Today's drug designer has access to vast quantities of data and an impressive array of sophisticated computational methods. At the same time, there is increasing pressure on the pharmaceutical industry to improve its productivity and reduce candidate drug attrition. We set out to develop a highly integrated suite of design and data analysis tools underpinned by the best predictive chemistry methods and models, with the aim of enabling multi-disciplinary compound design teams to make better informed design decisions. In this article we address the challenges of developing a powerful, flexible and user-friendly toolkit, and of maximising its exploitation by the design community. We describe the impact the toolkit has had on drug discovery projects and give our perspective on the future direction of this activity.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.drudis.2012.03.003 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Learning the language of antibody hypervariability.
Proc Natl Acad Sci U S A
January 2025
Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139.
Protein language models (PLMs) have demonstrated impressive success in modeling proteins. However, general-purpose "foundational" PLMs have limited performance in modeling antibodies due to the latter's hypervariable regions, which do not conform to the evolutionary conservation principles that such models rely on. In this study, we propose a transfer learning framework called Antibody Mutagenesis-Augmented Processing (AbMAP), which fine-tunes foundational models for antibody-sequence inputs by supervising on antibody structure and binding specificity examples.
View Article and Find Full Text PDFUnlocking the catalytic precision of ligand-controlled enzymatic halogenation.
Proc Natl Acad Sci U S A
January 2025
School of Biomolecular Science and Engineering, Vidyasirimedhi Institute of Science and Technology (VISTEC), Rayong 10120, Thailand.
A single-component flavin-dependent halogenase, AetF, has emerged as an attractive biocatalyst for catalyzing halogenation. However, its flavin chemistry remains unexplored and cannot be predicted due to its uniqueness in sequence and structure compared to other flavin-dependent monooxygenases. Here, we investigated the flavin reactions of AetF using transient kinetics.
View Article and Find Full Text PDFPrediction of Thermodynamic Properties of C-Based Fullerenols Using Machine Learning.
J Chem Theory Comput
January 2025
Guizhou Provincial Engineering Technology Research Center for Chemical Drug R&D, School of Pharmacy, Guizhou Medical University, Guiyang, Guizhou 550025, P. R. China.
Traditional machine learning methods face significant challenges in predicting the properties of highly symmetric molecules. In this study, we developed a machine learning model based on graph neural networks (GNNs) to accurately and swiftly predict the thermodynamic and photochemical properties of fullerenols, such as C(OH) ( = 1 to 30). First, we established a global method for generating fullerenol isomers through isomer fingerprinting, which can generate all possible isomers or produce diverse structural types on demand.
View Article and Find Full Text PDFThe efficacy of Lacticaseibacillus paracasei MSMC39-1 and Bifidobacterium animalis TA-1 probiotics in modulating gut microbiota and reducing the risk of the characteristics of metabolic syndrome: A randomized, double-blinded, placebo-controlled study.
PLoS One
January 2025
Center of Excellence in Probiotics, Srinakharinwirot University, Bangkok, Thailand.
Modern treatment, a healthy diet, and physical activity routines lower the risk factors for metabolic syndrome; however, this condition is associated with all-cause and cardiovascular mortality worldwide. This investigation involved a randomized controlled trial, double-blind, parallel study. Fifty-eight participants with risk factors of metabolic syndrome according to the inclusion criteria were randomized into two groups and given probiotics (Lacticaseibacillus paracasei MSMC39-1 and Bifidobacterium animalis TA-1) (n = 31) or a placebo (n = 27).
View Article and Find Full Text PDFGeochemical exploration of rare earth element resources in highland karstic bauxite deposits in the Sierra de Bahoruco, Pedernales Province, Southwestern Dominican Republic.
PLoS One
January 2025
Dirección General de Minería, República Dominicana.
This study investigates the geochemical characteristics of rare earth elements (REEs) in highland karstic bauxite deposits located in the Sierra de Bahoruco, Pedernales Province, Dominican Republic. These deposits, formed through intense weathering of volcanic material, represent a potentially valuable REE resource for the nation. Surface and subsurface soil samples were analyzed using portable X-ray fluorescence (pXRF) and a NixPro 2 color sensor validated with inductively coupled plasma optical emission spectrometry (ICP-OES).
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!