aiqbench analysis
SoftGene advances genomic annotation by integrating protein language model embeddings with LLM prompting to capture molecular structure beyond symbolic gene names. This approach demonstrates that incorporating amino acid sequence information directly improves the accuracy of functional genomics tasks like Gene Ontology classification. The work highlights a critical intersection where biological data structures enhance the reasoning capabilities of large language models in specialized scientific domains.
SoftGene: Protein Language Model-Enhanced Soft Prompting for Interpretable Gene Set Annotation
arXiv:2610.03029v1 Announce Type: new Abstract: Gene set analysis is a cornerstone of functional genomics, yet it remains labor-intensive and heavily dependent on manual curation and expert biological interpretation. While Large Language Models (LLMs) have emerged as powerful tools for genomic reasoning and annotation, most existing approaches rely on symbolic gene names and fail to capture domain-specific biological structure, particularly protein sequence information that governs molecular activity, interactions, and downstream gene function. In this work, we propose SoftGene, a novel framework for LLM-based gene set annotation that leverages the hierarchical structure of gene sets. First, we use a hierarchical attention-based encoder built on ESM, a protein language model, to represent each gene set using protein-level amino acid sequence information. Second, we construct a hybrid prompting scheme that combines soft prompts derived from gene set embeddings with hard prompts containing auxiliary context generated by an LLM, and feed the resulting prompt into a local LLM for annotation. We evaluate our framework on two benchmark datasets: Gene Ontology (GO) and the Molecular Signatures Database (MSigDB). Our results show that integrating protein-sequence representations with textual context improves gene set annotation overall, while per-domain analyses reveal that the contribution of protein embeddings varies across biological domains.
Abstract:Gene set analysis is a cornerstone of functional genomics, yet it remains labor-intensive and heavily dependent on manual curation and expert biological interpretation. While Large Language Models (LLMs) have emerged as powerful tools for genomic reasoning and annotation, most existing approaches rely on symbolic gene names and fail to capture domain-specific biological structure, particularly protein sequence information that governs molecular activity, interactions, and downstream gene function. In this work, we propose SoftGene, a novel framework for LLM-based gene set annotation that leverages the hierarchical structure of gene sets. First, we use a hierarchical attention-based encoder built on ESM, a protein language model, to represent each gene set using protein-level amino acid sequence information. Second, we construct a hybrid prompting scheme that combines soft prompts derived from gene set embeddings with hard prompts containing auxiliary context generated by an LLM, and feed the resulting prompt into a local LLM for annotation. We evaluate our framework on two benchmark datasets: Gene Ontology (GO) and the Molecular Signatures Database (MSigDB). Our results show that integrating protein-sequence representations with textual context improves gene set annotation overall, while per-domain analyses reveal that the contribution of protein embeddings varies across biological domains.
Artificial Intelligence (cs.AI)
arXiv:2610.03029 [cs.AI]
(or arXiv:2610.03029v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.03029 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 290 words
Related coverage
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · Sep 14, 2026
Building and evaluating model diffing agents
AI Alignment Forum · Jun 12, 2026
Presentation: From Models to Agents: Building Context-Aware Consumer AI at Scale at DoorDash
InfoQ · Aug 15, 2026
Links #3: 2026/06 Part 1
LessWrong · Jun 15, 2026