Skip to content

Commit

Permalink
Updated datasets 2023-04-29 UTC
Browse files Browse the repository at this point in the history
  • Loading branch information
@actions-user
actions-user committed Apr 29, 2023
1 parent 97a270d commit 848b2e4
Show file tree
Hide file tree
Showing 4 changed files with 359 additions and 207 deletions.
76 changes: 56 additions & 20 deletions aws_open_datasets.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -38,8 +38,8 @@
{
"Name": "1000 Genomes Phase 3 Reanalysis with DRAGEN 3.5 and 3.7 - BAM, SNV-vcf, SNV-gvcf, STR-vcf, STR-bam, SV-vcf, ROH-vcf, CNV-vcf, CNV-bw, cyp2",
"Description": "BAM, SNV-vcf, SNV-gvcf, STR-vcf, STR-bam, SV-vcf, ROH-vcf, CNV-vcf, CNV-bw, cyp2",
"ARN": "arn:aws:s3:::1000genomes-dragen-3.7.6",
"Region": "us-west-2",
"ARN": "arn:aws:s3:::1000genomes-dragen-v3.7.6",
"Region": "us-east-1",
"Type": "S3 Bucket",
"Explore": null,
"Documentation": "[DRAGEN Support Resources](https://support.illumina.com/sequencing/sequencing_so",
Expand All @@ -56,8 +56,8 @@
{
"Name": "1000 Genomes Phase 3 Reanalysis with DRAGEN 3.5 and 3.7 - BAM, SNV-vcf, SNV-gvcf, STR-vcf, STR-bam, SV-vcf, ROH-vcf, CNV-vcf, CNV-bw, cyp2",
"Description": "BAM, SNV-vcf, SNV-gvcf, STR-vcf, STR-bam, SV-vcf, ROH-vcf, CNV-vcf, CNV-bw, cyp2",
"ARN": "arn:aws:s3:::1000genomes-dragen-v3.7.6",
"Region": "us-east-1",
"ARN": "arn:aws:s3:::1000genomes-dragen-3.7.6",
"Region": "us-west-2",
"Type": "S3 Bucket",
"Explore": null,
"Documentation": "[DRAGEN Support Resources](https://support.illumina.com/sequencing/sequencing_so",
Expand Down Expand Up @@ -1052,11 +1052,11 @@
{
"Name": "Australasian Genomes - Data files",
"Description": "Data files",
"ARN": "arn:aws:s3:::koalagenomes",
"ARN": "arn:aws:s3:::threatenedspecies",
"Region": "ap-southeast-2",
"Type": "S3 Bucket",
"Explore": [
"[Browse Bucket](https://koalagenomes.s3.ap-southeast-2.amazonaws.com/index.html)"
"[Browse Bucket](https://threatenedspecies.s3.ap-southeast-2.amazonaws.com/index.html)"
],
"Documentation": "https://awgg-lab.github.io/australasiangenomes/",
"Contact": "[email protected]",
Expand All @@ -1072,11 +1072,11 @@
{
"Name": "Australasian Genomes - Data files",
"Description": "Data files",
"ARN": "arn:aws:s3:::threatenedspecies",
"ARN": "arn:aws:s3:::koalagenomes",
"Region": "ap-southeast-2",
"Type": "S3 Bucket",
"Explore": [
"[Browse Bucket](https://threatenedspecies.s3.ap-southeast-2.amazonaws.com/index.html)"
"[Browse Bucket](https://koalagenomes.s3.ap-southeast-2.amazonaws.com/index.html)"
],
"Documentation": "https://awgg-lab.github.io/australasiangenomes/",
"Contact": "[email protected]",
Expand Down Expand Up @@ -1854,7 +1854,7 @@
{
"Name": "Cancer Genome Characterization Initiatives - Burkitt Lymphoma, HIV+ Cervical Cancer - Clinical Supplement, Biospecimen Supplement, RNA-Seq Gene Expression Quantificat",
"Description": "Clinical Supplement, Biospecimen Supplement, RNA-Seq Gene Expression Quantificat",
"ARN": "arn:aws:s3:::gdc-cgci-phs000235-2-open",
"ARN": "arn:aws:s3:::gdc-cgci-blgsp-phs000235-2-open",
"Region": "us-east-1",
"Type": "S3 Bucket",
"Explore": null,
Expand All @@ -1872,7 +1872,7 @@
{
"Name": "Cancer Genome Characterization Initiatives - Burkitt Lymphoma, HIV+ Cervical Cancer - Clinical Supplement, Biospecimen Supplement, RNA-Seq Gene Expression Quantificat",
"Description": "Clinical Supplement, Biospecimen Supplement, RNA-Seq Gene Expression Quantificat",
"ARN": "arn:aws:s3:::gdc-cgci-blgsp-phs000235-2-open",
"ARN": "arn:aws:s3:::gdc-cgci-phs000235-2-open",
"Region": "us-east-1",
"Type": "S3 Bucket",
"Explore": null,
Expand Down Expand Up @@ -5187,7 +5187,7 @@
{
"Name": "Gabriella Miller Kids First Pediatric Research Program (Kids First) - Kids First Pediatric Research Study in Familial Predisposition to Hematopoietic",
"Description": "Kids First Pediatric Research Study in Familial Predisposition to Hematopoietic",
"ARN": "arn:aws:s3:::kf-study-us-east-1-prd-sd-w0v965xz",
"ARN": "arn:aws:s3:::kf-study-us-east-1-prd-sd-vttshwv4",
"Region": "us-east-1",
"Type": "S3 Bucket",
"Explore": null,
Expand All @@ -5205,7 +5205,7 @@
{
"Name": "Gabriella Miller Kids First Pediatric Research Program (Kids First) - Kids First Pediatric Research Study in Familial Predisposition to Hematopoietic",
"Description": "Kids First Pediatric Research Study in Familial Predisposition to Hematopoietic",
"ARN": "arn:aws:s3:::kf-study-us-east-1-prd-sd-vttshwv4",
"ARN": "arn:aws:s3:::kf-study-us-east-1-prd-sd-w0v965xz",
"Region": "us-east-1",
"Type": "S3 Bucket",
"Explore": null,
Expand Down Expand Up @@ -5661,10 +5661,12 @@
{
"Name": "Global Biodiversity Information Facility (GBIF) Species Occurrences - GBIF species occurrence data in Parquet format (eu-central-1 region)",
"Description": "GBIF species occurrence data in Parquet format (eu-central-1 region)",
"ARN": "arn:aws:sns:af-south-1:288719126026:gbif-open-data-eu-central-1-object_created",
"ARN": "arn:aws:s3:::gbif-open-data-eu-central-1",
"Region": "eu-central-1",
"Type": "SNS Topic",
"Explore": null,
"Type": "S3 Bucket",
"Explore": [
"[Browse bucket](https://gbif-open-data-eu-central-1.s3.eu-central-1.amazonaws.com/index.html)"
],
"Documentation": "Documentation can be found [here](https://github.com/gbif/occurrence/blob/master",
"Contact": "[email protected]",
"ManagedBy": "The Global Biodiversity Information Facility ([GBIF](https://www.gbif.org))",
Expand All @@ -5679,12 +5681,10 @@
{
"Name": "Global Biodiversity Information Facility (GBIF) Species Occurrences - GBIF species occurrence data in Parquet format (eu-central-1 region)",
"Description": "GBIF species occurrence data in Parquet format (eu-central-1 region)",
"ARN": "arn:aws:s3:::gbif-open-data-eu-central-1",
"ARN": "arn:aws:sns:af-south-1:288719126026:gbif-open-data-eu-central-1-object_created",
"Region": "eu-central-1",
"Type": "S3 Bucket",
"Explore": [
"[Browse bucket](https://gbif-open-data-eu-central-1.s3.eu-central-1.amazonaws.com/index.html)"
],
"Type": "SNS Topic",
"Explore": null,
"Documentation": "Documentation can be found [here](https://github.com/gbif/occurrence/blob/master",
"Contact": "[email protected]",
"ManagedBy": "The Global Biodiversity Information Facility ([GBIF](https://www.gbif.org))",
Expand Down Expand Up @@ -6491,6 +6491,24 @@
"Host": null,
"AccountRequired": null
},
{
"Name": "Integrative Analysis of Lung Adenocarcinoma in Environment and Genetics Lung cancer Etiology (Phase 2)",
"Description": "Whole Genome Sequencing, Whole Exome Sequencing",
"ARN": "arn:aws:s3:::gdc-cddp-eagle-1-phs001239-2-open",
"Region": "us-east-1",
"Type": "S3 Bucket",
"Explore": null,
"Documentation": "https://ftp.ncbi.nlm.nih.gov/dbgap/studies/phs001239/phs001239.v1.p1",
"Contact": "[email protected]",
"ManagedBy": "[Center for Translational Data Science at The University of Chicago](https://ctd",
"UpdateFrequency": "Genomic Data Commons (GDC) is source of truth for this dataset; GDC offers month",
"License": "(NIH Genomic Data Sharing Policy)[https://gdc.cancer.gov/access-data/data-access",
"Tags": "cancer, whole exome sequencing, whole genome sequencing, aws-pds, life sciences, STRIDES, genomic, epigenomics",
"RequesterPays": null,
"ControlledAccess": null,
"Host": null,
"AccountRequired": null
},
{
"Name": "International Neuroimaging Data-Sharing Initiative (INDI)",
"Description": "Neuroimaging data for the International Neuroimaging Data-Sharing Initiative (IN",
Expand Down Expand Up @@ -7096,6 +7114,24 @@
"Host": null,
"AccountRequired": null
},
{
"Name": "Molecular Profiling to Predict Response to Treatment (phs001965)",
"Description": "miRNA Sequencing, Total RNA Sequencing, Whole Genome Sequencing, Targeted Sequen",
"ARN": "arn:aws:s3:::gdc-mp2prt-wt-phs001965-2-open",
"Region": "us-east-1",
"Type": "S3 Bucket",
"Explore": null,
"Documentation": "https://datacatalog.ccdi.cancer.gov/dataset/GDC-MP2PRT",
"Contact": "[email protected]",
"ManagedBy": "[Center for Translational Data Science at The University of Chicago](https://ctd",
"UpdateFrequency": "Genomic Data Commons (GDC) is source of truth for this dataset; GDC offers month",
"License": "[NIH Genomic Data Sharing Policy](https://gdc.cancer.gov/access-data/data-access",
"Tags": "aws-pds, life sciences, cancer, genomic, whole genome sequencing, STRIDES",
"RequesterPays": null,
"ControlledAccess": null,
"Host": null,
"AccountRequired": null
},
{
"Name": "Mouse Brain Anatomy: MouseLight Imagery",
"Description": "Imagery and Metadata",
Expand Down
Loading

0 comments on commit 848b2e4

Please sign in to comment.