Debasisa Mohanty
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Debasisa Mohanty has a total of 148 co-authors. Here are the top co-authors by number of shared publications:
Rajesh S. Gokhale
10 shared publications- Rajesh S. Gokhale
National Institute of Immunology, Aruna Asaf Ali Marg, New Delhi, 110 067, India
8 shared publications Gitanjali Yadav
National Institute of Immunology, Aruna Asaf Ali Marg, New Delhi, 110067, India
7 shared publications- Shradha Khater
National Institute of Immunology, Aruna Asaf Ali Marg, New Delhi 110067, India
7 shared publications - Pooja Arora
Department of Microbiology and Immunology, Albert Einstein College of Medicine, Bronx, NY 10461, USA
6 shared publications Swadha Anand
Bioinformatics Center, National Institute of Immunology, Aruna Asaf Ali Marg, New Delhi 110067, India
5 shared publications
Latest Publications
- Open Access
- 1 March 2026
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 35 (1)
Deciphering the Structural Basis of Allosteric Inhibition of Mutant Epidermal Growth Factor Receptor and Identification of Novel Inhibitors
Highlights: • MD simulations reveal the structural basis of allosteric inhibition in EGFR L858R/T790M • Mutant EGFR shows key shifts in αC-helix, A-loop, and P-loop toward activation • The known allosteric inhibitor stabilizes the inactive EGFR mutant by modulating critical substructures • Novel virtual screening workflow combines ML-based scoring with MD simulations and MM/GBSA • Potent inhibitors are identified based on propensity to drive conformational transitions
- 1 March 2026
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 35 (1)
Open AccessDeciphering the Structural Basis of Allosteric Inhibition of Mutant Epidermal Growth Factor Receptor and Identification of Novel Inhibitors
Highlights: • MD simulations reveal the structural basis of allosteric inhibition in EGFR L858R/T790M • Mutant EGFR shows key shifts in αC-helix, A-loop, and P-loop toward activation • The known allosteric inhibitor stabilizes the inactive EGFR mutant by modulating critical substructures • Novel virtual screening workflow combines ML-based scoring with MD simulations and MM/GBSA • Potent inhibitors are identified based on propensity to drive conformational transitions
- Open Access
- 6 January 2026
- Published by Oxford University Press (OUP) in NAR Genomics and Bioinformatics
- Vol. 8 (1)
Comparative evaluation of the prediction accuracy of AlphaFold and ESMFold for monomeric and dimeric proteins
We have evaluated the prediction accuracy of three different tools, deep-learning-based AlphaFold2, AlphaFold3, and large language model-based ESMFold, utilizing the experimentally derived structures deposited in the Protein Data Bank between 2022 and 2024, excluding those entries with close homologs in the structures released prior to 2022. Based on the criteria of sequence identity lower than 40% and query coverage <70%, 1666 monomeric and 994 dimeric proteins were selected as challenging targets for benchmarking. Our analysis showed that AlphaFold2 and AlphaFold3 correctly predicted 88% of monomeric structures and 77% of dimeric proteins. On the other hand, ESMFold accurately predicted 76% of the monomeric proteins and 41% of the dimeric proteins. Since most incorrect predictions involved nuclear magnetic resonance structures, benchmarking on X-ray and cryo-electron microscopy structures showed that the prediction accuracy of AlphaFold and ESMFold was 95% and 83%, respectively, for monomeric proteins. Overall, these findings demonstrate significant differences in the prediction accuracy of these machine learning (ML)-based tools for monomeric and dimeric proteins, highlighting the advantages and limitations of these tools. Finally, to facilitate easy access to benchmarking data, we developed ProModEv (Protein Model Evaluation portal), an interactive web portal for systematic analysis of these benchmarking results, and it is available at http://pdbi.nii.ac.in/ProModEv/.
- 6 January 2026
- Published by Oxford University Press (OUP) in NAR Genomics and Bioinformatics
- Vol. 8 (1)
Open AccessComparative evaluation of the prediction accuracy of AlphaFold and ESMFold for monomeric and dimeric proteins
We have evaluated the prediction accuracy of three different tools, deep-learning-based AlphaFold2, AlphaFold3, and large language model-based ESMFold, utilizing the experimentally derived structures deposited in the Protein Data Bank between 2022 and 2024, excluding those entries with close homologs in the structures released prior to 2022. Based on the criteria of sequence identity lower than 40% and query coverage <70%, 1666 monomeric and 994 dimeric proteins were selected as challenging targets for benchmarking. Our analysis showed that AlphaFold2 and AlphaFold3 correctly predicted 88% of monomeric structures and 77% of dimeric proteins. On the other hand, ESMFold accurately predicted 76% of the monomeric proteins and 41% of the dimeric proteins. Since most incorrect predictions involved nuclear magnetic resonance structures, benchmarking on X-ray and cryo-electron microscopy structures showed that the prediction accuracy of AlphaFold and ESMFold was 95% and 83%, respectively, for monomeric proteins. Overall, these findings demonstrate significant differences in the prediction accuracy of these machine learning (ML)-based tools for monomeric and dimeric proteins, highlighting the advantages and limitations of these tools. Finally, to facilitate easy access to benchmarking data, we developed ProModEv (Protein Model Evaluation portal), an interactive web portal for systematic analysis of these benchmarking results, and it is available at http://pdbi.nii.ac.in/ProModEv/.
- Open Access
Design of Allosteric Inhibitors for Mutant EGFR by Combined use of Machine Learning and Molecular Dynamics Simulations
The non-small cell lung cancer (NSCLC)-associated Epidermal Growth Factor Receptor (EGFR) mutant L858R/T790M confers resistance to first- and second-generation tyrosine kinase inhibitors (TKIs). Allosteric inhibitors, binding outside the ATP-binding site, have emerged as alternative therapeutic agents. Unlike orthosteric inhibitors, they preferentially stabilize EGFR in an inactive conformation. Hence, understanding the mechanistic basis of this inhibition is essential for designing potent allosteric inhibitors. In this study, we performed microsecond-scale molecular dynamics (MD) simulations on the inactive conformations of apo-EGFR and apo-EGFR L858R/T790M to explore how cancer-associated mutations induce a conformational switch toward the active kinase state. Simulations of allosteric inhibitor (EAI001) bound EGFR L858R/T790M revealed that inhibitor binding enhances the inactive state population by disrupting the K745-E762 salt bridge and modulating key structural elements. These findings revealed the structural basis of allosteric inhibition in EGFR L858R/T790M, . It also emphasized the importance of MD simulations in allosteric drug design for assessing the ability of the inhibitor to enhance the population of the inactive state of the mutant EGFR. We have also standardized a virtual screening protocol involving screening of an allosteric TKI library by docking, re-ranking them with a machine learning-based scoring function (SG-ML-PLAP), and evaluating top-scoring molecules by MD and MM/GBSA to identify molecules stabilizing the inactive state of the EGFR L858R/T790M . This approach identified 10 novel allosteric kinase inhibitors predicted to be more potent than EAI001. Overall, our results not only elucidate the mechanism of allosteric inhibition in EGFR L858R/T790M but also offer promising leads for the development of next-generation therapies to overcome TKI resistance.
Open AccessDesign of Allosteric Inhibitors for Mutant EGFR by Combined use of Machine Learning and Molecular Dynamics Simulations
The non-small cell lung cancer (NSCLC)-associated Epidermal Growth Factor Receptor (EGFR) mutant L858R/T790M confers resistance to first- and second-generation tyrosine kinase inhibitors (TKIs). Allosteric inhibitors, binding outside the ATP-binding site, have emerged as alternative therapeutic agents. Unlike orthosteric inhibitors, they preferentially stabilize EGFR in an inactive conformation. Hence, understanding the mechanistic basis of this inhibition is essential for designing potent allosteric inhibitors. In this study, we performed microsecond-scale molecular dynamics (MD) simulations on the inactive conformations of apo-EGFR and apo-EGFR L858R/T790M to explore how cancer-associated mutations induce a conformational switch toward the active kinase state. Simulations of allosteric inhibitor (EAI001) bound EGFR L858R/T790M revealed that inhibitor binding enhances the inactive state population by disrupting the K745-E762 salt bridge and modulating key structural elements. These findings revealed the structural basis of allosteric inhibition in EGFR L858R/T790M, . It also emphasized the importance of MD simulations in allosteric drug design for assessing the ability of the inhibitor to enhance the population of the inactive state of the mutant EGFR. We have also standardized a virtual screening protocol involving screening of an allosteric TKI library by docking, re-ranking them with a machine learning-based scoring function (SG-ML-PLAP), and evaluating top-scoring molecules by MD and MM/GBSA to identify molecules stabilizing the inactive state of the EGFR L858R/T790M . This approach identified 10 novel allosteric kinase inhibitors predicted to be more potent than EAI001. Overall, our results not only elucidate the mechanism of allosteric inhibition in EGFR L858R/T790M but also offer promising leads for the development of next-generation therapies to overcome TKI resistance.
- 30 June 2025
- Published by American Chemical Society (ACS) in ACS Chemical Biology
- Vol. 20 (7) , 1492-1504
Enzymatic Pathway for Kupyaphore Degradation in Mycobacterium tuberculosis: Mechanism of Metal Homeostasis and Turnover
Metallophores are essential for metal homeostasis, regulating availability, and mediating host-pathogen interactions. Kupyaphores are specialized metallophores produced by Mycobacterium tuberculosis (Mtb) that primarily chelate zinc to support bacterial survival. Elevated kupyaphore levels early in infection highlight their importance, while their rapid decline, despite increasing bacterial loads, indicates tightly regulated mechanisms of production, consumption, and degradation. However, the processes driving kupyaphore catabolism and their role in preventing zinc toxicity in Mtb remain unclear. Here, we show that covalent modification of the isonitrile moiety in kupyaphores releases zinc, triggering degradation through a sequential three-step enzymatic pathway encoded by Mtb. Isonitrile hydratase converts isonitrile groups into formamides, which are subsequently processed into amines by N-substituted formamide deformylase and ultimately oxidized to β-ketoesters by amine oxidases. The biological significance of this pathway is underscored by the upregulation of these genes under metal-depleted and biofilm-forming conditions. Mutant Mtb strains lacking these genes exhibit impaired growth in metal-limiting environments and reduced levels of biofilm formation. Catalytic intermediates detected in Mtb cultures and infected mouse lung tissues confirm the pathway's in vivo activity. Further, genome mining reveals that similar enzymes are conserved across organisms producing isonitrile-containing metabolites, emphasizing the broader importance of this pathway. Understanding these processes could pave the way for novel therapeutic strategies targeting kupyaphore catabolism.
- 30 June 2025
- Published by American Chemical Society (ACS) in ACS Chemical Biology
- Vol. 20 (7) , 1492-1504
Enzymatic Pathway for Kupyaphore Degradation in Mycobacterium tuberculosis: Mechanism of Metal Homeostasis and Turnover
Metallophores are essential for metal homeostasis, regulating availability, and mediating host-pathogen interactions. Kupyaphores are specialized metallophores produced by Mycobacterium tuberculosis (Mtb) that primarily chelate zinc to support bacterial survival. Elevated kupyaphore levels early in infection highlight their importance, while their rapid decline, despite increasing bacterial loads, indicates tightly regulated mechanisms of production, consumption, and degradation. However, the processes driving kupyaphore catabolism and their role in preventing zinc toxicity in Mtb remain unclear. Here, we show that covalent modification of the isonitrile moiety in kupyaphores releases zinc, triggering degradation through a sequential three-step enzymatic pathway encoded by Mtb. Isonitrile hydratase converts isonitrile groups into formamides, which are subsequently processed into amines by N-substituted formamide deformylase and ultimately oxidized to β-ketoesters by amine oxidases. The biological significance of this pathway is underscored by the upregulation of these genes under metal-depleted and biofilm-forming conditions. Mutant Mtb strains lacking these genes exhibit impaired growth in metal-limiting environments and reduced levels of biofilm formation. Catalytic intermediates detected in Mtb cultures and infected mouse lung tissues confirm the pathway's in vivo activity. Further, genome mining reveals that similar enzymes are conserved across organisms producing isonitrile-containing metabolites, emphasizing the broader importance of this pathway. Understanding these processes could pave the way for novel therapeutic strategies targeting kupyaphore catabolism.
- Open Access
- 21 May 2025
- Published by eLife Sciences Publications, Ltd in eLife preprints
- Vol. 14
Single-cell profiling of the lung immune cells of diabetes-tuberculosis comorbidity reveals reduced type-II interferon and elevated Th17 responses
Understanding the perturbed lung immune cells distribution and its functionality in tuberculosis (TB) is well documented; however, limited reports have covered their disruption, if any, in diabetes-tuberculosis (DM-TB) comorbid conditions. Here, we employed single-cell RNA-seq to investigate the molecular mechanisms that govern the heterogeneity in host immune response in DM-TB comorbid conditions. Diabetes is associated with chronic hyperinflammation and reduced lung-infiltrating immune cells, which delays the immune response to Mycobacterial infection. scRNA-seq of lung CD3⁺ and CD11c⁺ cells revealed compromised adaptive and innate immunity, with decreased Th1 and M1 macrophage populations in DM-TB mice. A dampened immune response, marked by increased IL-16 signaling and reduced TNF and IFN-II responses, was observed in DM-TB. This study highlights chronic inflammation, hyperglycemia, and dyslipidemia associated with diabetes impairing anti-TB immunity. Selective inhibition of aberrant IL-16 secretion and Th17 cell activation might provide strategies for better managing DM-TB comorbidity.
- 21 May 2025
- Published by eLife Sciences Publications, Ltd in eLife preprints
- Vol. 14
Open AccessSingle-cell profiling of the lung immune cells of diabetes-tuberculosis comorbidity reveals reduced type-II interferon and elevated Th17 responses
Understanding the perturbed lung immune cells distribution and its functionality in tuberculosis (TB) is well documented; however, limited reports have covered their disruption, if any, in diabetes-tuberculosis (DM-TB) comorbid conditions. Here, we employed single-cell RNA-seq to investigate the molecular mechanisms that govern the heterogeneity in host immune response in DM-TB comorbid conditions. Diabetes is associated with chronic hyperinflammation and reduced lung-infiltrating immune cells, which delays the immune response to Mycobacterial infection. scRNA-seq of lung CD3⁺ and CD11c⁺ cells revealed compromised adaptive and innate immunity, with decreased Th1 and M1 macrophage populations in DM-TB mice. A dampened immune response, marked by increased IL-16 signaling and reduced TNF and IFN-II responses, was observed in DM-TB. This study highlights chronic inflammation, hyperglycemia, and dyslipidemia associated with diabetes impairing anti-TB immunity. Selective inhibition of aberrant IL-16 secretion and Th17 cell activation might provide strategies for better managing DM-TB comorbidity.
- 24 January 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 186, 109679
HgutMgene-Miner: In silico genome mining tool for deciphering the drug-metabolizing potential of human gut microbiome
- 24 January 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 186, 109679
HgutMgene-Miner: In silico genome mining tool for deciphering the drug-metabolizing potential of human gut microbiome
- Open Access
- 7 January 2025
- Published by Oxford University Press (OUP) in NAR Genomics and Bioinformatics
- Vol. 7 (1) , lqae186
SProtFP: a machine learning-based method for functional classification of small ORFs in prokaryotes
Small proteins (≤100 amino acids) play important roles across all life forms, ranging from unicellular bacteria to higher organisms. In this study, we have developed SProtFP which is a machine learning-based method for functional annotation of prokaryotic small proteins into selected functional categories. SProtFP uses independent artificial neural networks (ANNs) trained using a combination of physicochemical descriptors for classifying small proteins into antitoxin type 2, bacteriocin, DNA-binding, metal-binding, ribosomal protein, RNA-binding, type 1 toxin and type 2 toxin proteins. We have also trained a model for identification of small open reading frame (smORF)-encoded antimicrobial peptides (AMPs). Comprehensive benchmarking of SProtFP revealed an average area under the receiver operator curve (ROC-AUC) of 0.92 during 10-fold cross-validation and an ROC-AUC of 0.94 and 0.93 on held-out balanced and imbalanced test sets. Utilizing our method to annotate bacterial isolates from the human gut microbiome, we could identify thousands of remote homologs of known small protein families and assign putative functions to uncharacterized proteins. This highlights the utility of SProtFP for large-scale functional annotation of microbiome datasets, especially in cases where sequence homology is low. SProtFP is freely available at http://www.nii.ac.in/sprotfp.html and can be combined with genome annotation tools such as ProsmORF-pred to uncover the functional repertoire of novel small proteins in bacteria.
- 7 January 2025
- Published by Oxford University Press (OUP) in NAR Genomics and Bioinformatics
- Vol. 7 (1) , lqae186
Open AccessSProtFP: a machine learning-based method for functional classification of small ORFs in prokaryotes
Small proteins (≤100 amino acids) play important roles across all life forms, ranging from unicellular bacteria to higher organisms. In this study, we have developed SProtFP which is a machine learning-based method for functional annotation of prokaryotic small proteins into selected functional categories. SProtFP uses independent artificial neural networks (ANNs) trained using a combination of physicochemical descriptors for classifying small proteins into antitoxin type 2, bacteriocin, DNA-binding, metal-binding, ribosomal protein, RNA-binding, type 1 toxin and type 2 toxin proteins. We have also trained a model for identification of small open reading frame (smORF)-encoded antimicrobial peptides (AMPs). Comprehensive benchmarking of SProtFP revealed an average area under the receiver operator curve (ROC-AUC) of 0.92 during 10-fold cross-validation and an ROC-AUC of 0.94 and 0.93 on held-out balanced and imbalanced test sets. Utilizing our method to annotate bacterial isolates from the human gut microbiome, we could identify thousands of remote homologs of known small protein families and assign putative functions to uncharacterized proteins. This highlights the utility of SProtFP for large-scale functional annotation of microbiome datasets, especially in cases where sequence homology is low. SProtFP is freely available at http://www.nii.ac.in/sprotfp.html and can be combined with genome annotation tools such as ProsmORF-pred to uncover the functional repertoire of novel small proteins in bacteria.
- Open Access
- 1 January 2025
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 27, 5425-5440
In silico analysis of the functional implications of drug resistance associated mutations in Mycobacterium tuberculosis
The tuberculosis mutation catalogue published by World Health Organization (WHO) lists a large number of mutations based on the statistical significance of their association with resistance or susceptibility to various drugs. However, the mechanism by which they confer resistance to drugs is often not understood. To address these gaps, we combined known resistance associated mutations from the WHO catalogue and newly discovered mutations by explainable artificial intelligence (XAI). In order to decipher the mechanistic basis of drug resistance, we examined where these mutations occur in three dimensional (3D) structures of key drug targets, measured their proximity to drug binding sites and compared their abundance in drug resistant as well as drug susceptible Mycobacterium tuberculosis (M.tb) strains. In parallel, we analyzed the functions of 112 newly identified drug resistance associated genes and compared them to known resistance genes, finding that most novel genes fall into different functional categories, though six share families with known resistance genes. We mapped coding mutations in all 112 novel genes to their functional domains, predicted 3D structures using Alphafold3 and evaluated their effects on protein stability. Notably, our study highlights that mutations in ribosomal proteins (RpsN1, RpsN2) and the transporter PstB may introduce new resistance mechanisms, such as altered drug interactions or increased drug efflux. Whereas, analysis of non coding mutations revealed that most are located at transcription factor binding sites, potentially affecting gene regulation. The current analysis provides valuable insights for the design of experiments to decode mechanistic basis of drug resistance tuberculosis.
- 1 January 2025
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 27, 5425-5440
Open AccessIn silico analysis of the functional implications of drug resistance associated mutations in Mycobacterium tuberculosis
The tuberculosis mutation catalogue published by World Health Organization (WHO) lists a large number of mutations based on the statistical significance of their association with resistance or susceptibility to various drugs. However, the mechanism by which they confer resistance to drugs is often not understood. To address these gaps, we combined known resistance associated mutations from the WHO catalogue and newly discovered mutations by explainable artificial intelligence (XAI). In order to decipher the mechanistic basis of drug resistance, we examined where these mutations occur in three dimensional (3D) structures of key drug targets, measured their proximity to drug binding sites and compared their abundance in drug resistant as well as drug susceptible Mycobacterium tuberculosis (M.tb) strains. In parallel, we analyzed the functions of 112 newly identified drug resistance associated genes and compared them to known resistance genes, finding that most novel genes fall into different functional categories, though six share families with known resistance genes. We mapped coding mutations in all 112 novel genes to their functional domains, predicted 3D structures using Alphafold3 and evaluated their effects on protein stability. Notably, our study highlights that mutations in ribosomal proteins (RpsN1, RpsN2) and the transporter PstB may introduce new resistance mechanisms, such as altered drug interactions or increased drug efflux. Whereas, analysis of non coding mutations revealed that most are located at transcription factor binding sites, potentially affecting gene regulation. The current analysis provides valuable insights for the design of experiments to decode mechanistic basis of drug resistance tuberculosis.
- Open Access
- 26 December 2024
- Published by Oxford University Press (OUP) in Bioinformatics Advances
- Vol. 5 (1) , vbaf050
Machine learning-based approach for identification of new resistance associated mutations from whole genome sequences of Mycobacterium tuberculosis
Motivation: Currently available methods for the prediction of genotypic drug resistance in Mycobacterium tuberculosis utilize information on known markers of drug resistance. Hence, machine learning approaches are needed that can discover new resistance markers. Results: Whole genome sequences with known phenotypic drug resistance profiles have been utilized to train XGBoost and ANN classifiers for 5 first-line and 8 second-line tuberculosis drugs. Benchmarking on a completely independent dataset from CRyPTIC database revealed that our method has high sensitivity (90%–95%) and specificity (94%–99%) for five first-line drugs and robust performance for six second-line drugs with a sensitivity of 77%–89% at over 95% specificity. An explainable AI method, SHapley Additive exPlanations, has successfully identified resistance mutations for each drug in a completely automated way. This approach could not only identify known resistance associated mutations in agreement with the WHO mutation catalogue, but also predicted >100 other potential resistance associated mutations for 13 antibiotics in new genes outside the known resistance loci. Identification of new resistance markers opens up the opportunity for the discovery of novel mechanisms of drug resistance. Availability and implementation: Our prediction method has been implemented as TB-AMRpred webserver and command line tool, available freely at http://www.nii.ac.in/TB-AMRpred.html and https://github.com/Ankitapal1995/TB-AMRprd.
- 26 December 2024
- Published by Oxford University Press (OUP) in Bioinformatics Advances
- Vol. 5 (1) , vbaf050
Open AccessMachine learning-based approach for identification of new resistance associated mutations from whole genome sequences of Mycobacterium tuberculosis
Motivation: Currently available methods for the prediction of genotypic drug resistance in Mycobacterium tuberculosis utilize information on known markers of drug resistance. Hence, machine learning approaches are needed that can discover new resistance markers. Results: Whole genome sequences with known phenotypic drug resistance profiles have been utilized to train XGBoost and ANN classifiers for 5 first-line and 8 second-line tuberculosis drugs. Benchmarking on a completely independent dataset from CRyPTIC database revealed that our method has high sensitivity (90%–95%) and specificity (94%–99%) for five first-line drugs and robust performance for six second-line drugs with a sensitivity of 77%–89% at over 95% specificity. An explainable AI method, SHapley Additive exPlanations, has successfully identified resistance mutations for each drug in a completely automated way. This approach could not only identify known resistance associated mutations in agreement with the WHO mutation catalogue, but also predicted >100 other potential resistance associated mutations for 13 antibiotics in new genes outside the known resistance loci. Identification of new resistance markers opens up the opportunity for the discovery of novel mechanisms of drug resistance. Availability and implementation: Our prediction method has been implemented as TB-AMRpred webserver and command line tool, available freely at http://www.nii.ac.in/TB-AMRpred.html and https://github.com/Ankitapal1995/TB-AMRprd.
- 11 December 2024
- Published by Wiley in Protein Science
- Vol. 34 (1) , e5257
SG‐ML‐PLAP: A structure‐guided machine learning–based scoring function for protein–ligand binding affinity prediction
Computational methods to predict binding affinity of protein–ligand complex have been used extensively to design inhibitors for proteins selected as drug targets. In recent years machine learning (ML) is being increasingly used for design of drugs/inhibitors. However, ranking compounds as per their experimental binding affinity has remained a major challenge. Therefore, it is necessary to develop ML‐based scoring function (MLSF) for predicting the binding affinity of protein–ligand complexes. In this work, protein–ligand interaction features, namely, extended connectivity interaction fingerprints (ECIF), derived from the PDBbind dataset have been used to build ML models for binding affinity prediction. The benchmarking has been done on the Comparative Assessment of Scoring Functions (CASF) dataset and also by predicting the binding affinity of unseen protein–ligand complexes which have structural features different from those present in the training dataset. Furthermore, an improvement in the performance of MLSF on the redocked CASF complexes generated by AutoDock Vina software was seen when the training set consisting of crystal structures was supplemented with redocked protein–ligand complexes. The MLSF trained on crystal structures alone using a combination of ECIF and VINA features also predicted binding affinities of crystal as well as docked complexes with high accuracy. Overall, the MLSF developed in this work shows improved performance compared to conventional SFs and several other MLSFs. It will be a valuable resource for identifying novel inhibitors by structure‐based virtual screening protocols. The proposed MLSF SG‐ML‐PLAP (Structure‐Guided Machine‐Learning–based Protein‐Ligand Affinity Predictor) is freely accessible as a webserver, http://www.nii.ac.in/sg-ml-plap.html.
- 11 December 2024
- Published by Wiley in Protein Science
- Vol. 34 (1) , e5257
SG‐ML‐PLAP: A structure‐guided machine learning–based scoring function for protein–ligand binding affinity prediction
Computational methods to predict binding affinity of protein–ligand complex have been used extensively to design inhibitors for proteins selected as drug targets. In recent years machine learning (ML) is being increasingly used for design of drugs/inhibitors. However, ranking compounds as per their experimental binding affinity has remained a major challenge. Therefore, it is necessary to develop ML‐based scoring function (MLSF) for predicting the binding affinity of protein–ligand complexes. In this work, protein–ligand interaction features, namely, extended connectivity interaction fingerprints (ECIF), derived from the PDBbind dataset have been used to build ML models for binding affinity prediction. The benchmarking has been done on the Comparative Assessment of Scoring Functions (CASF) dataset and also by predicting the binding affinity of unseen protein–ligand complexes which have structural features different from those present in the training dataset. Furthermore, an improvement in the performance of MLSF on the redocked CASF complexes generated by AutoDock Vina software was seen when the training set consisting of crystal structures was supplemented with redocked protein–ligand complexes. The MLSF trained on crystal structures alone using a combination of ECIF and VINA features also predicted binding affinities of crystal as well as docked complexes with high accuracy. Overall, the MLSF developed in this work shows improved performance compared to conventional SFs and several other MLSFs. It will be a valuable resource for identifying novel inhibitors by structure‐based virtual screening protocols. The proposed MLSF SG‐ML‐PLAP (Structure‐Guided Machine‐Learning–based Protein‐Ligand Affinity Predictor) is freely accessible as a webserver, http://www.nii.ac.in/sg-ml-plap.html.