Chee Keong Kwoh

AI4Loop uses deep learning to infer chromatin interactions from RNA-seq data, revealing increased interactions in tumors and identifying potential therapeutic compounds.

This study benchmarks deep learning methods for RNA tertiary structure prediction, finding that ML methods outperform non-ML methods but struggle with novel RNAs and non-Watson-Crick pairs.

ViPal improves influenza virulence prediction by integrating prior viral knowledge into machine learning models using genomic sequences.

The paper constructs a virulence network of Influenza A virus-host protein domain interactions using lethal dose data and domain interaction scoring to aid in disease modeling and mechanism discovery.

Jupytope extracts structural properties of viral epitopes from 3D structures and demonstrates their utility in distinguishing viral subtypes and clades.

IAV-CNN predicts influenza A virus antigenic variants using a 2D convolutional neural network with a new amino acid representation, achieving state-of-the-art performance on three datasets.

Packpred predicts the functional effect of missense mutations using a statistical potential and substitution matrix, outperforming existing methods on multiple datasets.

ChINN predicts chromatin interactions from DNA sequences, showing good performance across samples and identifying sequence features associated with interactions in CLL patient data.

This paper introduces GCATSL, a graph contextualized attention network for predicting synthetic lethality in human cancers, outperforming existing methods on multiple datasets.

VirPreNet predicts influenza A virus virulence using all 8 viral segments with a weighted ensemble CNN, achieving state-of-the-art performance and highlighting the importance of PB2 and HA segments.

This study develops alignment-free machine learning models to predict the lethality of novel human coronaviruses using genomic nucleotide sequences, achieving 96.7% accuracy on existing strains.

The paper uses rule-based meta-analysis to identify PB2 as a major determinant of influenza A virus virulence in mice, outperforming other protein sites in model performance.