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

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.

Machine learning–based validation of Human Phenotype Ontology (HPO) terms for systemic autoinflammatory diseases using the Eurofever Registry: the ODINO project
Caterina Matucci-Cerinic, Giacomo Cavalca, Matteo Vergani +7
Frontiers in Immunology12 Oct 2026Peer-reviewedCC BY 4.0Full textMolecular biology & gene regulationPMCCrossrefEurope PMC
A novel LLM-based GPT-neo transformer with machine learning architecture for promoters prediction in Agrobacterium
Nagwan Abdel Samee, Rawan Talaat, Ali Raza +3
Scientific Reports27 Oct 2026Peer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCrossref
Interpretable Deep Learning of Endogenous Fluorophore Concentration and Entropy for Lung Tissue Classification
Z. Yin, M. Xu, L. Virany +1
bioRxiv26 Oct 2026PreprintAll rights reservedFull textBiophysicsbioRxiv
scDRP: disentangled representation learning for predicting single-cell responses to perturbations and estimating individual treatment effects
Briefings in bioinformatics1 Sep 2026Peer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC
Representation learning for low-data protein fitness prediction using sequence–structure embeddings and graph neural networks
Chanoknun Phunnasorn, Narupat Hongdilokkul, Wasakorn Laesanklang +2
Scientific Reports16 Oct 2026Peer-reviewedCC BY-NC-ND 4.0Full textMolecular biology & gene regulationCrossref

Cite

BibTeX RIS

BibTeX

@article{macaulay2026litgene,
  title = {{LitGene: an interpretable transformer model integrating text and ontology for gene representation learning}},
  author = {Oladimeji Macaulay and Ala Jararweh and David Arredondo and Luis E. Tafoya and Shrey Poshiya and Yue Hu and Olufunmilola M. Oyebamiji and Yanfu Zhang and Christopher I. Amos and Kushal Virupakshappa and Avinash Sahu},
  journal = {Nature Communications},
  year = {2026},
  month = oct,
  doi = {10.1038/s41467-026-78454-4},
  url = {https://www.nature.com/articles/s41467-026-78454-4},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - LitGene: an interpretable transformer model integrating text and ontology for gene representation learning
AU  - Oladimeji Macaulay
AU  - Ala Jararweh
AU  - David Arredondo
AU  - Luis E. Tafoya
AU  - Shrey Poshiya
AU  - Yue Hu
AU  - Olufunmilola M. Oyebamiji
AU  - Yanfu Zhang
AU  - Christopher I. Amos
AU  - Kushal Virupakshappa
AU  - Avinash Sahu
PY  - 2026
DA  - 2026/10/16
JO  - Nature Communications
DO  - 10.1038/s41467-026-78454-4
UR  - https://www.nature.com/articles/s41467-026-78454-4
AB  - 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.
SN  - 2041-1723
ER  -

Abstract

Related

Cite