Debrupa Pal
Debrupa Pal has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Papri Ghosh
Narula Institute of Technology
7 shared publications - Subhram Das
Narula Institute of Technology
7 shared publications - Aurpan Majumder
National Institute of Technology
2 shared publications - Bansibadan Maji
Department of Electronics and Communication Engineering, National Institute of Technology, Durgapur, India
2 shared publications - Tanvir Habib Sardar
Dayananda Sagar University
2 shared publications Aniruddha Adhikary
Computer Application, Narula Institute of Technology,Kolkata,India,700109
1 shared publication
Latest Publications
- 13 August 2026
- Published by Springer Nature
- p. 91-115
Explainable AI-Driven Intrusion Detection Framework for Sustainable and Trustworthy IoT Ecosystems
- 13 August 2026
- Published by Springer Nature
- p. 91-115
Explainable AI-Driven Intrusion Detection Framework for Sustainable and Trustworthy IoT Ecosystems
- 13 August 2026
- Published by Springer Nature
- p. 229-252
Blockchain-Enabled Trust Management and Secure Data Sharing for Smart Cities in Society 6.0
- 13 August 2026
- Published by Springer Nature
- p. 229-252
Blockchain-Enabled Trust Management and Secure Data Sharing for Smart Cities in Society 6.0
- 6 August 2026
- Published by Bentham Science Publishers Ltd. in Recent Advances in Computer Science and Communications
- Vol. 19, 1-9
MiniVec Technique: An Innovative Binary-Based Approach to Protein Sequence Comparison
Introduction: In this study, a new method for comparing protein sequences, called the Minimal Moment Vector (MiniVec), is presented; it operates in the frequency domain using binary representations. Methods: Each protein sequence is broken down into 20 binary sequences, each representing one of the 20 standard amino acids. The Fast Fourier Transform (FFT) converts these binary vectors from a time-domain representation to a frequency-domain representation. The power spectrum for each component is normalized to a unit sum, and the descriptor is constructed as a 20-dimensional vector derived from the minimized second-order moments of these spectra. A Euclidean distance matrix is computed, and phylogenetic trees are generated using the UPGMA algorithm and visualized in iTOL. Result: The phylogenetic trees obtained from the MiniVec provide meaningful clustering across all datasets. Discussion: Qualitative analysis of the method suggests that species classified by MiniVec are as per biological classifications. Quantitative analysis shows that the proposed method performs better than other existing methods. Conclusion: The method’s accuracy is verified by testing it on four unique datasets: 9ND5 proteins, 50 Betaglobin, 19NADH, and 50 Coronavirus Spike Proteins. The qualitative evaluation and the Symmetric Distance (SD)-based quantitative comparisons demonstrate that the suggested method outperforms existing approaches and shows a high degree of consistency with existing biological classifications. The qualitative evaluation and Symmetric Distance (SD)- based quantitative comparisons demonstrate that the suggested method outperforms existing approaches and exhibits a high degree of consistency with established biological classifications.
- 6 August 2026
- Published by Bentham Science Publishers Ltd. in Recent Advances in Computer Science and Communications
- Vol. 19, 1-9
MiniVec Technique: An Innovative Binary-Based Approach to Protein Sequence Comparison
Introduction: In this study, a new method for comparing protein sequences, called the Minimal Moment Vector (MiniVec), is presented; it operates in the frequency domain using binary representations. Methods: Each protein sequence is broken down into 20 binary sequences, each representing one of the 20 standard amino acids. The Fast Fourier Transform (FFT) converts these binary vectors from a time-domain representation to a frequency-domain representation. The power spectrum for each component is normalized to a unit sum, and the descriptor is constructed as a 20-dimensional vector derived from the minimized second-order moments of these spectra. A Euclidean distance matrix is computed, and phylogenetic trees are generated using the UPGMA algorithm and visualized in iTOL. Result: The phylogenetic trees obtained from the MiniVec provide meaningful clustering across all datasets. Discussion: Qualitative analysis of the method suggests that species classified by MiniVec are as per biological classifications. Quantitative analysis shows that the proposed method performs better than other existing methods. Conclusion: The method’s accuracy is verified by testing it on four unique datasets: 9ND5 proteins, 50 Betaglobin, 19NADH, and 50 Coronavirus Spike Proteins. The qualitative evaluation and the Symmetric Distance (SD)-based quantitative comparisons demonstrate that the suggested method outperforms existing approaches and shows a high degree of consistency with existing biological classifications. The qualitative evaluation and Symmetric Distance (SD)- based quantitative comparisons demonstrate that the suggested method outperforms existing approaches and exhibits a high degree of consistency with established biological classifications.
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Biology and Bioinformatics
- Vol. 23 (3) , 1331-1342
A New Alignment-Free Approach to Compare Protein Secondary Structure Families Through SSEs
Understanding the similarity and dissimilarity among protein secondary structural families is essential for interpreting their structural features and functional roles. This study presents a new alignment-free approach for comparing protein families based on their Secondary Structure Elements (SSEs), classified into helix (H), strand (E), and coil (C). By numerically representing these SSEs, a four-component descriptor is derived using the moment of inertia, enabling the computation of distance matrices through four distinct distance metrics: Manhattan, Standard, Euclidean, and Maximum. Phylogenetic trees are subsequently constructed using the Neighbor-Joining (NJ) method. The methodology is evaluated across six benchmark datasets of various length representing four protein superfamilies, sourced from the Structural Classification of Proteins (SCOP). Among the distance measures tested, the Manhattan metric consistently yielded the most reliable results in capturing the relationships between structural families. Comparative analysis with other metrics and existing approaches underscores the robustness and effectiveness of the proposed method. This work demonstrates that the introduced descriptor and comparative framework provide a reliable, quantitative means of assessing structural similarity among protein SSEs of varying length, offering a valuable alignment-free method for structural bioinformatics and protein classification.
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Biology and Bioinformatics
- Vol. 23 (3) , 1331-1342
A New Alignment-Free Approach to Compare Protein Secondary Structure Families Through SSEs
Understanding the similarity and dissimilarity among protein secondary structural families is essential for interpreting their structural features and functional roles. This study presents a new alignment-free approach for comparing protein families based on their Secondary Structure Elements (SSEs), classified into helix (H), strand (E), and coil (C). By numerically representing these SSEs, a four-component descriptor is derived using the moment of inertia, enabling the computation of distance matrices through four distinct distance metrics: Manhattan, Standard, Euclidean, and Maximum. Phylogenetic trees are subsequently constructed using the Neighbor-Joining (NJ) method. The methodology is evaluated across six benchmark datasets of various length representing four protein superfamilies, sourced from the Structural Classification of Proteins (SCOP). Among the distance measures tested, the Manhattan metric consistently yielded the most reliable results in capturing the relationships between structural families. Comparative analysis with other metrics and existing approaches underscores the robustness and effectiveness of the proposed method. This work demonstrates that the introduced descriptor and comparative framework provide a reliable, quantitative means of assessing structural similarity among protein SSEs of varying length, offering a valuable alignment-free method for structural bioinformatics and protein classification.
- 6 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Quantum Simulation of a New Multivariate Prediction Model SEIRDVIms to Assess the Impacts of Social Restriction and Vaccination on Spreading Disease Transmission and Mortality
This study deals with the challenge posed by the emergence of multiple versions of an infectious disease, each exhibiting different transmission and mortality characteristics. A new compartmental model, SEIRDVIms, is developed to examine the influence of vaccination levels and social restriction measures while considering two virus strains. The objective is to maximize hospital bed availability and minimize mortality, and this optimization problem is reformulated as an energy minimization task using a Binary Quadratic Model and solved on a D-Wave Quantum Annealer. The outputs demonstrate that quantum-assisted social restriction strategies lead to fewer infections and deaths compared to situations without restrictions. Specifically, over a 60 -days period, the model predicts 265 deaths under quantum-guided restrictions versus 383 without restrictions. The findings also show that stricter social restrictions consistently reduce infection levels, while lower partial immunity increases infection rates under fixed restriction conditions. Overall, this study highlights the efficiency of quantum-assisted societal restriction rules in decreasing disease spread and mortality.
- 6 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Quantum Simulation of a New Multivariate Prediction Model SEIRDVIms to Assess the Impacts of Social Restriction and Vaccination on Spreading Disease Transmission and Mortality
This study deals with the challenge posed by the emergence of multiple versions of an infectious disease, each exhibiting different transmission and mortality characteristics. A new compartmental model, SEIRDVIms, is developed to examine the influence of vaccination levels and social restriction measures while considering two virus strains. The objective is to maximize hospital bed availability and minimize mortality, and this optimization problem is reformulated as an energy minimization task using a Binary Quadratic Model and solved on a D-Wave Quantum Annealer. The outputs demonstrate that quantum-assisted social restriction strategies lead to fewer infections and deaths compared to situations without restrictions. Specifically, over a 60 -days period, the model predicts 265 deaths under quantum-guided restrictions versus 383 without restrictions. The findings also show that stricter social restrictions consistently reduce infection levels, while lower partial immunity increases infection rates under fixed restriction conditions. Overall, this study highlights the efficiency of quantum-assisted societal restriction rules in decreasing disease spread and mortality.
- 2 January 2026
- Published by Springer Nature
- p. 292-300
A Novel Numerical Representation-Based Approach for Protein Sequence Comparison Using Inter-Coefficient Difference and FFT
- 2 January 2026
- Published by Springer Nature
- p. 292-300
A Novel Numerical Representation-Based Approach for Protein Sequence Comparison Using Inter-Coefficient Difference and FFT
- 1 January 2026
- Published by Springer Nature
- p. 271-279
Machine Learning Approaches for Spam Email Detection: A Comparative Analysis of Classification Algorithms
- 1 January 2026
- Published by Springer Nature
- p. 271-279
Machine Learning Approaches for Spam Email Detection: A Comparative Analysis of Classification Algorithms
- 1 January 2026
- Published by Springer Nature
- p. 280-290
Frequency-Domain Analysis of Protein Secondary Structures Using Max-Min Moment Vectors
- 1 January 2026
- Published by Springer Nature
- p. 280-290
Frequency-Domain Analysis of Protein Secondary Structures Using Max-Min Moment Vectors
- 9 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
The Use of Interpretable AI Models in Breast Cancer Risk and Detection: A Scoping Review Approach
Artificial intelligence (AI) has transformed healthcare, with data-driven algorithms gaining popularity for clinical applications. Despite their promise, many such models are perceived as “black boxes” due to their complexity, limiting their trust among clinicians. To address this, explainable AI (XAI) has emerged, offering insights into AI decision-making. This scoping review explores how XAI has been applied to breast cancer detection and risk prediction. A systematic search across Scopus, IEEE Xplore, PubMed, and Google Scholar (top 50 results) was conducted for peer-reviewed literature from January 2017 to July 2023. From this search, 30 relevant studies were identified. The findings show that SHapley Additive exPlanations (SHAP) is the most widely used modelagnostic XAI method in breast cancer studies. SHAP excels in interpreting predictions, identifying biomarkers, and supporting prognosis and survival assessments, particularly in tree-based machine learning models. Its popularity stems from being versatile, easy to implement, and highly compatible with ensemble models. Overall, the adoption of explainable AI improves the transparency, fairness, and clinical utility of AI tools, paving the way for more trustworthy and effective healthcare technologies.
- 9 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
The Use of Interpretable AI Models in Breast Cancer Risk and Detection: A Scoping Review Approach
Artificial intelligence (AI) has transformed healthcare, with data-driven algorithms gaining popularity for clinical applications. Despite their promise, many such models are perceived as “black boxes” due to their complexity, limiting their trust among clinicians. To address this, explainable AI (XAI) has emerged, offering insights into AI decision-making. This scoping review explores how XAI has been applied to breast cancer detection and risk prediction. A systematic search across Scopus, IEEE Xplore, PubMed, and Google Scholar (top 50 results) was conducted for peer-reviewed literature from January 2017 to July 2023. From this search, 30 relevant studies were identified. The findings show that SHapley Additive exPlanations (SHAP) is the most widely used modelagnostic XAI method in breast cancer studies. SHAP excels in interpreting predictions, identifying biomarkers, and supporting prognosis and survival assessments, particularly in tree-based machine learning models. Its popularity stems from being versatile, easy to implement, and highly compatible with ensemble models. Overall, the adoption of explainable AI improves the transparency, fairness, and clinical utility of AI tools, paving the way for more trustworthy and effective healthcare technologies.
- 1 May 2025
- Published by Springer Nature
- p. 471-483
Exploring Protein–Protein Interaction Network Alignment: Bridging Pathway Comparison to Global Alignment
- 1 May 2025
- Published by Springer Nature
- p. 471-483
Exploring Protein–Protein Interaction Network Alignment: Bridging Pathway Comparison to Global Alignment