Track genomics, neuroscience and molecular biology.
Search papers, labs, and topics across Lattice.
This work investigates Gene Expression-to-Image (GE2I) learning by analyzing the trade-off between spatial smoothness and gene-level fidelity in convolutional neural network representations of scRNA-seq data. Structured pixel mappings accelerate early optimization by generating smooth, low-frequency patterns, but can obscure gene expression differences. Conversely, one-to-one gene-to-pixel assignments improve predictive performance across visual backbones, even with reduced image smoothness, offering practical guidance for leveraging vision priors.
Assigning one gene per pixel, not spatial smoothness, unlocks superior predictive performance in gene expression-to-image learning.
Single-cell RNA sequencing (scRNA-seq) enables cell-level analysis of biological heterogeneity, but learning effective representations from high-dimensional, unordered gene expression profiles remains challenging. Gene Expression-to-Image (GE2I) offers an effective learning strategy by arranging gene values on pixel grids for convolutional neural networks, but its underlying mechanisms remain unclear. We study GE2I on full-transcriptome data while keeping the network and training procedure fixed. Our results reveal a trade-off between spatial smoothness and gene-level fidelity. Structured mappings produce smooth, low-frequency patterns that support faster early optimization, whereas assigning multiple genes to the same pixel obscures expression differences and can reduce predictive performance. This trade-off explains why random mappings can compete with structured layouts when many genes are represented. One-to-one gene-to-pixel assignment improves prediction across the tested visual backbones even when image smoothness decreases. We further find that the benefits of pretraining and augmentation depend on the backbone and mapping. These findings provide practical guidance for pixel allocation and the transfer of vision priors to gene expression data.