All Competitors

Multimodal deep-learning framework that detects and localizes DNA lesions directly from native nanopore sequencing, built on the damage-aware LesionBERT foundation model.

A genomic foundation model that learns DNA representations through joint-embedding prediction in latent space rather than nucleotide reconstruction.

A family of genomic language models fine-tuned from a pretrained DNA language model to detect and classify antibiotic resistance genes beyond reference-database limits.

A 422M-parameter pan-viral genomic language model that produces fixed genome-level embeddings reused across viral classification tasks without re-training.

Bidirectional state-space (Mamba-2) genomic model for ultra-long extrachromosomal circular DNA, scaling linearly with sequence length.

BERT-based pre-trained model for DNA sequences using k-mer tokenization. Achieves state-of-the-art performance on promoter, splice site, and transcription factor binding prediction.