Knowledge-Driven Feature Selection and Engineering for Genotype Data with Large Language Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915244473843712 |
|---|---|
| author | Lee, Joseph Yang, Shu Baik, Jae Young Liu, Xiaoxi Tan, Zhen Li, Dawei Wen, Zixuan Hou, Bojian Duong-Tran, Duy Chen, Tianlong Shen, Li |
| author_facet | Lee, Joseph Yang, Shu Baik, Jae Young Liu, Xiaoxi Tan, Zhen Li, Dawei Wen, Zixuan Hou, Bojian Duong-Tran, Duy Chen, Tianlong Shen, Li |
| contents | Predicting phenotypes with complex genetic bases based on a small, interpretable set of variant features remains a challenging task. Conventionally, data-driven approaches are utilized for this task, yet the high dimensional nature of genotype data makes the analysis and prediction difficult. Motivated by the extensive knowledge encoded in pre-trained LLMs and their success in processing complex biomedical concepts, 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-shot regimes. FREEFORM is available as open-source framework at GitHub: https://github.com/PennShenLab/FREEFORM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_01795 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Knowledge-Driven Feature Selection and Engineering for Genotype Data with Large Language Models Lee, Joseph Yang, Shu Baik, Jae Young Liu, Xiaoxi Tan, Zhen Li, Dawei Wen, Zixuan Hou, Bojian Duong-Tran, Duy Chen, Tianlong Shen, Li Machine Learning Computation and Language Genomics Predicting phenotypes with complex genetic bases based on a small, interpretable set of variant features remains a challenging task. Conventionally, data-driven approaches are utilized for this task, yet the high dimensional nature of genotype data makes the analysis and prediction difficult. Motivated by the extensive knowledge encoded in pre-trained LLMs and their success in processing complex biomedical concepts, 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-shot regimes. FREEFORM is available as open-source framework at GitHub: https://github.com/PennShenLab/FREEFORM. |
| title | Knowledge-Driven Feature Selection and Engineering for Genotype Data with Large Language Models |
| topic | Machine Learning Computation and Language Genomics |
| url | https://arxiv.org/abs/2410.01795 |