跳到正文
AI 科研动态
科学发现

LitGene：整合文本与基因本体的可解释基因表示学习模型

LitGene: an interpretable transformer model integrating text and ontology for gene representation learning

Nature · Machine Learning 主题预印本未入选
阅读原文

摘要

研究团队在 Nature Communications 发表 LitGene，一个通过对比学习把非结构化文本与 Gene Ontology 注释整合起来、改进基因表示的可解释 transformer 模型。

摘要由模型根据原文撰写，以原文为准。

正文 · 原文

Nature Communications (2026) Cite this article

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.

Abstract

Representation learning in genomics often relies on sequence, expression, and network data, thereby overlooking a wealth of insights in the scientific literature. Here, we present LitGene, an interpretable transformer-based model that refines gene representations by integrating unstructured textual information with Gene Ontology annotations through contrastive learning. In evaluations across eight benchmark tasks for protein properties, LitGene achieves competitive accuracy and exhibits zero-shot prediction of GO terms, KEGG pathways, and gene-disease associations. LitGene identified ANGPTL6 as a potential candidate gene for idiopathic pulmonary fibrosis (IPF), supported by its differential expression in independent IPF samples, illustrating LitGene’s utility for hypothesis generation. A SHAP-based interpretability tool highlights text features influencing predictions, while an automated literature-grounding framework provides corroborating support where available. Our results suggest that integrating textual and genetic information may help reduce biases associated with under-studied genes. The model is released as open-source code, along with a publicly accessible web interface at https://litgene.cs.unm.edu/, which allows users to submit gene names, disease names, drug names, or custom text (e.g., publication abstracts) to obtain evidence-based predictions of related biomedical entities.

Similar content being viewed by others

Acknowledgements

We thank the members of the Tumor AI Lab for helpful discussions and feedback on this work. We are grateful to the domain experts who reviewed the ANGPTL6/IPF candidate prediction for their clinical insight.

Funding

This work was supported by the Ovarian Cancer Research Alliance (Proposal/Award Number CRDGAI-2026-3-2438 to A.S.), by the National Institutes of Health, National Cancer Institute (NIH/NCI; Award Number 5R00CA248953-05 to A.S.), and by the National Institute of General Medical Sciences of the National Institutes of Health (NIH/NIGMS; Award Number R35GM166590 to A.S.).

Author information

Author notes

  1. These authors contributed equally: Oladimeji Macaulay, Ala Jararweh, David Arredondo.

Authors and Affiliations

  1. Comprehensive Cancer Center, The University of New Mexico, Albuquerque, NM, USA

    Oladimeji Macaulay, Ala Jararweh, David Arredondo, Luis E. Tafoya, Shrey Poshiya, Yue Hu, Olufunmilola M. Oyebamiji, Christopher I. Amos, Kushal Virupakshappa & Avinash Sahu

  2. Department of Computer Science, The University of New Mexico, Albuquerque, NM, USA

    Ala Jararweh, Yue Hu & Avinash Sahu

  3. Jordan University of Science and Technology, Irbid, Jordan

    Ala Jararweh

  4. Department of Computer Science, William & Mary College, Williamsburg, VA, USA

    Yanfu Zhang

Authors

  1. Oladimeji Macaulay
  2. Ala Jararweh
  3. David Arredondo
  4. Luis E. Tafoya
  5. Shrey Poshiya
  6. Yue Hu
  7. Olufunmilola M. Oyebamiji
  8. Yanfu Zhang
  9. Christopher I. Amos
  10. Kushal Virupakshappa
  11. Avinash Sahu

Corresponding authors

Correspondence to Ala Jararweh, Kushal Virupakshappa or Avinash Sahu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Macaulay, O., Jararweh, A., Arredondo, D. et al. LitGene: an interpretable transformer model integrating text and ontology for gene representation learning. Nat Commun (2026). https://doi.org/10.1038/s41467-026-78454-4

Download citation

  • Received: 14 October 2025

  • Accepted: 18 September 2026

  • Published: 16 October 2026

  • DOI: https://doi.org/10.1038/s41467-026-78454-4

注意转载授权 · 阅读原文

来源：Nature · Machine Learning 主题 · nature.com

引用原文

Nature · Machine Learning 主题. LitGene: an interpretable transformer model integrating text and ontology for gene representation learning[EB/OL]. (2026-10-16)[访问日期]. https://www.nature.com/articles/s41467-026-78454-4.