TwinBooster：利用 Barlow Twins 与梯度提升协同大语言模型以增强分子性质预测
TwinBooster: Synergising Large Language Models with Barlow Twins and Gradient Boosting for Enhanced Molecular Property Prediction
AI总结：
TwinBooster 结合微调大语言模型与 Barlow Twins 自监督孪生网络，融合生物测定文本和分子指纹，在 FS-Mol 基准上实现优异的零样本分子性质预测，助力数据稀缺场景下的药物发现。
摘要：
药物发现与开发的成功依赖于对分子活性和性质的精确预测。尽管计算机模拟分子性质预测已展现出显著潜力，但其应用迄今仅限于可获得大量数据的测定实验。在本研究中，我们使用一个经过微调的大语言模型，基于生物测定实验的文本信息对其进行整合，并结合 Barlow Twins——一种采用新型自监督学习方法的孪生神经网络。该架构同时利用测定实验信息和分子指纹来提取真实的分子信息。TwinBooster 通过提供最先进的零样本学习任务，能够预测未见过的生物测定实验和分子的性质。值得注意的是，我们的人工智能流程在 FS-Mol 基准上表现出卓越性能。这一突破展示了深度学习在数据通常稀缺的关键性质预测任务中的应用。通过加速药物发现与开发中活性分子的早期识别，该方法有望帮助简化新型治疗药物的发现流程。
英文摘要：
The success of drug discovery and development relies on the precise prediction of molecular activities and properties. While in silico molecular property prediction has shown remarkable potential, its use has been limited so far to assays for which large amounts of data are available. In this study, we use a fine-tuned large language model to integrate biological assays based on their textual information, coupled with Barlow Twins, a Siamese neural network using a novel self-supervised learning approach. This architecture uses both assay information and molecular fingerprints to extract the true molecular information. TwinBooster enables the prediction of properties of unseen bioassays and molecules by providing state-of-the-art zero-shot learning tasks. Remarkably, our artificial intelligence pipeline shows excellent performance on the FS-Mol benchmark. This breakthrough demonstrates the application of deep learning to critical property prediction tasks where data is typically scarce. By accelerating the early identification of active molecules in drug discovery and development, this method has the potential to help streamline the identification of novel therapeutics.
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。
