A5101892657- Computational Drug Discovery Methods
- Machine Learning in Materials Science
- Microbial Natural Products and Biosynthesis
- Analytical Chemistry and Chromatography
- Protein Structure and Dynamics
- Chemical Synthesis and Analysis
- Metabolomics and Mass Spectrometry Studies
- Genetics, Bioinformatics, and Biomedical Research
- Bioinformatics and Genomic Networks
- Microbial Metabolic Engineering and Bioproduction
- Viral Infectious Diseases and Gene Expression in Insects
- Process Optimization and Integration
- Chemistry and Chemical Engineering
- Monoclonal and Polyclonal Antibodies Research
- vaccines and immunoinformatics approaches
- Natural Language Processing Techniques
- Organic Chemistry Cycloaddition Reactions
- Pharmacogenetics and Drug Metabolism
- Protein Degradation and Inhibitors
- Plant biochemistry and biosynthesis
- X-ray Diffraction in Crystallography
- Fluorine in Organic Chemistry
- Various Chemistry Research Topics
- Topic Modeling
- Synthesis and biological activity
BenevolentAI (United Kingdom)
2018-2024
Sandia National Laboratories
2023
Penn Center for AIDS Research
2023
University of Pennsylvania Health System
2023
Clemson University
2023
Institute of Cancer Research
2009-2018
Cancer Research UK
2010-2018
University of Hull
2002-2016
Naval Postgraduate School
2013-2014
United States Army Combat Capabilities Development Command
2011
De novo design seeks to generate molecules with required property profiles by virtual design-make-test cycles. With the emergence of deep learning and neural generative models in many application areas, for molecular based on networks appeared recently show promising results. However, new have not been profiled consistent tasks, comparative studies well-established algorithms only seldom performed. To standardize assessment both classical de design, we propose an evaluation framework,...
Bromodomains are readers of the epigenetic code that specifically bind acetyl-lysine containing recognition sites on proteins. Recently BET family bromodomains has been demonstrated to be druggable through discovery potent inhibitors, sparking an interest in protein–protein interaction inhibitors directly target gene transcription. Here, we assess druggability diverse members bromodomain using SiteMap and show there significant differences predicted druggability. Furthermore, trace these...
Bioisosteric replacement and scaffold hopping are twin methods used in drug design to improve the synthetic accessibility, potency like properties of a compound move into novel chemical space. involves swapping functional groups molecule with other that have similar biological properties. Scaffold is core framework another will or find potent compounds exist This review outlines key concepts, importance challenges both using examples comparisons techniques available for finding bioisosteric...
In this paper we propose a novel graph-based genetic algorithm for the evolution of molecular graphs from predefined set elements or fragments with an external objective function. A brief overview existing approaches in design is provided followed by description our approach. The continues to suggest application program multiobjective median molecules that are structurally representative molecules. We conclude summary initial results along discussion variety improvements and applications
The scaffold diversity of 7 representative commercial and proprietary compound libraries is explored for the first time using both Murcko frameworks Scaffold Trees. We show that Level 1 Tree useful characterization in offers advantages over use frameworks. This analysis also demonstrates majority compounds we analyzed contain only a small number well represented scaffolds high percentage singleton represent remaining compounds. Maps to clearly visualize space libraries, example, display...
While many of the new approaches have yet to bear fruit in terms drugs being progressed market, initial reports tend toward belief that they will become even more integral drug discovery process than has hitherto been seen.
Bromodomains (BRDs) are epigenetic readers that recognize acetylated-lysine (KAc) on proteins and implicated in a number of diseases. We describe virtual screening approach to identify BRD inhibitors. Key elements this the extensive design use substructure queries compile set commercially available compounds featuring novel putative KAc mimetics docking for final compound selection. validation by applying it first BRD4. The selection testing 143 lead discovery six hits, including four...
We describe a computational method, plane of best fit (PBF), to quantify and characterize the 3D character molecules. This method is rapid amenable analysis large diverse data sets. compare PBF with alternative literature methods used assess apply sets fragment-like, drug-like, natural product compound libraries. show that exemplar fragment libraries underexploit potential in fragment-like chemical space drug-like molecules examined are predominantly 2D character.
Aim: Many medicinal chemistry-relevant structures and core scaffolds tend toward geometric planarity, which hampers the optimization of physicochemical properties desirable in drug-like molecules. As challenging drug target classes emerge, exploitation molecular three-dimensionality lead is becoming increasingly important. While recent interest has emphasized importance enhanced fragment designs, extent to this required remains unclear. Materials & methods: Three computational methods,...
Over the past few years, many machine learning-based scoring functions for predicting binding of small molecules to proteins have been developed. Their objective is approximate distribution which takes two as input and outputs energy their interaction. Only a function that accounts interatomic interactions involved in can accurately predict affinity on unseen molecules. However, make predictions based data set biases rather than an understanding physics binding. These perform well when...
Genome-wide association studies (GWAS) have identified more than 30 prostate cancer (PrCa) susceptibility loci. One of these (rs2735839) is located close to a plausible candidate gene, KLK3, which encodes prostate-specific antigen (PSA). PSA widely used as biomarker for PrCa detection and disease monitoring. To refine the between variants in this region, we genotyping data from two-stage GWAS using samples UK Australia, Cancer Genetic Markers Susceptibility (CGEMS) study. Genotypes were...
Abstract The twin concepts of bioisosteric replacement and scaffold hopping are increasingly becoming important in modern drug design. isosterism stretch back over a century, but only recently have systematic data‐intensive methods been used to explore appropriate replacements. Here, summary the history bioisosterism is presented provide context applied. Molecular similarity data mining introduced as approaches introduce these replacements rationalise space synthetic targets consider...
Following the theoretical model by Hann et al. moderately complex structures are preferable lead compounds since they to specific binding events involving complete ligand molecule. To make this concept usable in practice for library design, we studied several complexity measures on biological activity of molecules. We applied historical IC50/EC50 summary data 160 assays run at Novartis covering a diverse range targets, among them kinases, proteases, GPCRs, and protein-protein interactions,...
We describe the development and application of an integrated, multiobjective optimization workflow (MOARF) for directed medicinal chemistry design. This couples a rule-based molecular fragmentation scheme (SynDiR) with pharmacophore fingerprint-based fragment replacement algorithm (RATS) to broaden scope reconnection options considered in generation potential solution structures. Solutions are ranked by scoring comprising ligand-based (shape similarity) biochemical activity predictions as...