Pralay Mitra

@iitkgp.ac.in

Associate Professor in Computer Science and Engineering
Indian Institute of Technology Kharagpur

Pralay Mitra


                     Download Compact PDF  
https://researchid.co/pralaymitra

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science Applications, Software, Biotechnology, Molecular Biology
44

Scopus Publications

621

Scholar Citations

15

Scholar h-index

22

Scholar i10-index

Scopus Publications

  • Targeting of HSP27 and MMP-2/9 Crosstalk by High-Throughput Drug Repurposing Strategies Identifies Paroxetine as a Potential Candidate in Glioblastoma
    Suvendu Nandi, Shreya Banerjee, Debolina Manna, Animesh Awasthi, Angana Biswas, Abhijit Das, Budhaditya Mukherjee, Pralay Mitra, Mahitosh Mandal
    Journal of Medicinal Chemistry, 2026
    Glioblastoma is the most malignant and treatment-resistant primary brain tumor, driven by extensive cellular plasticity, epithelial-mesenchymal transition (EMT), and extracellular matrix (ECM) remodeling. Heat shock protein 27 (HSP27) stabilizes oncogenic signaling complexes and activates matrix metalloproteinases MMP-2 and MMP-9, facilitating invasion and metastasis. We implemented a structure-based high-throughput screening of FDA-approved compounds to identify inhibitors targeting HSP27-MMP-2/9 crosstalk. In silico studies have identified paroxetine, a selective serotonin reuptake inhibitor, as a high-affinity ligand for HSP27, inducing conformational destabilization and compromising its chaperone activity. Research on LN18 and LN229 glioblastoma cell lines showed that paroxetine treatment decreased cell viability and migration and lowered the levels of HSP27, MMP-2, and MMP-9. The C6 glioma rat model further confirmed the suppression of HSP27 and its crosstalk partner MMP-2/9 in tumor tissue. Collectively, these findings establish paroxetine as a functional HSP27 inhibitor that disrupts the interaction between HSP27 and MMP-2/9, thereby inhibiting glioblastoma progression.
  • PEPpip: A Vision-Inspired Explainable Deep Learning Framework for Sequence-Based Protein–Protein Interaction Prediction and Interaction Map Estimation
    Shubhrangshu Ghosh, Pralay Mitra
    IEEE Access, 2026
    Predicting protein–protein interaction (PPI) patterns from primary sequences constitutes a complex pattern recognition task that demands advanced and explainable deep learning frameworks, as PPIs underpin critical cellular and pathological mechanisms.We propose PEPpip, a deep learning framework for binary sequence-based PPI prediction that also derives interaction maps via explainable-AI (XAI) methods. PEPpip encodes sequence pairs into 3D image-like feature maps using three pre-trained protein language models(PLMs). To learn PPI patterns, it applies two vision-based classifiers—ResNet and Vision Transformer( ViT)—whose predictions are fused through a novel Post-hoc Inference Combiner(PIC) leveraging their complementary strengths. In addition, PEPpip uniquely generates PPI maps by combining XAI-based interaction maps from integrated gradients and ViT attention, further refined through a modular noise-cleaning pipeline. We introduce a novel residue-residue interaction-aware, class-discriminative attention map(RiaCdAm) mechanism that embeds biological priors into ViT attention, improving interpretability and contact relevance. PEPpip achieves state-of-the-art AUPR (Area Under Precision-Recall curve) scores across species—91.1%(Mouse), 89.1%(Fly), 87.7%(Worm), 68.1%(Yeast), and 71.9%(E.coli)—outperforming existing methods by 2–3%. It also performs strongly on Human-PPI tasks. While its sequence-driven, XAI-based PPI map approach is not directly comparable to structure-based learners, PEPpip surpasses competing sequence-based classifiers in interaction map estimation, exceeding the next-best method by over 5% in top-L/10 and top-L/5 categories (<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</i>: shorter protein-length in the pair). PEPpip provides a unified and interpretable framework for binary PPI prediction with coarse-grained interaction map estimation, offering a practical first-pass screening tool for large-scale interactome analysis and paving the way for future XAI-integrated models.
  • A transformer-based method for the cap analysis of gene expression and gene expression tag associated capping region prediction in RNA
    Dibya Kanti Haldar, Avik Pramanick, Chandrama Mukherjee, Pralay Mitra
    RNA Biology, 2026
    5' RNA capping is one of the major post-transcriptional modifications for the mobility and stability of RNA molecules. Measuring 5' caps of RNAs can help quantify expression levels of mRNAs and lncRNAs. One of the most successful RNAseq methods that has used capping as a tool to quantify expression of transcription is Cap Analysis of Gene Expression (CAGE). Computational prediction of capping can therefore be used as a precursor to the prediction of transcriptional expression. Unfortunately, there is hardly any computational technique that has focused purely on predicting 5' capping. We have developed a transformer-based method for computational prediction of capping from DNA sequences. Our Llama and ReLoRA-based pre-training model, and Llama and LoRA-based fine-tuning model predict capping associated regions. We have used Leave-one-chromosome-out-cross-validation for our model. The average accuracy, and F1-score after fine-tuning the human genome hg19 (mouse genome mm9) for sequence classification is 79.12% (78.09%) and 78.11% (76.17%), respectively. We noted attention peak-based motifs having an aggregate Wilcoxon rank-sum p-value of 1.075e-10 between the attention peak region and the entire context window for the predicted positive motifs; an aggregate p-value of 7.17e-18 for the predicted negative motifs; and an aggregate p-value of 6.70e-08 between the attention peaks of the predicted positive and the predicted negative motifs. Our Llama-based approach aims to create a sequence-based framework to identify capping associated regions corresponding to CAGE peaks. Our analysis reveals statistically significant motifs from the regions of peak attention scores, which demonstrates biological relevance for some through their resident sites matching with known TF motifs.
  • ConfPred: ML-Based Conformational B-cell Epitope Prediction Using Novel Features
    Purnima Gautam, Pralay Mitra
    Icbra 2025 Proceedings of the 12th International Conference on Bioinformatics Research and Applications, 2025
    Epitopes are distinct regions on the surface of proteins or viruses that are specifically recognised by antibodies. Epitopes play a pivotal role in initiating immune responses and vaccine development. Among them, conformational epitopes, formed by spatially distant amino acid residues, are challenging to predict due to their structural complexity and thus remain underexplored. In this work, we propose ConfPred, a machine learning-based framework for conformational B-cell epitope prediction. ConfPred introduces a novel feature formation strategy based on the 566 AAIndex property set and 20 aggregation-based features and leverages six classifiers: logistic regression, random forest, decision tree, support vector machine (SVM), gradient boosting, and XGBoost to enhance the prediction accuracy of conformational B-cell epitopes. We further integrate these features into the clinically curated Immune Epitope Database (IEDB) to facilitate public accessibility and reproducibility. Our augmented database with a proper feature extraction technique, when trained on these classifiers, achieves high prediction accuracies of up to 97%. These results highlight the potential of our augmented database to open new avenues for future in silico methods towards the improvement of prediction accuracy.
  • E(Q)AGNN-PPIS: Attention Enhanced Equivariant Graph Neural Network for Protein-Protein Interaction Site Prediction
    Animesh, Rishi Suvvada, Plaban Kumar Bhowmick, Pralay Mitra
    IEEE Transactions on Signal and Information Processing Over Networks, 2025
    In this work, we tackle the problem of beampattern design for a transmit system employing a large reconfigurable intelligent surface (RIS) to redirect radio frequency signals emitted by a few active antennas (sources). We begin by establishing a convenient signal model and discussing the impact of signal bandwidth, source-RIS channel, and system geometry on our derivations. Subsequently, we propose a joint optimization of the waveform emitted by each source and the phase shifts introduced by the RIS. The objective is to match a desired space-frequency distribution of the far-field radiation pattern, relevant to both radar and communication applications. We present a sub-optimal solution to this problem, subject to a constraint on the total power radiated by the sources and, optionally, on the constant modulus of the waveforms. The provided example demonstrates the effective beampattern shaping capabilities of this RIS-based transmit architecture. Specifically, for the same array size and the same desired radiation pattern, the resulting approximation error is comparable to that obtained with a fully-digital MIMO array, especially when constant-modulus waveforms are enforced, and significantly smaller than that of a phased array.
  • The molecular prognostic score, a classifier for risk stratification of high-grade serous ovarian cancer
    Siddik Sarkar, Sarbar Ali Saha, Abhishek Swarnakar, Arnab Chakrabarty, Avipsa Dey, Poulomi Sarkar, Sarthak Banerjee, Pralay Mitra
    Journal of Ovarian Research, 2024
    BACKGROUND: The clinicopathological parameters such as residual tumor, grade, the International Federation of Gynecology and Obstetrics (FIGO) score are often used to predict the survival of ovarian cancer patients, but the 5-year survival of high grade serous ovarian cancer (HGSOC) still remains around 30%. Hence, the relentless pursuit of enhanced prognostic tools for HGSOC, this study introduces an unprecedented gene expression-based molecular prognostic score (mPS). Derived from a novel 20-gene signature through Least Absolute Shrinkage and Selection Operator (LASSO)-Cox regression, the mPS stands out for its predictive prowess. RESULTS: Validation across diverse datasets, including training and test sets (n = 491 each) and a large HGSOC patient cohort from the Ovarian Tumor Tissue Analysis (OTTA) consortium (n = 7542), consistently shows an area-under-curve (AUC) around 0.7 for predicting 5-year overall survival. The mPS's impact on prognosis resonates profoundly, yielding an adjusted hazard-ratio (HR) of 6.1 (95% CI: 3.65-10.3; p < 0.001), overshadowing conventional parameters-FIGO score, residual disease, and age. Molecular insights gleaned from mPS stratification uncover intriguing pathways, with focal-adhesion, Wnt, and Notch signaling upregulated, and antigen processing and presentation downregulated (p < 0.001) in high-risk HGSOC cohorts. CONCLUSION: Positioned as a robust prognostic marker, the 20-gene signature-derived mPS emerges as a potential game-changer in clinical settings. Beyond its role in predicting overall survival, its implications extend to guiding alternative therapies, especially targeting Wnt/Notch signaling pathways and immune evasion-a promising avenue for improving outcomes in high-risk HGSOC patients.
  • Deciphering the Lexicon of Protein Targets: A Review on Multifaceted Drug Discovery in the Era of Artificial Intelligence
    Suvendu Nandi, Soumyadeep Bhaduri, Debraj Das, Priya Ghosh, Mahitosh Mandal, Pralay Mitra
    Molecular Pharmaceutics, 2024
    Understanding protein sequence and structure is essential for understanding protein-protein interactions (PPIs), which are essential for many biological processes and diseases. Targeting protein binding hot spots, which regulate signaling and growth, with rational drug design is promising. Rational drug design uses structural data and computational tools to study protein binding sites and protein interfaces to design inhibitors that can change these interactions, thereby potentially leading to therapeutic approaches. Artificial intelligence (AI), such as machine learning (ML) and deep learning (DL), has advanced drug discovery and design by providing computational resources and methods. Quantum chemistry is essential for drug reactivity, toxicology, drug screening, and quantitative structure-activity relationship (QSAR) properties. This review discusses the methodologies and challenges of identifying and characterizing hot spots and binding sites. It also explores the strategies and applications of artificial-intelligence-based rational drug design technologies that target proteins and protein-protein interaction (PPI) binding hot spots. It provides valuable insights for drug design with therapeutic implications. We have also demonstrated the pathological conditions of heat shock protein 27 (HSP27) and matrix metallopoproteinases (MMP2 and MMP9) and designed inhibitors of these proteins using the drug discovery paradigm in a case study on the discovery of drug molecules for cancer treatment. Additionally, the implications of benzothiazole derivatives for anticancer drug design and discovery are deliberated.
  • MaTPIP: A deep-learning architecture with eXplainable AI for sequence-driven, feature mixed protein-protein interaction prediction
    Shubhrangshu Ghosh, Pralay Mitra
    Computer Methods and Programs in Biomedicine, 2024
  • Deep Reinforcement Learning in Healthcare and Biomedical Research
    Shruti Agrawal, Pralay Mitra
    Deep Reinforcement Learning and Its Industrial Use Cases AI for Real World Applications, 2024
    Advances in biological research have generated a wealth of data, which prompted the exploration of various machine learning techniques, notably reinforcement learning (RL) and deep reinforcement learning (DRL), for applications in the healthcare and biomedical domain. The utilization of Q-learning, a foundational RL algorithm, and its diverse variants, coupled with the integration of deep neural networks as seen in deep Q-networks (DQN), along with techniques like experience replay, has demonstrated remarkable efficacy in tackling intricate challenges such as protein folding. RL strategies, grounded in proximal policy optimization (PPO), have been extensively employed to meet the protein folding challenges, where the utilization of Markov decision processes aids in formulating intricate protein conformations. The intricate challenge of the protein–ligand docking finds a solution in the innovative application of DRL, employing the advantage asynchronous actor–critic model. Additionally, this complex problem can be effectively tackled using the deep deterministic policy gradient approach, enhanced by the incorporation of a graph neural network to adeptly represent the intricate interactions within the protein–ligand complex. Within the healthcare and biomedical sectors, the integration of deep learning techniques holds the potential for a range of applications. These include the analysis of medical imagery, the prediction of patient outcomes, the identification of intricate patterns within extensive datasets, and support in the field of drug discovery. These techniques harness the capabilities of neural networks, which excel in their ability to discern intricate patterns and relationships from voluminous and complex datasets. DRL has emerged as a transformative force in healthcare and biomedical domains, revolutionizing biomolecular structure prediction, decoding intricate molecular interactions, and elevating therapeutic strategies. Multiple use cases of reinforcement learning techniques are delineated within the realm of healthcare and biomedical applications. The analysis spans diverse applications from protein engineering to healthcare domains, showcasing the transformative impact of these techniques in advancing biomedical research, diagnostics, drug discovery, and the utilization of biological data.
  • Genome surveillance of SARS-CoV-2 variants and their role in pathogenesis focusing on second wave of COVID-19 in India
    Poulomi Sarkar, Sarthak Banerjee, Sarbar Ali Saha, Pralay Mitra, Siddik Sarkar
    Scientific Reports, 2023
    India had witnessed unprecedented surge in SARS-CoV-2 infections and its dire consequences during the second wave of COVID-19, but the detailed report of the epidemiological based spatiotemporal incidences of the disease is missing. In the manuscript, we have applied various statistical approaches (correlation, hierarchical clustering) to decipher the pattern of pathogenesis of the circulating VoCs responsible for surge in the incidences. B.1.617.1 (Kappa) was the predominant VoC during the early phase of the second wave, whereas, Delta (B.1.617.2) or Delta-like (AY.x) VoC constitutes majority ($$&gt;90.17$$ &gt; 90.17 %) of the cases during the peak of the second wave. The correlation plot of Delta/Delta-like lineage demonstrates inverse correlation with other lineages including B.1.617.1, B.1.1.7, B.1, B.1.36.29 and B.1.36. The spatiotemporal analysis shows that most of the Indian states were affected during the peak of the second wave due to the Delta surge, and fall under the same cluster. The second cluster populated mostly by north-eastern states and the islands of India were minimally affected. The presence of signature mutations (T478K, D950N, E156G) along with L452K, D614G and P681R within the spike protein of Delta or Delta-like might cause elevation in the host cell attachment, increased transmission and altered antigenicity which in due course of time has replaced the other circulating variants.The timely assessment of new VoCs including Delta-like will provide a rationale for updating the diagnostic, vaccine development by medical industries and decision making by various agencies including government, educational institutions, and corporate industries.
  • A novel computational predictive biological approach distinguishes Integrin β1 as a salient biomarker for breast cancer chemoresistance
    Subhayan Das, Moumita Kundu, Atif Hassan, Aditya Parekh, Bikash Ch. Jena, Swati Mundre, Indranil Banerjee, Rajesh Yetirajam, Chandan K. Das, Anjan K. Pradhan, Swadesh K. Das, Luni Emdad, Pralay Mitra, Paul B. Fisher, Mahitosh Mandal
    Biochimica Et Biophysica Acta Molecular Basis of Disease, 2023
  • Correction to: ProFuMCell and ProModb: Web services for analyzing interaction‑based functionally localized protein modules in a cell (Journal of Molecular Modeling, (2022), 28, 6, (167), 10.1007/s00894-022-05133-8)
    Barnali Das, Pralay Mitra
    Journal of Molecular Modeling, 2023
  • A sequence space search engine for computational protein design to modulate molecular functionality
    Ayush Malik, Anupam Banerjee, Abantika Pal, Pralay Mitra
    Journal of Biomolecular Structure and Dynamics, 2023
  • Therapeutic targeting of RBPJ, an upstream regulator of ETV6 gene, abrogates ETV6-NTRK3 fusion gene transformations in glioblastoma
    Angana Biswas, Yetirajam Rajesh, Subhayan Das, Indranil Banerjee, Neelkamal Kapoor, Pralay Mitra, Mahitosh Mandal
    Cancer Letters, 2022
  • ProMoCell and ProModb: Web services for analyzing interaction-based functionally localized protein modules in a cell
    Barnali Das, Pralay Mitra
    Journal of Molecular Modeling, 2022
  • Modularity-based parallel protein design algorithm with an implementation using shared memory programming
    Abantika Pal, Rohith Mulumudy, Pralay Mitra
    Proteins Structure Function and Bioinformatics, 2022
  • Human prion protein: exploring the thermodynamic stability and structural dynamics of its pathogenic mutants
    Puspita Halder, Pralay Mitra
    Journal of Biomolecular Structure and Dynamics, 2022
  • A computational framework for modeling functional protein-protein interactions
    Abantika Pal, Debnath Pal, Pralay Mitra
    Proteins Structure Function and Bioinformatics, 2021
  • Protein Interaction Network-based Deep Learning Framework for Identifying Disease-Associated Human Proteins
    Barnali Das, Pralay Mitra
    Journal of Molecular Biology, 2021
  • High-Performance Whole-Cell Simulation Exploiting Modular Cell Biology Principles
    Barnali Das, Pralay Mitra
    Journal of Chemical Information and Modeling, 2021
  • An Evolutionary Profile Guided Greedy Parallel Replica-Exchange Monte Carlo Search Algorithm for Rapid Convergence in Protein Design
    Anupam Banerjee, Kuntal Pal, Pralay Mitra
    IEEE ACM Transactions on Computational Biology and Bioinformatics, 2021
  • Estimating Change in Foldability Due to Multipoint Deletions in Protein Structures
    Anupam Banerjee, Amit Kumar, Kushal Kanti Ghosh, Pralay Mitra
    Journal of Chemical Information and Modeling, 2020
  • Ebola Virus VP35 Protein: Modeling of the Tetrameric Structure and an Analysis of Its Interaction with Human PKR
    Anupam Banerjee, Pralay Mitra
    Journal of Proteome Research, 2020
  • ETV6 gene aberrations in non-haematological malignancies: A review highlighting ETV6 associated fusion genes in solid tumors
    Angana Biswas, Yetirajam Rajesh, Pralay Mitra, Mahitosh Mandal
    Biochimica Et Biophysica Acta Reviews on Cancer, 2020
  • Estimating the Effect of Single-Point Mutations on Protein Thermodynamic Stability and Analyzing the Mutation Landscape of the p53 Protein
    Anupam Banerjee, Pralay Mitra
    Journal of Chemical Information and Modeling, 2020
  • Boosting phosphorylation site prediction with sequence feature-based machine learning
    Shyantani Maiti, Atif Hassan, Pralay Mitra
    Proteins Structure Function and Bioinformatics, 2020
  • Delineation of crosstalk between HSP27 and MMP-2/MMP-9: A synergistic therapeutic avenue for glioblastoma management
    Y. Rajesh, Anupam Banerjee, Ipsita Pal, Angana Biswas, Subhayan Das, Kaushik Kumar Dey, Neelkamal Kapoor, Ananta Kumar Ghosh, Pralay Mitra, Mahitosh Mandal
    Biochimica Et Biophysica Acta General Subjects, 2019
  • Analyzing Change in Protein Stability Associated with Single Point Deletions in a Newly Defined Protein Structure Database
    Anupam Banerjee, Yaakov Levy, Pralay Mitra
    Journal of Proteome Research, 2019
  • Changing the Apoptosis Pathway through Evolutionary Protein Design
    David Shultis, Pralay Mitra, Xiaoqiang Huang, Jarrett Johnson, Naureen Aslam Khattak, Felicia Gray, Clint Piper, Jeff Czajka, Logan Hansen, Bingbing Wan, Krishnapriya Chinnaswamy, Liu Liu, Mi Wang, Jingxi Pan, Jeanne Stuckey, Tomasz Cierpicki, Christoph H. Borchers, Shaomeng Wang, Ming Lei, Yang Zhang
    Journal of Molecular Biology, 2019
  • A network-based zoning for parallel whole-cell simulation
    Barnali Das, Abhijeet Rajendra Patil, Pralay Mitra
    Bioinformatics, 2019
  • Ebolavirus interferon antagonists-protein interaction perspectives to combat pathogenesis
    Anupam Banerjee, Abantika Pal, Debnath Pal, Pralay Mitra
    Briefings in Functional Genomics, 2018
  • Protein Design Assisted Residue Conservation and Functional Stability Analysis for Bacterial Chemotaxis
    Shyantani Maiti, Pralay Mitra
    International Conference on Bioinformatics and Systems Biology Bsb 2018, 2018
  • Bacterial flagellar switching: a molecular mechanism directed by the logic of an electric motor
    Shyantani Maiti, Pralay Mitra
    Journal of Molecular Modeling, 2018
  • EvoDesign: De novo protein design based on structural and evolutionary profiles.
    Pralay Mitra, David Shultis, Yang Zhang
    Nucleic Acids Research, 2013
  • An Evolution-Based Approach to De Novo Protein Design and Case Study on Mycobacterium tuberculosis
    Pralay Mitra, David Shultis, Jeffrey R. Brender, Jeff Czajka, David Marsh, Felicia Gray, Tomasz Cierpicki, Yang Zhang
    Plos Computational Biology, 2013
  • How many protein-protein interactions types exist in nature?
    Leonardo Garma, Srayanta Mukherjee, Pralay Mitra, Yang Zhang
    Plos One, 2012
  • PRUNE and PROBE - Two modular web services for protein-protein docking
    P. Mitra, D. Pal
    Nucleic Acids Research, 2011
  • Using correlated parameters for improved ranking of protein-protein docking decoys
    Pralay Mitra, Debnath Pal
    Journal of Computational Chemistry, 2011
  • Combining Bayes classification and point group symmetry under Boolean framework for enhanced protein quaternary structure inference
    Pralay Mitra, Debnath Pal
    Structure, 2011
  • DockYard-a repository to assist modeling of protein-protein docking
    Pralay Mitra, Debnath Pal
    Journal of Molecular Modeling, 2011
  • Identifying the nature of the interface in protein-protein complexes
    Pralay Mitra
    Isb 2010 Proceedings International Symposium on Biocomputing, 2010
  • New measures for estimating surface complementarity and packing at protein-protein interfaces
    Pralay Mitra, Debnath Pal
    FEBS Letters, 2010
  • Interface of apoptotic protein complexes has distinct properties.
    Pralay Mitra, Riddhiman Dhar, Debnath Pal
    In Silico Biology, 2009
  • A graph theoretic approach to minimize total wire length in channel routing
    IEEE Region 10 Annual International Conference Proceedings TENCON, 2003

RECENT SCHOLAR PUBLICATIONS

  • A transformer-based method for the cap analysis of gene expression and gene expression tag associated capping region prediction in RNA
    DK Haldar, A Pramanick, C Mukherjee, P Mitra
    RNA biology 23 (1), 1-15 , 2026
    2026
  • Targeting of HSP27 and MMP-2/9 Crosstalk by High-Throughput Drug Repurposing Strategies Identifies Paroxetine as a Potential Candidate in Glioblastoma
    S Nandi, S Banerjee, D Manna, A Awasthi, A Biswas, A Das, B Mukherjee, ...
    Journal of Medicinal Chemistry 69 (4), 4659-4676 , 2026
    2026
  • Deep learning framework reveals drug combinations involving Dipeptidyl peptidase-4 inhibitors for treatment of Polycystic Ovarian Syndrome on a heterogeneous network
    S Dutta, P Mitra
    In Silico Research in Biomedicine, 100223 , 2026
    2026
  • PEPpip: A Vision-Inspired Explainable Deep Learning Framework for Sequence-Based Protein-Protein Interaction Prediction and Interaction Map Estimation
    S Ghosh, P Mitra
    IEEE Access , 2026
    2026
  • An Artificial Intelligence-based framework for protein interaction design with accelerated KAN-based Positive-Unlabeled learning
    S Ghosh, P Mitra
    bioRxiv, 2026.01. 28.702421 , 2026
    2026
  • Identification of a Novel miRNA Expression Signature for Lung Adenocarcinoma Using Systematic Machine Learning Optimization
    S Agrawal, P Mitra
    bioRxiv, 2026.01. 10.698764 , 2026
    2026
  • A Transformer based method for the Cap Analysis of Gene Expression and Gene Expression Tag associated 5’cap site prediction in RNA
    DK Haldar, A Pramanick, C Mukherjee, P Mitra
    bioRxiv, 2025.09. 21.677558 , 2025
    2025
    Citations: 1
  • ConfPred: ML-Based Conformational B-cell Epitope Prediction Using Novel Features
    P Gautam, P Mitra
    Proceedings of the 12th International Conference on Bioinformatics Research … , 2025
    2025
  • E (Q) AGNN-PPIS: Attention Enhanced Equivariant Graph Neural Network for Protein-Protein Interaction Site Prediction
    Animesh, R Suvvada, PK Bhowmick, P Mitra
    IEEE Transactions on Signal and Information Processing over Networks 11, 740-751 , 2025
    2025
    Citations: 2
  • HOPE survey: Insights from 1271 experts in women's health on homocysteine, calcium
    A Kumari, SK Mohakul, N Bhatnagar, J Shah, A Singh, P Mitra, ...
    BJOG-AN INTERNATIONAL JOURNAL OF OBSTETRICS AND GYNAECOLOGY 132, 197-197 , 2025
    2025
  • DeepPROTECTNeo: A Deep learning-based Personalized and RV-guided Optimization tool for TCR Epitope interaction using Context-aware Transformers
    D Das, S Bhaduri, A Pramanick, P Mitra
    bioRxiv, 2025.01. 04.631301 , 2025
    2025
    Citations: 1
  • rpcFold: residual parallel convolutional neural network to decipher RNA folding from RNA sequence
    N Sharma, P Mitra
    bioRxiv, 2024.08. 26.609824 , 2024
    2024
  • The molecular prognostic score, a classifier for risk stratification of high-grade serous ovarian cancer
    S Sarkar, SA Saha, A Swarnakar, A Chakrabarty, A Dey, P Sarkar, ...
    Journal of Ovarian Research 17 (1), 159 , 2024
    2024
    Citations: 6
  • Deciphering the lexicon of protein targets: a review on multifaceted drug discovery in the era of artificial intelligence
    S Nandi, S Bhaduri, D Das, P Ghosh, M Mandal, P Mitra
    Molecular Pharmaceutics 21 (4), 1563-1590 , 2024
    2024
    Citations: 24
  • MaTPIP: A deep-learning architecture with eXplainable AI for sequence-driven, feature mixed protein-protein interaction prediction
    S Ghosh, P Mitra
    Computer Methods and Programs in Biomedicine 244, 107955 , 2024
    2024
    Citations: 26
  • Parsers, Data Structures, and Algorithms for Macromolecular Analysis Toolkit (MAT): Design and Implementation
    G Kalyan, V Junghare, SJ S, P Mitra, A Chattopadhyay, S Hazra
    authorea , 2024
    2024
  • Deep Reinforcement Learning in Healthcare and Biomedical Research
    S Agrawal, P Mitra
    Deep Reinforcement Learning and Its Industrial Use Cases: AI for Real‐World … , 2024
    2024
    Citations: 4
  • A novel computational predictive biological approach distinguishes Integrin β1 as a salient biomarker for breast cancer chemoresistance
    S Das, M Kundu, A Hassan, A Parekh, BC Jena, S Mundre, I Banerjee, ...
    Biochimica et Biophysica Acta (BBA)-Molecular Basis of Disease 1869 (6), 166702 , 2023
    2023
    Citations: 13
  • A sequence space search engine for computational protein design to modulate molecular functionality
    A Malik, A Banerjee, A Pal, P Mitra
    Journal of Biomolecular Structure and Dynamics 41 (7), 2937-2946 , 2023
    2023
    Citations: 2
  • ProFuMCell and ProModb: Web services for analyzing interaction-based functionally localized protein modules in a cell (vol 28, 167, 2022)
    B Das, P Mitra
    JOURNAL OF MOLECULAR MODELING 29 (5) , 2023
    2023

MOST CITED SCHOLAR PUBLICATIONS

  • EvoDesign: de novo protein design based on structural and evolutionary profiles
    P Mitra, D Shultis, Y Zhang
    Nucleic acids research 41 (W1), W273-W280 , 2013
    2013
    Citations: 67
  • An Evolution-Based Approach to De Novo Protein Design and Case Study on Mycobacterium tuberculosis
    P Mitra, D Shultis, JR Brender, J Czajka, D Marsh, F Gray, T Cierpicki, ...
    PLoS computational biology 9 (10), e1003298 , 2013
    2013
    Citations: 55
  • How many protein-protein interactions types exist in nature?
    L Garma, S Mukherjee, P Mitra, Y Zhang
    PLoS One 7 (6), e38913 , 2012
    2012
    Citations: 42
  • Combining Bayes classification and point group symmetry under Boolean framework for enhanced protein quaternary structure inference
    P Mitra, D Pal
    Structure 19 (3), 304-312 , 2011
    2011
    Citations: 40
  • Delineation of crosstalk between HSP27 and MMP-2/MMP-9: A synergistic therapeutic avenue for glioblastoma management
    Y Rajesh, A Banerjee, I Pal, A Biswas, S Das, KK Dey, N Kapoor, ...
    Biochimica et Biophysica Acta (BBA)-General Subjects 1863 (7), 1196-1209 , 2019
    2019
    Citations: 38
  • ETV6 gene aberrations in non-haematological malignancies: A review highlighting ETV6 associated fusion genes in solid tumors
    A Biswas, Y Rajesh, P Mitra, M Mandal
    Biochimica et Biophysica Acta (BBA)-Reviews on Cancer 1874 (1), 188389 , 2020
    2020
    Citations: 36
  • New measures for estimating surface complementarity and packing at protein–protein interfaces
    P Mitra, D Pal
    FEBS letters 584 (6), 1163-1168 , 2010
    2010
    Citations: 29
  • MaTPIP: A deep-learning architecture with eXplainable AI for sequence-driven, feature mixed protein-protein interaction prediction
    S Ghosh, P Mitra
    Computer Methods and Programs in Biomedicine 244, 107955 , 2024
    2024
    Citations: 26
  • Deciphering the lexicon of protein targets: a review on multifaceted drug discovery in the era of artificial intelligence
    S Nandi, S Bhaduri, D Das, P Ghosh, M Mandal, P Mitra
    Molecular Pharmaceutics 21 (4), 1563-1590 , 2024
    2024
    Citations: 24
  • Estimating the effect of single-point mutations on protein thermodynamic stability and analyzing the mutation landscape of the p53 protein
    A Banerjee, P Mitra
    Journal of chemical information and modeling 60 (6), 3315-3323 , 2020
    2020
    Citations: 24
  • Changing the apoptosis pathway through evolutionary protein design
    D Shultis, P Mitra, X Huang, J Johnson, NA Khattak, F Gray, C Piper, ...
    Journal of molecular biology 431 (4), 825-841 , 2019
    2019
    Citations: 22
  • Boosting phosphorylation site prediction with sequence feature‐based machine learning
    S Maiti, A Hassan, P Mitra
    Proteins: Structure, Function, and Bioinformatics 88 (2), 284-291 , 2020
    2020
    Citations: 17
  • Using correlated parameters for improved ranking of protein–protein docking decoys
    P Mitra, D Pal
    Journal of Computational Chemistry 32 (5), 787-796 , 2011
    2011
    Citations: 17
  • PRUNE and PROBE—two modular web services for protein–protein docking
    P Mitra, D Pal
    Nucleic acids research 39 (suppl_2), W229-W234 , 2011
    2011
    Citations: 16
  • Genome surveillance of SARS-CoV-2 variants and their role in pathogenesis focusing on second wave of COVID-19 in India
    P Sarkar, S Banerjee, SA Saha, P Mitra, S Sarkar
    Scientific Reports 13 (1), 4692 , 2023
    2023
    Citations: 15
  • Analyzing change in protein stability associated with single point deletions in a newly defined protein structure database
    A Banerjee, Y Levy, P Mitra
    Journal of proteome research 18 (3), 1402-1410 , 2019
    2019
    Citations: 15
  • A novel computational predictive biological approach distinguishes Integrin β1 as a salient biomarker for breast cancer chemoresistance
    S Das, M Kundu, A Hassan, A Parekh, BC Jena, S Mundre, I Banerjee, ...
    Biochimica et Biophysica Acta (BBA)-Molecular Basis of Disease 1869 (6), 166702 , 2023
    2023
    Citations: 13
  • Therapeutic targeting of RBPJ, an upstream regulator of ETV6 gene, abrogates ETV6-NTRK3 fusion gene transformations in glioblastoma
    A Biswas, Y Rajesh, S Das, I Banerjee, N Kapoor, P Mitra, M Mandal
    Cancer Letters 544, 215811 , 2022
    2022
    Citations: 13
  • Ebola virus VP35 protein: modeling of the tetrameric structure and an analysis of its interaction with human PKR
    A Banerjee, P Mitra
    Journal of proteome research 19 (11), 4533-4542 , 2020
    2020
    Citations: 13
  • Ebolavirus interferon antagonists—protein interaction perspectives to combat pathogenesis
    A Banerjee, A Pal, D Pal, P Mitra
    Briefings in functional genomics 17 (6), 392-401 , 2018
    2018
    Citations: 12