ADAPTS: Automated deconvolution augmentation of profiles for tissue specific cells

Abstract

Immune cell infiltration of tumors and the tumor microenvironment can be an important component for determining patient outcomes. For example, immune and stromal cell presence inferred by deconvolving patient gene expression data may help identify high risk patients or suggest a course of treatment. One particularly powerful family of deconvolution techniques uses signature matrices of genes that uniquely identify each cell type as determined from single cell type purified gene expression data. Many methods from this family have been recently published, often including new signature matrices appropriate for a single purpose, such as investigating a specific type of tumor. The package ADAPTS helps users make the most of this expanding knowledge base by introducing a framework for cell type deconvolution. ADAPTS implements modular tools for customizing signature matrices for new tissue types by adding custom cell types or building new matrices de novo, including from single cell RNAseq data. It includes a common interface to several popular deconvolution algorithms that use a signature matrix to estimate the proportion of cell types present in heterogenous samples. ADAPTS also implements a novel method for clustering cell types into groups that are difficult to distinguish by deconvolution and then re-splitting those clusters using hierarchical deconvolution. We demonstrate that the techniques implemented in ADAPTS improve the ability to reconstruct the cell types present in a single cell RNAseq data set in a blind predictive analysis. ADAPTS is currently available for use in R on CRAN and GitHub.

Fig 1. Overview of ADAPTS modules.

New gene expression data from cell types (e.g. from a tumor microenvironment) will be used to construct a new signature matrix de novo or by augmenting an existing signature matrix. First ADAPTS will rank marker genes for the cell types using the function rankByT described in Eq 4. Then ADAPTS adds marker genes in rank order using the function AugmentSigMatrix as described in Algorithm 1 resulting in a new signature matrix. This matrix may be tested for spillover between cell types using the function spillToConvergence described in Algorithm 2. Finally, ADAPTS separates cell types with heavy spillover using the hierarchical deconvolution function hierarchicalSplit described in Algorithm 3 to estimate the percentage of cell types present in bulk gene expression data.

Fig 2. MGSM27 construction.

Curve showing the selection of an optimal condition number for MGSM27.

Fig 3. LM22 spillover matrix.

Spillover matrix showing mean misclassification of purified samples for LM22. Rows show purified cell types and columns show what those samples deconvolve as. Cells are colored by percentage, such that each row adds up to 100%. For example, if the row is ‘B.cell.memory’, the column is ‘Plasma.cells’, then the color is light blue indicating that purified ‘B.cell.memory’ samples deconvolve as containing (on average) 18% ‘Plasma.cells’.

Fig 4. LM22 converged spillover matrix.

Iterative deconvolution shows how easily confused cell types conspicuously form clusters. Rows show purified cell types and columns show what those samples deconvolve as. Cells are colored by percentage, such that each row adds up to 100%.

Fig 5. scRNAseq signature matrix construction.

Curve showing the selection of an optimal condition number for the single cell RNAseq augmented signature matrix data.

Fig 6. Clustering of Top 100 gene signature matrix.

The cell type clusters identified using the signature matrix constructed from the 100 genes with the highest variance across cell types in the single cell data drawn from a normal pancreas sample. Rows show purified cell types and columns show what those samples deconvolve as. Cells are colored by percentage, such that each row adds up to 100%.

Fig 7. Clustering of augmented gene signature matrix.

The cell type clusters identified using the augmented signature matrix that was seeded with the 100 genes exhibiting the highest variance in the normal pancreas sample. Rows show purified cell types and columns show what those samples deconvolve as. Cells are colored by percentage, such that each row adds up to 100%.