Scoring gene importance by interpreting single-cell foundation models

Determining a gene’s functional importance within a cellular context has long been a challenge, as absolute expression level is an unreliable indicator. Here we introduce SIGnature, a framework for scoring gene importance using attributions derived from single-cell RNA-sequencing (scRNA-seq) foundation models. Attribution scores reduce technical noise, emphasize regulatory genes and facilitate cross-dataset comparison—a core challenge for scRNA-seq analyses. We developed the SIGnature package as a tool for generating and querying attributions, enabling rapid gene set searches across large scRNA-seq atlases. We demonstrate its utility using the MS1 monocyte signature, a poorly understood gene program activated in severe COVID-19 and sepsis. Searching 400 studies identified associations between the MS1 signature and multiple hyperinflammatory conditions, including Kawasaki disease. Experimental validation confirmed that serum from persons with Kawasaki disease induces the MS1 phenotype. These findings highlight that SIGnature can uncover shared mechanisms across conditions, demonstrating its power for large-scale signature scoring and cross-disease analysis. SIGnature enables scalable cross-dataset analyses by combining explainable artificial intelligence with RNA foundation models.