AbLang2 is a Transformer language model developed by the Oxford Protein Informatics Group specifically for antibody sequences. It can perform antibody sequence analysis, restoration, and representation learning, providing a powerful computational tool for antibody design and research.

Natural Language ProcessingTransformersOther

This is a high-precision model specifically designed for biomedical entity recognition. It is fine-tuned based on the deberta-v3-base architecture and can identify biomedical entities such as proteins, DNA, RNA, cell lines, and cell types, providing an enterprise-level solution for clinical and research applications.

Natural Language ProcessingTransformersMultiple Languages

This is a model specifically designed for gene/protein entity recognition, capable of accurately identifying and extracting information about gene and protein mentions in biomedical texts. The model is trained on the BC2GM dataset, featuring high precision and domain-specific optimization, providing reliable support for clinical and research applications.

Natural Language ProcessingTransformersEnglish

OpenMed-NER-ProteinDetect-MultiMed-568M is an advanced model specifically designed for biomedical entity recognition. Based on the bge-m3 architecture, it has 568M parameters. This model is trained on the FSU dataset and can accurately identify various biomedical entities, including proteins, protein complexes, protein families, etc. It has extremely high practical value in clinical and research applications.

Natural Language ProcessingTransformersEnglish

Trias is an encoder-decoder language model designed for reverse translating protein sequences into codon sequences, trained on 10 million mRNA coding sequences from 640 vertebrate species.

Scientific ComputingSafetensors

This is an autoregressive protein language model specifically designed for generating paired antibody libraries. The model is pre-trained on unpaired heavy and light chain sequences from the Observed Antibody Space (OAS) and fine-tuned on paired sequences, with good generalization ability.

Scientific ComputingTransformers

The ProtST framework enhances the pre-training and understanding of protein sequences through biomedical text, constructs the ProtDescribe dataset, designs three pre-training tasks, and supports supervised learning and zero-shot prediction.

Scientific ComputingTransformers

A sequence classifier based on the ESM-2 protein language model, designed for zero-shot classification tasks of protein sequences.

Natural Language ProcessingTransformers

AbLang is an antibody language model specifically designed for processing antibody sequences, particularly heavy chain sequences. The model is trained on uppercase amino acid letters and is suitable for protein feature extraction and downstream task fine-tuning.

Scientific ComputingTransformers

This is a named entity recognition model fine-tuned on PubMedBERT, specifically designed to identify gene and protein entities in biomedical texts.

Natural Language ProcessingTransformersEnglish

This model is a fine-tuned version based on Rostlab/prot_bert, designed for tasks involving the relationship between protein sequences and SMILES molecular representations.

Natural Language ProcessingTransformers

This model is trained on the jnlpba dataset, fine-tuned based on the pre-trained PubMed version of RoBERTa, specifically designed to identify biomedical entities such as genes, DNA, RNA, and proteins

Natural Language ProcessingTransformersMultiple Languages