Stable-Shift: Biologically Structured Prediction of Transcriptional Responses to Unseen Gene Perturbations
For researchers in functional genomics, Stable-Shift offers a structured method to extrapolate perturbation responses to unseen genes, reducing experimental burden, though its lower gene-space accuracy and sensitivity to sparse graph neighborhoods limit current conclusions.
Stable-Shift predicts transcriptional responses to unseen gene perturbations by aggregating single-cell data into expression shifts and fitting a low-rank response basis from training perturbations. It achieves 0.592 cosine similarity on the K562 Perturb-seq benchmark, outperforming GEARS (0.569), with higher Spearman correlation and top-gene precision.
Predicting transcriptional responses to genetic perturbations could reduce the experimental burden of functional genomics, but extrapolation to genes that were never perturbed during training remains difficult. We present Stable-Shift, a structured method for estimating unseen-gene responses. Stable-Shift aggregates single-cell measurements into perturbation-level expression shifts, fits a low-rank response basis using training perturbations only, and predicts an unseen gene's coordinates in that basis from biological context. The context combines STRING interactions, network structure, control-cell expression statistics, and Gene Ontology annotations; the evaluated implementation uses graph convolution to integrate these inputs. On the supplied K562 Perturb-seq benchmark, Stable-Shift obtained 0.592 cosine similarity, compared with 0.569 for GEARS, together with higher Spearman correlation and top-gene precision among the evaluated methods. Its mean cosine similarity over five unseen-gene splits was 0.589 +/- 0.008. The same ordering was observed in the supplied graph-aware, residualized, gene-space, and Norman-dataset comparisons. These results support further study of biologically structured latent-response prediction, while the lower gene-space accuracy and sensitivity to sparse graph neighborhoods limit the scope of the present conclusions.