Enock Niyonkuru

CDRPipe integrates single-cell and bulk transcriptomic perturbation data to improve drug repurposing predictions by combining complementary resources.

This study benchmarks large language models against a traditional diagnostic tool for genetic disease diagnosis using 5,213 case reports, finding LLMs lag behind in accuracy.

The paper replaces non-biomedical synonyms with biomedical terms to improve concept embeddings using Word2Vec, reducing mean intracluster distance by 8%.

AutoMAxO uses LLMs to semi-automate MAxO curation for rare diseases, identifying 538 confirmed disease-treatment annotations from 4,918 medical abstracts.