitors as potential drug candidates based on their molecular similarities to known HCC drugs. CONCLUSIONS: We expect that these series of data-driven analyses can be used as a roadmap to propose early-stage potential inhibitors (from database-scale sets of compounds) to both HCC and other complex diseases, which may subsequently be analyzed with more targeted in silico and experimental approaches.
Authors: Sudeep Pushpakom; Francesco Iorio; Patrick A Eyers; K Jane Escott; Shirley Hopper; Andrew Wells; Andrew Doig; Tim Guilliams; Joanna Latimer; Christine McNamee; Alan Norris; Philippe Sanseau; David Cavalla; Munir Pirmohamed Journal: Nat Rev Drug Discov Date: 2018-10-12 Impact factor: 84.694
Authors: Stephen R Heller; Alan McNaught; Igor Pletnev; Stephen Stein; Dmitrii Tchekhovskoi Journal: J Cheminform Date: 2015-05-30 Impact factor: 5.514
Authors: Michael K Gilson; Tiqing Liu; Michael Baitaluk; George Nicola; Linda Hwang; Jenny Chong Journal: Nucleic Acids Res Date: 2015-10-19 Impact factor: 16.971