University of Sydney

Genomic foundation model on a Mamba, attention, and mixture-of-experts backbone, with 1M-token context for variant scoring and regulatory DNA design.

Molecular glue degrader design model that jointly generates the glue molecule and the E3 ligase-target ternary complex from unbound monomers.

Histopathology model reconstructing tissue-wide single-cell gene expression from H&E slides, using sparse TMA measurements as molecular anchors.

Hyperbolic protein language model for alignment-free phylogenetic inference, turning ESM2-650M embeddings into distance matrices for tree placement.

Retrieval-augmented framework for de novo peptide binder design that conditions generation on retrieved, structurally aligned binding evidence.

Multimodal viral foundation model over nucleotide and protein sequence, built for virus discovery, function annotation, and antibody design.

Spatiotemporal foundation model that learns representations directly from 4D functional MRI volumes for disease diagnosis and phenotype prediction.

Multi-omics instruction-tuned LLM that reads DNA, RNA, protein, and multi-molecule sequences and answers natural-language questions about them.

Spatial transcriptomics prediction from H&E slides, inferring spot-level expression and tumor microenvironment composition in breast cancer.

Unified DNA, RNA, and protein foundation model with 1.8B parameters, pretrained across 169,861 species to learn the central dogma from sequence.

Open large language models for natural science, fine-tuned on physics, chemistry, and materials science literature with automated instruction tuning.