Supercomputer-Based Ensemble Docking Drug Discovery Pipeline with Application to Covid-19

Acharya, Atanu; Agarwal, Rupesh; Baker, Matthew; Baudry, Jérôme; Bhowmik, Debsindhu; Boehm, Swen; Byler, Kendall G.; Coates, Leighton; Chen, Sam Yen-Chi; Cooper, Connor J.; Demerdash, Omar; Daidone, Isabella; Eblen, John D.; Ellingson, Sally R.; Forli, Stefano; Gläser, Jens; Gumbart, James C.; Gunnels, John A.; Hernández, Óscar; Irle, Stephan; Larkin, Jeffery; Lawrence, Travis J; LeGrand, Scott; Liu, Shih-Hsien; Mitchell, Julie C.; Park, Gilchan; Parks, Jerry M.; Pavlova, Ànna; Petridis, Loukas; Poole, Duncan; Pouchard, Line; Ramanathan, Arvind; Rogers, David; Santos-Martins, Diogo; Scheinberg, Aaron; Sedova, Ada; Shen, Shawn; Smith, Jeremy C.; Soto, Carlos; Tsaris, Aristides; Thavappiragasam, Mathialakan; Tillack, Andreas F.; Vermaas, Josh V.; Vuong, Van; Yin, Junqi; Yoo, Shinjae; Zahran, Mai; Zanetti-Polzi, Laura

doi:10.26434/chemrxiv.12725465.v1

Cited by 26 publications

(46 citation statements)

References 126 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Probabilities of assignment to each conformational state can be used as reaction coordinates. We are presently applying the method to classify chemical compound space using binary MACCS fingerprints [21], and to characterize conformational space of SARS-CoV-2 proteins simulated using replica exchange molecular dynamics [22]. Now that the principle has been demonstrated, more informative classification schemes can be devised.…”

Section: Discussionmentioning

confidence: 99%

Protein Conformational States—A First Principles Bayesian Method

Rogers¹

2020

Entropy

Self Cite

View full text Add to dashboard Cite

Automated identification of protein conformational states from simulation of an ensemble of structures is a hard problem because it requires teaching a computer to recognize shapes. We adapt the naïve Bayes classifier from the machine learning community for use on atom-to-atom pairwise contacts. The result is an unsupervised learning algorithm that samples a `distribution’ over potential classification schemes. We apply the classifier to a series of test structures and one real protein, showing that it identifies the conformational transition with > 95% accuracy in most cases. A nontrivial feature of our adaptation is a new connection to information entropy that allows us to vary the level of structural detail without spoiling the categorization. This is confirmed by comparing results as the number of atoms and time-samples are varied over 1.5 orders of magnitude. Further, the method’s derivation from Bayesian analysis on the set of inter-atomic contacts makes it easy to understand and extend to more complex cases.

show abstract

Section: Discussionmentioning

confidence: 99%

Protein Conformational States—A First Principles Bayesian Method

Rogers¹

2020

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, OpenEye GigaDocking 44 was used to dock the Enamine REAL database into the purine nucleoside phosphorylase and heat shock protein 90 targets in <1 d using 27,000 and 45,000 Amazon Web Services (AWS) cloud CPUs, respectively. The popular Autodock program has been parallelized for Compute Unified Device Architecture (CUDA) 45 and deployed on the Summit supercomputer (comprising >27,000 GPUs) to dock the same library into the SARS-CoV-2 Mpro active site in ~1 d 5 .…”

Section: Comparison With Alternative Methodsmentioning

confidence: 99%

“…On the other hand, the emergence of ultra-large libraries has highlighted significant limitations of conventional docking approaches that typically operate on the scale of millions of molecules. With chemical libraries comprising 100 billion molecules on the horizon 4 , it will soon become impossible to deploy conventional docking at its full potential, and so far, only a handful of billion-sized docking campaigns have been conducted on elite supercomputing facilities 2,5 .…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence–enabled virtual screening of ultra-large chemical libraries with deep docking

et al. 2022

View full text Add to dashboard Cite

With the recent explosion of chemical libraries beyond a billion molecules, more efficient virtual screening approaches are needed. The Deep Docking (DD) platform enables up to 100-fold acceleration of structure-based virtual screening by docking only a subset of a chemical library, iteratively synchronized with a ligand-based prediction of the remaining docking scores. This method results in hundreds-to thousands-fold virtual hit enrichment (without significant loss of potential drug candidates) and hence enables the screening of billion molecule-sized chemical libraries without using extraordinary computational resources. Herein, we present and discuss the generalized DD protocol that has been proven successful in various computer-aided drug discovery (CADD) campaigns and can be applied in conjunction with any conventional docking program. The protocol encompasses eight consecutive stages: molecular library preparation, receptor preparation, random sampling of a library, ligand preparation, molecular docking, model training, model inference and the residual docking. The standard DD workflow enables iterative application of stages 3-7 with continuous augmentation of the training set, and the number of such iterations can be adjusted by the user. A predefined recall value allows for control of the percentage of top-scoring molecules that are retained by DD and can be adjusted to control the library size reduction. The procedure takes 1-2 weeks (depending on the available resources) and can be completely automated on computing clusters managed by job schedulers. This open-source protocol, at https://github.com/jamesgleave/DD_protocol, can be readily deployed by CADD researchers and can significantly accelerate the effective exploration of ultra-large portions of a chemical space.

show abstract

“…In one of the largest docking studies reported to date, 138 million and 99 million compounds from the Enamine REAL library were docked against the D 4 receptor and AmpC, respectively [55]; this was enabled by a fast computational pipeline requiring only one second per library compound. More recent studies have since screened over one billion enumerated molecules from the same database [65,66]. As several make-on-demand libraries exceed this scale by multiple orders of magnitude, we argue that such exhaustive screening techniques are not a viable long-term approach even for inexpensive evaluations like docking.…”

Section: Exploring Finite Chemical Spacesmentioning

confidence: 98%

Defining and Exploring Chemical Spaces

Coley

2021

Trends in Chemistry

View full text Add to dashboard Cite

Designing functional molecules with desirable properties is often a challenging, multi-objective optimization. For decades, there have been computational approaches to facilitate this process through the simulation of physical processes, the prediction of molecular properties using structure-property relationships, and the selection or generation of molecular structures. This piece provides an overview of some algorithmic approaches to defining and exploring chemical spaces that have the potential to operationalize the process of molecular discovery. We emphasize the potential roles of machine learning and consideration of synthetic feasibility, which is a prerequisite to "closing the loop". We conclude by summarizing important directions for the future development and evaluation of these methods.

show abstract

Supercomputer-Based Ensemble Docking Drug Discovery Pipeline with Application to Covid-19

Cited by 26 publications

References 126 publications

Protein Conformational States—A First Principles Bayesian Method

Protein Conformational States—A First Principles Bayesian Method

Artificial intelligence–enabled virtual screening of ultra-large chemical libraries with deep docking

Defining and Exploring Chemical Spaces

Contact Info

Product

Resources

About