Published June 5, 2023
| Version v1.0.2
Journal article
Open
DeSide: A unified deep learning approach for cellular decomposition of bulk tumors based on limited scRNA-seq data
Authors/Creators
- 1. Hong Kong Baptist University
- 2. Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
Description
DeSide_workflow
This is the whole workflow and results of the DeSide project, which includes the following parts:
- main_workflow.py: the main workflow of the DeSide project
- datasets/*: the datasets used in the DeSide project, including the TCGA dataset, the simulated bulk cell dataset, and the single cell dataset
- model_evaluation/*: the predicted cell proportions of different methods for performance evaluation
- results/*: the results of the DeSide project, including the predicted cell proportions by DeSide with different datasets
- plot_fig/*: the scripts for plotting the figures in the DeSide project
- single_cell_dataset_integration/*: the scripts for integrating the single cell datasets
The file structure of the project
DeSide_workflow
├── LICENSE
├── README.md
├── main_workflow.py
├── TCGA_dataset_preprocessing.py
├── datasets
│ ├── Independent_Test_Set
│ ├── TCGA
│ │ └── tpm
│ │ ├── merged_tpm.csv
│ │ └── tcga_sample_id2cancer_type.csv
│ ├── cancer_purity
│ │ └── cancer_purity.csv
│ ├── generated_sc_dataset_7ds_n_base100
│ │ ├── generated_frac_SCT_POS_N100.csv
│ │ ├── generated_frac_SCT_POS_N10K.csv
│ │ ├── simu_bulk_exp_SCT_POS_N100_log2cpm1p.h5ad
│ │ └── simu_bulk_exp_SCT_POS_N10K_log2cpm1p.h5ad
│ ├── simulated_bulk_cell_dataset
│ │ ├── README.md
│ │ ├── random_7ds_n_base100
│ │ │ ├── generated_frac_Mixed_N100K_random.csv
│ │ │ ├── simu_bulk_exp_Mixed_N100K_random_log2cpm1p.h5ad
│ │ │ └── simu_bulk_exp_Test_set0_log2cpm1p.h5ad
│ │ └── segment_7ds_0.95_n_base100_median_gep
│ │ ├── D2
│ │ │ ├── corr_cell_frac_with_gene_exp_D2.csv
│ │ │ ├── corr_cell_frac_with_gene_exp_D2.xlsx
│ │ │ └── gene_list_filtered_by_high_corr_gene.csv
│ │ ├── Mixed_N100K_segment
│ │ │ ├── Mixed_N100K_segment_PCA_with_TCGA_high_corr_gene_and_quantile_range.csv
│ │ │ ├── Mixed_N100K_segment_PCA_with_TCGA_high_corr_gene_and_quantile_range_PC0_PC1.png
│ │ │ ├── Mixed_N100K_segment_PCA_with_TCGA_high_corr_gene_and_quantile_range_PC0_PC2.png
│ │ │ ├── Mixed_N100K_segment_PCA_with_TCGA_high_corr_gene_and_quantile_range_PC1_PC2.png
│ │ │ └── gene_list_filtered_by_high_corr_gene_and_quantile_range_q_5.0_q_95.0.csv
│ │ ├── simu_bulk_exp_Mixed_N100K_segment_log2cpm1p.h5ad
│ │ ├── simu_bulk_exp_Mixed_N100K_segment_log2cpm1p_filtered_by_high_corr_gene_and_quantile_range_q_5.0_q_95.0.h5ad
│ │ ├── simu_bulk_exp_Mixed_N100K_segment_without_filtering_log2cpm1p.h5ad
│ │ ├── simu_bulk_exp_Test_set1_log2cpm1p.csv
│ │ ├── simu_bulk_exp_Test_set1_log2cpm1p.h5ad
│ │ ├── simu_bulk_exp_Test_set1_sampled_sc_cell_id.csv
│ │ ├── simu_bulk_exp_Test_set2_log2cpm1p.csv
│ │ ├── simu_bulk_exp_Test_set2_log2cpm1p.h5ad
│ │ └── simu_bulk_exp_Test_set2_sampled_sc_cell_id.csv
│ └── single_cell
│ ├── Add_subgroup_name.ipynb
│ ├── Pan_cancer_cell_lines
│ │ ├── Metadata.txt
│ │ ├── Metadata.xlsx
│ │ └── pan_cancer_07_GSE157220_log2cpm1p_filtered.h5ad
│ ├── gene_list_in_merged_7_sc_datasets.csv
│ ├── merged_7_sc_datasets_log2cpm1p.h5ad
│ ├── merged_7_sc_datasets_sample_info.csv
│ ├── merged_7_sc_datasets_sample_info.xlsx
│ ├── merged_after_batch_correction
│ │ ├── 01_all_HNSCC_TIL_Cillo_Immunity_2020_merged_after_batch_correction.h5ad
│ │ ├── 02_PDAC_Peng_J_Cell_Res_2019_merged_after_batch_correction.h5ad
│ │ ├── 03_all_HNSCC_Puram_Cell_2017_merged_after_batch_correction.h5ad
│ │ ├── 04_PDAC_Steele_NCancer_2020_merged_after_batch_correction.h5ad
│ │ ├── 05_LUAD_primary_site_cancer_Kim_NCommun_2020_merged_after_batch_correction.h5ad
│ │ ├── 06_NSCLC_tumor_tissue_Guo_NMed_2018_merged_after_batch_correction.h5ad
│ │ └── 07_pan_cancer_07_GSE157220_log2cpm1p_filtered.h5ad
│ └── selected_marker_genes.csv
├── model_evaluation
│ ├── Fig.3a_compare_different_algos.py
│ ├── Fig.3c_predict_cell_prop_other_test_set.py
│ ├── cibersortx_preprocessing.py
│ └── predicted_cell_fractions
│ ├── CIBERSORT_result/*
│ ├── DeSide_result/*
│ ├── EPIC_1125/*
│ ├── Kassandra_result/*
│ ├── Scaden_result/*
│ └── merged_result
│ ├── CIBERSORT_hnscc_pred_cell_prop.csv
│ ├── CIBERSORT_luad_pred_cell_prop.csv
│ ├── DeSide_pred_cell_prop.csv
│ ├── DeSide_softmax_pred_cell_prop.csv
│ ├── EPIC_self_pred_cell_prop.csv
│ ├── Kassandra_self_pred_cell_prop.csv
│ ├── Scaden_ascites_pred_cell_prop.csv
│ └── Scaden_simu_bulk_pred_cell_prop.csv
├── plot_fig
│ ├── Fig.1 - PCA Plot.ipynb
│ ├── Fig.1.ipynb
│ ├── Fig.2.ipynb
│ ├── Fig.3.ipynb
│ ├── sup_figures/*
│ └── sup_figures.ipynb
├── results
│ └── whole_workflow_20230216_7ds_new_hp_without_caner_cell
│ ├── DeSide_009
│ │ ├── Mixed_N100K_random/*
│ │ ├── Mixed_N100K_random_1/*
│ │ ├── Mixed_N100K_random_2/*
│ │ ├── Mixed_N100K_random_3/*
│ │ ├── Mixed_N100K_random_4/*
│ │ ├── Mixed_N100K_segment_filtered/*
│ │ ├── Mixed_N100K_segment_filtered_1/*
│ │ ├── Mixed_N100K_segment_filtered_2/*
│ │ ├── Mixed_N100K_segment_filtered_3/*
│ │ ├── Mixed_N100K_segment_filtered_4/*
│ │ ├── Mixed_N100K_segment_filtered-Mixed_N100K_segment_without_filtering/*
│ │ ├── Mixed_N100K_segment_filtered_1-Mixed_N100K_segment_without_filtering/*
│ │ ├── Mixed_N100K_segment_filtered_2-Mixed_N100K_segment_without_filtering/*
│ │ ├── Mixed_N100K_segment_filtered_3-Mixed_N100K_segment_without_filtering/*
│ │ ├── Mixed_N100K_segment_filtered_4-Mixed_N100K_segment_without_filtering/*
│ │ ├── Mixed_N100K_segment_without_filtering/*
│ │ ├── Mixed_N100K_segment_without_filtering_1/*
│ │ ├── Mixed_N100K_segment_without_filtering_2/*
│ │ ├── Mixed_N100K_segment_without_filtering_3/*
│ │ ├── Mixed_N100K_segment_without_filtering_4/*
│ │ ├── Mixed_N200K_random/*
│ │ ├── Mixed_N200K_segment_filtered/*
│ │ └── Mixed_N200K_segment_without_filtering/*
│ ├── new_workflow_2_009.log
│ ├── new_workflow_2_009_2.log
│ ├── new_workflow_2_009_3.log
│ ├── new_workflow_2_009_3_random.log
│ ├── new_workflow_2_random_sampling1.log
│ └── new_workflow_2_random_sampling2.log
└── single_cell_dataset_integration
├── 01deal_with_Cillo et al Immunity.ipynb
├── 02deal_with_PengJ et al Cell Res.ipynb
├── 03deal_with_Puram et al Cell.ipynb
├── 04deal_with_Steele et al Nat Cancer.ipynb
├── 05deal_with_Kim et al Nat Commun.ipynb
├── 06deal_with_Guo et al Nat Med.ipynb
├── 07deal_with_pan_cancer_cell_lines.ipynb
├── 08filter_and_merge_01_06.py
├── 09add_pan_cancer_dataset.ipynb
└── UMAP_of_D1.ipynb
Files
DeSide-1.0.2.zip
Additional details
Related works
- Is cited by
- 10.1101/2023.05.11.540466 (DOI)