Ajamete Kaykas

This paper introduces a pooled CRISPR screening platform combined with self-supervised deep learning to infer gene function from morphological phenotypes without target-specific biomarkers.

The paper uses deep learning on images of iPSC-derived motor neurons with fALS mutations to identify disease-relevant phenotypes and molecular differences.

The paper benchmarks scRNA-seq methods and introduces CellSIUS, a tool that improves detection of rare cell populations and identifies their functional signatures in human stem cell differentiation.

This study shows that CRISPR/Cas9 induces toxicity in human pluripotent stem cells, which is dependent on TP53 and hinders genome engineering.