<p>Single-cell transcriptomes are not sufficient in describing cell phenotypes. Here we propose an algorithm for single cells’ phenotype prediction (ScPP) based on the expression profiles of phenotype-associated marker genes in bulks and single cells. ScPP first analyzes bulk data to identify phenotype-associated marker genes. Next, ScPP evaluates the enrichment scores of the marker genes in single cells using the AUCell algorithm. The single cells with the phenotype are defined as the intersection of the single cells with top <i>α</i> ranks according to the phenotype-associated AUC values and the single cells with bottom <i>α</i> ranks according to the opposite phenotype-associated AUC values. Finally, all single cells are determined as phenotype⁺, phenotype⁻ or background. We demonstrate that ScPP can effectively recognize cell subpopulations with specific phenotypes. Compared to the established algorithms (Scissor and scAB), ScPP displays excellent predictive performance. Thus, ScPP is an effective and competitive tool for inferring cell phenotypes.</p> Graphical Abstract <p></p>