Jamie Soul

The paper develops a low-annotation-budget classifier using active learning and PubMedBERT to identify chondrogenesis regulators from PubMed abstracts, achieving high performance with fewer annotations.

The paper develops an automated pipeline using large language models to generate a gene perturbation transcriptomic atlas from public data, achieving high precision and recall in identifying perturbation groups.

This study quantifies DNA methylation changes during human articular cartilage development and identifies epigenomic mediators of osteoarthritis risk in prenatal joint tissues.

The paper identifies miR-199a/b-5p as pro-chondrogenic regulators and constructs a multi-miRNA kinetic model of chondrogenesis.

The paper identifies miR-140-3p as more abundant in human cartilage and shows its isomiRs have distinct functional targets.