Research Impact Overview

With 7 published papers and 152 citations, my research spans multiple domains including healthcare AI, computational biology, and machine learning applications. I’ve also contributed to the academic community through 25 peer reviews across prestigious venues like AAAI, ICLR, and CHIL.

Peer Review & Academic Service

Current Review Responsibilities (2024-2025)

  • AAAI 2025 - Program Committee Member & Reviewer
  • ICLR 2025 - Conference Reviewer
  • CHIL 2025 - Conference on Health, Inference, and Learning
  • ICLR 2024 - Machine Learning for Genomics Explorations Workshop
  • ICLR 2024 - Time Series for Health Workshop (Program Committee)

Review Statistics

  • Total Peer Reviews: 25 completed reviews
  • Average Review Quality: Consistently high-quality, constructive feedback
  • Expertise Areas: Machine Learning, Healthcare AI, Computational Biology

Published Research Papers

1. SAMbinder: Protein Binding Prediction Web Server

Agrawal, P., Mishra, G., & Raghava, G. P. S. (2020)
Frontiers in Pharmacology, 10, 1690

Research Focus: Developed a web server for predicting S-adenosyl-L-methionine binding residues of proteins from amino acid sequences.

Key Contributions:

  • Created an accessible web interface for protein binding prediction
  • Achieved high accuracy in predicting binding sites critical for drug development
  • Focused on SAM binding, which is crucial for treating arthritis, cancer, dementia, and depression
  • Made the tool open-source for the research community

Impact: This work has significant implications for drug discovery, particularly in identifying target sites for therapeutic interventions.

2. Explainable Disease Classification via Weakly-Supervised Segmentation

Joshi, A., Mishra, G., & Sivaswamy, J. (2020)
Interpretable and Annotation-Efficient Learning for Medical Image Computing: Third International Workshop, iMIMIC 2020, MIL3ID 2020, and LABELS 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4–8, 2020, Proceedings 3 (pp. 54–62). Springer International Publishing.

Research Focus: Developed explainable AI methods for medical image analysis using weakly-supervised learning techniques.

Key Contributions:

  • Achieved 97.86% accuracy in disease classification from medical images
  • Implemented U-Net architecture for segmentation with explainable predictions
  • Provided multi-class classification and segmentation of affected regions
  • Collaborated with 5 doctors to ensure clinical relevance

Impact: This work addresses the critical need for explainable AI in healthcare, enabling doctors to understand and trust AI-assisted diagnoses.

3. NAGbinder: N-acetylglucosamine Interaction Prediction

Patiyal, S., Agrawal, P., Kumar, V., Dhall, A., Kumar, R., Mishra, G., & Raghava, G. P. S. (2020)
Protein Science, 29(1), 201–210

Research Focus: Developed computational methods for identifying N-acetylglucosamine interacting residues in proteins.

Key Contributions:

  • Created novel algorithms for predicting protein-carbohydrate interactions
  • Achieved high accuracy in identifying interaction sites
  • Contributed to understanding glycoprotein interactions
  • Provided insights into protein modification processes

Impact: This research advances our understanding of protein-carbohydrate interactions, which are crucial for many biological processes and drug design.

4. In-Silico Drug Discovery using Protein-Small Molecule Interaction

Mishra, G., & Raghava, G. P. S. (2019)
PhD Thesis, Shiv Nadar University

Research Focus: Comprehensive research on computational approaches to drug discovery through protein-small molecule interaction analysis.

Key Contributions:

  • Developed novel machine learning approaches for drug discovery
  • Achieved 95.99% accuracy in protein-ligand interaction prediction
  • Created automated feature generation systems for molecular analysis
  • Established theoretical foundations for computational drug discovery

Impact: This thesis work laid the foundation for multiple subsequent research papers and practical applications in pharmaceutical research.

5. RF and RFID based Object Identification and Navigation System for the Visually Impaired

Mishra, G., Ahluwalia, U., Praharaj, K., & Prasad, S. (2019)
2019 32nd International Conference on VLSI Design and 2019 18th International Conference on Embedded Systems (VLSID) (pp. 533–534). IEEE

Research Focus: Developed assistive technology for visually impaired individuals using RF and RFID technologies.

Key Contributions:

  • Created a practical navigation system for accessibility
  • Integrated RF and RFID technologies for object identification
  • Designed user-friendly interfaces for visually impaired users
  • Demonstrated real-world applicability of the system

Impact: This work contributes to assistive technology and demonstrates the practical application of engineering solutions for social good.

6. Computing Wide Range of Protein/Peptide Features

Pande, A., Patiyal, S., Lathwal, A., Arora, C., Kaur, D., Dhall, A., … Raghava, G. P. S. (2019)
BioRxiv, 599126

Research Focus: Comprehensive computational framework for extracting diverse features from protein and peptide sequences and structures.

Key Contributions:

  • Developed automated feature extraction algorithms
  • Created comprehensive protein analysis pipeline
  • Established standardized methods for protein characterization
  • Contributed to open-source computational biology tools

Impact: This work provides essential tools for the computational biology community, enabling more efficient and standardized protein analysis.

7. SAMbinder: Web Server for SAM Binding Residue Prediction

Agrawal, P., Mishra, G., & Raghava, G. P. S. (2019)
BioRxiv, 625806

Research Focus: Early-stage development of the SAMbinder web server for predicting SAM binding residues.

Key Contributions:

  • Preliminary development of SAM binding prediction algorithms
  • Established proof-of-concept for web-based protein analysis
  • Created foundation for subsequent published work
  • Demonstrated feasibility of automated binding site prediction

Impact: This preprint work led to the development of the full SAMbinder system, contributing to drug discovery research.

Research Themes & Expertise

🏥 Healthcare AI & Medical Imaging

My research in medical imaging focuses on developing explainable AI systems that clinicians can trust and understand. The work on mammogram and X-ray analysis achieved exceptional accuracy while maintaining interpretability.

🧬 Computational Biology & Drug Discovery

Through protein-ligand interaction prediction and binding site identification, my research contributes to accelerating drug discovery processes. The development of web servers makes these tools accessible to the broader research community.

🤖 Machine Learning Applications

My work spans various machine learning applications, from assistive technology to computational biology, demonstrating the versatility and practical impact of AI solutions.

🔬 Open Science & Reproducibility

A consistent theme in my research is making tools and methods accessible through open-source web servers and detailed methodologies, contributing to reproducible science.

Current Research Interests

🧠 Large Language Models in Healthcare

Exploring applications of LLMs for medical text analysis, clinical decision support, and patient communication.

🔬 Multimodal AI for Drug Discovery

Integrating various data types (molecular, clinical, genomic) for more comprehensive drug discovery approaches.

🏭 AI in Manufacturing

Applying machine learning to pharmaceutical manufacturing processes for quality control and optimization.

🌐 Federated Learning for Healthcare

Developing privacy-preserving machine learning methods for sensitive medical data.