Alexandrina Pancheva

This paper uses self-supervised AI to identify under-appreciated stromal morphologies in lung adenocarcinoma linked to poor prognosis, independent of current clinical schemas.

PLM-interact improves PPI prediction by jointly encoding protein pairs, achieving 16-28% AUPR gains across multiple species.

The paper introduces a topic modeling method using LDA to detect gene expression changes in interacting cells from scRNA-seq data, applied to synthetic and real datasets.