Merge branch 'main' into main

cstner · web-flow · commit 4957527e3899 · 2025-10-10T09:15:59.000-08:00
diff --git a/datasets/aws-public-blockchain.yaml b/datasets/aws-public-blockchain.yaml
@@ -13,6 +13,7 @@ Description: >
   - XRP Ledger              - SonarX  - <code>s3://aws-public-blockchain/v1.1/sonarx/xrp/</code><br>
   - Stellar(<a href="https://developers.stellar.org/docs/learn/fundamentals/data-format/xdr" rel="noopener noreferrer">XDR files</a>)              - Stellar - <code>s3://aws-public-blockchain/v1.1/stellar/</code><br>
   - The Open Network (TON)  - TON - <code>s3://aws-public-blockchain/v1.1/ton/</code><br>
+  - Cronos                  - Cronos - <code>s3://aws-public-blockchain/v1.1/cronos/</code><br>
   </br> 
 
   <h4>Become a Data Provider</h4>
@@ -24,6 +25,7 @@ Contact: aws-blockchain-data@amazon.com
 ManagedBy: "[Amazon Web Services](https://aws.amazon.com/)"
 UpdateFrequency: New data is delivered daily to the current date folders Parquet files.
 Tags:
+  - aws-pds
   - blockchain
   - web3
 License: https://github.com/aws-samples/digital-assets-examples/blob/main/LICENSE
diff --git a/datasets/colorado-elevation-data.yaml b/datasets/colorado-elevation-data.yaml
@@ -2,7 +2,7 @@ Name: State of Colorado Elevation Data
 Description: The State of Colorado has gathered public historical elevation data.
 Documentation: https://docs.google.com/document/d/1HMO-d4cCrBvFa2F6-N3lhP6rkezlvBmSUFA5S8t_ekQ/edit?usp=sharing
 Contact: oit_gis@state.co.us
-ManagedBy: State of Colorado Governor's Office of Information Technology (OIT) GIS team
+ManagedBy: State of Colorado Governors Office of Information Technology OIT GIS team
 UpdateFrequency: Periodically
 Tags:
   - aws-pds
diff --git a/datasets/colorado-imagery.yaml b/datasets/colorado-imagery.yaml
@@ -2,7 +2,7 @@ Name: State of Colorado Imagery
 Description: The State of Colorado has gathered public historical imagery ranging from 2005 to 2021.
 Documentation: https://docs.google.com/document/d/1YDHignUj9lQTMw2J-SqA96MTP8KmJYtk2ZKKC2ZYuPE/edit?usp=sharing
 Contact: oit_gis@state.co.us
-ManagedBy: State of Colorado Governor's Office of Information Technology (OIT) GIS team
+ManagedBy: State of Colorado Governors Office of Information Technology OIT GIS team
 UpdateFrequency: Periodically
 Collabs:
   ASDI:
diff --git a/datasets/deepdrug-dpeb.yaml b/datasets/deepdrug-dpeb.yaml
@@ -15,8 +15,8 @@ License: MIT
 Citation: "Sajol MSI et al. DeepDrug Protein Embeddings Bank (DPEB) was accessed on [DATE] at https://registry.opendata.aws/dpeb"
 Resources:
   - Description: Multimodal human protein embeddings (AlphaFold2, BioEmbeddings, ESM-2, ProtVec) with JSONL-formatted metadata containing FASTA, UniProt IDs, and embeddings.
-    ARN: arn:aws:s3:::deepdrug-dpeb-human-protein-embeddings
-    Region: us-east-1
+    ARN: arn:aws:s3:::deepdrug-dpeb
+    Region: us-west-2
     Type: S3 Bucket
 DataAtWork:
   Tutorials:
diff --git a/datasets/depmap-omics-ccle.yaml b/datasets/depmap-omics-ccle.yaml
@@ -0,0 +1,71 @@
+Name: The Cancer Dependency Map (DepMap) Cancer Cell Line Encyclopedia (CCLE) Dataset
+Description: This dataset consists of whole genome sequencing (WGS), whole exome sequencing (WES), and RNA sequencing files generated from ~1000 cancer cell lines described in Ghandi et al., 2019.
+Documentation: https://github.com/broadinstitute/depmap-omics-ccle
+Contact: https://forum.depmap.org
+ManagedBy: "[Cancer Data Science](https://cancerdatascience.org/), [Broad Institute](https://www.broadinstitute.org/)"
+UpdateFrequency: occasionally (as additional sequencings are generated for publicly-releasible CCLE models)
+Tags:
+  - aws-pds
+  - bam
+  - biology
+  - bioinformatics
+  - cancer
+  - genetic
+  - genomic
+  - Homo sapiens
+  - life sciences
+  - short read sequencing
+  - transcriptomics
+  - whole exome sequencing
+  - whole genome sequencing
+License: https://grants.nih.gov/policy-and-compliance/policy-topics/sharing-policies/accessing-data/using-genomic-data
+Citation: Ghandi, Huang, Jané-Valbuena et al. Next-generation characterization of the Cancer Cell Line Encyclopedia. Nature 569, 503–508 (2019). https://doi.org/10.1038/s41586-019-1186-3
+Resources:
+  - Description: CRAM/BAM files (and their corresponding CRAI/BAI indexes) for RNA, WES, and WGS samples released by The Cancer Dependency Map (DepMap) as part of the Cancer Cell Line Encyclopedia (CCLE) project
+    ARN: arn:aws:s3:::depmap-omics-ccle
+    Region: us-east-1
+    Type: S3 Bucket
+  - Description: Notifications for new depmap-omics-ccle data
+    ARN: arn:aws:sns:us-east-1:019511184952:depmap-omics-ccle-object_created
+    Region: us-east-1
+    Type: SNS Topic
+DataAtWork:
+  Tutorials:
+    - Title: DepMap Omics CCLE data on the AWS Open Data Registry
+      URL: https://github.com/broadinstitute/depmap-omics-ccle
+      AuthorName: Devin McCabe
+  Tools & Applications:
+    - Title: The Cancer Dependency Map (DepMap)
+      URL: https://depmap.org
+      AuthorName: Arafeh, Shibue, Dempster et al.
+    - Title: Cancer Cell Line Encyclopedia (CCLE)
+      URL: https://sites.broadinstitute.org/ccle
+      AuthorName: Ghandi, Huang, Jané-Valbuena et al.
+  Publications:
+    - Title: Next-generation characterization of the Cancer Cell Line Encyclopedia
+      URL: https://www.nature.com/articles/s41586-019-1186-3
+      AuthorName: Ghandi, Huang, Jané-Valbuena et al.
+    - Title: The present and future of the Cancer Dependency Map
+      URL: https://www.nature.com/articles/s41568-024-00763-x
+      AuthorName: Arafeh, Shibue, Dempster et al.
+      AuthorURL: https://depmap.org
+    - Title: Partial gene suppression improves identification of cancer vulnerabilities when CRISPR-Cas9 knockout is pan-lethal
+      URL: https://genomebiology.biomedcentral.com/articles/10.1186/s13059-023-03020-w
+      AuthorName: Krill-Burger, Dempster, Borah et al.
+    - Title: Genetic dependencies associated with transcription factor activities in human cancer cell lines
+      URL: https://www.sciencedirect.com/science/article/pii/S2211124724005035
+      AuthorName: Thatikonda, Supper, Wachter et al.
+    - Title: Bridging the gap between cancer cell line models and tumours using gene expression data
+      URL: https://www.nature.com/articles/s41416-021-01359-0
+      AuthorName: Noorbakhsh, Vazquez & McFarland
+    - Title: Integrated cross-study datasets of genetic dependencies in cancer
+      URL: https://www.nature.com/articles/s41467-021-21898-7
+      AuthorName: Pacini, Dempster, Boyle et al.
+    - Title: Machine learning multi-omics analysis reveals cancer driver dysregulation in pan-cancer cell lines compared to primary tumors
+      URL: https://www.nature.com/articles/s42003-022-04075-4
+      AuthorName: Sanders, Chandra, Zebarjadi et al.
+    - Title: "The Network Zoo: a multilingual package for the inference and analysis of gene regulatory networks"
+      URL: https://link.springer.com/article/10.1186/s13059-023-02877-1
+      AuthorName: Ben Guebila, Wang, Lopes-Ramos et al.
+ADXCategories:
+  - Healthcare & Life Sciences Data
diff --git a/datasets/dmi-danra-05.yaml b/datasets/dmi-danra-05.yaml
@@ -0,0 +1,50 @@
+Name: Danish Meteorological Institute (DMI) Reanalysis dataset v0.5
+Description: DANRA is a high-resolution meteorological reanalysis dataset for Denmark and Northwestern Europe covering the period September 1990 to December 2023
+Documentation: https://dmidk.github.io/danradocs/intro.html
+Contact: https://www.dmi.dk/kontakt
+ManagedBy: "[Danish Meteorological Institute](https://www.dmi.dk/)"
+UpdateFrequency: Not updated
+Collabs:
+  ASDI:
+    Tags:
+      - climate
+      - weather
+Tags:
+  - aws-pds
+  - air temperature
+  - atmosphere
+  - geospatial
+  - global
+  - land
+  - meteorological
+  - near-surface air temperature
+  - near-surface relative humidity
+  - near-surface specific humidity
+  - model
+  - water
+  - weather
+  - zarr
+License: DMI Reanalysis dataset v0.5 is distributed under the [Creative Commons License CC BY 4.0](https://creativecommons.org/licenses/by/4.0/legalcode.en)
+Resources:
+  - Description: DMI Reanalysis dataset v0.5
+    ARN: arn:aws:s3:::dmi-danra-05
+    Region: eu-north-1
+    Type: S3 Bucket
+DataAtWork:
+  Tutorials:
+    - Title: Looking at distributions
+      URL: https://dmidk.github.io/danradocs/notebooks/distributions.html
+      NotebookURL: https://dmidk.github.io/danradocs/_sources/notebooks/distributions.ipynb
+      AuthorName: Danish Meteorological Institute
+      AuthorURL: https://www.dmi.dk/
+      Services:
+        - Amazon S3
+    - Title: DANRA figures
+      URL: https://dmidk.github.io/danradocs/notebooks/paper-figures.html
+      NotebookURL: https://dmidk.github.io/danradocs/_sources/notebooks/paper-figures.ipynb
+      AuthorName: Danish Meteorological Institute
+      AuthorURL: https://www.dmi.dk/
+      Services:
+        - Amazon S3
+ADXCategories:
+  - Environmental Data
diff --git a/datasets/e11bio-prism.yaml b/datasets/e11bio-prism.yaml
@@ -0,0 +1,62 @@
+Name: E11bio PRISM
+Description: |
+  This dataset was generated using E11.bio's PRISM technology (Protein Reconstruction and Identification through Multiplexing),
+  a platform that combines viral barcoding, expansion microscopy, and iterative immunolabeling for large-scale neuronal reconstruction.
+
+  Neurons in the mouse hippocampal CA3 were transduced with a library of adeno-associated viruses (AAVs)
+  encoding diverse “protein bits”—small epitope tags that act as combinatorial barcodes. 
+  Tissue was then processed with an expansion microscopy protocol, physically enlarging the sample ~5×
+  to achieve an effective voxel size of ~35 × 35 × 80 nm.
+  Across multiple cycles of staining, imaging, and antibody stripping, the same expanded tissue was repeatedly labeled,
+  enabling iterative immunostaining for dozens of molecular targets.
+
+  The dataset includes:
+  1) Light microscopy data of multiplexed brain tissue
+  2) Segmentations of cell morphology and protein expression in the tissue
+  3) Files for faster visualization of the data (e.g. precomputed format)
+  4) Additional supporting files (e.g. model predictions, manual annotations etc.)
+Documentation: https://github.com/e11bio/e11-open-data
+Contact: hello@e11.bio
+ManagedBy: "[E11.bio](https://e11.bio)"
+UpdateFrequency: As required
+Tags:
+  - bioinformatics
+  - biology
+  - brain images
+  - cell imaging
+  - computer vision
+  - fluorescence imaging
+  - high-throughput imaging
+  - image processing
+  - imaging
+  - ion channels
+  - life sciences
+  - machine learning
+  - microscopy
+  - morphological reconstructions
+  - Mus musculus
+  - neurobiology
+  - neuroimaging
+  - neuroscience
+  - protein
+  - segmentation
+  - zarr
+  - aws-pds
+License: https://e11.bio/terms-of-use
+Resources:
+  - Description: Data files in a public bucket
+    ARN: arn:aws:s3:::e11bio-prism
+    Region: us-east-1
+    Type: S3 Bucket
+DataAtWork:
+  Tutorials:
+    - Title: E11.Bio PRISM OpenData
+      URL: https://github.com/e11bio/e11-open-data
+      NotebookURL:
+      AuthorName: Arlo Sheridan & Johan Winnubst
+      AuthorURL: https://e11.bio/team
+  Tools & Applications:
+    - Title: Volara 
+      URL: https://github.com/e11bio/volara
+      AuthorName: Arlo Sheridan & Will Patton
+      AuthorURL: https://e11.bio/team
diff --git a/datasets/ecmwf-era5.yaml b/datasets/ecmwf-era5.yaml
@@ -1,5 +1,6 @@
 Deprecated: True
-DeprecatedNotice: The provider of this dataset will no longer maintain this dataset.  We are open to talking with anyone else who might be willing to provide this dataset to the community.  Contact <a href="mailto:opendata@amazon.com">opendata@amazon.com</a>.
+DeprecatedNotice: |
+  <h3>The provider of this dataset will no longer maintain it, but has instead worked with NSF NCAR to rehost the dataset here: <a href=https://registry.opendata.aws/nsf-ncar-era5/>https://registry.opendata.aws/nsf-ncar-era5/</a> </h3>
 Name: ECMWF ERA5 Reanalysis
 Description: |
   ERA5 is the fifth generation of ECMWF atmospheric reanalyses of the global climate, and the first reanalysis produced as an operational service. It utilizes the best available observation data from satellites and in-situ stations, which are assimilated and processed using ECMWF's Integrated Forecast System (IFS) Cycle 41r2.
diff --git a/datasets/fvcom_gom3.yaml b/datasets/fvcom_gom3.yaml
@@ -0,0 +1,28 @@
+Name: UMASSD-FVCOM-GOM3-Hindcast
+Description: The Finite Volume Community Ocean Model (FVCOM) was used to simulate ocean water levels, velocity, temperature and salinity over a multi-decadal period (1984-present) in the waters of the Northeast US including the Gulf of Maine.  The model was configured and run by the Dr. Changshen Chen, Director of the Marine Ecosystems Dynamics Modeling Laboratory in the School for Marine Science & Technology at the University of Massachusetts Dartmouth.  The triangular mesh has a varying horizontal resolution from several hundred meters inshore to several kilometers offshore, and 45 terrain-following vertical layers.  The model output was saved at hourly intervals from 2009-08-21 to 2022-06-17. 
+Documentation: https://en.wikipedia.org/wiki/Finite_Volume_Community_Ocean_Model
+Contact: rich@opensciencecomputing.com
+ManagedBy: Open Science Computing, LLC
+UpdateFrequency: None
+Citation: https://web.archive.org/web/20161229211546id_/http://fvcom.smast.umassd.edu/wp-content/uploads/2013/11/MITSG_12-25.pdf
+Tags:
+  - aws-pds
+  - oceans
+License: CC0
+Resources:
+  - Description: A collection of NetCDF files, kerchunk-generated Parquet reference files, and an Intake catalog
+    ARN: arn:aws:s3:::fvcom-gom3
+    Region: us-east-1
+    Type: S3 Bucket
+DataAtWork:
+  Tutorials:
+    - Title: FVCOM Explorer Notebook
+      URL: https://github.com/opensciencecomputing/fvcom
+      NotebookURL: https://github.com/opensciencecomputing/umassd-fvcom/blob/main/fvcom_gom3_explore.ipynb
+      AuthorName: Rich Signell
+      AuthorURL: https://about.me/rich.signell
+      Services:
+  Publications:
+    - Title: An Unstructured Grid, Finite Volume, Three Dimensional, Primitive Equations Ocean Model with Application to Coastal Ocean and Estuaries
+      URL: https://doi.org/10.1175/1520-0426(2003)020%3C0159:AUGFVT%3E2.0.CO;2
+      AuthorName: Changsheng Chen, Hedong Liu, and Robert C. Beardsley
diff --git a/datasets/humancellatlas.yaml b/datasets/humancellatlas.yaml
@@ -12,7 +12,7 @@ Documentation: https://data.humancellatlas.org/
 
 Contact: https://data.humancellatlas.org/contact
 
-ManagedBy: UC Santa Cruz Genomics Institute, University of California, Santa Cruz (UCSC)
+ManagedBy: UC Santa Cruz Genomics Institute, University of California, Santa Cruz, UCSC
 
 UpdateFrequency: Monthly
 
@@ -95,4 +95,4 @@ DataAtWork:
       AuthorName: "Various authors"
 
 ADXCategories:
-  - Healthcare & Life Sciences Data
+  - Healthcare & Life Sciences Data
diff --git a/datasets/ideam-radares.yaml b/datasets/ideam-radares.yaml
@@ -29,9 +29,9 @@ DataAtWork:
     - Title: Read and plot Sigmet files available on AWS using Xradar
       URL: https://docs.openradarscience.org/projects/xradar/en/stable/notebooks/Read-plot-Sigmet-data-from-AWS.html
       AuthorName: Alfonso Ladino
-    - Title: Taller de datos científicos con Python y R - AtmosCol 2023
-      URL: https://projectpythia.org/AtmosCol-2023/notebooks/2.acceso-datos/2.2.Radares.html
+    - Title: Ciencia de Datos Hidrometeorológicos con Python
+      URL: https://projectpythia.org/AtmosCol-2023/radares
       AuthorName: Alfonso Ladino, Nicole Rivera, Max Grover
     - Title: Specific Differential Phase (KDP) retrieval methods comparison
-      URL: https://projectpythia.org/radar-cookbook/notebooks/example-workflows/kdp-comparison.html
+      URL: https://projectpythia.org/radar-cookbook/notebooks/example-workflows/kdp-comparison/
       AuthorName: Alfonso Ladino, Max Grover
diff --git a/datasets/noaa-nexrad.yaml b/datasets/noaa-nexrad.yaml
@@ -52,14 +52,6 @@ Resources:
     ARN: arn:aws:sns:us-east-1:684042711724:NewNEXRADLevel3Object
     Region: us-east-1
     Type: SNS Topic
-  - Description: "*OLD NEXRAD Level II archive bucket* which is now <b>Deprecated</b>. It is recommended to move to the new bucket: unidata-nexrad-level2 and SNS topic: arn:aws:sns:us-east-1:684042711724:NewNEXRADLevel2Archive"
-    ARN: arn:aws:s3:::noaa-nexrad-level2
-    Region: us-east-1
-    Type: S3 Bucket
-  - Description: "Notifications for the *OLD Level II archival bucket*  which is now <b>Deprecated</b>. It is recommended to move to the new bucket: unidata-nexrad-level2 and SNS topic: arn:aws:sns:us-east-1:684042711724:NewNEXRADLevel2Archive"
-    ARN: arn:aws:sns:us-east-1:811054952067:NewNEXRADLevel2Archive
-    Region: us-east-1
-    Type: SNS Topic
 DataAtWork:
   Tutorials:
     - Title: Using Python to Access NCEI Archived NEXRAD Level 2 Data (Jupyter notebook)
diff --git a/datasets/noaa-wod.yaml b/datasets/noaa-wod.yaml
@@ -3,8 +3,8 @@ Description: >
   The World Ocean Database (WOD) is the largest uniformly formatted, quality-controlled, publicly available historical subsurface ocean profile database. From Captain Cook's second voyage in 1772 to today's automated Argo floats, global aggregation of ocean variable information including temperature, salinity, oxygen, nutrients, and others vs. depth allow for study and understanding of the changing physical, chemical, and to some extent biological state of the World's Oceans. Browse the bucket via the AWS S3 explorer: https://noaa-wod-pds.s3.amazonaws.com/index.html
 Documentation: https://www.nodc.noaa.gov/OC5/WOD/pr_wod.html
 Contact: |
-  For any questions regarding data delivery not associated with this platform or any general questions regarding the NOAA Big Data Program, email noaa.bdp@noaa.gov.
-  <br /> We also seek to identify case studies on how NOAA data is being used and will be featuring those stories in joint publications and in upcoming events. If you are interested in seeing your story highlighted, please share it with the NOAA BDP team here: noaa.bdp@noaa.gov
+  For any questions regarding data delivery not associated with this platform or any general questions regarding the NOAA Open Data Dissemination (NODD) Program, email the NODD Team at nodd@noaa.gov.
+  We also seek to identify case studies on how NOAA data is being used and will be featuring those stories in joint publications and in upcoming events. If you are interested in seeing your story highlighted, please share it with the NODD team by emailing nodd@noaa.gov
 ManagedBy: "[NOAA](http://www.noaa.gov/)"
 UpdateFrequency: Data is update on a quarterly basis
 Collabs:
@@ -34,3 +34,4 @@ DataAtWork:
     - Title: The World Ocean Database User's Manual
       URL: https://data.nodc.noaa.gov/woa/WOD/DOC/wodreadme.pdf
       AuthorName: Hernan E. Garcia, Tim P. Boyer, Ricardo A. Locarnini, Olga K. Baranova, Melissa M. Zweng
+  
diff --git a/datasets/oceanomics.yaml b/datasets/oceanomics.yaml
@@ -2,7 +2,7 @@ Name: OceanOmics
 Description: "Minderoo Foundation OceanOmics aims to establish environmental DNA (eDNA) as a tool to measure, understand, and protect oceans. OceanOmics mainly generates two types of data: eDNA sequencing data (metabarcoding, metagenomics), and genome assembly data (marine vertebrates)."
 Documentation: https://edna.minderoo.org
 Contact: oceanomics@minderoo.org
-ManagedBy: Minderoo Foundation OceanOmics (Dr Shannon Corrigan, Dr Philipp Bayer)
+ManagedBy: Minderoo Foundation OceanOmics, Dr Shannon Corrigan, Dr Philipp Bayer
 UpdateFrequency: Data will be continually updated as it is generated.
 Collabs:
   ASDI:
diff --git a/datasets/proteingym.yaml b/datasets/proteingym.yaml
@@ -3,7 +3,7 @@ Description: |
   ProteinGym is a benchmark suite for assessing the performance of protein fitness prediction and design models. It comprises a large curated collection of 200+ high-throughput experimental assays (~3M mutated sequences), as well as clinical annotations from experts about the pathogenicity of mutants in over 3k human genes.
 Documentation: https://github.com/OATML-Markslab/ProteinGym/blob/main/README.md
 Contact: pascal_notin@hms.harvard.edu
-ManagedBy: "Harvard Medical School; University of Oxford"
+ManagedBy: "Harvard Medical School, University of Oxford"
 UpdateFrequency: Quarterly
 Tags:
   - aws-pds
diff --git a/datasets/st-open-data.yaml b/datasets/st-open-data.yaml
