利用基于深度学习的状态形态特征改善分子-形态对比预训练

中文摘要 AI 辅助

近年来，基于图像的形态分析技术的进展使得收集大规模细胞形态数据成为可能，从而使新的分子嵌入模型能够从实验中分子对细胞的表型扰动中学习。此前，我们开发了分子-形态对比预训练（MoCoP）策略，该策略将小分子嵌入与通过CellProfiler提取的形态指纹进行对齐。所得的分子表示在定量结构-活性关系（QSAR）预测任务中表现出可迁移的性能。在此，我们通过使用基于深度学习的细胞图像编码流程来提取更具特征丰富性的形态特征，并通过对比学习将其与分子嵌入对齐，从而扩展了该方法。新的嵌入编码了关于分子如何扰动细胞形态的更准确信息，并通过固定嵌入线性探针或完全灵活的微调，实现了QSAR预测的改进。形态检索性能随训练数据规模呈对数线性增长，表明随着更大数据集的可用，性能将持续提升。改进的MoCoP v2在毒性预测方面也取得了优越性能，并在ADME和活性基准上与使用细胞形态和转录组数据训练的现有分子嵌入模型相比，取得了有竞争力的结果。

英文摘要

Recent advancements in image-based profiling techniques have enabled the collection of high-volume cell morphology data, allowing new molecular embedding models to learn from the experimental phenotypic perturbations of a molecule in a cell. Previously, we developed Molecule-Morphology Contrastive Pretraining (MoCoP), a strategy for aligning small molecule embeddings to morphology fingerprints extracted through CellProfiler. The resulting molecular representation showed transferable performance for quantitative structure--activity relationship (QSAR) prediction tasks. Here, we extend the method by using a deep-learning-based cell image encoding pipeline to extract more feature-rich morphology profiles and align them to the molecular embeddings through contrastive learning. The new embeddings encode more accurate information on how molecules perturb cell morphology and enable improvements for QSAR predictions through either fixed-embedding linear probes or fully flexible fine-tuning. Morphology retrieval performance scales log-linearly with training data size, suggesting continued improvements as larger datasets become available. The improved MoCoP v2 also achieves superior performance on toxicity prediction and competitive results on ADME and activity benchmarks, when compared with existing molecular embedding models that use both cell morphology and transcriptomic data during training.

发表机构

• GSK（葛兰素史克）

机构由 AI 辅助整理，请以论文原文为准。