James R. Green

This work introduces a transformer-based model for lysine methylation site prediction, achieving state-of-the-art accuracy through multitask learning and validation with mass spectrometry.

This paper investigates using a fractal-based image representation and deep learning for predicting protein binding sites but concludes the approach is ineffective.

This study evaluates sequence-based protein-protein interaction predictors for therapeutic peptide engineering, finding similarity-based methods more effective than deep learning models for known targets.

The paper identifies two distinct astroglial phenotypes across mouse cortical development and reveals significant sex differences in developmental gene expression patterns.

The paper predicts the SARS-CoV-2 vs. human interactome using sequence-based PPI predictors and identifies high-confidence interactions to guide therapeutic design.

This paper introduces a multi-view co-training approach for miRNA prediction, improving classification accuracy using unlabelled data without requiring additional labelled training samples.

miPIE improves miRNA prediction by integrating expression-based and sequence-based features across six species, outperforming existing methods like miRDeep2 and miRanalyzer.

This study predicts human-Zika virus protein-protein interactions and designs synthetic peptides to disrupt these interactions as potential anti-Zika virus therapeutics.