scCont turns single-cell time courses into readable gene modules: nearest-neighbor pairing plus Shapley attribution splits EMT into interpretable transition units
scCont breaks cell-state transitions in time-course single-cell RNA data into interpretable functional transition units: instead of explicit time labels or clustering priors, it selects positive pairs with a k-nearest-neighbor graph in expression space for contrastive learning, then uses Shapley attribution to map latent dimensions back to gene programs. Across four SERGIO simulated datasets and 13 epithelial-to-mesenchymal transition time-course datasets, its gene modules carry statistical filtering and GO enrichment annotation; on simulated data at k=10, background genes make up 7.0% of the 100 highest-attributed genes per latent, against a 73.3% chance level.