King Abdullah University of Science and Technology

Physics-guided distillation that transfers 3D molecular dynamics knowledge into SMILES language models, improving MoleculeNet property prediction.

RNA modification profiling from nanopore direct RNA-seq signal; self-supervised pretraining resolves 11 modification types and extends to new ones.

Protein-protein interface prediction from 3D structure using face-centered surface fingerprints and geometric graph attention, at ROC AUC 0.89.

Diffusion protein language model for de novo design conditioned jointly on GO terms, InterPro domains, EC numbers, motifs, and backbone structure.

Cytogenetics foundation model detecting numerical and structural chromosome abnormalities from metaphase images, pretrained on 84,000 specimens.

Single-cell chromatin accessibility foundation model with genome-aware tokenization, pretrained on 1.97 million scATAC-seq cells across 30 tissues.

Single-cell foundation model inferring cis-regulatory relationships from scRNA-seq and scATAC-seq, pretrained on an atlas of 1.3 million cells.

Nanobody CDR design framework that alternates structure prediction, docking, and CDR generation in an expectation-maximization refinement loop.

Ultrasound foundation model pretrained by federated learning across 16 institutions, transferring to disease diagnosis and lesion segmentation.

Context-only BERT for bacterial protein function prediction, reading genomes as sentences of protein-cluster tokens with no sequence input.

Histopathology image translation with diffusion, moving H&E tiles between stains, tumor types, and organ sites and editing them from omics profiles.