Applications of Large Language Models in Drug Development (IMAGE)
Caption
Large language models (LLMs) can be broadly applied across multiple key stages in drug development: (1) Target identification and drug screening. Llama-Gram, GPCR LLM, and ProtChat systems effectively predict drug-target interactions and facilitate the screening of specific targeted drugs. (2) Drug molecule design and optimization. 3DSMILES-GPT and FragGPT enable the innovative design of drug molecular structures, while the DrugAssist system optimizes drug molecular structures and enhances their performance. (3) Drug repurposing. ChatGPT and DrugReAlign effectively leverage the therapeutic potential of existing drugs. (4) Preclinical research. GPT-4, CancerGPT, and LEDAP models demonstrate significant potential in facilitating the evaluation of pharmacokinetic properties, drug toxicity, and drug-drug interactions. (5) Clinical trials. Large language models such as SEETrial support clinical decision-making through the extraction, management, and prediction of clinical trial data. (LLMs: large language models; PLLMs: protein large language models; GPCR: G protein-coupled receptor; FU-SMILES: fragment unordered simplified molecular input line system)
Credit
Anqi Lin, Xiuhui Fang, Aimin Jiang, Chang Qi, Wenyi Gan, Lingxuan Zhu, Weiming Mou, Dongqiang Zeng, Mingjia Xiao, Guangdi Chu, Shengkun Peng, Hank Z.H. Wong, Lin Zhang, Hengguo Zhang, Xinpei Deng, Quan Cheng, Haoran Zhang, Zhuocheng Zhong, Zhengrui Li, Bufu Tang, and Peng Luo
Usage Restrictions
Credit must be given to the creator.
License
CC BY