Organic Chemistry: Current Research
Open Access

Implicit-descriptor ligand-based virtual screening by means of collaborative filtering

4^th European Organic Chemistry Congress

March 01-03, 2018 | London, UK

Raghuram Srinivas

Southern Methodist University, USA

Posters & Accepted Abstracts: Organic Chem Curr Res

Abstract :

Current ligand-based machine learning methods in virtual screening rely heavily on molecular fingerprinting preprocessing, i.e. explicit description of ligands structural and physicochemical properties in a vectorized form. Of particular importance to these current methods are the extent to which molecular fingerprints describe a particular ligand and what metric sufficiently captures similarity among ligands. In this work, we propose and evaluate methods that do not require explicit feature vectorization through fingerprinting, but, instead, provide implicit descriptors based only on other known assays. Our methods are based upon collaborative filtering algorithms. Our implicit descriptor method does not require the fingerprint similarity search, which makes the method free of the bias arising from the empirical nature of the fingerprint models and similarity search assumptions. The main strengths of this method are its resilience to target-ligand sparsity and high potential for spotting promiscuous ligands.

Biography :

Raghuram Srinivas is a Research Assistant with the Master of Science in Data Science program at Southern Methodist University, Dallas, Texas. He has extensive experience in Cognitive Computing and Artificial Intelligence Space with his work at the Watson Group at International Business Machines and contributed seven patents in the field.
Email:rsrinivas@smu.edu