Knowledge-Driven Feature Selection and Engineering for Genotype Data with Large Language Models.
Year: 2025
Type: article
Abstract: Predicting phenotypes with complex genetic bases based on a small, interpretable set of variant features remains a challenging task. Conventionally, data-driven approaches are used for this task, yet the high dimensional nature of genotype data makes the analysis and prediction difficult. Motivated by the biomedical knowledge encoded in pre-trained LLMs and the emerging applications for genetics, we set to examine the ability of LLMs in feature selection and engineering for tabular genotype data, with a novel knowledge-driven framework. We develop FREEFORM, Free-flow Reasoning and Ensembling for Enhanced Feature Output and Robust Modeling, designed with chain-of-thought and ensembling principles, to select and engineer features with the intrinsic knowledge of LLMs. Evaluated on two distinct genotype-phenotype datasets, genetic ancestry and hereditary hearing loss, we find this framework outperforms several data-driven methods, particularly on low-data regimes. FREEFORM is available as open-source framework at GitHub: https://github.com/PennShenLab/FREEFORM.
DOI: 10.17615/fjd2-j454
Authors: Li, Dawei, Duong-Tran, Duy, Wen, Zixuan, Liu, Xiaoxi, Yang, Shu, Lee, Joseph, Chen, Tianlong, Hou, Bojian, Shen, Li, Tan, Zhen, Baik, Jae Young
Institution: University of North Carolina at Chapel Hill
Language: English
Subfield: Genetics
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W6962759017
FWCI:
Cites:
Cited by:
Related to: