Learnable Topological Features for Phylogenetic Inference via Graph Neural Networks
This work addresses a domain-specific problem in computational biology by automating structural representation for phylogenetic inference, though it appears incremental as it builds on existing graph representation learning techniques.
The paper tackles the challenge of requiring domain expertise to design appropriate topological structures for phylogenetic inference by proposing learnable topological features that automatically adapt to different tasks. The method demonstrates effectiveness on simulated tree probability estimation and real data variational Bayesian phylogenetic inference benchmarks.
Structural information of phylogenetic tree topologies plays an important role in phylogenetic inference. However, finding appropriate topological structures for specific phylogenetic inference tasks often requires significant design effort and domain expertise. In this paper, we propose a novel structural representation method for phylogenetic inference based on learnable topological features. By combining the raw node features that minimize the Dirichlet energy with modern graph representation learning techniques, our learnable topological features can provide efficient structural information of phylogenetic trees that automatically adapts to different downstream tasks without requiring domain expertise. We demonstrate the effectiveness and efficiency of our method on a simulated data tree probability estimation task and a benchmark of challenging real data variational Bayesian phylogenetic inference problems.