Descriptor-free QSAR: effectiveness in screening for putative inhibitors of FGFR1

The long short-term memory (LSTM) algorithm has provided solutions to the limitations of the descriptors-utilizing QSAR models in drug design. However, the direct application of LSTM remains scarce. The effectiveness of a descriptor-free QSAR (LSTM-SM) in modeling the FGFR1 inhibitors dataset while...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of biomolecular structure & dynamics Vol. 41; no. 5; pp. 2016 - 2032
Main Authors:	Joel, I. Y., Sulaimon, L. A., Idris, M. O., Adigun, T. O., Adisa, R. A., Ademoye, T. A., Ogunleye, M. O., Olaniyi, T. O.
Format:	Journal Article
Language:	English
Published:	England Taylor & Francis 24-03-2023
Subjects:	Algorithms Catalytic Domain Descriptor-free QSAR FGFR1 induced-fit docking LSTM Molecular Docking Simulation Molecular Dynamics Simulation QM-MM optimization Quantitative Structure-Activity Relationship induced-fit docking LSTM Descriptor-free QSAR QM-MM optimization FGFR1
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The long short-term memory (LSTM) algorithm has provided solutions to the limitations of the descriptors-utilizing QSAR models in drug design. However, the direct application of LSTM remains scarce. The effectiveness of a descriptor-free QSAR (LSTM-SM) in modeling the FGFR1 inhibitors dataset while comparing with two conventional QSAR using descriptors (126 bits Morgan fingerprint and 2 D descriptors respectively) as a baseline model was investigated in this study. The validated descriptor-free QSAR model was thereafter used to screen for active FGFR1 inhibitors in the ChemDiv database and subjected to molecular docking, induced-fit docking, QM-MM optimization, and molecular dynamics simulations to filter for compounds with high binding affinity and suggest the putative mechanism of inhibition and specificity. The LSTM-SM model performed better than conventional QSAR; having accuracy, specificity, and sensitivity of 0.92, model loss of 0.025, and AUC of 0.95. Fifteen thousand compounds were predicted as actives from the ChemDiv database and four compounds were finally selected. Of the four, two showed putatively effective binding interactions with key active site residues. Molecular dynamics simulations on these compounds in complex with the receptor further give insight into the conformational dynamics of each compound bounded to the receptor. The complexes formed are stable and exhibit a similar degree of compactness. Our findings predicted the advent of self-feature extracting machine learning algorithms of compounds, and have provided the possibility of better predictive model quality that is not necessarily limited by compound descriptors. The putative FGFR1 inhibitors, with their mechanism of inhibition and specificity, were elucidated using this approach Communicated by Ramaswamy H. Sarma
ISSN:	0739-1102 1538-0254
DOI:	10.1080/07391102.2022.2026248