DAISM-DNN: Highly accurate cell type proportion estimation with in silico data augmentation and deep neural networks

Abstract

Understanding the immune cell abundance of cancer and other disease-related tissues has an important role in guiding disease treatments. Computational cell type proportion estimation methods have been previously developed to derive such information from bulk RNA sequencing (RNA-seq) data. Unfortunately, our results show that the performance of these methods can be seriously plagued by the mismatch between training data and real-world data. To tackle this issue, we propose the DAISM-DNNXMBD1 pipeline that trains a deep neural network (DNN) with dataset-specific training data populated from a small number of calibrated samples using DAISM, a novel Data Augmentation method with an In Silico Mixing strategy. The evaluation results demonstrate that the DAISM-DNN pipeline outperforms other existing methods consistently and substantially for all the cell types under evaluation on real-world datasets.