BLMPred predicts linear B-cell epitopes using pre-trained protein language models and machine learning, outperforming existing tools on multiple datasets.

DOI 10.1016/j.csbj.2025.12.014

protein sequencemachine learning (classical)

𝕏 PostBluesky

BioinformaticsJournal of Molecular ModelingPeer-reviewedMay 25, 2022

ProFuMCell and ProModb: web services for analyzing interaction-based functionally localized protein modules in a cell

B.N. Das, Pralay Mitra

The paper introduces ProFuMCell and ProModb, web services that identify and analyze spatially localized protein modules in cells using interaction networks and KEGG pathway data.

DOI 10.1007/s00894-022-05133-8

protein structurestatistical model

𝕏 PostBluesky

BioinformaticsJournal of Molecular BiologyPeer-reviewedJul 14, 2021

Protein Interaction Network-based Deep Learning Framework for Identifying Disease-Associated Human Proteins

B.N. Das, Pralay Mitra

The paper introduces PINDeL, a GCN-based model for identifying disease-associated human proteins, achieving high accuracy and outperforming existing methods with experimentally verified results.

9 citations

humanprotein sequence

𝕏 PostBluesky

BioinformaticsbioRxivPreprintJun 3, 2021

Deciphering biological evolution exploiting the topology of Protein Locality Graph

B.N. Das, Pralay Mitra

This paper introduces a method using Protein Locality Graph topology to infer species trees by analyzing inter-module interactions in protein networks.

DOI 10.1101/2021.06.03.446976

protein structuregraph neural network

𝕏 PostBluesky