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

Abstract

Understanding the immune-cell abundances of cancer and other disease-related tissues has an important role in guiding cancer treatments. We propose data augmentation through in silico mixing with deep neural networks (DAISM-DNN), where highly accurate and unbiased immune-cell proportion estimation is achieved through DNN with dataset-specific training data created from partial samples from the same batch with ground truth cell proportions. We evaluated the performance of DAISM-DNN on three publicly available real-world datasets and results showed that DAISM-DNN is robust against platform-specific variations among different datasets and outperforms other existing methods by a significant margin on all the datasets evaluated.

Multiplexed imaging mass cytometry reveals distinct tumor-immune microenvironments linked to immunotherapy responses in melanoma

“…Recently, numerous gene expression signatures 26–29 have been developed to study cellular composition of TMEs based on bulk RNA-seq data when single cell information is not available. Here, we investigated the consistency between our single cell analysis results from IMC data and the results from these signatures using RNA-seq data generated from adjacent serial section from the same samples in the PUCH cohort 30 .…”

Open Problems in Extracellular RNA Data Analysis: Insights From an ERCC Online Workshop

“…The team’s solution was to augment the existing training datasets by shuffling them together in silico with expression data from target cells, either bulk RNAseq from purified cell samples or single-cell RNAseq. Finally, although DNN models are generally considered to be difficult to interpret black boxes, it is possible to apply methods such as the SHapley Additive explanation (SHAP) model from game theory ( Lundberg and Lee 2017 ) to output a ranked list of the genes that contribute most to the deconvolution results from DAISM-DNN ( Lin et al, 2021 ).…”