BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine

Foundation models (FMs) have exhibited remarkable performance across a wide range of downstream tasks in various domains. Nevertheless, general-purpose FMs often face challenges when confronted with domain-specific problems, due to their limited access to the proprietary training data in a particular domain. In life science, a large portion of biomedical knowledge is encapsulated within heterogeneous biological data, such as molecular structures, wet-lab experiment results, and knowledge bases, which exhibit significant modality gaps with human natural language. In this paper, we introduce BioMedGPT, an open multimodal generative pre-trained transformer (GPT) for biomedicine, to bridge the gap between biomedical data and natural language. BioMedGPT allows users to easily "communicate" with various biological modalities through free text, which is the first of its kind. BioMedGPT aligns different biological modalities with the text modality via a large generative language model, namely, BioMedGPT-LM. We publish BioMedGPT-10B, which unifies the feature spaces of molecules, proteins, and natural language via encoding and alignment. Through fine-tuning, BioMedGPT-10B outperforms or is on par with human and significantly larger general-purpose foundation models on the biomedical QA task. It also demonstrates promising performance in the molecule QA and protein QA tasks, which could greatly accelerate the discovery of new drugs and therapeutic targets. In addition, BioMedGPT-LM-7B is the first large generative language model based on Llama2 in the biomedical domain, therefore is commercial friendly. Both BioMedGPT-10B and BioMedGPT-LM-7B are open-sourced to the research community. We also publish the datasets that are meticulously curated for the alignment of multi-modalities, i.e., PubChemQA and UniProtQA. All the models, codes, and datasets are publicly available.