Home

SherlockCell: Nextflow pipeline for malignant cell identification from tumor scRNA-seq data

SherlockCell is a nextflow pipeline for identifying malignant cells based on their copy number variation (CNV) profiles and tumor heterogeneity features. It is built on SwiftCNV, a fast and scalable Python implementation of the original InferCNV algorithm extended with additional features.

The pipeline comprises 3 different modules:

1. An automatic malignant cell classification using the SCF classifier to define reference and query cells for SwitfCNV.
2. CNV detection with SwiftCNV.
3. Malignant classification step.

The first module combines the results from a malignant cell classifier, the original cell labels and the sample type to create the reference and query annotations needed for CNV inference, which is performed using SwiftCNV. During the final malignant classification step three different malignancy scores are calculated from the CNV matrix to generate an initial classification, which is later refined based on transcriptional features using a KNN algorithm. For a more detailed explanation of the logic behind the classification read Malignant Classification Logic.