QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation
Abstract
Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far faster than the capacity for manual curation. Most computational approaches consider annotation as multi-label classification over a fixed ontology, which constrains predictions to a predefined label set. In this work we study the the protein annotation as a sequence-to-text generation problem. We fine-tune the 3B-parameter Ministral 3 base model with QLoRA (4-bit NF4 quantization with low-rank adapters) on sequence annotation pairs. We assess predictions with an LLM-as-expert protocol: a GPT model prompted as a senior molecular-biology curator scores organism identification as binary and function annotation quality. We conclude that QLoRA-fine-tuned compact LLMs can generate curator-style annotations with genuine biological value for a substantial subset of proteins. We also discuss future directions in data quality, model scaling, and evidence grounding that are needed to make the approach sufficiently reliable for practical use.
Related
- From neuropeptide and receptor annotation to ligand-receptor pairing: a sequence- and structure-based framework for mapping the neuropeptide-receptor interactome in Gryllus bimaculatus
- MerKurio: sequence extraction and annotation based on matching k-mers
- Reading Between the Reads: A Decade On, Revisiting Sequencing Protocol Annotation in the Sequence Read Archive
- PalmLab: A Comprehensive Computational Platform for Systematic Annotation and Functional Interrogation of Protein Palmitoylation
- Fine-tuning sequence-to-expression models on personal genome and transcriptome data
BibTeX
@misc{pavlyshenko2026qlora,
title = {{QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation}},
author = {Demian Pavlyshenko and Bohdan Pavlyshenko},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.24538},
eprint = {2609.24538},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.24538},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation
AU - Demian Pavlyshenko
AU - Bohdan Pavlyshenko
PY - 2026
DA - 2026/09/21
PB - arXiv
DO - 10.48550/arxiv.2609.24538
UR - https://arxiv.org/abs/2609.24538
AB - Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far faster than the capacity for manual curation. Most computational approaches consider annotation as multi-label classification over a fixed ontology, which constrains predictions to a predefined label set. In this work we study the the protein annotation as a sequence-to-text generation problem. We fine-tune the 3B-parameter Ministral 3 base model with QLoRA (4-bit NF4 quantization with low-rank adapters) on sequence annotation pairs. We assess predictions with an LLM-as-expert protocol: a GPT model prompted as a senior molecular-biology curator scores organism identification as binary and function annotation quality. We conclude that QLoRA-fine-tuned compact LLMs can generate curator-style annotations with genuine biological value for a substantial subset of proteins. We also discuss future directions in data quality, model scaling, and evidence grounding that are needed to make the approach sufficiently reliable for practical use.
ER -