Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1038/s41592-024-02249-y | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Powerful generative AI models of protein-ligand structure have recently been proposed, but few of these methods support both flexible protein-ligand docking and affinity estimation. Of those that do, none can directly model multiple binding ligands concurrently or have been rigorously benchmarked on pharmacologically relevant drug targets, hindering their widespread adoption in drug discovery efforts. In this work, we propose FlowDock, the first deep geometric generative model based on conditional flow matching that learns to directly map unbound (apo) structures to their bound (holo) counterparts for an arbitrary number of binding ligands.
View Article and Find Full Text PDFAchievements and Approaches in the Search for Small-Molecule Dengue NS2B/NS3 Inhibitors.
Curr Med Chem
January 2025
Faculty of Pharmacy, University of Medicine and Pharmacy at Ho Chi Minh City, Ho Chi Minh City, Vietnam.
With the escalation of viral infections in recent decades, including the COVID- 19 pandemic, viral infectious diseases have increasingly become a global concern, attracting significant attention. Among many viral epidemics, the dengue virus, an RNA virus from the Flaviviridae family, has been reported by the WHO as one of the most prevalent mosquito-borne diseases, infecting roughly 400 million people yearly and spreading across all continents worldwide. In the last two decades, researchers from academia and industry have diligently studied many aspects of the virus, including its structure, life cycle, potential therapeutic agents, and vaccines.
View Article and Find Full Text PDFTransformer Decoder Learns from a Pretrained Protein Language Model to Generate Ligands with High Affinity.
J Chem Inf Model
January 2025
Institute of Intelligent Industrial Technologies and Systems for Advanced Manufacturing, Consiglio Nazionale delle Ricerche, Via G. Amendola, 122/d, Bari 70126, Italy.
The drug discovery process can be significantly accelerated by using deep learning methods to suggest molecules with druglike features and, more importantly, that are good candidates to bind specific proteins of interest. We present a novel deep learning generative model, Prot2Drug, that learns to generate ligands binding specific targets leveraging (i) the information carried by a pretrained protein language model and (ii) the ability of transformers to capitalize the knowledge gathered from thousands of protein-ligand interactions. The embedding unveils the receipt to follow for designing molecules binding a given protein, and Prot2Drug translates such instructions by using the syntax of the molecular language generating novel compounds which are predicted to have favorable physicochemical properties and high affinity toward specific targets.
View Article and Find Full Text PDFRationalizing protein-ligand interactions via the effective fragment potential method and structural data from classical molecular dynamics.
J Chem Phys
January 2025
Department of Chemistry, Purdue University, West Lafayette, Indiana 47907, USA.
The Effective Fragment Potential (EFP) method, a polarizable quantum mechanics-based force field for describing non-covalent interactions, is utilized to calculate protein-ligand interactions in seven inactive cyclin-dependent kinase 2-ligand complexes, employing structural data from molecular dynamics simulations to assess dynamic and solvent effects. Our results reveal high correlations between experimental binding affinities and EFP interaction energies across all the structural data considered. Using representative structures found by clustering analysis and excluding water molecules yields the highest correlation (R2 of 0.
View Article and Find Full Text PDFElucidating the therapeutic potential of indazole derivative bindarit against K-ras receptor: An analysis using molecular dynamics exploration.
Biochem Biophys Rep
March 2025
School of Biosciences and Technology, Vellore Institute of Technology, Vellore, India.
Ras gene is frequently mutated in cancer. Among different subtypes of Ras gene, K-Ras mutation occurs in nearly 30 % of human cancers. K-Ras mutation, specifically K-Ras (G12D) mutation is prevalent in cancers like lung, colon and pancreatic cancer.
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!