Deep Docking - a Deep Learning Approach for Virtual Screening of Big Chemical Datasets

Abstract

Drug discovery is an extensive and rigorous process that requires up to 2 billion dollars of investments and more than ten years of research and development to bring a molecule "from bench to a bedside". While virtual screening can significantly enhance drug discovery workflow, it ultimately lags the current rate of expansion of chemical databases that already incorporate billions of purchasable compounds. This surge of available small molecules presents great opportunities for drug discovery but also demands for faster virtual screening methods and protocols. In order to address this challenge, we herein introduce Deep Docking (D 2 ) -a novel deep learning-based approach which is suited for docking billions of molecular structures. The developed D 2 -platform utilizes quantitative structure-activity relationship (QSAR) based deep models trained on docking scores of subsets of a large chemical library (Big Base) to approximate the docking outcome for yet unprocessed molecular entries and to remove unfavorable structures in an iterative manner. We applied D 2 to virtually screen 1.36 billion molecules form the ZINC15 library against 12 prominent target proteins, and demonstrated up to 100-fold chemical data reduction and 6,000-fold enrichment for top hits, without notable loss of well-docked entities. The developed D 2 protocol can readily be used in conjunction with any docking program and was made publicly available.Drug discovery is an expensive and time-demanding process that faces many challenges, including low hit rates of high-throughput screening approaches among many others 1-2 . Methods of computer-aided drug discovery (CADD) can significantly speed up the pace of screening and help improving hit discovery rates 3 . Molecular docking is routinely used to process virtual libraries containing millions of molecular structures against a variety of drug targets with known three-

A Deep-Learning Approach toward Rational Molecular Docking Protocol Selection

“…Finally, while we firmly believe that future-generation docking protocols will more tightly incorporate machine-learning elements into their pipelines [18,19] (e.g., by the design of more efficient search algorithms or scoring functions [55,56]), we think that the approach proposed in this paper represents a novel research direction that will drive structure-based drug design researchers towards more rational existing docking protocol choices. Hence, with the intent of improving research reproducibility and lowering accessibility barriers, we have open-sourced all evaluation and deployment code as well as trained models related to this work.…”

“…In the context of molecular docking, DL approaches have been investigated to replace classical scoring functions, showing moderate success [18,19], but still far behind the accuracy provided by standard docking procedures. Partially due to this fact, in this study, we explored the potential of DL approaches to both select the best possible docking protocol given a protein-ligand pair and to provide insight into which protein-ligand pairs will result in a better pose given a docking protocol.…”

Computer-Aided Ligand Discovery for Estrogen Receptor Alpha

“…In the same year, Fernandez et al developed a deep learning model on Tox21 dataset to predict compound toxicity for both AR and ER, based merely on molecular images [347]. In 2019, Francesco et al created DeepDocking, a QSAR-based method allowing to predict docking scores for 1.36 billion ZINC15 molecules against ER-AF2 target site [348].…”

“…Finding a potent protein-protein interface enhancer is challenging. Using a large chemical library with the help of DeepDocking would increase the chances of finding novel and diverse "molecular glue" molecules against this large binding site [348]. This strategy may very well help in alternative inhibition of ER activity through AF1 inhibition.…”

Rapid Identification of Potential Inhibitors of SARS-CoV-2 Main Protease by Deep Docking of 1.3 Billion Compounds

“…This Deep Docking (DD) platform utilizes quantitative structure-activity relationship (QSAR) models trained on docking scores of database subsets to approximate in an iterative manner the docking outcome of the remaining entries. More details can be found in our recent preprint 29 .…”