University of Bern

Three fixed ProtGPT2 fine-tunes specialized for metalloprotein generation, trained on ProteinMPNN-derived synthetic sequences.

Antibody language model pretrained only on CDR-H3 loops, giving embeddings for immune repertoire analysis and antibody sequence classification.

Generative antibody model that produces light-chain sequences conditioned on a heavy chain, pairing a RoBERTa encoder with a GPT-2 decoder.

Chest CT masked autoencoder pretrained on over 5,000 volumes, fine-tuned to classify interstitial lung disease under Fleischner Society criteria.

Whole-slide pathology embedding framework that ranks tiles, keeps only the 25 most informative, and encodes a slide in 2.27 seconds.

Generative toolkit that synthesizes six aligned immunohistochemistry markers from one H&E histopathology image, trained on unpaired stains.