Rahul Kaushik

Benchmarking Protein Language Models for Protein Crystallization

This study benchmarks protein language models for predicting protein crystallization propensity and identifies novel potentially crystallizable proteins.

Decoding Protein Aggregation through Computational Approach: Identification and Scoring of Aggregation-Prone Regions in Protein Sequences

This paper introduces APR-Score, a machine-learning method to identify aggregation-prone regions in protein sequences, achieving high accuracy in predicting these regions.

MATE-Pred: Multimodal Attention-based TCR-Epitope interaction Predictor

MATE-Pred predicts TCR-epitope binding affinity using multi-modal attention, outperforming baselines with +8.4% MCC and +5.5% AUC.

A novel consensus-based computational pipeline for rapid screening of antibody therapeutics for efficacy against SARS-CoV-2 variants of concern including omicron variant

This paper introduces a computational pipeline to predict binding affinity of SARS-CoV-2 variants to hACE2 and neutralizing antibodies, showing Omicron variants have reduced binding to most RBD-directed antibodies.

A novel structure-based approach for identification of vertebrate susceptibility to SARS-CoV-2: implications for future surveillance programmes

This study predicts SARS-CoV-2 spike protein binding affinity to ACE2 orthologs across 299 vertebrate species, revealing broad host range and potential for cross-species transmission.