cBioPortal · dippindots · Apr 10, 2023 · Apr 11, 2023 · Apr 11, 2023 · Jun 27, 2023
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -4,25 +4,6 @@
 #
 version: 2
 jobs:
-
- # Job to validate only the changed studies
- build:
- docker:
- - image: circleci/python:3.6
- resource_class: large
- working_directory: ~/repo/
- steps:
- - checkout
- - run:
- name: Validate changed studies
- command: |
- cd ~/repo/.circleci
- ./install_dependencies.sh
- ./validate_changed_studies.sh
- no_output_timeout: 2h
- - store_artifacts:
- path: ~/test-reports
- destination: ~/test-reports
 
  # Job to validate all studies
  validate_all_studies:
@@ -92,10 +73,6 @@ workflows:
  # is merged into the master branch.
  workflow_on_commit:
  jobs:
- - build:
- filters:
- branches:
- ignore: master
  - validate_changed_seed:
  filters:
  branches:

diff --git a/.github/workflows/validate_changed_studies.yml b/.github/workflows/validate_changed_studies.yml
@@ -0,0 +1,25 @@
+name: Validate Changed Studies
+
+on:
+ pull_request:
+ branches:
+ - master
+
+jobs:
+ build:
+ runs-on: ubuntu-latest
+
+ steps:
+ - name: Checkout code
+ uses: actions/checkout@v2
+
+ - name: Configure Git
+ run: |
+ git config user.name "Continuous Integration"
+ git config user.email "[email protected]"
+
+ - name: Validate changed studies
+ run: |
+ cd .circleci
+ ./install_dependencies.sh
+ ./validate_changed_studies.sh
diff --git a/public/acc_tcga_pan_can_atlas_2018/README.md b/public/acc_tcga_pan_can_atlas_2018/README.md
@@ -7,4 +7,22 @@
 - File Used: `Merge_Clinical.Level_1.20160128` (clin.merged.txt) for each cancer type.
 
 **Data Transformation** 
-- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+
+### The Genetic Ancestry data:
+
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020
+- File Used: `Admixture_by_sample.txt` (Admix percent by sample) for each cancer type.
+
+
+### The Methylation data:
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/node/977
+- File Used: `jhu-usc.edu_PANCAN_HumanMethylation450.betaValue_whitelisted.tsv` (DNA methylation 450K only beta value data matrix) for each cancer type.
+
+**Data Transformation** 
+ - The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+ - The meta info for the Infinium Illumina 450k probes used for this profile is under the folder "probe_meta" "probe_450k_mapinfo_PQ.txt" is the original download from Illumina.
diff --git a/public/acc_tcga_pan_can_atlas_2018/data_clinical_patient.txt b/public/acc_tcga_pan_can_atlas_2018/data_clinical_patient.txt
diff --git a/public/acc_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt b/public/acc_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt
diff --git a/public/acc_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt b/public/acc_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt
@@ -0,0 +1,10 @@
+cancer_study_identifier: acc_tcga_pan_can_atlas_2018
+genetic_alteration_type: GENERIC_ASSAY
+generic_assay_type: ARMLEVEL_CNA
+datatype: LIMIT-VALUE
+stable_id: genetic_ancestry
+profile_name: Genetic Ancestry
+profile_description: Genetic ancestries were determined using five different methods as described in Carrot-Zhang et al (2020). These consensus calls were created based on the ancestral population that received the majority of assignments for each patient. The original data is <a href="https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020">here</a>.
+data_filename: data_genetic_ancestry.txt
+show_profile_in_analysis_tab: true
+generic_entity_meta_properties: NAME
diff --git a/public/blca_tcga_pan_can_atlas_2018/README.md b/public/blca_tcga_pan_can_atlas_2018/README.md
@@ -7,4 +7,22 @@
 - File Used: `Merge_Clinical.Level_1.20160128` (clin.merged.txt) for each cancer type.
 
 **Data Transformation** 
-- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+
+### The Genetic Ancestry data:
+
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020
+- File Used: `Admixture_by_sample.txt` (Admix percent by sample) for each cancer type.
+
+
+### The Methylation data:
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/node/977
+- File Used: `jhu-usc.edu_PANCAN_HumanMethylation450.betaValue_whitelisted.tsv` (DNA methylation 450K only beta value data matrix) for each cancer type.
+
+**Data Transformation** 
+ - The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+ - The meta info for the Infinium Illumina 450k probes used for this profile is under the folder "probe_meta" "probe_450k_mapinfo_PQ.txt" is the original download from Illumina.
diff --git a/public/blca_tcga_pan_can_atlas_2018/data_clinical_patient.txt b/public/blca_tcga_pan_can_atlas_2018/data_clinical_patient.txt
diff --git a/public/blca_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt b/public/blca_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt
diff --git a/public/blca_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt b/public/blca_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt
@@ -0,0 +1,11 @@
+cancer_study_identifier: blca_tcga_pan_can_atlas_2018
+genetic_alteration_type: GENERIC_ASSAY
+generic_assay_type: GENETIC_ANCESTRY
+datatype: LIMIT-VALUE
+stable_id: genetic_ancestry
+profile_name: Genetic Ancestry
+profile_description: Genetic ancestries were determined using five different methods as described in Carrot-Zhang et al (2020). These consensus calls were created based on the ancestral population that received the majority of assignments for each patient. The original data is <a href="https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020">here</a>.
+data_filename: data_genetic_ancestry.txt
+show_profile_in_analysis_tab: true
+generic_entity_meta_properties: NAME
+value_sort_order: ASC
diff --git a/public/brca_tcga_pan_can_atlas_2018/README.md b/public/brca_tcga_pan_can_atlas_2018/README.md
@@ -7,4 +7,22 @@
 - File Used: `Merge_Clinical.Level_1.20160128` (clin.merged.txt) for each cancer type.
 
 **Data Transformation** 
-- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+
+### The Genetic Ancestry data:
+
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020
+- File Used: `Admixture_by_sample.txt` (Admix percent by sample) for each cancer type.
+
+
+### The Methylation data:
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/node/977
+- File Used: `jhu-usc.edu_PANCAN_HumanMethylation450.betaValue_whitelisted.tsv` (DNA methylation 450K only beta value data matrix) for each cancer type.
+
+**Data Transformation** 
+ - The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+ - The meta info for the Infinium Illumina 450k probes used for this profile is under the folder "probe_meta" "probe_450k_mapinfo_PQ.txt" is the original download from Illumina.
diff --git a/public/brca_tcga_pan_can_atlas_2018/data_clinical_patient.txt b/public/brca_tcga_pan_can_atlas_2018/data_clinical_patient.txt
diff --git a/public/brca_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt b/public/brca_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt
diff --git a/public/brca_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt b/public/brca_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt
@@ -0,0 +1,11 @@
+cancer_study_identifier: brca_tcga_pan_can_atlas_2018
+genetic_alteration_type: GENERIC_ASSAY
+generic_assay_type: GENETIC_ANCESTRY
+datatype: LIMIT-VALUE
+stable_id: genetic_ancestry
+profile_name: Genetic Ancestry
+profile_description: Genetic ancestries were determined using five different methods as described in Carrot-Zhang et al (2020). These consensus calls were created based on the ancestral population that received the majority of assignments for each patient. The original data is <a href="https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020">here</a>.
+data_filename: data_genetic_ancestry.txt
+show_profile_in_analysis_tab: true
+generic_entity_meta_properties: NAME
+value_sort_order: ASC
diff --git a/public/cesc_tcga_pan_can_atlas_2018/README.md b/public/cesc_tcga_pan_can_atlas_2018/README.md
@@ -7,4 +7,22 @@
 - File Used: `Merge_Clinical.Level_1.20160128` (clin.merged.txt) for each cancer type.
 
 **Data Transformation** 
-- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+
+### The Genetic Ancestry data:
+
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020
+- File Used: `Admixture_by_sample.txt` (Admix percent by sample) for each cancer type.
+
+
+### The Methylation data:
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/node/977
+- File Used: `jhu-usc.edu_PANCAN_HumanMethylation450.betaValue_whitelisted.tsv` (DNA methylation 450K only beta value data matrix) for each cancer type.
+
+**Data Transformation** 
+ - The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+ - The meta info for the Infinium Illumina 450k probes used for this profile is under the folder "probe_meta" "probe_450k_mapinfo_PQ.txt" is the original download from Illumina.
diff --git a/public/cesc_tcga_pan_can_atlas_2018/data_clinical_patient.txt b/public/cesc_tcga_pan_can_atlas_2018/data_clinical_patient.txt
diff --git a/public/cesc_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt b/public/cesc_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt
diff --git a/public/cesc_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt b/public/cesc_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt
@@ -0,0 +1,11 @@
+cancer_study_identifier: cesc_tcga_pan_can_atlas_2018
+genetic_alteration_type: GENERIC_ASSAY
+generic_assay_type: GENETIC_ANCESTRY
+datatype: LIMIT-VALUE
+stable_id: genetic_ancestry
+profile_name: Genetic Ancestry
+profile_description: Genetic ancestries were determined using five different methods as described in Carrot-Zhang et al (2020). These consensus calls were created based on the ancestral population that received the majority of assignments for each patient. The original data is <a href="https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020">here</a>.
+data_filename: data_genetic_ancestry.txt
+show_profile_in_analysis_tab: true
+generic_entity_meta_properties: NAME
+value_sort_order: ASC
diff --git a/public/chol_tcga_pan_can_atlas_2018/README.md b/public/chol_tcga_pan_can_atlas_2018/README.md
@@ -7,4 +7,22 @@
 - File Used: `Merge_Clinical.Level_1.20160128` (clin.merged.txt) for each cancer type.
 
 **Data Transformation** 
-- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+
+### The Genetic Ancestry data:
+
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020
+- File Used: `Admixture_by_sample.txt` (Admix percent by sample) for each cancer type.
+
+
+### The Methylation data:
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/node/977
+- File Used: `jhu-usc.edu_PANCAN_HumanMethylation450.betaValue_whitelisted.tsv` (DNA methylation 450K only beta value data matrix) for each cancer type.
+
+**Data Transformation** 
+ - The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+ - The meta info for the Infinium Illumina 450k probes used for this profile is under the folder "probe_meta" "probe_450k_mapinfo_PQ.txt" is the original download from Illumina.
diff --git a/public/chol_tcga_pan_can_atlas_2018/data_clinical_patient.txt b/public/chol_tcga_pan_can_atlas_2018/data_clinical_patient.txt
diff --git a/public/chol_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt b/public/chol_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt
diff --git a/public/chol_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt b/public/chol_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt
@@ -0,0 +1,11 @@
+cancer_study_identifier: chol_tcga_pan_can_atlas_2018
+genetic_alteration_type: GENERIC_ASSAY
+generic_assay_type: GENETIC_ANCESTRY
+datatype: LIMIT-VALUE
+stable_id: genetic_ancestry
+profile_name: Genetic Ancestry
+profile_description: Genetic ancestries were determined using five different methods as described in Carrot-Zhang et al (2020). These consensus calls were created based on the ancestral population that received the majority of assignments for each patient. The original data is <a href="https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020">here</a>.
+data_filename: data_genetic_ancestry.txt
+show_profile_in_analysis_tab: true
+generic_entity_meta_properties: NAME
+value_sort_order: ASC
diff --git a/public/coadread_tcga_pan_can_atlas_2018/README.md b/public/coadread_tcga_pan_can_atlas_2018/README.md
@@ -7,4 +7,22 @@
 - File Used: `Merge_Clinical.Level_1.20160128` (clin.merged.txt) for each cancer type.
 
 **Data Transformation** 
-- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+
+### The Genetic Ancestry data:
+
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020
+- File Used: `Admixture_by_sample.txt` (Admix percent by sample) for each cancer type.
+
+
+### The Methylation data:
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/node/977
+- File Used: `jhu-usc.edu_PANCAN_HumanMethylation450.betaValue_whitelisted.tsv` (DNA methylation 450K only beta value data matrix) for each cancer type.
+
+**Data Transformation** 
+ - The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+ - The meta info for the Infinium Illumina 450k probes used for this profile is under the folder "probe_meta" "probe_450k_mapinfo_PQ.txt" is the original download from Illumina.
diff --git a/public/coadread_tcga_pan_can_atlas_2018/data_clinical_patient.txt b/public/coadread_tcga_pan_can_atlas_2018/data_clinical_patient.txt
diff --git a/public/coadread_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt b/public/coadread_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt
diff --git a/public/coadread_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt b/public/coadread_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt
@@ -0,0 +1,11 @@
+cancer_study_identifier: coadread_tcga_pan_can_atlas_2018
+genetic_alteration_type: GENERIC_ASSAY
+generic_assay_type: GENETIC_ANCESTRY
+datatype: LIMIT-VALUE
+stable_id: genetic_ancestry
+profile_name: Genetic Ancestry
+profile_description: Genetic ancestries were determined using five different methods as described in Carrot-Zhang et al (2020). These consensus calls were created based on the ancestral population that received the majority of assignments for each patient. The original data is <a href="https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020">here</a>.
+data_filename: data_genetic_ancestry.txt
+show_profile_in_analysis_tab: true
+generic_entity_meta_properties: NAME
+value_sort_order: ASC
diff --git a/public/dlbc_tcga_pan_can_atlas_2018/README.md b/public/dlbc_tcga_pan_can_atlas_2018/README.md
@@ -7,4 +7,22 @@
 - File Used: `Merge_Clinical.Level_1.20160128` (clin.merged.txt) for each cancer type.
 
 **Data Transformation** 
-- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+- The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+
+### The Genetic Ancestry data:
+
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020
+- File Used: `Admixture_by_sample.txt` (Admix percent by sample) for each cancer type.
+
+
+### The Methylation data:
+
+**Data Source**
+- GDAC Firehose: https://gdc.cancer.gov/node/977
+- File Used: `jhu-usc.edu_PANCAN_HumanMethylation450.betaValue_whitelisted.tsv` (DNA methylation 450K only beta value data matrix) for each cancer type.
+
+**Data Transformation** 
+ - The detailed transformation steps are listed in the Pull Request [here](https://github.com/cBioPortal/datahub/pull/1597)
+ - The meta info for the Infinium Illumina 450k probes used for this profile is under the folder "probe_meta" "probe_450k_mapinfo_PQ.txt" is the original download from Illumina.
diff --git a/public/dlbc_tcga_pan_can_atlas_2018/data_clinical_patient.txt b/public/dlbc_tcga_pan_can_atlas_2018/data_clinical_patient.txt
diff --git a/public/dlbc_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt b/public/dlbc_tcga_pan_can_atlas_2018/data_genetic_ancestry.txt
diff --git a/public/dlbc_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt b/public/dlbc_tcga_pan_can_atlas_2018/meta_genetic_ancestry.txt
@@ -0,0 +1,11 @@
+cancer_study_identifier: dlbc_tcga_pan_can_atlas_2018
+genetic_alteration_type: GENERIC_ASSAY
+generic_assay_type: GENETIC_ANCESTRY
+datatype: LIMIT-VALUE
+stable_id: genetic_ancestry
+profile_name: Genetic Ancestry
+profile_description: Genetic ancestries were determined using five different methods as described in Carrot-Zhang et al (2020). These consensus calls were created based on the ancestral population that received the majority of assignments for each patient. The original data is <a href="https://gdc.cancer.gov/about-data/publications/CCG-AIM-2020">here</a>.
+data_filename: data_genetic_ancestry.txt
+show_profile_in_analysis_tab: true
+generic_entity_meta_properties: NAME
+value_sort_order: ASC