arXiv 2410.223672025-05-06q-bio.QMcs.AIcs.LG

MAMMAL——分子对齐的多模态架构与语言

MAMMAL -- Molecular Aligned Multi-Modal Architecture and Language

IBM Research-Israel（IBM研究以色列分公司）；IBM TJ Watson Research Center（IBM TJ Watson研究中心）；Faculty of Biomedical Engineering（生物医学工程学院）

Yoel Shoshan, Moshiko Raboh, Michal Ozery-Flato, Vadim Ratner, Alex Golts, Jeffrey K. Weber, Ella Barkan, Simona Rabinovici-Cohen, Sagi Polaczek, Ido Amos, Ben … 展开作者

Yoel Shoshan, Moshiko Raboh, Michal Ozery-Flato, Vadim Ratner, Alex Golts, Jeffrey K. Weber, Ella Barkan, Simona Rabinovici-Cohen, Sagi Polaczek, Ido Amos, Ben Shapira, Liam Hazan, Matan Ninio, Sivan Ravid, Michael M. Danziger, Yosi Shamay, Sharon Kurant, Joseph A. Morrone, Parthasarathy Suryanarayanan, Michal Rosen-Zvi, Efrat Hexter

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

MAMMAL提出一种分子对齐的多模态基础模型，统一整合蛋白质、小分子和组学数据以支持分类、回归与生成，在11个下游任务中9项达到SOTA，并在抗体-抗原结合预测上优于Alphafold 3。

摘要：

应用于大规模生物数据集的大语言模型有潜力通过揭示疾病机制和加速药物开发来变革生物学。然而，当前模型往往是孤立的，分别在小分子、蛋白质或转录组数据上训练，限制了它们捕捉复杂多模态交互的能力。有效的药物发现需要能够整合多种生物实体并同时支持预测和生成的计算工具，而现有模型难以应对这一挑战。为此，我们提出了MAMMAL——分子对齐的多模态架构与语言——一种通用方法，用于创建一个多任务基础模型，该模型从跨多种模态的大规模生物数据集中学习，包括蛋白质、小分子和组学数据。MAMMAL的结构化提示语法支持分类、回归和生成任务，同时处理token和标量输入与输出。在十一个不同的下游任务上评估时，它在九个任务中达到了新的最优水平（SOTA），在两个任务中与SOTA相当，且全部在统一架构内完成，不同于以往的任务特定模型。此外，我们探索了Alphafold 3在抗体-抗原和纳米抗体-抗原复合物上的结合预测能力，显示MAMMAL在4个靶标中的3个上具有显著更好的分类性能。模型代码和预训练权重已在https://github.com/BiomedSciAI/biomed-multi-alignment和https://huggingface.co/ibm/biomed.omics.bl.sm.ma-ted-458m公开提供。

英文摘要：

Large language models applied to vast biological datasets have the potential to transform biology by uncovering disease mechanisms and accelerating drug development. However, current models are often siloed, trained separately on small-molecules, proteins, or transcriptomic data, limiting their ability to capture complex, multi-modal interactions. Effective drug discovery requires computational tools that integrate multiple biological entities while supporting prediction and generation, a challenge existing models struggle to address. For this purpose, we present MAMMAL - Molecular Aligned Multi-Modal Architecture and Language - a versatile method applied to create a multi-task foundation model that learns from large-scale biological datasets across diverse modalities, including proteins, small-molecules, and omics. MAMMAL's structured prompt syntax supports classification, regression, and generation tasks while handling token and scalar inputs and outputs. Evaluated on eleven diverse downstream tasks, it reaches a new state of the art (SOTA) in nine tasks and is comparable to SOTA in two tasks, all within a unified architecture, unlike prior task-specific models. Additionally, we explored Alphafold 3 binding prediction capabilities on antibody-antigen and nanobody-antigen complexes showing significantly better classification performance of MAMMAL in 3 out of 4 targets. The model code and pretrained weights are publicly available at https://github.com/BiomedSciAI/biomed-multi-alignment and https://huggingface.co/ibm/biomed.omics.bl.sm.ma-ted-458m

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。