Liisi Laaniste

The paper identifies TP53 and RB1 wild-type status as predictors of cytarabine sensitivity in gliomas using CRISPRi screening and machine learning analysis.

The paper introduces a contrastive fine-tuning method for single-cell foundation models to detect subtle transcriptomic changes in Perturb-seq data, outperforming traditional differential expression methods.

The paper introduces dynamic token adaptation to combine single-cell foundation models with DNA-sequence embeddings to predict gene regulation in different genetic contexts.

The paper uses single-cell Mendelian randomisation to identify cell-type specific genetic effects on brain disease and behaviour, revealing 118 genes with causal associations to 16 brain phenotypes.

This paper introduces CRAFT, a computational framework for drug target identification, and validates Csf1R as a novel anti-epileptic target using pre-clinical models.