Divide-and-conquer: a flexible deep learning strategy for exploring metabolic heterogeneity from mass spectrometry imaging data

There is growing awareness that metabolic heterogeneity of organism provides vital insight into the disease with molecular mechanism and personalized therapy. The screening of metabolism-related sub-regions that affect disease development is essential for the more focused exploration how disease progress aberrant phenotypes, even carcinogenesis and metastasis. Mass spectrometry imaging (MSI) technique has distinct advantages to reveal the heterogeneity of organism based on the in situ molecular profiles. The challenge of heterogeneous analysis has been to perform an objective identification among biological tissues with different characteristics. By introducing the divide-and-conquer strategy to architecture design and application, we establish here a flexible unsupervised deep learning model, called divide-and-conquer (dc)-DeepMSI, for metabolic heterogeneity analysis from MSI data without prior knowledge of histology. dc-DeepMSI can be used to identify either spatially contiguous region-of-interest (ROIs) or spatially sporadic ROIs. We demonstrate that the novel learning strategy successfully obtain sub-regions that are statistically linked to invasion status and molecular phenotypes of breast cancer, as well as organizing principles during developmental phase.