Computational drug discovery and repurposing for the treatment of COVID-19: A systematic review

K Mohamed, N Yazdanpanah, A Saghazadeh… - Bioorganic …, 2021 - Elsevier
Background Since the beginning of the novel coronavirus (SARS-CoV-2) disease outbreak,
there has been an increasing interest in finding a potential therapeutic agent for the disease …

Exploring chemical space using natural language processing methodologies for drug discovery

H Öztürk, A Özgür, P Schwaller, T Laino… - Drug Discovery Today, 2020 - Elsevier
Highlights•Biochemical data can be represented with text-based languages codified by
humans.•Natural language processing (NLP) can be applied to textual biochemical …

In need of bias control: evaluating chemical data for machine learning in structure-based virtual screening

J Sieg, F Flachsenberg, M Rarey - Journal of chemical information …, 2019 - ACS Publications
Reports of successful applications of machine learning (ML) methods in structure-based
virtual screening (SBVS) are increasing. ML methods such as convolutional neural networks …

Three-dimensional convolutional neural networks and a cross-docked data set for structure-based drug design

PG Francoeur, T Masuda, J Sunseri, A Jia… - Journal of chemical …, 2020 - ACS Publications
One of the main challenges in drug discovery is predicting protein–ligand binding affinity.
Recently, machine learning approaches have made substantial progress on this task …

Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis

X Jia, A Lynch, Y Huang, M Danielson, I Lang'at… - Nature, 2019 - nature.com
Most chemical experiments are planned by human scientists and therefore are subject to a
variety of human cognitive biases, heuristics and social influences. These anthropogenic …

Shaping the interaction landscape of bioactive molecules

D Gfeller, O Michielin, V Zoete - Bioinformatics, 2013 - academic.oup.com
Motivation: Most bioactive molecules perform their action by interacting with proteins or other
macromolecules. However, for a significant fraction of them, the primary target remains …

FRED pose prediction and virtual screening accuracy

M McGann - Journal of chemical information and modeling, 2011 - ACS Publications
Results of a previous docking study are reanalyzed and extended to include results from the
docking program FRED and a detailed statistical analysis of both structure reproduction and …

Most ligand-based classification benchmarks reward memorization rather than generalization

I Wallach, A Heifets - Journal of chemical information and …, 2018 - ACS Publications
Undetected overfitting can occur when there are significant redundancies between training
and validation data. We describe AVE, a new measure of training–validation redundancy for …

Surflex-Dock: Docking benchmarks and real-world application

R Spitzer, AN Jain - Journal of computer-aided molecular design, 2012 - Springer
Benchmarks for molecular docking have historically focused on re-docking the cognate
ligand of a well-determined protein–ligand complex to measure geometric pose prediction …

Molecular shape and medicinal chemistry: a perspective

A Nicholls, GB McGaughey, RP Sheridan… - Journal of medicinal …, 2010 - ACS Publications
In his philosophic musings “Meditations” the Emperor Marcus Aurelius asks “This thing, what
is it in itself, in its own constitution? What is its substance and material? And what its causal …