Publications

2026

1. NeurIPS

   Leak-CURBER: A Leakage-Controlled Multimodal Evaluation Benchmark for Enzymatic Reaction Tasks

   Adhil Ahmed P M Shums*, Roshan Balaji*, and Nirav Pravinbhai Bhatt

   In The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS), Evaluations and Datasets Track, 2026

   * Equal contribution

   HTML
2. arXiv

   An Integrative Computational Approach to Predict Viral Epitopes by Targeting the MHC-TCR Complexation

   Jaya Vasavi Pamidimukkala, Roshan Balaji, Nirav Pravinbhai Bhatt, and 1 more author

   arXiv preprint arXiv:2609.03182, 2026

   arXiv
3. JCIM

   Functional Groups are All you Need for Chemically Interpretable Molecular Property Prediction

   Roshan Balaji, Joe Bobby, and Nirav Pravinbhai Bhatt

   Journal of Chemical Information and Modeling, 2026

   HTML
4. bioRxiv

   Interpretable machine learning meets systems biology to decode genotype-phenotype maps

   R M Rajeeva Lokshanan, Roshan Balaji, Himanshu Sinha, and 1 more author

   bioRxiv preprint 2026.03.16.712082, 2026

   HTML
5. AAAI

   BiCA: Effective Biomedical Dense Retrieval with Citation-Aware Hard Negatives

   Aarush Sinha, Roshan Balaji, and Nirav Pravinbhai Bhatt

   In Proceedings of the AAAI Conference on Artificial Intelligence, 2026

   Oral presentation (top 5%)

   HTML

2025

1. ICML-W

   NovoMolGen: Rethinking Molecular Language Model Pretraining

   Kamran Chitsaz*, Roshan Balaji*, Quentin Fournier, and 2 more authors

   In ICML 2025 Generative AI and Biology (GenBio) Workshop, 2025

   * Equal contribution

   arXiv HTML
2. ICML-W

   Intrinsic Evaluation of DNA Embeddings in Genome Language Models: Insights from Yeast Genomic Sequences

   Ruhaib Muhammad, Rajeeva Lokshanan Reguna Madhan, Roshan Balaji, and 1 more author

   In ICML 2025 Generative AI and Biology (GenBio) Workshop, 2025

   HTML

2023

1. 

   Chemically Interpretable Molecular Representation for Property Prediction

   Roshan M S B, and Nirav Pravinbhai Bhatt

   In Third Conference on Deployable AI, 2023

   Best paper award

   Abs HTML PDF

   Molecular property prediction using a molecule’s structure is a crucial step in drug and novel material discovery, as computational screening approaches rely on predicted properties to refine the existing design of molecules. Although the problem has existed for decades, it has recently gained attention due to the advent of big data and deep learning. On average, one FDA drug is approved for 250 compounds entering the preclinical research stage, requiring screening of chemical libraries containing more than 20000 compounds. In-silico property prediction approaches using learnable representations increase the pace of development and reduce the cost of discovery. We propose developing molecule representations using functional groups in chemistry to address the problem of deciphering the relationship between a molecule’s structure and property. Functional groups are substructures in a molecule with distinctive chemical properties that influence its chemical characteristics. These substructures are found by (i) curating functional groups annotated by chemists and (ii) mining a large corpus of molecules to extract frequent substructures using a pattern-mining algorithm. We show that the Functional Group Representation (FGR) framework beats state-of-the-art models on several benchmark datasets while ensuring explainability between the predicted property and molecular structure to experimentalists.