University of Pittsburgh

RNA foundation model for m6A epitranscriptomics, pretrained on MeRIP-seq peak sequences to call base-resolution sites, regulator binding, and decay.

Structure-based drug design model that unifies de novo generation, docking, conformer generation, and pharmacophore conditioning via flow matching.

Histopathology model predicting homologous recombination deficiency from H&E slides in ovarian cancer, reaching 0.846 AUC and 0.938 specificity.

Site-specific structure prediction conditioning AlphaFold3 diffusion on a fixed receptor and known binding pocket. 81.2% success on PoseBusters V2.

Spatial proteomics imputation model inferring surface protein abundance from transcriptomics-only tissue sections via dual graph attention networks.

Autoregressive transformer pretrained on 2,000 hours of intracortical spiking activity, decoding motor intent across subjects, species, and tasks.

Adenylation domain substrate specificity prediction from frozen ESM-2 embeddings, with zero-shot calls on substrates absent from training.

Vector-based virtual screening model that co-embeds proteins and small molecules so a drug-target interaction reduces to a single dot product.

Vision-language foundation model pre-trained on screening mammogram-report pairs to improve data efficiency and robustness in breast cancer detection.

Spatial proteomics imputation from a 7-plex immunofluorescence panel, generating in silico CODEX expression for 33 more biomarkers per cell.

Histopathology patch encoder giving 1024-dimensional embeddings for slide search and cancer subtyping, trained on TCGA with weak slide labels.