The gene expression profile of a tissue averages the expression profiles of all cells in this tissue. Digital tissue deconvolution addresses the following inverse problem: given the expression profile y of a tissue, what is the cellular composition c of that tissue? If X is a matrix whose columns are reference profiles of individual cell types, the composition c can be computed by minimizing L(y - Xc) for a given loss function L. Current methods use predefined all-purpose loss functions. They successfully quantify the dominating cells of a tissue, while often falling short in detecting small cell populations. In this study we use training data to learn the loss function L along with the composition c. This allows us to adapt to application-specific requirements such as focusing on small cell populations or distinguishing phenotypically similar cell populations. Our method quantifies large cell fractions as accurately as existing methods and significantly improves the detection of small cell populations and the distinction of similar cell types.

We propose Adaptive Digital Tissue Deconvolution (ADTD) to estimate cellular proportions of pre-selected cell types together with possibly unknown and hidden background contributions. Moreover, ADTD adapts prototypic reference profiles to the molecular environment of the cells, which further resolves cell-type specific gene regulation from bulk transcriptomics data. We verify this in simulation studies and demonstrate that ADTD improves existing approaches in estimating cellular compositions. In an application to bulk transcriptomics data from breast cancer patients, we demonstrate that ADTD provides insights into cell-type specific molecular differences between breast cancer subtypes.

Gene expression profiles of heterogeneous bulk samples contain signals from multiple cell populations. Studying variations in their composition can help to identify cell populations relevant for disease. Moreover, analyses, such as the identification of differentially expressed genes, can be confounded by cellular composition, as differences in gene expression may arise from both variations in cellular composition and gene regulation. Here, we present Deconvolution of omics data (Deconomix) – a comprehensive toolbox for the cell-type deconvolution of bulk transcriptomics data. Deconomix stands apart from competing solutions with rich functionality and highly efficient implementations. It facilitates (A) the inference of cellular compositions from bulk transcriptomics data, (B) the machine learning-based optimization of gene weights to resolve small cell populations and to disentangle phenotypically related cells, (C) the inference of background contributions which otherwise would deteriorate cell-type deconvolution, and (D) population estimates of cell-type specific gene regulation.