Transfer Orthology Networks
This addresses the problem of leveraging transcriptomic data across species for biologists, but it appears incremental as it builds on existing transfer learning methods with a specific biological twist.
The authors tackled cross-species transfer learning by introducing Transfer Orthology Networks (TRON), a neural network architecture that uses orthologous relationships to guide knowledge transfer, resulting in a biologically grounded and interpretable approach for predicting phenotypes from gene expression data.
We present Transfer Orthology Networks (TRON), a novel neural network architecture designed for cross-species transfer learning. TRON leverages orthologous relationships, represented as a bipartite graph between species, to guide knowledge transfer. Specifically, we prepend a learned species conversion layer, whose weights are masked by the biadjacency matrix of this bipartite graph, to a pre-trained feedforward neural network that predicts a phenotype from gene expression data in a source species. This allows for efficient transfer of knowledge to a target species by learning a linear transformation that maps gene expression from the source to the target species' gene space. The learned weights of this conversion layer offer a potential avenue for interpreting functional orthology, providing insights into how genes across species contribute to the phenotype of interest. TRON offers a biologically grounded and interpretable approach to cross-species transfer learning, paving the way for more effective utilization of available transcriptomic data. We are in the process of collecting cross-species transcriptomic/phenotypic data to gain experimental validation of the TRON architecture.