Shubham Choudhury

AntiFP2 predicts antifungal proteins from genomic and metagenomic data using an ensemble of ESM2, BLAST, and MERCI, achieving high accuracy through cross-validation and offering a scalable pipeline.

The paper predicts lncRNA-protein interacting pairs using embeddings from DNABERT-2 and ESM-2-t30, achieving high accuracy on an independent dataset.

The paper develops separate models for predicting neurotoxic peptides and neurotoxins using machine learning and protein language models, achieving high AUC scores and outperforming existing methods.

The paper uses large language models to predict pancreatic ductal adenocarcinoma from gene expression data by converting numerical features into peptide sequences.

HemoPI2.0 predicts peptide hemolysis and pHC50 from sequence; a hybrid of MERCI motif scoring and ESM2-t6 reaches AUC 0.909 on held-out peptides, beating the earlier tools tested.

The paper develops a hybrid model combining alignment-based and alignment-free methods to predict plant resistance proteins, achieving high AUROC scores and creating an online platform for this purpose.

This paper introduces CytoLNCpred, a method to predict cytoplasm-associated lncRNAs in 15 human cell lines using machine learning and DNABERT-2 embeddings, showing correlation-based models outperform LLM-based ones.

This paper develops a machine learning model to predict antifreeze proteins using evolutionary information, achieving higher accuracy than existing methods on an independent dataset.

This paper introduces ToxinPred 3.0, an improved method for predicting peptide toxicity using alignment-free machine/deep learning and ensemble approaches, achieving high accuracy and sensitivity.

This paper introduces AntiBP3, a hybrid method for predicting antibacterial peptides effective against gram-positive, gram-negative, and gram-variable bacteria, achieving high AUC scores on independent datasets.

This paper develops a fast method for predicting multi-label subcellular localization of mRNA at genome scale, achieving high AUROC scores using hybrid techniques.

This paper develops models to predict, scan, and design TNF-α inducing epitopes for human and mouse, achieving AUROC values up to 0.83 for human and 0.77 for mouse.

This paper develops methods to predict and design T1DM-associated peptides, achieving high accuracy with a hybrid approach and a webserver for peptide prediction.

This paper develops an ensemble model to predict phage-host interactions for phage therapy, achieving higher accuracy than existing methods across multiple taxonomic levels.