anvilproject.yaml

Name: NHGRI AnVIL Project

Description: "The NHGRI Analysis, Visualization, and Informatics Lab-space
  (AnVIL) Project (https://anvilproject.org/) is the National Human Genome
  Research Institute's cloud-based platform for genomic data sharing and
  analysis. AnVIL hosts widely used human genome reference datasets generated
  through NHGRI-funded research. AnVIL on Open Data on AWS provides public
  access to open-access datasets available through AnVIL. The project is a
  collaborative effort involving NHGRI, the Broad Institute, Johns Hopkins
  University, the University of California Santa Cruz, Vanderbilt University
  Medical Center, Brigham and Women's Hospital, the Carnegie Institution for
  Science, the City University of New York, the Fred Hutchinson Cancer Research
  Center, Harvard University, Oregon Health & Science University, Massachusetts
  General Hospital, Moffitt Cancer Center, Penn State University, and Washington
  University."

Documentation: "https://explore.anvilproject.org/datasets"

Contact: "https://anvilproject.org/help"

ManagedBy: "The AnVIL Project, and UC Santa Cruz Genomics Institute, University of California, Santa Cruz (UCSC)"

UpdateFrequency: Quarterly

Tags:
  - life sciences
  - biology
  - genome
  - genomic
  - gene expression
  - Homo sapiens

License: "https://anvilproject.org/faq/data-security"

Citation: "Schatz MC, Philippakis AA, Afgan E, Banks E, Carey VJ, Carroll RJ, et al. [Inverting the model of genomics data sharing with the NHGRI Genomic Data Science Analysis, Visualization, and Informatics Lab-space (AnVIL)](https://www.cell.com/cell-genomics/fulltext/S2666-979X(21)00106-3). Cell Genomics. 2022;2. doi:10.1016/j.xgen.2021.100085"

Resources:
  - Description: "An S3 bucket containing all publicly accessible data files in the AnVIL Project. The bucket layout and access procedures are documented at https://github.com/DataBiosphere/azul/blob/develop/docs/mirror.rst and metadata can be viewed at https://explore.anvilproject.org/datasets or accessed programmatically at https://service.explore.anvilproject.org/"
    ARN: arn:aws:s3:::anvilproject
    Region: us-east-1
    Type: S3 Bucket
    Explore:
      - "[Data Browser UI](https://explore.anvilproject.org/datasets)"
      - "[Azul REST Web Service](https://service.explore.anvilproject.org/)"
  - Description: "Notifications for new NHGRI AnVIL data"
    ARN: arn:aws:sns:us-east-1:160936121715:anvilproject-object_created
    Region: us-east-1
    Type: SNS Topic

DataAtWork:
  Publications:
    - Title: "Inverting the model of genomics data sharing with the NHGRI Genomic Data Science Analysis, Visualization, and Informatics Lab-space (AnVIL)"
      URL: "https://doi.org/10.1016/j.xgen.2021.100085"
      AuthorName: "Michael C. Schatz, Anthony A. Philippakis, Enis Afgan, Eric
        Banks, Vincent J. Carey, Robert J. Carroll, Alessandro Culotti, Kyle
        Ellrott, Jeremy Goecks, Robert L. Grossman, Ira M. Hall, Kasper D.
        Hansen, Jonathan Lawson, Jeffrey T. Leek, Anne O’Donnell Luria, Stephen
        Mosher, Martin Morgan, Anton Nekrutenko, Brian D. O’Connor, Kevin
        Osborn, Benedict Paten, Candace Patterson, Frederick J. Tan, Casey
        Overby Taylor, Jennifer Vessio, Levi Waldron, Ting Wang, Kristin
        Wuichet, AnVIL Team"
    - Title: "Beyond the Human Genome Project: The Age of Complete Human Genome
        Sequences and Pangenome References"
      URL: "https://doi.org/10.1146/annurev-genom-021623-081639"
      AuthorName: "Dylan J. Taylor, Jordan M. Eizenga, Qiuhui Li, Arun Das,
        Katharine M. Jenike, Eimear E. Kenny, Karen H. Miga, Jean Monlong, Rajiv
        C. McCoy, Benedict Paten, and Michael C. Schatz"
    - Title: "CNPI: Rapid Analyses of Human Copy Number Data"
      URL: "https://doi.org/10.1016/j.jmb.2025.169313"
      AuthorName: "Jack Ustanik, Tychele N. Turner"
    - Title: "The Galaxy platform for accessible, reproducible, and
        collaborative data analyses: 2024 update"
      URL: "https://doi.org/10.1093/nar/gkae410"
      AuthorName: "The Galaxy Community"
    - Title: "The complete sequence of a human Y chromosome"
      URL: "https://doi.org/10.1038/s41586-023-06457-y"
      AuthorName: "Arang Rhie, Sergey Nurk, Monika Cechova, Savannah J. Hoyt,
        Dylan J. Taylor, Nicolas Altemose, Paul W. Hook, Sergey Koren, Mikko
        Rautiainen, Ivan A. Alexandrov, Jamie Allen, Mobin Asri, Andrey V.
        Bzikadze, Nae-Chyun Chen, Chen-Shan Chin, Mark Diekhans, Paul Flicek,
        Giulio Formenti, Arkarachai Fungtammasan, Carlos Garcia Giron, Erik
        Garrison, Ariel Gershman, Jennifer L. Gerton, Patrick G. S. Grady,
        Andrea Guarracino, Leanne Haggerty, Reza Halabian, Nancy F. Hansen,
        Robert Harris, Gabrielle A. Hartley, William T. Harvey, Marina Haukness,
        Jakob Heinz, Thibaut Hourlier, Robert M. Hubley, Sarah E. Hunt, Stephen
        Hwang, Miten Jain, Rupesh K. Kesharwani, Alexandra P. Lewis, Heng Li,
        Glennis A. Logsdon, Julian K. Lucas, Wojciech Makalowski, Christopher
        Markovic, Fergal J. Martin, Ann M. Mc Cartney, Rajiv C. McCoy, Jennifer
        McDaniel, Brandy M. McNulty, Paul Medvedev, Alla Mikheenko, Katherine M.
        Munson, Terence D. Murphy, Hugh E. Olsen, Nathan D. Olson, Luis F.
        Paulin, David Porubsky, Tamara Potapova, Fedor Ryabov, Steven L.
        Salzberg, Michael E. G. Sauria, Fritz J. Sedlazeck, Kishwar Shafin,
        Valery A. Shepelev, Alaina Shumate, Jessica M. Storer, Likhitha
        Surapaneni, Angela M. Taravella Oill, Françoise Thibaud-Nissen, Winston
        Timp, Marta Tomaszkiewicz, Mitchell R. Vollger, Brian P. Walenz, Allison
        C. Watwood, Matthias H. Weissensteiner, Aaron M. Wenger, Melissa A.
        Wilson, Samantha Zarate, Yiming Zhu, Justin
        M. Zook, Evan E. Eichler, Rachel J. O’Neill, Michael C. Schatz, Karen H.
        Miga, Kateryna D. Makova, Adam M. Phillippy"
    - Title: "Approaching complete genomes, transcriptomes and epi-omes with
        accurate long-read sequencing"
      URL: "https://doi.org/10.1038/s41592-022-01716-8"
      AuthorName: "Sam Kovaka, Shujun Ou, Katharine M. Jenike, Michael C.
      Schatz"
    - Title: "The complete sequence and comparative analysis of ape sex
        chromosomes"
      URL: "https://doi.org/10.1038/s41586-024-07473-2"
      AuthorName: "Kateryna D. Makova, Brandon D. Pickett, Robert S. Harris,
        Gabrielle A. Hartley, Monika Cechova, Karol Pal, Sergey Nurk, DongAhn
        Yoo, Qiuhui Li, Prajna Hebbar, Barbara C. McGrath, Francesca Antonacci,
        Margaux Aubel, Arjun Biddanda, Matthew Borchers, Erich Bornberg-Bauer,
        Gerard G. Bouffard, Shelise Y. Brooks, Lucia Carbone, Laura Carrel,
        Andrew Carroll, Pi-Chuan Chang, Chen-Shan Chin, Daniel E. Cook, Sarah J.
        C. Craig, Luciana de Gennaro, Mark Diekhans, Amalia Dutra, Gage H.
        Garcia, Patrick G. S. Grady, Richard E. Green, Diana Haddad, Pille
        Hallast, William T. Harvey, Glenn Hickey, David A. Hillis, Savannah J.
        Hoyt, Hyeonsoo Jeong, Kaivan Kamali, Sergei L. Kosakovsky Pond, Troy
        M. LaPolice, Charles Lee, Alexandra P. Lewis, Yong-Hwee E. Loh,
        Patrick Masterson, Kelly M. McGarvey, Rajiv C. McCoy, Paul Medvedev,
        Karen H. Miga, Katherine M. Munson, Evgenia Pak, Benedict Paten,
        Brendan J. Pinto, Tamara Potapova, Arang Rhie, Joana L. Rocha, Fedor
        Ryabov, Oliver A. Ryder, Samuel Sacco, Kishwar Shafin, Valery A.
        Shepelev, Viviane Slon, Steven J. Solar, Jessica M. Storer, Peter H.
        Sudmant, Sweetalana, Alex Sweeten, Michael G. Tassia, Françoise
        Thibaud-Nissen, Mario Ventura, Melissa A. Wilson, Alice C. Young,
        Huiqing Zeng, Xinru Zhang, Zachary A. Szpiech, Christian D. Huber,
        Jennifer L. Gerton, Soojin V. Yi, Michael C. Schatz, Ivan A.
        Alexandrov, Sergey Koren, Rachel J. O’Neill, Evan E. Eichler, Adam M.
        Phillippy"
    - Title: "Scalable Nanopore sequencing of human genomes provides a
        comprehensive view of haplotype-resolved variation and methylation"
      URL: "https://doi.org/10.1038/s41592-023-01993-x"
      AuthorName: "Mikhail Kolmogorov, Kimberley J. Billingsley, Mira Mastoras,
        Melissa Meredith, Jean Monlong, Ryan Lorig-Roach, Mobin Asri, Pilar
        Alvarez Jerez, Laksh Malik, Ramita Dewan, Xylena Reed, Rylee M. Genner,
        Kensuke Daida, Sairam Behera, Kishwar Shafin, Trevor Pesout, Jeshuwin
        Prabakaran, Paolo Carnevali, Jianzhi Yang, Arang Rhie, Sonja W. Scholz,
        Bryan J. Traynor, Karen H. Miga, Miten Jain, Winston Timp, Adam M.
        Phillippy, Mark Chaisson, Fritz J. Sedlazeck, Cornelis Blauwendraat,
        Benedict Paten"
    - Title: "The Human Pangenome Project: a global resource to map genomic
        diversity"
      URL: "https://doi.org/10.1038/s41586-022-04601-8"
      AuthorName: "Ting Wang, Lucinda Antonacci-Fulton, Kerstin Howe, Heather A.
        Lawson, Julian K. Lucas, Adam M. Phillippy, Alice B. Popejoy, Mobin
        Asri, Caryn Carson, Mark J. P. Chaisson, Xian Chang, Robert Cook-Deegan,
        Adam L. Felsenfeld, Robert S. Fulton, Erik P. Garrison, Nanibaa’ A.
        Garrison, Tina A. Graves-Lindsay, Hanlee Ji, Eimear E. Kenny, Barbara A.
        Koenig, Daofeng Li, Tobias Marschall, Joshua F. McMichael, Adam M.
        Novak, Deepak Purushotham, Valerie A. Schneider, Baergen I. Schultz,
        Michael W. Smith, Heidi J. Sofia, Tsachy Weissman, Paul Flicek, Heng Li,
        Karen H. Miga, Benedict Paten, Erich D. Jarvis, Ira M. Hall, Evan E.
        Eichler, David Haussler, the Human Pangenome Reference Consortium"
    - Title: "Deciphering the impact of genomic variation on function"
      URL: "https://doi.org/10.1038/s41586-024-07510-0"
      AuthorName: "IGVF Consortium"
    - Title: "A complete reference genome improves analysis of human genetic variation"
      URL: "https://doi.org/10.1126/science.abl3533"
      AuthorName: "Sergey Aganezov, Stephanie M. Yan, Daniela C. Soto, Melanie
        Kirsche, Samantha Zarate, Pavel Avdeyev, Dylan J. Taylor, Kishwar
        Shafin, Alaina Shumate, Chunlin Xiao, Justin Wagner, Jennifer McDaniel,
        Nathan D. Olson, Michael E. G. Sauria, Mitchell R. Vollger, Arang Rhie,
        Melissa Meredith, Skylar Martin, Joyce Lee, Sergey Koren, Jeffrey A.
        Rosenfeld, Benedict Paten, Ryan Layer, Chen-Shan Chin, Fritz J.
        Sedlazeck, Nancy F. Hansen, Danny E. Miller, Adam M. Phillippy, Karen H.
        Miga, Rajiv C. McCoy, Megan Y. Dennis, Justin M. Zook, Michael C.
        Schatz"
    - Title: "Jasmine and Iris: population-scale structural variant comparison
        and analysis"
      URL: "https://doi.org/10.1038/s41592-022-01753-3"
      AuthorName: "Melanie Kirsche, Gautam Prabhu, Rachel Sherman, Bohan Ni,
        Alexis Battle, Sergey Aganezov, Michael C. Schatz"
    - Title: "A draft human pangenome reference"
      URL: "https://www.nature.com/articles/s41586-023-05896-x"
      AuthorName: "Wen-Wei Liao, Mobin Asri, Jana Ebler, Daniel Doerr, Marina
        Haukness, Glenn Hickey, Shuangjia Lu, Julian K. Lucas, Jean Monlong,
        Haley J. Abel, Silvia Buonaiuto, Xian H. Chang, Haoyu Cheng, Justin Chu,
        Vincenza Colonna, Jordan M. Eizenga, Xiaowen Feng, Christian Fischer,
        Robert S. Fulton, Shilpa Garg, Cristian Groza, Andrea Guarracino,
        William T. Harvey, Simon Heumos, Kerstin Howe, Miten Jain, Tsung-Yu Lu,
        Charles Markello, Fergal J. Martin, Matthew W. Mitchell, Katherine M.
        Munson, Moses Njagi Mwaniki, Adam M. Novak, Hugh E. Olsen, Trevor
        Pesout, David Porubsky, Pjotr Prins, Jonas A. Sibbesen, Jouni Sirén,
        Chad Tomlinson, Flavia Villani, Mitchell R. Vollger, Lucinda L.
        Antonacci-Fulton, Gunjan Baid, Carl A. Baker, Anastasiya Belyaeva,
        Konstantinos Billis, Andrew Carroll, Pi-Chuan Chang, Sarah Cody, Daniel
        E. Cook, Robert M. Cook-Deegan, Omar E. Cornejo, Mark Diekhans, Peter
        Ebert, Susan Fairley, Olivier Fedrigo, Adam L. Felsenfeld, Giulio
        Formenti, Adam Frankish, Yan Gao, Nanibaa’ A. Garrison, Carlos Garcia
        Giron, Richard E. Green, Leanne Haggerty, Kendra Hoekzema, Thibaut
        Hourlier, Hanlee P. Ji, Eimear E. Kenny, Barbara A. Koenig, Alexey
        Kolesnikov, Jan O. Korbel, Jennifer Kordosky, Sergey Koren, HoJoon Lee,
        Alexandra P. Lewis, Hugo Magalhães, Santiago Marco-Sola, Pierre Marijon,
        Ann McCartney, Jennifer McDaniel, Jacquelyn Mountcastle, Maria
        Nattestad, Sergey Nurk, Nathan D. Olson, Alice B. Popejoy, Daniela Puiu,
        Mikko Rautiainen, Allison A. Regier, Arang Rhie, Samuel Sacco, Ashley D.
        Sanders, Valerie A. Schneider, Baergen I. Schultz, Kishwar Shafin,
        Michael W. Smith, Heidi J. Sofia, Ahmad N. Abou Tayoun, Françoise
        Thibaud-Nissen, Francesca Floriana Tricomi, Justin Wagner, Brian Walenz,
        Jonathan M. D. Wood, Aleksey V. Zimin, Guillaume Bourque, Mark J. P.
        Chaisson, Paul Flicek, Adam M. Phillippy, Justin M. Zook, Evan E.
        Eichler, David Haussler, Ting Wang, Erich D. Jarvis, Karen H. Miga, Erik
        Garrison, Tobias Marschall, Ira M. Hall, Heng Li, Benedict Paten"

ADXCategories:
  - Healthcare & Life Sciences Data