论文标题
改善了分子形象合成的条件流模型
Improved Conditional Flow Models for Molecule to Image Synthesis
论文作者
论文摘要
在本文中，我们的目标是在不同的分子干预措施下合成细胞显微镜图像，这是由药物开发的实际应用。基于图形神经网络用于学习分子嵌入的最新成功和图像产生的基于流动的模型，我们提出了mol2image：一种基于流的生成模型，用于分子到细胞图像合成。为了在不同的分辨率和规模上生成细胞特征到高分辨率图像，我们基于HAAR小波图像金字塔开发了一种新型的多尺度流量结构。为了最大化生成的图像和分子干预措施之间的相互信息，我们根据对比度学习制定了训练策略。为了评估我们的模型，我们为生物形象生成的一组新的指标集，这些指标与从业人员有力，可解释且相关。我们定量地表明，我们的方法学习了分子干预的有意义的嵌入，该介入被转化为反映干预措施生物学效应的图像表示。
In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development. Building on the recent success of graph neural networks for learning molecular embeddings and flow-based models for image generation, we propose Mol2Image: a flow-based generative model for molecule to cell image synthesis. To generate cell features at different resolutions and scale to high-resolution images, we develop a novel multi-scale flow architecture based on a Haar wavelet image pyramid. To maximize the mutual information between the generated images and the molecular interventions, we devise a training strategy based on contrastive learning. To evaluate our model, we propose a new set of metrics for biological image generation that are robust, interpretable, and relevant to practitioners. We show quantitatively that our method learns a meaningful embedding of the molecular intervention, which is translated into an image representation reflecting the biological effects of the intervention.
