Biology subjects

Durrant, J. D.

Publications and source records attributed to Durrant, J. D..

6 recordsLinked to original sources

bioRxiv2023

CENsible: Interpretable Insights into Small-Molecule Binding with Context Explanation Networks

We present a novel and interpretable approach for predicting small-molecule binding affinities using context explanation networks (CENs). Given the specific structure of a protein/ligand complex, our CENsible scoring function uses a deep convolutional neural network to predict the contributions of pre-calculated terms to the overall binding affinity. We show that CENsible can effectively distinguish active vs. inactive compounds for many systems. Its primary benefit over related machine-learning scoring functions, however, is that it retains interpretability, allowing researchers to identify the contribution of each pre-calculated term to the final affinity prediction, with implications for subsequent lead optimization.

pharmacology and toxicology↗

bioRxiv2022

Prot2Prot: A Deep Learning Model for Rapid, Photorealistic Macromolecular Visualization

MotivationMolecular visualization is a cornerstone of structural biology, providing insights into the form and function of biomolecules that are difficult to achieve any other way. Scientific analysis, publication, education, and outreach often benefit from photorealistic molecular depictions rendered using advanced computer-graphics programs such as Maya, 3ds Max, and Blender. However, setting up molecular scenes in these programs can be laborious even for expert users, and rendering often requires substantial time and computer resources. ResultsWe have created a deep-learning model called Prot2Prot that quickly imitates photorealistic visualization styles, given a much simpler, easy-to-generate molecular representation. The resulting images are often indistinguishable from images rendered using industry-standard 3D graphics programs, but they can be created in a fraction of the time, even when running in a web browser. To the best of our knowledge, Prot2Prot is the first example of image-to-image translation applied to macromolecular visualization. AvailabilityProt2Prot is available free of charge, released under the terms of the Apache License, Version 2.0. Users can access a Prot2Prot-powered web app without registration at http://durrantlab.com/prot2prot.

molecular biology↗

bioRxiv2021

Defining the Yeast Resistome through in vitro Evolution and Whole Genome Sequencing

In vitro evolution and whole genome analysis were used to comprehensively identify the genetic determinants of chemical resistance in the model microbe, Saccharomyces cerevisiae. Analysis of 355 curated, laboratory-evolved clones, resistant to 80 different compounds, demonstrates differences in the types of mutations that are identified in selected versus neutral evolution and reveals numerous new, compound-target interactions. Through enrichment analysis we further identify a set of 137 genes strongly associated with or conferring drug resistance as indicated by CRISPR-Cas9 engineering. The set of 25 most frequently mutated genes was enriched for transcription factors and for almost 25 percent of the compounds, resistance was mediated by one of 100 independently derived, gain-of-function, single nucleotide variants found in 170-amino-acid domains in two Zn2C6 transcription factors, YRR1 and YRM1 (p < 1x 10 -100). This remarkable enrichment for transcription factors as drug resistance genes may explain why it is challenging to develop effective antifungal killing agents and highlights their important role in evolution.

genetics↗

bioRxiv2021

DeepFrag: A Deep Convolutional Neural Network for Fragment-based Lead Optimization

1Machine learning has been increasingly applied to the field of computer-aided drug discovery in recent years, leading to notable advances in binding-affinity prediction, virtual screening, and QSAR. Surprisingly, it is less often applied to lead optimization, the process of identifying chemical fragments that might be added to a known ligand to improve its binding affinity. We here describe a deep convolutional neural network that predicts appropriate fragments given the structure of a receptor/ligand complex. In an independent benchmark of known ligands with missing (deleted) fragments, our DeepFrag model selected the known (correct) fragment from a set over 6,500 about 58% of the time. Even when the known/correct fragment was not selected, the top fragment was often chemically similar and may well represent a valid substitution. We release our trained DeepFrag model and associated software under the terms of the Apache License, Version 2.0. A copy can be obtained free of charge from http://durrantlab.com/deepfragmodel.

pharmacology and toxicology↗

bioRxiv2020

MutantHuntWGS: A Pipeline for Identifying Saccharomyces cerevisiae Mutations

MutantHuntWGS is a user-friendly pipeline for analyzing Saccharomyces cerevisiae whole-genome sequencing data. It uses available open-source programs to: (1) perform sequence alignments for paired and single-end reads, (2) call variants, and (3) predict variant effect and severity. MutantHuntWGS outputs a shortlist of variants while also enabling access to all intermediate files. To demonstrate its utility, we use MutantHuntWGS to assess multiple published datasets; in all cases, it detects the same causal variants reported in the literature. To encourage broad adoption and promote reproducibility, we distribute a containerized version of the MutantHuntWGS pipeline that allows users to install and analyze data with only two commands. The MutantHuntWGS software and documentation can be downloaded free of charge from https://github.com/mae92/MutantHuntWGS.

genetics↗

bioRxiv2019

Webina: An Open-Source Library and Web App that Runs AutoDock Vina Entirely in the Web Browser

1Molecular docking is a computational technique for predicting how a small molecule might bind a macromolecular target. Among docking programs, AutoDock Vina is particularly popular. Like many docking programs, Vina requires users to download/install an executable file and to run that file from a Unix- or DOS-like command-line interface. Choosing proper configuration parameters and analyzing Vina output is also sometimes challenging. These issues are particularly problematic for students and novice researchers. We have created Webina, a new version of Vina, to address these challenges. Webina is a JavaScript/WebAssembly library that runs AutoDock Vina entirely in a web browser. To use Webina, users need only visit a Webina-enabled webpage. The docking calculations take place on the users own computer rather than a remote server. To encourage use, we have incorporated the Webina library into our own Webina web app. The app includes a convenient interface so users can easily setup their docking runs and analyze the results. Webina will be a useful open-source tool for the research and educational communities. A working version of the app can be accessed free of charge from http://durrantlab.com/webina.

pharmacology and toxicology↗