Dataset Information

Fragment-Based Analysis of Ligand Dockings Improves Classification of Actives.

ABSTRACT: We describe ADChemCast, a method for using results from virtual screening to create a richer representation of a target binding site, which may be used to improve ranking of compounds and characterize the determinants of ligand-receptor specificity. ADChemCast clusters docked conformations of ligands based on shared pairwise receptor-ligand interactions within chemically similar structural fragments, building a set of attributes characteristic of binders and nonbinders. Machine learning is then used to build rules from the most informational attributes for use in reranking of compounds. In this report, we use ADChemCast to improve the ranking of compounds in 11 diverse proteins from the Database of Useful Decoys-Enhanced (DUD-E) and demonstrate the utility of the method for characterizing relevant binding attributes in HIV reverse transcriptase.

SUBMITTER: Belew RK

PROVIDER: S-EPMC5023760 | biostudies-literature | 2016 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Fragment-Based Analysis of Ligand Dockings Improves Classification of Actives.

Belew Richard K RK Forli Stefano S Goodsell David S DS O'Donnell T J TJ Olson Arthur J AJ

Journal of chemical information and modeling 20160725 8

We describe ADChemCast, a method for using results from virtual screening to create a richer representation of a target binding site, which may be used to improve ranking of compounds and characterize the determinants of ligand-receptor specificity. ADChemCast clusters docked conformations of ligands based on shared pairwise receptor-ligand interactions within chemically similar structural fragments, building a set of attributes characteristic of binders and nonbinders. Machine learning is then ...[more]

PMID: 27384036

Similar Datasets

Project description:Survivin is an apoptosis suppressing protein linked to different forms of cancer. As it stands, there are no approved drugs for the inhibition of survivin in cancer cells despite a number of promising compounds in clinical trials. This study designed a new set of compounds from fragments of active survivin inhibitors to potentiate their binding with survivin at BIR domain. Three hundred and five (305) fragments made from eight potent inhibitors of survivin were reconstructed to form a new set of compounds. The compounds were optimized using R group enumeration and bioisostere replacement after extensive docking analysis. The optimised compounds were filtered by a validated pharmacophore model to reveal how well they are aligned to the pharmacophore sites. Molecular docking of the well aligned compounds revealed the top-scoring compounds; and these compounds were compared with the eight inhibitors used as template for fragment-based design on the basis of binding affinity (rigid and flexible docking), predicted pIC50 and intermolecular interactions. The electronic behaviours (global descriptors, HOMO/LUMO, molecular electrostatic potential and Fukui functions) of newly designed compounds were calculated to investigate their reactivity and atomic sites prone to neutrophilic/electrophilic attack. The nine newly designed compounds had better rigid and flexible docking scores, free energy of binding and intermolecular interactions with survivin at BIR domain than the eight active inhibitors. Based on frontier molecular orbitals, OPE-3 was found to be the most reactive and less stable compound (0.13194 eV), followed by OPE-4 and OPE-9. The global descriptive parameters showed that OPE-3 had highest softness value (7.5245 eV) while OPE-8 recorded the maximum hardness value (0.08486 eV). The well-validated QSAR model also showed that OPE-3, OPE-7 and OPE-8 had the most significant bioactivity of all the inhibitors. This study thus provides new insight into the design of compounds capable of modulating the activity of survivin.Supplementary informationThe online version contains supplementary material available at 10.1007/s40203-021-00108-8.

Project description:To reduce time and cost, virtual ligand screening (VLS) often precedes experimental ligand screening in modern drug discovery. Traditionally, high-resolution structure-based docking approaches rely on experimental structures, while ligand-based approaches need known binders to the target protein and only explore their nearby chemical space. In contrast, our structure-based FINDSITEcomb2.0 approach takes advantage of predicted, low-resolution structures and information from ligands that bind distantly related proteins whose binding sites are similar to the target protein. Using a boosted tree regression machine learning framework, we significantly improved FINDSITEcomb2.0 by integrating ligand fragment scores as encoded by molecular fingerprints with the global ligand similarity scores of FINDSITEcomb2.0. The new approach, FRAGSITE, exploits our observation that ligand fragments, e.g., rings, tend to interact with stereochemically conserved protein subpockets that also occur in evolutionarily unrelated proteins. FRAGSITE was benchmarked on the 102 protein DUD-E set, where any template protein whose sequence identify >30% to the target was excluded. Within the top 100 ranked molecules, FRAGSITE improves VLS precision and recall by 14.3 and 18.5%, respectively, relative to FINDSITEcomb2.0. Moreover, the mean top 1% enrichment factor increases from 25.2 to 30.2. On average, both outperform state-of-the-art deep learning-based methods such as AtomNet. On the more challenging unbiased set LIT-PCBA, FRAGSITE also shows better performance than ligand similarity-based and docking approaches such as two-dimensional ECFP4 and Surflex-Dock v.3066. On a subset of 23 targets from DEKOIS 2.0, FRAGSITE shows much better performance than the boosted tree regression-based, vScreenML scoring function. Experimental testing of FRAGSITE's predictions shows that it has more hits and covers a more diverse region of chemical space than FINDSITEcomb2.0. For the two proteins that were experimentally tested, DHFR, a well-studied protein that catalyzes the conversion of dihydrofolate to tetrahydrofolate, and the kinase ACVR1, FRAGSITE identified new small-molecule nanomolar binders. Interestingly, one new binder of DHFR is a kinase inhibitor predicted to bind in a new subpocket. For ACVR1, FRAGSITE identified new molecules that have diverse scaffolds and estimated nanomolar to micromolar affinities. Thus, FRAGSITE shows significant improvement over prior state-of-the-art ligand virtual screening approaches. A web server is freely available for academic users at http:/sites.gatech.edu/cssb/FRAGSITE.

Dataset Information

Fragment-Based Analysis of Ligand Dockings Improves Classification of Actives.

Publications

Fragment-Based Analysis of Ligand Dockings Improves Classification of Actives.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets