Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2020.09.28.316224v1?rss=1 Authors: Ahmed, A., Mam, B., Sowdhamini, R. Abstract: Protein-ligand binding prediction has extensive biological significance. Binding affinity helps in understanding the degree of protein-ligand interactions and has wide protein applications. Protein-ligand docking using virtual screening and molecular dynamic simulations are required to predict the binding affinity of a ligand to its cognate receptor. In order to perform such analyses, it requires intense computational power and it becomes impossible to cover the entire chemical space of small molecules. It has been aided by a shift towards using Machine Learning-based methodologies that aids in binding prediction using regression. Recent developments using deep learning has enabled us to make sense of massive amounts of complex datasets. Herein, the ability of the model to learn intrinsic patterns in a complex plane of data is the strength of the approach. Here, we have incorporated Convolutional Neural Networks that find spatial relationships among data to help us predict affinity of binding of proteins in whole superfamilies towards a diverse set of ligands. The models were trained and validated using a detailed methodology for feature extraction. We have also tested DEELIG on protein complexes relevant to the current public health scenario. Our approach to network construction and training on protein-ligand dataset prepared in-house has provided significantly better results than previously existing methods in the field. Copy rights belong to original authors. Visit the link for more info