Ran, T. | bioRxiv Science

bioRxiv2023

A Comprehensive Benchmark Study on Biomedical Text Generation and Mining with ChatGPT

In recent years, the development of natural language process (NLP) technologies and deep learning hardware has led to significant improvement in large language models(LLMs). The ChatGPT, the state-of-the-art LLM built on GPT-3.5, shows excellent capabilities in general language understanding and reasoning. Researchers also tested the GPTs on a variety of NLP related tasks and benchmarks and got excellent results. To evaluate the performance of ChatGPT on biomedical related tasks, this paper presents a comprehensive benchmark study on the use of ChatGPT for biomedical corpus, including article abstracts, clinical trials description, biomedical questions and so on. Through a series of experiments, we demonstrated the effectiveness and versatility of Chat-GPT in biomedical text understanding, reasoning and generation.

bioinformatics↗

bioRxiv2022

Physiology and structure of pathogenic Escherichia coli pOmpT reveal two substrate-binding sites

The pathogenicity of bacteria can be achieved by cleaving antimicrobial peptides (AMPs) through the outer membrane protease family (Omptins) to evade or resist the hosts innate immune response. The OmpT-like proteins in Escherichia coli are members of Omptins, which have highly conserved proteolytic activity. Here, sequence alignment and physiological studies have determined that pOmpT is a virulence factor with atypical proteolytic activity. Comparing pOmpT with cOmpT in terms of structure, proteolytic activity and target substrates, it is found that Asp267 and Ser276 of cOmpT are substrate-binding sites and help its catalytic center to cleave substrates (protamine,synthetic peptide or RNase 7). However, special structural features and the nature of residues Ser267 and Thr276 of pOmpT caused the inability of cleavage protamine, but allows it to specifically cleave the human AMP RNase 7. It is suggested that two sites are related with the substrate specificity. In short, we found that pOmpT presents a new structural basis for the specific recognition of substrates, and providing new clues for the development of antimicrobial drugs.

microbiology↗