Bayesian method matches single cells across data types with confidence
BASILISC: Bayesian Alignment of Siamese-Integrated Latents for Inferring Single-cell Correspondence
Machine Learning
Summary
When scientists study individual cells, they often measure different kinds of data about each cell, but linking those measurements across types is tricky. The authors introduce BASILISC, a new model that not only matches cells from different data types but also tells you how confident it is in each match. This helps identify uncertain matches and improves reliability. Their approach works well even with cell types the model hasn’t seen before.
What this means in practice
- •For bioinformatics engineers: Improve single-cell data integration pipelines by providing confidence scores that help filter reliable cell matches across data types.
- •For pharmaceutical development teams: Enhance biomarker discovery workflows by identifying more accurate and confident correspondences between different single-cell molecular profiles.
Authors
Sepideh Saran, Mahsa Ghanbari, Uwe Ohler
Abstract
Single-cell assays study the genome one cell at a time. Unimodal assays measure one molecular layer, the newer multimodal assays measure several. Most data are single-modality, so integrating them relies on models trained on multimodal assays, where the cell correspondence across modalities is known. These models return a matching, but rarely a confidence measure. We present BASILISC (Bayesian Alignment of Siamese-Integrated Latents for Inferring Single-cell Correspondence), a framework for matching single-cell representations with uncertainty on the correspondence itself. A BASILISC model is a probabilistic siamese network over the two modalities with a predictive distribution over the correspondence for a cross-modal pair of cells. We instantiate it at two levels: at the cell-type level the question is whether two cells share a cell type, at the cell level which cell is the partner in the other modality. To our knowledge, this is the first uncertainty score on a learned cross-modal correspondence evaluated against a known ground-truth pairing. BASILISC learns a similarity across modalities that reflects cell lineage: an unseen cell type is matched to its lineage relative, matching still works on such held-out types (balanced accuracy 0.86 on unseen against 0.93 on seen types), and the predictive uncertainty rises on these out-of-distribution cells. The uncertainty score also selects high-quality matches for downstream analysis: discarding the least certain fifth of the pairs raises accuracy from 0.93 to 0.98. At the cell level, a deep ensemble of the deterministic matcher reaches 0.062 matching accuracy on the benchmark test set, above the competition winner; on the Bayesian matcher's assignment, the posterior flags the wrong matches that cross a cell-type boundary better than a deterministic read of the same scores (AUROC 0.68 against 0.64).