BGI Research

Gene representation framework fusing DNA, transcript, protein, text, and single-cell embeddings into one latent space that survives missing views.

Phylogeny-aware genome annotation model predicting exons, introns, UTRs and repeats directly from eukaryotic DNA, with no RNA or protein evidence.

Genomic foundation model for rice, pretrained on 422 Oryza genomes with a 1 Mbp context window and a 1.25B-parameter mixture-of-experts transformer.

Single-cell foundation model combining regulatory network priors with a Mamba backbone for clustering, batch integration, and perturbation modeling.

Cross-modal single-cell foundation model that aligns gene-expression profiles with LLM-enriched cell descriptions in a shared embedding space.

470M-parameter microbial genome foundation model trained on 234.5B base pairs for multi-scale genomic representation and trait prediction.

Transcriptomic foundation model pretrained on 67M single-cell and spatial profiles, modeling gene expression and inter-cellular dependencies.