{"ID":2860828,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.03370","arxiv_id":"2510.03370","title":"InstructPLM-mu: 1-Hour Fine-Tuning of ESM2 Beats ESM3 in Protein Mutation Predictions","abstract":"Multimodal protein language models deliver strong performance on mutation-effect prediction, but training such models from scratch demands substantial computational resources. In this paper, we propose a fine-tuning framework called InstructPLM-mu and try to answer a question: \\textit{Can multimodal fine-tuning of a pretrained, sequence-only protein language model match the performance of models trained end-to-end? } Surprisingly, our experiments show that fine-tuning ESM2 with structural inputs can reach performance comparable to ESM3. To understand how this is achieved, we systematically compare three different feature-fusion designs and fine-tuning recipes. Our results reveal that both the fusion method and the tuning strategy strongly affect final accuracy, indicating that the fine-tuning process is not trivial. We hope this work offers practical guidance for injecting structure into pretrained protein language models and motivates further research on better fusion mechanisms and fine-tuning protocols.","short_abstract":"Multimodal protein language models deliver strong performance on mutation-effect prediction, but training such models from scratch demands substantial computational resources. In this paper, we propose a fine-tuning framework called InstructPLM-mu and try to answer a question: \\textit{Can multimodal fine-tuning of a pr...","url_abs":"https://arxiv.org/abs/2510.03370","url_pdf":"https://arxiv.org/pdf/2510.03370v3","authors":"[\"Junde Xu\",\"Yapin Shi\",\"Lijun Lang\",\"Taoyong Cui\",\"Zhiming Zhang\",\"Guangyong Chen\",\"Jiezhong Qiu\",\"Pheng-Ann Heng\"]","published":"2025-10-03T07:42:22Z","proceeding":"q-bio.QM","tasks":"[\"q-bio.QM\",\"cs.AI\",\"cs.CE\"]","methods":"[\"Language Model\"]","has_code":false}