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.
Footnotes
Error correction on the total number of methods being evaluated on page 4, which should be nine instead of seven.
List of abbreviations
- RNA-seq
- Next Generation RNA Sequencing
- scRNA-seq
- Single cell RNA-seq
- GEP
- Gene expression profile matrix
- SVR
- Support Vector Regression
- DNN
- Deep Neural Network
- PBMC
- Peripheral Blood Mononuclear Cells
- CCC
- Lin’s Concordance Correlation Coefficient
- r
- Pearson’s correlation coefficient
- RMSE
- Root Mean Square Error
- CS
- CIBERSORT
- CSx
- CIBERSORTx