Although an essential step, cell functional annotation often proves particularly challenging from single-cell transcriptional data. Several methods have been developed to accomplish this task. However, in most cases, these rely on techniques initially developed for bulk RNA sequencing or simply make use of marker genes identified from cell clustering followed by supervised annotation. To overcome these limitations and automatize the process, we have developed two novel methods, the single-cell gene set enrichment analysis (scGSEA) and the single-cell mapper (scMAP). scGSEA combines latent data representations and gene set enrichment scores to detect coordinated gene activity at single-cell resolution. scMAP uses transfer learning techniques to re-purpose and contextualize new cells into a reference cell atlas. Using both simulated and real datasets, we show that scGSEA effectively recapitulates recurrent patterns of pathways’ activity shared by cells from different experimental conditions. At the same time, we show that scMAP can reliably map and contextualize new single-cell profiles on a breast cancer atlas we recently released. Both tools are provided in an effective and straightforward workflow providing a framework to determine cell function and significantly improve annotation and interpretation of scRNA-seq data.

Although many primary triple negative breast cancers (TNBCs) have enhanced expression of epidermal growth factor receptor (EGFR), EGFR-targeted therapies have shown only variable and unpredictable clinical responses in TNBCs. Here we integrate cellular barcoding and single-cell transcriptomics methods to comprehensively characterize the subclonal dynamics of adaptation of TNBC cells in response to afatinib, tyrosine kinase inhibitor (TKI) that irreversibly inhibits EGFR. Integrated lineage tracing analysis on these cells uncovered a pre-existing subpopulation of cells composed of 192 clones (out of the initial 2,336) with distinct biological features, such as elevated IGFBP2 (Insulin-Like Growth Factor Binding Protein 2) expression levels. We demonstrate that IGFBP2 overexpression is sufficient to make TNBC cells tolerant to afatinib treatment by activating the compensatory IGF1-R signalling pathway. Finally, by using deep learning techniques, we devise an algorithm to predict the afatinib sensitivity of TNBC cells from the transcriptional status of identified marker genes of the afatinib response. Our findings provide a new understanding of EGFR-dependent hierarchy in TNBC.

Drug response prediction at the single cell level is an emerging field of research that aims to improve the efficacy and precision of cancer treatments. Here, we introduce DREEP (Drug Response Estimation from single-cell Expression Profiles), a computational method that leverages publicly available pharmacogenomic screens and functional enrichment analysis to predict single cell drug sensitivity from transcriptomic data. We extensively tested DREEP on several independent single-cell datasets with over 200 cancer cell lines and showed its accuracy and robustness. Additionally, we also applied DREEP to molecularly barcoded breast cancer cells and identified drugs that can selectively target specific cell populations. DREEP provides an in-silico framework to prioritize drugs from single-cell transcriptional profiles of tumours and thus helps in designing personalized treatment strategies and accelerate drug repurposing studies. DREEP is available at https://github.com/gambalab/DREEP.

Although an essential step, the functional annotation of cells often proves particularly challenging in the analysis of single-cell transcriptional data. Several methods have been developed to accomplish this task. However, in most cases, these rely on techniques initially developed for bulk RNA sequencing or simply make use of marker genes identified from cell clustering followed by supervised annotation. To overcome these limitations and automatise the process, we have developed two novel methods, the single-cell gene set enrichment analysis (scGSEA) and the single cell mapper (scMAP). scGSEA combines latent data representations and gene set enrichment scores to detect coordinated gene activity at single-cell resolution. scMAP uses transfer learning techniques to re-purpose and contextualise new cells into a reference cell atlas. Using both simulated and real datasets, we show that scGSEA effectively recapitulates recurrent patterns of pathways' activity shared by cells from different experimental conditions. At the same time, we show that scMAP can reliably map and contextualise new single cell profiles on a breast cancer atlas we recently released. Both tools are provided in an effective and straightforward workflow providing a framework to determine cell function and significantly improve annotation and interpretation of scRNA-seq data.