Search

Objective: Most existing fine-tuned biomedical large language models (LLMs) focus on enhancing performance in monolingual biomedical question answering and conversation tasks. To investigate the effectiveness of the fine-tuned LLMs on diverse biomedical NLP tasks in different languages, We present Taiyi, a bilingual fine-tuned LLM for diverse biomedical tasks. Materials and Methods: We first curated a comprehensive collection of 140 existing biomedical text mining datasets (102 English and 38 Chinese datasets) across over 10 task types. Subsequently, a two-stage strategy is proposed for supervised fine-tuning to optimize the model performance across varied tasks. Results: Experimental results on 13 test sets covering named entity recognition, relation extraction, text classification, question answering tasks demonstrate that Taiyi achieves superior performance compared to general LLMs. The case study involving additional biomedical NLP tasks further shows Taiyi's considerable potential for bilingual biomedical multi-tasking. Conclusion: Leveraging rich high-quality biomedical corpora and developing effective fine-tuning strategies can significantly improve the performance of LLMs within the biomedical domain. Taiyi shows the bilingual multi-tasking capability through supervised fine-tuning. However, those tasks such as information extraction that are not generation tasks in nature remain challenging for LLM-based generative approaches, and they still underperform the conventional discriminative approaches of smaller language models.

Nucleophosmin (NPM1) is a ubiquitously expressed nucleolar protein with a wide range of biological functions. In 30% of acute myeloid leukemia (AML), the terminal exon of NPM1 is often found mutated, resulting in the addition of a nuclear export signal and a shift of the protein to the cytoplasm (NPM1c). AMLs carrying this mutation have aberrant expression of the HOXA/B genes, whose overexpression leads to leukemogenic transformation. Here, for the first time, we comprehensively prove that NPM1c binds to a subset of active gene promoters in NPM1c AMLs, including well-known leukemia-driving genes-HOXA/B cluster genes and MEIS1. NPM1c sustains the active transcription of key target genes by orchestrating a transcription hub and maintains the active chromatin landscape by inhibiting the activity of histone deacetylases. Together, these findings reveal the neomorphic function of NPM1c as a transcriptional amplifier for leukemic gene expression and open up new paradigms for therapeutic intervention., Significance: NPM1 mutation is the most common mutation in AML, yet the mechanism of how the mutant protein results in AML remains unclear. Here, for the first time, we prove mutant NPM1 directly binds to active chromatin regions and hijacks the transcription of AML-driving genes. See related article by Uckelmann et al., p. 746. This article is highlighted in the In This Issue feature, p. 517., (©2022 The Authors; Published by the American Association for Cancer Research.)