Wesley De Neve

This study uses deep learning to show that shorter and multiple U2-type introns improve splice site prediction in Arabidopsis thaliana.

This paper introduces a DNA sequence imaging method for splice site prediction, showing that DFCP outperforms FCGR using deep learning on Arabidopsis and human data.

This paper introduces a frequency-blended diffusion model to generate biologically realistic splice site sequences, showing improved motif conservation and model transferability.

This study evaluates a multitask learning model for predicting splice sites and translation initiation sites, finding comparable performance to single-task models with minor statistical differences.

This study develops a machine learning pipeline to predict Parkinson's disease severity using CSF-MS data and identifies potential biomarkers.

CRISPR-Cas-Docker predicts optimal crRNA-Cas pairs using in silico docking and machine learning classification.

This study optimizes RNA-protein interactions for CRISPR-Cas13-based antimicrobials by improving in silico docking of crRNAs with Cas13 proteins.

This paper uses accurate structure prediction to analyze anti-CRISPR proteins and identifies new strategies for protein drug design.

The paper develops SECRiFY, a method to assess secretability of protein fragments in yeast, revealing intrinsic disorder and flexibility as key factors.