CIViC External Ontology Discussion
Chat #1
You
01:21 AM
What external ontologies does CIViC utilize?
CIViC Bot
01:21 AM
Tool Call
search_docs(query: "external ontologies CIViC uses What ontologies does CIViC utilize external ontologies ReadTheDocs site:CIViC ReadTheDocs")
Tool Result
01:21 AM
Tool Result
Click to expand
[
{
"link": "https://civic.readthedocs.io/en/latest/generated/civic.docs-aliases.html",
"title": "civic.docs-aliases",
"contents": "<no title> — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » <no title> View page source Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/about/citations.html",
"title": "citations",
"contents": "Citations — CIViC documentation About CIViC Participating Meetings & Events FAQ Instructional Videos Scientific Advisory Board Domain Experts AI Editorial Policies Partners Data Clients Figures and Graphics Acknowledgements Citations CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » About CIViC » Citations View page source Citations¶ The following publications are directly related to the CIViC project. Project Organization Title Link(s) CIViC public proposal WashU / Scripps Organizing knowledge to enable personalization of medicine in cancer PubMed: 25222080(2014. Genome Biology) CIViC original publication WashU CIViC is a community knowledgebase for expert crowdsourcing the clinical interpretation of variants in cancer PubMed: 28138153(2017. Nature Genetics) Standards for variant sharing Multi-institution initiative / ClinGen Somatic Working Group ClinGen Cancer Somatic Working Group standardizing and democratizing access to cancer molecular diagnostic data to drive translational research PubMed: 29218886(2018. PSB) Minimum variant level data Multi-institution initiative / ClinGen Somatic Working Group Adapting crowdsourced clinical cancer curation in CIViC to the ClinGen minimum variant level data community‐driven standards PubMed: 30311370(2018. Human Mutation) CIViC SOP WashU Standard operating procedure for curation and clinical interpretation of variants in cancer PubMed: 31779674(2019. Genome Medicine) CIViCmine Canada’s Michael Smith Genome Sciences Centre Text-mining clinically relevant cancer biomarkers for curation into the CIViC database PubMed: 31796060(2019. Genome Medicine) OpenCAP WashU Open-Sourced CIViC Annotation Pipeline to Identify and Annotate Clinically Relevant Variants Using Single-Molecule Molecular Inversion Probes PubMed: 31618044(2019. JCO Clinical Cancer Informatics) CIViCpy WashU CIViCpy: a Python software development and analysis toolkit for the CIViC knowledgebase PubMed: 32191543(2020. JCO Clinical Cancer Informatics) Virtual Molecular Tumor Board Multi-institution initiative / GA4GH (VICC) Collaborative, Multidisciplinary Evaluation of Cancer Variants Through Virtual Molecular Tumor Boards Informs Local Clinical Practices PubMed: 32644817(2020. JCO Clinical Cancer Informatics) Meta-knowledgebase Multi-institution initiative / GA4GH (VICC) A harmonized meta-knowledgebase of clinical interpretations of somatic genomic variants in cancer PubMed: 32246132(2020. Nature Genetics) CIViC community approach Multi-institution WashU / ClinGen / GA4GH (VICC) A community approach to the cancer variant interpretation bottleneck PubMed: 35624339(2022. Nature Cancer) CIViC update 2022 (NAR) Multi-institution WashU / ClinGen / GA4GH (VICC) Evolution of the open-access CIViC knowledgebase is driven by the needs of the cancer variant interpretation community PubMed: 36373660(2022. Nucleic Acids Research) Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/index.html",
"title": "index",
"contents": "Introduction to CIViC — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Introduction to CIViC View page source Introduction to CIViC¶ The Clinical Interpretation of Variants in Cancer (CIViC) knowledgebase is a free and open resource for public use, available online at civicdb.org. To get started using and contributing to CIViC, we recommend that you review the Video Tutorials. These videos cover CIViC and its goals; finding documentation and help resources; browsing and searching knowledgebase contents; adding new evidence, variant summaries, coordinates, gene summaries, and assertions to CIViC; and editing existing CIViC content. For a primer on the fundamentals of cancer variant interpretation, we highly recommend that new users start by reading the CIViC paper and these recently published Standards and Guidelines proposals: CIViC is a community knowledgebase for expert crowdsourcing the clinical interpretation of variants in cancer. Standard operating procedure for curation and clinical interpretation of variants in cancer. ACMG/AMP - Standards and guidelines for the interpretation of sequence variants. ClinGen - Somatic cancer variant curation and harmonization through consensus minimum variant level data (MVLD). AMP/ASCO/CAP - Standards and guidelines for the interpretation and reporting of sequence variants in cancer. ClinGen/CGC/VICC - Standards for the classification of pathogenicity of somatic variants in cancer (oncogenicity). Evaluating the Clinical Validity of Gene-Disease Associations: An Evidence-Based Framework Developed by the Clinical Genome Resource Standardized decision support in next generation sequencing reports of somatic cancer variants The CIViC Ecosystem of Collaborators, Moderators, and Other Stakeholders¶ The CIViC project aims to facilitate a collaborative ecosystem of research scientists, clinical scientists, and patient advocates dedicated to curating an accurate and relevant knowledgebase of clinical interpretations of cancer variants. A principle goal of CIViC is to systematically document the evidence that supports any variant interpretation. The diagram below shows how the various stakeholders in the CIViC ecosystem collaborate to curate and utilize the knowledgebase. The CIViC Ecosystem of Collaborators, Moderators, and Other Stakeholders Using the CIViC Help Docs¶ Navigate the CIViC Help Docs with the navigation menu to the left of each page or the Table of Contents below. About pages provide a high level overview of the CIViC resource. Using CIViC pages provide detailed instructions (including videos) on how to browse, search, and use CIViC data. Curating CIViC pages provide general instruction for contributor (curators and editors) on how to add content to the knowledgebase and CIViC Knowledge Model pages provide detailed definitions and curation instruction for each concept/field in CIViC. Finally, CIViC API and Get Help pages provide additional guidance on using the CIViC API and getting more help. About CIViC Participating Meetings & Events FAQ Instructional Videos Scientific Advisory Board Domain Experts AI Editorial Policies Partners Data Clients Figures and Graphics Acknowledgements Citations CIViC Knowledge Model Evidence Items Assertions Features Molecular Profiles Variants Genes Fusions Factors Variant Groups Sources Curating CIViC General Curation Practices Curating Features Curating Variants Curating Genes Curating Fusions Curating Factors Curating Molecular Profiles Curating Evidence Curating Assertions Curating and Suggesting Sources Prioritizing Curation Effort Example Curation Activities User and Community Pages Becoming an Editor User Interface and Data Instructional Videos Browsing Searching Data Grids Users Organizations Comments Notifications & Mentions Community Data Releases Statistics CIViC API V2 API V1 API (deprecated) Get Help Report a Problem Next Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/genindex.html",
"title": "genindex",
"contents": "Index — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Index Index Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
}
]
CIViC Bot
01:21 AM
Tool Call
search_docs(query: "ontologies used CIViC external ontologies 'ontology' site:civic.readthedocs.io")
Tool Result
01:21 AM
Tool Result
Click to expand
[
{
"link": "https://civic.readthedocs.io/en/latest/generated/civic.docs-aliases.html",
"title": "civic.docs-aliases",
"contents": "<no title> — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » <no title> View page source Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/genindex.html",
"title": "genindex",
"contents": "Index — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Index Index Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/about/citations.html",
"title": "citations",
"contents": "Citations — CIViC documentation About CIViC Participating Meetings & Events FAQ Instructional Videos Scientific Advisory Board Domain Experts AI Editorial Policies Partners Data Clients Figures and Graphics Acknowledgements Citations CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » About CIViC » Citations View page source Citations¶ The following publications are directly related to the CIViC project. Project Organization Title Link(s) CIViC public proposal WashU / Scripps Organizing knowledge to enable personalization of medicine in cancer PubMed: 25222080(2014. Genome Biology) CIViC original publication WashU CIViC is a community knowledgebase for expert crowdsourcing the clinical interpretation of variants in cancer PubMed: 28138153(2017. Nature Genetics) Standards for variant sharing Multi-institution initiative / ClinGen Somatic Working Group ClinGen Cancer Somatic Working Group standardizing and democratizing access to cancer molecular diagnostic data to drive translational research PubMed: 29218886(2018. PSB) Minimum variant level data Multi-institution initiative / ClinGen Somatic Working Group Adapting crowdsourced clinical cancer curation in CIViC to the ClinGen minimum variant level data community‐driven standards PubMed: 30311370(2018. Human Mutation) CIViC SOP WashU Standard operating procedure for curation and clinical interpretation of variants in cancer PubMed: 31779674(2019. Genome Medicine) CIViCmine Canada’s Michael Smith Genome Sciences Centre Text-mining clinically relevant cancer biomarkers for curation into the CIViC database PubMed: 31796060(2019. Genome Medicine) OpenCAP WashU Open-Sourced CIViC Annotation Pipeline to Identify and Annotate Clinically Relevant Variants Using Single-Molecule Molecular Inversion Probes PubMed: 31618044(2019. JCO Clinical Cancer Informatics) CIViCpy WashU CIViCpy: a Python software development and analysis toolkit for the CIViC knowledgebase PubMed: 32191543(2020. JCO Clinical Cancer Informatics) Virtual Molecular Tumor Board Multi-institution initiative / GA4GH (VICC) Collaborative, Multidisciplinary Evaluation of Cancer Variants Through Virtual Molecular Tumor Boards Informs Local Clinical Practices PubMed: 32644817(2020. JCO Clinical Cancer Informatics) Meta-knowledgebase Multi-institution initiative / GA4GH (VICC) A harmonized meta-knowledgebase of clinical interpretations of somatic genomic variants in cancer PubMed: 32246132(2020. Nature Genetics) CIViC community approach Multi-institution WashU / ClinGen / GA4GH (VICC) A community approach to the cancer variant interpretation bottleneck PubMed: 35624339(2022. Nature Cancer) CIViC update 2022 (NAR) Multi-institution WashU / ClinGen / GA4GH (VICC) Evolution of the open-access CIViC knowledgebase is driven by the needs of the cancer variant interpretation community PubMed: 36373660(2022. Nucleic Acids Research) Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/index.html",
"title": "index",
"contents": "Introduction to CIViC — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Introduction to CIViC View page source Introduction to CIViC¶ The Clinical Interpretation of Variants in Cancer (CIViC) knowledgebase is a free and open resource for public use, available online at civicdb.org. To get started using and contributing to CIViC, we recommend that you review the Video Tutorials. These videos cover CIViC and its goals; finding documentation and help resources; browsing and searching knowledgebase contents; adding new evidence, variant summaries, coordinates, gene summaries, and assertions to CIViC; and editing existing CIViC content. For a primer on the fundamentals of cancer variant interpretation, we highly recommend that new users start by reading the CIViC paper and these recently published Standards and Guidelines proposals: CIViC is a community knowledgebase for expert crowdsourcing the clinical interpretation of variants in cancer. Standard operating procedure for curation and clinical interpretation of variants in cancer. ACMG/AMP - Standards and guidelines for the interpretation of sequence variants. ClinGen - Somatic cancer variant curation and harmonization through consensus minimum variant level data (MVLD). AMP/ASCO/CAP - Standards and guidelines for the interpretation and reporting of sequence variants in cancer. ClinGen/CGC/VICC - Standards for the classification of pathogenicity of somatic variants in cancer (oncogenicity). Evaluating the Clinical Validity of Gene-Disease Associations: An Evidence-Based Framework Developed by the Clinical Genome Resource Standardized decision support in next generation sequencing reports of somatic cancer variants The CIViC Ecosystem of Collaborators, Moderators, and Other Stakeholders¶ The CIViC project aims to facilitate a collaborative ecosystem of research scientists, clinical scientists, and patient advocates dedicated to curating an accurate and relevant knowledgebase of clinical interpretations of cancer variants. A principle goal of CIViC is to systematically document the evidence that supports any variant interpretation. The diagram below shows how the various stakeholders in the CIViC ecosystem collaborate to curate and utilize the knowledgebase. The CIViC Ecosystem of Collaborators, Moderators, and Other Stakeholders Using the CIViC Help Docs¶ Navigate the CIViC Help Docs with the navigation menu to the left of each page or the Table of Contents below. About pages provide a high level overview of the CIViC resource. Using CIViC pages provide detailed instructions (including videos) on how to browse, search, and use CIViC data. Curating CIViC pages provide general instruction for contributor (curators and editors) on how to add content to the knowledgebase and CIViC Knowledge Model pages provide detailed definitions and curation instruction for each concept/field in CIViC. Finally, CIViC API and Get Help pages provide additional guidance on using the CIViC API and getting more help. About CIViC Participating Meetings & Events FAQ Instructional Videos Scientific Advisory Board Domain Experts AI Editorial Policies Partners Data Clients Figures and Graphics Acknowledgements Citations CIViC Knowledge Model Evidence Items Assertions Features Molecular Profiles Variants Genes Fusions Factors Variant Groups Sources Curating CIViC General Curation Practices Curating Features Curating Variants Curating Genes Curating Fusions Curating Factors Curating Molecular Profiles Curating Evidence Curating Assertions Curating and Suggesting Sources Prioritizing Curation Effort Example Curation Activities User and Community Pages Becoming an Editor User Interface and Data Instructional Videos Browsing Searching Data Grids Users Organizations Comments Notifications & Mentions Community Data Releases Statistics CIViC API V2 API V1 API (deprecated) Get Help Report a Problem Next Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
}
]
CIViC Bot
01:21 AM
Tool Call
search_docs(query: "external ontologies used by CIViC 'Disease Ontology' 'Sequence Ontology' 'NCIt' 'MONDO' site:civic.readthedocs.io")
Tool Result
01:21 AM
Tool Result
Click to expand
[
{
"link": "https://civic.readthedocs.io/en/latest/model/evidence/disease.html",
"title": "disease",
"contents": "Disease — CIViC documentation About CIViC CIViC Knowledge Model Evidence Items Evidence Overview Gene Molecular Profile Statement Evidence Level Type Direction Significance Origin Disease Curating Diseases Therapy Associated Phenotype Source Clinical Trial Evidence Rating Assertions Features Molecular Profiles Variants Genes Fusions Factors Variant Groups Sources Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » CIViC Knowledge Model » Evidence Items » Disease View page source Disease¶ The disease field generally requires an value that is known to the Disease Ontology database. (Kibbe et al. 2015) The Disease Ontology (DO) database provides an open-sourced ontology for the integration of biomedical data that is associated with human disease. Within the CIViC database, the disease should be the cancer or cancer subtype that is associated to the described Molecular Profile (variant or ensemble of variants) by the evidence being curated. The disease selected should be as specific as possible and should reflect the disease type described in the source that supports the evidence statement. In CIViC, Disease is largely synonymous with cancer type or sub-type. Curating Diseases¶ The disease field will autofill based on existing diseases in the Disease Ontology (DO) database and the most specific disease subtype should be selected, if possible. Only a single disease can be associated with an evidence item. If the Molecular Profile and clinical evidence is implicated in multiple diseases in the source that is being curated, then multiple evidence items should be created. If the disease cannot be identified in the Disease Ontology database, the curator can add this new disease to CIViC during the curation of the associated Evidence Item (Figure 1). Alternatively, new DO terms, definitions, suggestions and questions in regard the Disease Ontology can be submitted to the DO Term Tracker. Figure 1: A new disease term can be added to CIViC during the Evidence Item curation process The current Diseases (cancer types) with associated with Evidence, Assertions and other information in CIViC can be explored on the CIViC Disease Page. Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/generated/civic.docs-aliases.html",
"title": "civic.docs-aliases",
"contents": "<no title> — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » <no title> View page source Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/about/citations.html",
"title": "citations",
"contents": "Citations — CIViC documentation About CIViC Participating Meetings & Events FAQ Instructional Videos Scientific Advisory Board Domain Experts AI Editorial Policies Partners Data Clients Figures and Graphics Acknowledgements Citations CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » About CIViC » Citations View page source Citations¶ The following publications are directly related to the CIViC project. Project Organization Title Link(s) CIViC public proposal WashU / Scripps Organizing knowledge to enable personalization of medicine in cancer PubMed: 25222080(2014. Genome Biology) CIViC original publication WashU CIViC is a community knowledgebase for expert crowdsourcing the clinical interpretation of variants in cancer PubMed: 28138153(2017. Nature Genetics) Standards for variant sharing Multi-institution initiative / ClinGen Somatic Working Group ClinGen Cancer Somatic Working Group standardizing and democratizing access to cancer molecular diagnostic data to drive translational research PubMed: 29218886(2018. PSB) Minimum variant level data Multi-institution initiative / ClinGen Somatic Working Group Adapting crowdsourced clinical cancer curation in CIViC to the ClinGen minimum variant level data community‐driven standards PubMed: 30311370(2018. Human Mutation) CIViC SOP WashU Standard operating procedure for curation and clinical interpretation of variants in cancer PubMed: 31779674(2019. Genome Medicine) CIViCmine Canada’s Michael Smith Genome Sciences Centre Text-mining clinically relevant cancer biomarkers for curation into the CIViC database PubMed: 31796060(2019. Genome Medicine) OpenCAP WashU Open-Sourced CIViC Annotation Pipeline to Identify and Annotate Clinically Relevant Variants Using Single-Molecule Molecular Inversion Probes PubMed: 31618044(2019. JCO Clinical Cancer Informatics) CIViCpy WashU CIViCpy: a Python software development and analysis toolkit for the CIViC knowledgebase PubMed: 32191543(2020. JCO Clinical Cancer Informatics) Virtual Molecular Tumor Board Multi-institution initiative / GA4GH (VICC) Collaborative, Multidisciplinary Evaluation of Cancer Variants Through Virtual Molecular Tumor Boards Informs Local Clinical Practices PubMed: 32644817(2020. JCO Clinical Cancer Informatics) Meta-knowledgebase Multi-institution initiative / GA4GH (VICC) A harmonized meta-knowledgebase of clinical interpretations of somatic genomic variants in cancer PubMed: 32246132(2020. Nature Genetics) CIViC community approach Multi-institution WashU / ClinGen / GA4GH (VICC) A community approach to the cancer variant interpretation bottleneck PubMed: 35624339(2022. Nature Cancer) CIViC update 2022 (NAR) Multi-institution WashU / ClinGen / GA4GH (VICC) Evolution of the open-access CIViC knowledgebase is driven by the needs of the cancer variant interpretation community PubMed: 36373660(2022. Nucleic Acids Research) Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/genindex.html",
"title": "genindex",
"contents": "Index — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Index Index Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
}
]
CIViC Bot
01:21 AM
Tool Call
search_docs(query: "Sequence Ontology CIViC 'Sequence Ontology' site:civic.readthedocs.io")
Tool Result
01:21 AM
Tool Result
Click to expand
[
{
"link": "https://civic.readthedocs.io/en/latest/generated/civic.docs-aliases.html",
"title": "civic.docs-aliases",
"contents": "<no title> — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » <no title> View page source Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/genindex.html",
"title": "genindex",
"contents": "Index — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Index Index Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://pubmed.ncbi.nlm.nih.gov/32191543",
"title": "CCI1900127 245..253",
"contents": "SPECIAL SERIES: INFORMATICS TOOLS FOR CANCER RESEARCH AND CARE o CIViCpy: A Python Software Development and r i i Analysis Toolkit for the CIViC Knowledgebase n 1,2 1 1 1 1 l Alex H. Wagner, PhD ;1Susanna Kiwala, MS ; Ad1m C. Coffman, BS ; J3shua F. McMichael, 1S ; Kelsy C. Cott1, BS ; r Thomas B. Mooney,1,2,4,5rica K. Barnell, MD,1,2,4,5Kilannin Krysiak, PhD ; Arpad M. Danos, PhD ; Jason Walker, MS ; e Obi L. Griffith, PhD ; and Malachi Griffith, PhD p o t s b PURPOSE Precision oncology depends on the matching of tumor variants to relevant knowledge describing the s r clinical significance of those variants. We recently developed the Clinical Interpretations for Variants in Cancer a (CIViC; civicdb.org) crowd-sourced, expert-moderated, and open-access knowledgebase. CIViC provides c a structured framework for evaluating genomic variants of various types (eg, fusions, single-nucleotide variants) t for their therapeutic, prognostic, predisposing, diagnostic, or functional utility. CIViC has a documented ap- plication programming interface for accessing CIViC records: assertions, evidence, variants, and genes. Third- party tools that analyze or access the contents of this knowledgebase programmatically must leverage this application programming interface, often reimplementing redundant functionality in the pursuit of common analysis tasks that are beyond the scope of the CIViC Web application. METHODS To address this limitation, we developed CIViCpy (civicpy.org), a software development kit for extractingandanalyzingthecontentsoftheCIViCknowledgebase.CIViCpy enablesusersto queryCIViCcontent as dynamic objects in Python. We assess the viability of CIViCpy as a tool for advancing individualized patient care by using it to systematically match CIViC evidence to observed variants in patient cancer samples. RESULTS We used CIViCpy to evaluate variants from 59,437 sequenced tumors of the American Association for Cancer Research Project GENIE data set. We demonstrate that CIViCpy enables annotation of . 1,200 variants per second, resulting in precise variant matches to CIViC level A (professional guideline) or B (clinical trial) evidence for 38.6% of tumors. CONCLUSION The clinical interpretation of genomic variants in cancers requires high-throughput tools for in- teroperability and analysis of variant interpretation knowledge. These needs are met by CIViCpy, a software developmentkitfordownstream applicationsandrapidanalysis.CIViCpy is fullydocumented,open-source,and available free online. JCO Clin Cancer Inform 4:245-253. © 2020 by American Society of Clinical Oncology Licensed under the Creative Commons Attribution 4.0 License INTRODUCTION inCIViCisusedtoconstructinterpretationassertionsof The use of massively parallel sequencing to profile the clinical significance (ie, therapeutic, prognostic, di- ASSOCIATED molecular composition of human tissues has become agnostic, or predisposing effects) of gene variants on CONTENT increasingly commonplace in the clinical setting to the basis of published criteria and guidelines for the classification of variant interpretations. 5,6CIViC evi- Data Supplement inform d1,2nosis and therapeutic strategy for patients’ dence and assertions are also linked to data classes Author affiliations tumors. This has led to an ever-growing body of describing genes, drugs (if applicable), and diseases, and support biomedical literature describing the impact of tumor information (if variants on disease progression and response to in addition to the myriad supporting data for tracking applicable) appear atherapy, creating a bottleneck of expert review of the provenance and community activity surrounding the end of this relevant literature to construct a clinical report. The these concepts and their relationships. These data are article. released under a Creative Commons public domain Accepted on January Clinical Interpretations for Variants in Cancer (CIViC) attribution (CC0), promoting their redistribution and 15, 2020 and community knowledgebase (civicdb.org) is a platform published at for expert crowdsourcing the clinical interpretation of use in downstream applications. ascopubs.org/journalvariants in cancer. 4 To date, CIViC contains 6,471 As a curation platform for the Clinical Genome Re- cci on March 19, interpretation evidence records (ie, clinical signifi- source (ClinGen) Somatic Working Group, 7 CIViC 2020: DOI https://docance statements extracted from biomedical litera- supports the export of generated assertions to ClinVar, org/10.1200/CCI.19. 00127 ture)describing2,312variantsin402genes.Evidence in line with existing ClinGen submission practices for 245Wagner et al CONTEXT Key Objective To develop a software development and analysis toolkit for performant search and inspection of records from the Clinical Interpretations for Variants in Cancer (CIViC) knowledgebase. Knowledge Generated We developed the CIViCpy software development kit and analysis toolkit, a software package that enables high-throughput retrieval and inspection of CIViC records. Useful features include precached content hosted live by CIViC, and utilities for exporting CIViC content as variant call format (VCF) files. Relevance This work enables (1) building of downstream applications, such as the civic2clinvar ClinVar submission utility; (2) clinical analysis tasks, such as the demonstrated analysis of the American Association for Cancer Research Project GENIE cohort; and (3) CIViC integration into clinical annotation pipelines, via VCF export or direct record annotation with native Python objects. germline diseases. This was accomplished through the CIViC: Genes, Variants, Variant Groups, Evidence, and development of the civic2clinvar export utility and Python Assertions. First-class entities are delineated from other package, which constructs ClinVar-style submission re- object classes in CIViC by the combination of persistent cords from CIViC assertions. 7In developing civic2clinvar, public identifiers, dedicated API end points for returning several issues with building an application from the CIViC object details, and tracked provenance (Table 1). Prove- database and application programming interface (API) nance tracking records the history of all actions taken on were identified: (1) simplified retrieval and use of CIViC the object as part of the CIViC curation cycle: object records as native Python objects, (2) routines for local submission, revisions, and editor approval. We also create caching of CIViC data for analysis, (3) support for high- CivicRecord objects from CIViC Sources, Users, and Or- throughput queries, and (4) export of CIViC records to ganizations, despite their lack of provenance tracking; established variant representation formats, such as variant CivicRecord objects only require that a CIViC class is call format (VCF).9 identifiable and has supporting API end points. Docu- Here, we describe CIViCpy, a software development kit mentation for each of the CivicRecord subclasses can be (SDK) that addresses these needs and enables rapid found online at http://bit.ly/civicrecord-types. downstream tool development and analysis by removing The CIViCpy CivicAttribute is a data class for representing the burden of implementing these features in independent composite data entities not captured by CivicRecord. This applications. We demonstrate the use of the SDK in an includescompositeentitieswithnestedorlistattributes(eg, associated analysis notebook to evaluate 59,437 tumors diseases, coordinates, or variant_aliases), as opposed to from patients cataloged by the American Association for primitive, single-valued entities (eg, description, allele_ Cancer Research Project GENIE cohort. 10CIViCpy is open- registry_id, or evidence_direction). CivicAttribute inherits source, Massachusetts Institute of Technology (MIT) li- from CivicRecord but is not indexed and accordingly censed, and readily available for installation on the Python overrides many of the features of its parent class. Impor- Package Index (PyPI; pypi.org). CIViCpy documentation is tantly, CivicAttribute is not cached (see Caching) except as available online at civicpy.org. a linked object to other (non-CivicAttribute) CivicRecord objects, and cannot be retrieved independently. METHODS One of the strengths of the CivicRecord class is the ability We designed the CIViCpy Python SDK as a standalone package to retrieve the CIViC knowledgebase content and to dynamically evaluate nested CivicRecord objects. A Variant, for instance, may have multiple associated Ev- transform responses into Python objects with intuitive idence records, each of which may have a source linked structures and interobject linkages. The resulting software to multiple Evidence records describing other Variants. is a toolkit to support numerous downstream operations, including exploratory analyses, variant annotation, and ap- A CivicRecord will automatically link nested objects; consequently, one can chain through linked objects plication development (Fig 1). Here, we describe the opti- when analyzing CIViC records to efficiently get to values mizations and design choices made to construct CIViCpy. of interest, such as evaluating the Association for Mo- lecular Pathology/ASCO/College of American Patholo- CIViCpy Objects gists somatic variant classification 6 for a CIViC Assertion The primary data class in CIViCpy is the CivicRecord. This (Fig 1, Object Inspection). Therefore, when evaluating evi- class provides the framework for all first-class entities in dence for a variant using CIViCpy, the associated Evidence 246 © 2020 by American Society of Clinical OncologyCIViCpy: the Python SDK for CIVIC Transform Records Formatted Variant Export Annotation Caching .VCF Pipelines In-memory Cache Rapid Record Retrieval -2602026858 <CIViC variant 1653> 4737968234 <CIViC evidence 4827> Analysis Python Package -6827800777 <CIViC gene 26599> App Development -5557954445 <CIViC variant 568> 6470440788 <CIViC evidence 2444> ... ... Object Inspection >> from civicpy import civic >> assertion = civic.get_assertion_by_id(3) Load / Save Load Remote Precache Prepackaged and Open Source and >> assertion.variant Indexed on PyPI MIT Licensed <CIViC variant 499> >> assertion.variant.name 'ALK FUSIONS' Daily >> assertion.amp_level 'Tier I - Level A' Build >> assertion.status Downstream Applications 'accepted' civic2clinvar VICC Community Apps Local Disk CIViC Server Cache FIG 1. TheCIViCpysoftwaredevelopmentkit(SDK).CIViCpyisaPythonSDKandanalysistoolkitforClinicalInterpretationofVariantsinCancer(CIViC).The primaryfunctionof CIViCpyis to extractrecords fromCIViC,convertthem into linkedPython objects,and provideusefultools and featuresfor exploringand analyzing those records. Caching: An important feature of CIViCpy is rapid retrieval via caching, with support for saving and loading CIViC record caches. CIViCpy is used to build caches hosted on civicdb.org, which can be automatically downloaded to other CIViCpy clients for daily snapshots of all content in CIViC. Object Inspection: CIViCpyenables dynamicevaluationof linked CIViCrecords through Python dot notation. Here, we see an example of the CIViCpy library in use to explore details about an Association for Molecular Pathology Tier I somatic classification Assertion about ALK fusion transcripts. Python Package: CIViCpy isavailable on thePythonPackage Index (PyPI), andisfully opensource andpermissivelylicensed for downstream applications. Formatted Variant Export: CIViCpy supports the export of CIViC records into the established variant call format for use in annotation pipelines and existing bioinformatics tools. App, application; MIT, Massachusetts Institute of Technology; VICC, Variant Interpretation for Cancer Consortium; VCF, variant call format. objects are returned rather than a list of evidence identifiers. inaccurate, in a partial state, or incongruent with the CIViC Evidence, in turn, will link to other CivicRecord objects (eg, knowledge model. Assertion,Source),whichcanalsobeexplored.Anexampleof CivicRecord objects may be retrieved by the corresponding exploring Assertions linked to a Variant using CIViCpy is get_allfunctions(eg,get_all_variants(),get_all_assertions()). provided in the Data Supplement (see the CIViCpy Objects These functions may optionally be passed a parameter for section). explicitly including only objects of a given status. For ex- ample, a user may request only evidence that has been Querying CIViC accepted or submitted (and exclude any rejected evi- CIViC is built on a segregated server/client architecture, dence). Although these behaviors are readily reproducible where all functionality of the CIViC Web client is managed by users without leveraging this feature (eg, through in- through RESTful API calls to the underlying Rails server. spection of evidence.status), we expect most downstream CIViCpy leverages this architectural design to post complex workflows would desire to include only accepted and/or queries to the CIViC advanced search API end points. This submitted evidence, and so we have provided this func- enables high-throughput searches for records of interest, tionality as a convenience. An example of filtering evidence including full data set requests. CIViC full data sets include by status using CIViCpy is provided in the Data Supplement Evidence and Assertions in multiple states of the CIViC (see the Filtering Evidence section). review cycle: those that have been editor-reviewed and approved (accepted), those that are pending review Caching (submitted),andthosethathavebeenrejectedforinclusion CIViCpy also is a standalone component for services in CIViC. Because the CIViC full data set contains rejected intended to perform large-volume operations on the CIViC and submitted Evidence items and Assertions that have not knowledgebase. A key design consideration, therefore, is been approved by CIViC editors, these records may be the local caching of CIViC content for quick retrieval and JCO Clinical Cancer Informatics 247Wagner et al TABLE 1. CIViC Class Entities CIViC Object Provenance Tracking Persistent CIViC ID Detailed Record End Point CIViCpy Class First-class entities Genes Y Y Y CivicRecord Variants Y Y Y CivicRecord Variant groups Y Y Y CivicRecord Evidence Y Y Y CivicRecord Assertions Y Y Y CivicRecord Second-class entities User N Y Y CivicRecord Organization N Y Y CivicRecord Sources N N Y CivicRecord Country N N N CivicAttribute Drugs N N N CivicAttribute Diseases N N N CivicAttribute Phenotypes N N N CivicAttribute Abbreviations: CIViC, Clinical Interpretations for Variants in Cancer; ID, identifier. local indexing operations. When loaded, each cached (Fig 1) by providing a VCFWriter class. After instantiat- CivicRecord is assigned a unique key using the native ing a VCFWriter object, a Variant record may be added to Python hash function, which is recomputed on loading it for future output by calling the addrecord() function. a stored cache from disk (by design, the hash seed The addrecord() function supports various variant types, changes with each Python session). This hash is computed depending on the curated coordinates available for a Var- on the CivicRecord type and id values, such that user- iant. All Variants require the chromosome name and start generated partial CivicRecords with these minimal values position. For single-nucleotide variants and complex vari- provide the same hash (and are treated as equivalent to) ants, the reference sequence and altered sequence in- complete CivicRecords. formation also must be available. By contrast, insertions require only variant sequence information and deletions Each cache also maintains a timestamp of when the cache was last generated. This information is used when loading require only reference sequence information. Variants that the cache from file to determine whether a fresh cache donotmeettheseminimumrequirementswillnotbeadded needs to be built or retrieved from a remote source. CIViCpy and a warning message is emitted instead. Fusions and will expire a cache 7 days (or after user-configurable length other variants with a second set of coordinates are currently not supported. To verify whether a Variant can be added to of time) after it is initially built and will retrieve the newest (nightly) cache from the CIViC live server. The local cache a VCFWriter object, the convenience method is_valid_for_ can also be manually updated from the command line with vcf() can be called on a Variant object before calling the civicpy update utility. addrecord(). More information about variant types that may lack reference and variant sequence information (eg, fu- Variant Coordinate Search sions) can be found at bit.ly/civic-coordinates. Those var- When loading all variants from CIViC, a sorted variant co- iants that cannot be exported into the VCF format are still ordinate index is also constructed after cache generation to retrievable asCIViCpy records. Once alldesired variants are enable coordinate search and lookup strategies (Fig 2A). A added to the VCFWriter object, writerecords() needs to be similarly sorted list of CoordinateQuery objects represent called to write the VCF file. An example of using CIViCpy to variants to query, such as those observed in a patient’s generate a CIViC VCF file is provided in the Data Supple- tumor (Fig 2B). The index and CoordinateQuery objects are ment (see the Exporting to VCF section). used by the search algorithm for high-throughput searches (Fig 2C). Importantly, the search algorithm supports the The variants added to the VCFWriter object are written to the VCF file, one VCF record for each Variant object. If two notion of variant ranges for CIViC records and queries, and Variant objects share the same chromosome, start position, provides several search modes to accommodate varying sensitivity and specificity tradeoffs (Fig 2D). and reference allele(s), they will not be combined into one VCF record but instead will be written as separate VCF Variant Exports records. Additional CIViC data are added to the VCF as CIViCpy enables the export of CIViC Variant records and annotationstotheCSQ(consequence)INFOfield(Table2). theirassociatedEvidenceItemsandAssertionsintotheVCF CIViC Evidence items and Assertions linked to the Variant 248 © 2020 by American Society of Clinical OncologyCIViCpy: the Python SDK for CIVIC A B On Cache Update/Load Variants to Query Extract Variants Sort Criteria Filter Missing Coordinates 1) Chromosome Extract Coordinates Requirements Split Compound Coordinates 2) Start Coordinate 1) GRCh37 reference Convert to DataFrame 3) Stop Coordinate Convert to CoordinateQuery Objects 2) Genomic coordinates Sort 4) Alternate Sequence Sort 3) 1-based coordinates Variant Coordinate Index (VCI) Bulk Coordinate Query (Q) Chr Start Stop Alt v_hash Chr Start Stop Alt Key 1 1000 1100 None 4398339850 vci_ptr 1 100 150 None MyRange1 q_ptr 1 50000 60000 None 2515228793 1 45000 55000 None MyRange2 1 51075 51075 C -5647252664 1 51075 51075 A MyVariant1.2 1 68000 68000 T 3297066642 1 51075 51075 None MyVariant1 ... ... ... ... ... ... ... ... ... ... C D State 1: State 2: State 3: VCI Q VCI Q VCI Q Record 1 Query 1 Record 1 Query 1 Record 1 Query 1 Search Mode Behavior Record 2 Query 2 Record 2 Query 2 Record 2 Query 2 Scenario Search Mode Record 3 Query 3 Record 3 Query 3 Record 3 Query 3 Record 4 Query 4 Record 4 Query 4 Record 4 Query 4 ... ... ... ... ... ... Partial Overlap Any QE RE Exact Compare Values: Compare Values: Compare Values: Record Query Record 1 > Query 1 Record 1 > Query 2 Partial overlap Actions: Actions: Actions: Increment q_ptr Increment vci_ptr Report match for some modes Query Encompassing Store vci_ptr tomp Record Increment vci_ptr Query State 4: State 5: State 6: Record Encompassing VCI Q VCI Q VCI Q Record 1 Query 1 Record 1 Query 1 Record 1 Query 1 Record tmp tmp Query Record 2 Query 2 Record 2 Query 2 Record 2 Query 2 Record 3 Query 3 Record 3 Query 3 Record 3 Query 3 Coordinate Match Record 4 Query 4 Record 4 Query 4 Record 4 Query 4 ... ... ... ... ... ... Record A Query T Compare Values: Compare Values: Compare Values: Query 2 encompassing Record 4 > Query 2 Record 2 < Query 3 Allele Match Actions: Actions: Actions: Report match for some modes Reset vci_ptr tomp Increment vci_ptr Record A Increment vci_ptr Increment q_ptr Query A FIG 2. Variant coordinate search with CIViCpy. (A) On updating or loading the in-memory cache, all variant records are extracted and converted into a sorted Variant Coordinate Index (VCI). Variants missing coordinate values are excluded, and variants with compound coordinates (eg, fusion variants) have the coordinates split into distinct records. Each coordinate is sorted by chromosome, start coordinate, stop coordinate, and alternate sequence (see the purple box). The VCI also contains a reference to the cache key for the corresponding variant. The vci_ptr is a reference to a record of the VCI. (B) CoordinateQuery objects are used to query against the VCI and should match the coordinate system requirements from CIViC (see the blue box). These objects contain an optional key field for user reference. When searching the knowledgebase for several variants, CoordinateQuery objects should be presorted by the same procedure for sorting the VCI. The q_ptr serves an analogous role to the vci_ptr for the variant queries. (C) Starting at the first sorted VCI and Query record, searches will increment the smaller of the vci_ptr or q_ptr until an overlapping coordinate range is identified. When overlaps occur, matchesare reportedonthe basisof the searchmodel specified. Thevci_ptr is restoredonce all overlapping recordsfor aquery are evaluated.(D) Several searchmodelsexistforthisalgorithm,includingahighlysensitiveAnysearch,aconservativeExactsearch,andtwointermediatemodes.Overlapscenarios and report behavior for each scenario are presented. 3, a scenario is reported; ✕, a scenario is not reported. QE, query encompassing; RE, record encompassing. are added to the CSQ field with one CSQ entry for each CSQ field for annotations, the resulting VCF is compatible Evidence item and/or Assertion. Whether a specific CSQ for import into Google BigQuery (git.io/bigquery-variant- entry reflects an Evidence item or an Assertion is annotation). determined by the CIViC Entity Type CSQ field. To differ- A command line utility, civicpy create-vcf, allows users entiate special characters in the field values from field to create a VCF file of all supported CIViC variants. The delimiters, spaces are replaced with underscores and -i/–include-status required parameter will restrict the an- other special characters are hex encoded. By using the notations to only those Evidence Items and Assertions that JCO Clinical Cancer Informatics 249Wagner et al TABLE 2. Variant Call Format CSQ Field Attributes CSQ Field Description Compound Fielda Allele Alternate allele N Consequence CIViC sequence ontology variant types for this variant Y SYMBOL HGNC gene symbol for the gene associated with this variant N Entrez Gene ID Entrez gene ID for the gene associated with this variant N Feature_type “transcript” N Feature The Ensembl ID for the CIViC representative transcripts of this variant N HGVSc Variant representation using HGVS notation (DNA level), corresponding to N the Feature HGVSp Variant representation using HGVS notation (protein level), corresponding N to the Feature CIViC Variant Name The CIViC variant name of this variant N CIViC Variant ID The CIViC internal ID for this variant N CIViC Variant Aliases CIViC aliases for this variant Y CIViC HGVS CIViC HGVS strings for this variant Y Allele Registry ID The allele registry ID for this variant N ClinVar IDs ClinVar IDs associated with this variant Y CIViC Variant Evidence Score The CIViC evidence score for this variant N CIViC Entity Type The type of entity being annotated, either “evidence” or “assertion” N CIViC Entity ID The CIViC internal ID for the entity being annotated N CIViC Entity URL The CIViC direct URL to the entity being annotated N CIViC Entity Source For evidence entities, the ID of the publication used to create the evidence N including the source type in the format “sourceId_(sourceType)” CIViC Entity Variant Origin The variant origin of the entity being annotated, either “Somatic,” “Rare N Germline,” “Common Germline,” “Unknown,” or “N/A” CIViC Entity Status The status of the CIViC entity being annotated, either “submitted,” N “accepted,” or “rejected” Abbreviations: CIViC, Clinical interpretation of Variants in Cancer; CSQ, consequence; HGNC, HUGO Gene Nomenclature Committee; HGVS, Human Genome Variation Society; ID, identifier; N/A, not applicable. aCompound fields contain multiple values and use the ampersand (&) character to delineate values. match the given status(es). If a variant does not have any Thisdocumentation serves asboth a “quick start”guide and supporting Evidence Items or Assertions with the required a detailed reference for developers and bioinformaticians. statuses, it will not be included in the VCF. This project is licensed under the MIT License (https:// opensource.org/licenses/MIT).CIViCpyhasbeenpackaged Software Engineering and Availability and uploaded to the PyPI under the civicpy package name The CIViCpy codebase is hosted publicly on GitHub (git.io/ and can be installed by running the pip install civicpy civicpy). The test suite is implemented using the pytest frameworkandGitHubintegrationtestsarerunusingtravis- command. Installation requires a Python version 3.7 en- vironment. Releases are also made available on GitHub ci (travis-ci.org). Coveralls (https://coveralls.io/) is used t(https://github.com/griffithlab/civicpy/releases). track test coverage (77%). Code changes are integrated using GitHub pull requests (https://github.com/griffithlab/ GENIE Analysis civicpy/pulls). Feature additions, user requests, and bug reports are managed using GitHub issue tracking (https:// ToevaluatetheperformanceofCIViCpyinannotatingpatient data, we performed a demonstrative analysis in a Jupyter github.com/griffithlab/civicpy/issues). Collectively, these Notebook, available on the CIViCpy GitHub repository (git.io/ features enable robust community development and fa- 10 civicpy-genie). The Project GENIE version 5.0 extended cilitate adoption of the CIViCpy SDK. mutations file, which describes 445,655 variants across User documentation is written using reStructuredText 59,437 patient tumors, was downloaded from https://www. markuplanguage and the Sphinx documentation framework synapse.org/#!Synapse:syn17394041. Coordinates from the (sphinx-doc.org). Documentation is hosted on Read the reported variants were extracted and each coordinate set Docs (readthedocs.org) and can be viewed at civicpy.org. was tagged using the corresponding tumor sample barcode. 250 © 2020 by American Society of Clinical OncologyCIViCpy: the Python SDK for CIVIC The extracted coordinates were then transformed into variants, and using the Any strategy, an additional 42.9% a sorted list of CIViCpy CoordinateQuery objects, which were of variants (n = 195,349) were matched (Fig 3A). Fur- passed to the bulk-query search method using an exact thermore, 46.3% of tumors (n = 27,545) had at least one searchstrategy(Fig2D).Matchresultsandquerytimeswere Exact match to a reported variant and an additional 40.2% recorded for the full set of GENIE variants in addition to of tumors (n = 23,925) had at least one Any match. timings from exponentially increasing subsets from one to Notably, 8.7% of tumors (n = 5,200) in the cohort had no 300,000. Match results from an anticonservative search reported variants to query against the knowledgebase. We strategy, which allowed for any coordinate overlap (Fig 2D), evaluated the highest CIViC evidence level reported for the were also recorded. 27,545 tumors with matched evidence, and found 14.0% Match results from the full set of variants were grouped by of those tumors (n = 3,852) matched to a CIViC Validated Association (Level A). An additional 69.3% of tumors (n = tumor identifier and summarized by counts of Exact, Any, and no matches. In addition, tumors for which no varia- 19,098) matched to Clinical Evidence (Level B). Far fewer tumors had Case Study (Level C, 11.8%; n= 3,248), tions were reported for querying were also summarized. Finally, we grouped tumors on the number of variants Preclinical (Level D, 3.9%; n = 1,066), or Inferential (Level E, 1.0%; n = 281) as the highest-level evidence match matching CIViC evidence by Exact search, and summarized the highest level of evidence found across the tumors in those (Fig 3B). In total, 38.6% (n = 22,950) of all GENIE tumors (including those without reported variants) had at least groups. one variant that matched to Level A or B evidence. Tumors from the cohort had an average of 6.88 (median, 4) variants RESULTS reported, and although most tumors (53.7%; n = 31,892) GENIE Tumor Variant Results didnotExactmatchtoCIViCvariants,manytumorsmatched Using the Exact search strategy, CIViCpy successfully one (35.4%; n = 21,026), two (9.4%; n = 5,592), three matched CIViC evidence to 7.6% (n = 34,642) of GENIE (1.3%; n = 796), or more (0.2%; n = 131) CIViC variants. A B GENIE Cohort Matching to CIViC Tumors Exact match Variants Any match No match Highest Evidence Level per Tumor No variants Evidence Level 104 A B C D 103 E C r CIViCpy Search Performance o 2 103 u 10 T 102 Overall d 101 101 o c 100 S 10-1 m = 0.808 ms/variant 100 10-2 100 101 10 2 103 104 10 5 1 2 3 4 5 6 7 8 Variants Variants Matched FIG 3. Variant coordinate search with CIViCpy. (A) Querying GENIE variants against the CIViC knowledgebase results in 7.6% (n = 34,642) of variant (n = 445,655) and 46.3% (n = 27,545) of tumors (n = 59,437) with Exact matches to CIViC variants. Allowing for Any matches, these values increase to 50.5% of variants (n = 229,991) and 86.6% of tumors (n = 51,470). A small percentage (8.7%; n = 5,200) of all tumors had no reported variants with which to search. (B) Tumors were grouped by the number of variants that Exact matched CIViC records. For each tumor, the highest level of evidence supportingthematchedvariantswascounted.Weobservedthat83.3%oftumors(n=22,950)withExactmatchingvariants(whichequatesto38.6%ofall tumors) were linked to CIViC Validated (Level A) or Clinical (Level B) evidence. (C) Response time of CIViCpy bulk queries against the CIViC knowl- edgebase. As the number of variants queried increase . 1,000, response time is linear to the number of queries, with an increase in overall time of 0.808 ms/variant. CIViC, Clinical Interpretations for Variants in Cancer. JCO Clinical Cancer Informatics 251Wagner et al CIViCpy Search Performance The CIViCpy SDK has demonstrated utility in downstream CIViCpy uses a search strategy (Fig 2C) designed to scale applications,includingthepreviouslypublishedcivic2clinvar utility and the Variant Interpretation for Cancer Consortium. 11 linearly with input query size. We evaluated the perfor- mance of CIViCpy annotation of the GENIE cohort and Additional features to improve CIViCpy are already being planned, including extensions for other variant export formats found that queries with ≥ 1,000 variants scale linearly with 12 input size, increasing total search time by approximately suchastheBrowserExtensibleData andtheGlobalAlliance forGenomicsandHealthVRspecification. 13Theseextensions 0.808 ms/variant (Fig 3C). Queries with , 1,000 variants will also support export of variant types beyond the single- exhibit higher performance and are returned in , 1 sec- nucleotide variants and insertions/deletions currently sup- ond. We annotated the entire GENIE data set (n = 445,655 ported by our VCF export utility. In addition, we are planning variants) in 369 seconds at a rate of 1,236 variants/s. to develop utilities to allow users to annotate their own VCFs with CIViC data. We are also developing strategies to in- DISCUSSION corporateCIViCDrug,Disease,andPhenotypeentitiesasfull CIViCpy is an SDK and high-throughput analysis toolkit for CivicRecord objects. exploring and analyzing content within the CIViC knowl- Finally, we have provided all source code for CIViCpy (git.io/ edgebase. CIViCpy has tools for object inspection, with civicpy) and the analyses in this manuscript (git.io/cpy- convenient features for record retrieval and search. Variant genie) in a public repository under the permissive MIT annotation through CIViCpy is demonstrated to handle licenseandhaveuploadedCIViCpydistributionstothePyPI variant searches at 1,236 variants/s through the provided for ease of installation. The permissive licensing and easy coordinate search methods. In addition, the SDK provides installation through PyPI allow for rapid integration into convenient tools for exporting CIViC content to VCF for existing analytical workflows. See our documentation and integration in external annotation pipelines and tools. project homepage at civicpy.org for more details. AFFILIATIONS AUTHOR CONTRIBUTIONS 1McDonnell Genome Institute, Washington University School of Conception and design: Alex H. Wagner, Susanna Kiwala, Adam C. Medicine, St Louis, MO Coffman, Joshua F. McMichael, Kelsy C. Cotto, Erica K. Barnell, Jason 2 Department of Medicine, Washington University School of Medicine, Walker, Obi L. Griffith, Malachi Griffith St Louis, MO Financial support: Alex H. Wagner, Obi L. Griffith, Malachi Griffith 3Department of Pathology and Immunology, Washington University Administrative support: Jason Walker, Malachi Griffith School of Medicine, St Louis, MO Collection and assembly of data: Alex H. Wagner, Susanna Kiwala, 4 Siteman Cancer Center, Washington University School of Medicine, Kilannin Krysiak, Malachi Griffith St Louis, MO Dataanalysisandinterpretation:AlexH.Wagner,SusannaKiwala,Thomas 5Department of Genetics, Washington University School of Medicine, B. Mooney, Arpad M. Danos St Louis, MO Manuscript writing: All authors Final approval of manuscript: All authors Preprint version available on bioRxiv. Accountable for all aspects of the work: All authors CORRESPONDING AUTHOR Obi L. Griffith, PhD, McDonnell GenomeInstitute, Washington University AUTHORS’ DISCLOSURES OF POTENTIAL CONFLICTS OF School of Medicine, Campus Box 8501 4444 Forest Park Ave, St Louis, INTEREST The following represents disclosure information provided by authors of MO 63108; email: obigriffith@wustl.edu this manuscript. All relationships are considered compensated unless otherwise noted. Relationships are self-held unless noted. I = Immediate EQUAL CONTRIBUTION Family Member, Inst = My Institution. Relationships may not relate to the A.H.W. and S.K. contributed equally to this work. O.L.G. and M.G. subject matter of this manuscript. For more information about ASCO’s contributed equally to this work. conflict of interest policy, please refer to www.asco.org/rwc or ascopubs. org/cci/author-center. SUPPORT Open Payments is a public database containing information reported by A.H.W.wassupportedbyafellowshipfromtheNationalCancerInstitute(NCI; companies about payments made to US-licensed physicians (Open Payments). National Institutes of Health [NIH] Grant No. F32CA206247), a National Human Genome Research Institute (NHGRI) career development award (NIH Erica K. Barnell Grant No. K99HG010157), and the Foundation for Barnes-Jewish Hospital (Award Group 615735). M.G. was supported by a career development award Employment: Geneoscopy Stock and Other Ownership Interests: Geneoscopy from the NHGRI (NIH Grant No. R00HG007940). A.H.W., S.K., A.C.C., Patents, Royalties, Other Intellectual Property: Inventor on intellectual J.F.M.,E.K.B.,K.K.,A.M.D.,O.L.G.,M.G.,andtheCIViCknowledgebasewere property in start-up company (Geneoscopy). supported by the NCI (NIH Grant No. U01CA209936 and U24CA237719). VCF export development was supported by Google Genomics. This research Travel, Accommodations, Expenses: Geneoscopy was also supported by a Cancer Moonshot funding opportunity, specifically annnin Krysiak ActivitiestoPromoteTechnologyResearchCollaborationsforCancerResearch Consulting or Advisory Role: Gerson Lehrman Group (Administrative Support) award to O.L.G. (Grant No. U01CA209936-S). No other potential conflicts of interest were reported. 252 © 2020 by American Society of Clinical OncologyCIViCpy: the Python SDK for CIVIC REFERENCES 1. Freedman AN, Klabunde CN, Wiant K, et al: Use of next-generation sequencing tests to guide cancer treatment: Results from a nationally representative survey of oncologists in the United States. JCO Precision Oncology 2:1-13, 2018 2. Lander ES: Initial impact of the sequencing of the human genome. Nature 470:187-197, 2011 3. Good BM, Ainscough BJ, McMichael JF, et al: Organizing knowledge to enable personalization of medicine in cancer. Genome Biol 15:438, 2014 4. Griffith M, Spies NC, Krysiak K, et al: CIViC is a community knowledgebase for expert crowdsourcing the clinical interpretation of variants in cancer. Nat Genet 49:170-174, 2017 5. Richards S, Aziz N, Bale S, et al: Standards and guidelines for the interpretation of sequence variants: A joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology. Genet Med 17:405-424, 2015 6. Li MM, Datto M, Duncavage EJ, et al: Standards and guidelines for the interpretation and reporting of sequence variants in cancer: A joint consensus recommendationoftheAssociationforMolecularPathology, American SocietyofClinicalOncology,andCollegeofAmerican Pathologists. JMolDiagn19:4-23, 2017 7. Danos AM, Ritter DI, Wagner AH, et al: Adapting crowdsourced clinical cancer curation in CIViC to the ClinGen minimum variant level data community-driven standards. Hum Mutat 39:1721-1732, 2018 8. US Food and Drug Administration: Genetic Database Recognition Decision Summary for ClinGen Expert Curated Human Variant Data. Submission No: Q181150. https://www.fda.gov/media/119313/download 9. Danecek P, Auton A, Abecasis G, et al: The variant call format and VCFtools. Bioinformatics 27:2156-2158, 2011 10. AACR Project GENIE Consortium: AACR Project GENIE: Powering precision medicine through an international consortium. Cancer Discov 7:818-831, 2017 11. Wagner AH, Walsh B, Mayfield G, et al: A harmonized meta-knowledgebase of clinical interpretations of cancer genomic variants. bioRxiv 366856. doi: https:// doi.org/10.1101/366856. 12. Karolchik D, Hinrichs AS, Furey TS, et al: The UCSC Table Browser data retrieval tool. Nucleic Acids Res 32:D493-D496, 2004 13. Wagner A, Babb L, Lopez J, et al: ga4gh/vr-spec: 1.0 GA4GH Approved. 2019. https://zenodo.org/record/3572974 n n n JCO Clinical Cancer Informatics 253",
"document_type": "publication"
},
{
"link": "https://civic.readthedocs.io/en/latest/model/variants/types.html",
"title": "types",
"contents": "Types — CIViC documentation About CIViC CIViC Knowledge Model Evidence Items Assertions Features Molecular Profiles Variants Variants Overview Name Aliases My Variant Info Types Curating Variant Types Coordinates HGVS Expressions ClinVar IDs Genes Fusions Factors Variant Groups Sources Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » CIViC Knowledge Model » Variants » Types View page source Types¶ Variant Type(s) are used to classify variants by Sequence Ontology terms. Variant Types permit advanced searching for categories of variants in the CIViC interface and downstream semantic analyses of CIViC variants. Some examples of variant types are listed below. Curating Variant Types¶ The most specific term(s) that can be applied to a given variant should be utilized. Use of the Sequence Ontology browser is recommended to identify appropriate terms. When choosing variant types, selection of multiple terms is supported in order to capture both functional and structural effects of the variant. However, these terms should not be ancestors or descendents of one another, and all selected terms should be descendents of the ‘sequence_variant’ term whenever possible. Variant Type Guidelines¶ Choose the most specific terms. Do not use terms that are ancestors/decendants of each other. Wherever possible use the ‘sequence_variant’ tree of the sequence ontology. Curation Guidelines for Specific Sequence Ontology Types¶ Sequence Ontology Term Sequence Ontology Definition Comments missense_variant A sequence variant, that changes one or more bases, resulting in a different amino acid sequence but where the length is preserved. stop_gained A sequence variant whereby at least one base of a codon is changed, resulting in a premature stop codon, leading to a shortened polypeptide. Also known as a nonsense variant. protein_altering_variant A sequence_variant which is predicted to change the protein encoded in the coding sequence. frameshift_truncation A frameshift variant that causes the translational reading frame to be shortened relative to the reference feature. inframe_deletion An inframe non synonymous variant that deletes bases from the coding sequence. inframe_insertion An inframe non synonymous variant that inserts bases into in the coding sequence. splice_acceptor_variant A variant the impacts the RNA splice acceptor site (i.e. at or upstream/3prime of an exon edge) splice_donor_variant A variant the impacts the RNA donor acceptor site (i.e. at or downstream/5prime of an exon edge) [ gene_variant OR transcript_variant ] AND [ loss_of_function_variant OR gain_of_function_variant ] [ gene_variant: A sequence variant where the structure of the gene is changed. OR transcript_variant: A sequence variant that changes the structure of the transcript ] AND [ loss_of_function_variant: A sequence variant whereby the gene product has diminished or abolished function. OR gain_of_function_variant: A sequence variant whereby new or enhanced function is conferred on the gene product. ] Depends on situation. exon_variant A sequence variant that changes exon sequence. transcript_fusion OR RARELY… gene_fusion transcript_fusion: A feature fusion where the deletion brings together transcript regions. OR gene_fusion: A sequence variant whereby a two genes have become joined. Depends on situation. Note that transcript_fusion mentions “deletion” specifically as the genomic alteration, and both gene_fusion and transcript_fusion are children of feature_fusion, which also mentions “deletion” specifically. However, it is assumed that deletion is just one possible mechanism (along with translocation, inversion, etc) for bringing two gene or transcribed regions together. The decision of which term to use therefore rests on the level of specificity. If the genomic event is thought to result in a fusion transcript then “transcript_fusion” is the preferred term. transcript_fusion AND missense_variant transcript_fusion: A feature fusion where the deletion brings together transcript regions. AND missense_variant: A sequence variant that changes one or more bases, resulting in a different amino acid sequence but where the length is preserved. transcript_translocation OR feature_translocation OR transcript_fusion transcript_translocation: A feature translocation where the region contains a transcript. OR feature_translocation: A sequence variant, caused by an alteration of the genomic sequence, where the structural change, a translocation, is greater than the extent of the underlying genomic features. OR transcript_fusion: A feature fusion where the deletion brings together transcript regions. Depends on situation. wild_type An attribute describing sequence with the genotype found in nature and/or standard laboratory stock. loss_of_heterozygosity A functional variant whereby the sequence alteration causes a loss of function of one allele of a gene. transcript_amplification A feature amplification of a region containing a transcript. transcript_ablation A feature ablation whereby the deleted region includes a transcript feature. copy_number_change A sequence variant where copies of a feature (CNV) are either increased or decreased. loss_of_function_variant A sequence variant whereby the gene product has diminished or abolished function. loss_of_function_variant…? transcript_ablation…? loss_of_fuction_variant: A sequence variant whereby the gene product has diminished or abolished function. transcript_ablation: A feature ablation whereby the deleted region includes a transcript feature. Depends on situation. exon_loss_variant A sequence variant whereby an exon is lost from the transcript. 5_prime_UTR_variant A UTR variant of the 5’ UTR. 3_prime_UTR_variant A UTR variant of the 3’ UTR. synonymous_variant A sequence variant where there is no resulting change to the encoded amino acid. N/A The Sequence Ontology does not currently describe expression or epigenetic variants. Variant Type Examples¶ Sequence Ontology Term Examples missense_variant G12D stop_gained R130* protein_altering_variant G12 KINASE DOMAIN MUTATION frameshift_truncation V2288fs*1 inframe_deletion DEL I843 V560DEL DEL 755-759 inframe_insertion P780INS M774INSAYVM ITD [ gene_variant OR transcript_variant ] AND [ loss_of_function_variant OR gain_of_function_variant ] MUTATION exon_variant EXON 10 MUTATION transcript_fusion OR RARELY… gene_fusion EML4-ALK ALK FUSIONS transcript_fusion AND missense_variant EML4-ALK G1269A transcript_translocation OR feature_translocation OR transcript_fusion REARRANGEMENT wild_type WILD TYPE loss_of_heterozygosity LOH transcript_amplification AMPLIFICATION transcript_ablation DELETION copy_number_change COPY NUMBER VARIATION loss_of_function_variant LOSS-OF-FUNCTION loss_of_function_variant…? transcript_ablation…? LOSS exon_loss_variant EXON 14 SKIPPING MUTATION 5_prime_UTR_variant 5’ UTR MUTATION 3_prime_UTR_variant 3’ UTR MUTATION N/A EXPRESSION NUCLEAR EXPRESSION CYTOPLASMIC EXPRESSION OVEREXPRESSION UNDEREXPRESSION METHYLATION PROMOTER METHYLATION PROMOTER HYPERMETHYLATION Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
}
]
CIViC Bot
01:21 AM
Tool Call
search_docs(query: "ontology 'Ontology' 'CIViC' 'Disease Ontology' 'Sequence Ontology' 'MONDO' 'NCIt' 'HGNC' 'HPO' site:civic.readthedocs.io")
Tool Result
01:21 AM
Tool Result
Click to expand
[
{
"link": "https://civic.readthedocs.io/en/latest/generated/civic.docs-aliases.html",
"title": "civic.docs-aliases",
"contents": "<no title> — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » <no title> View page source Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/genindex.html",
"title": "genindex",
"contents": "Index — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Index Index Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/model/evidence/disease.html",
"title": "disease",
"contents": "Disease — CIViC documentation About CIViC CIViC Knowledge Model Evidence Items Evidence Overview Gene Molecular Profile Statement Evidence Level Type Direction Significance Origin Disease Curating Diseases Therapy Associated Phenotype Source Clinical Trial Evidence Rating Assertions Features Molecular Profiles Variants Genes Fusions Factors Variant Groups Sources Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » CIViC Knowledge Model » Evidence Items » Disease View page source Disease¶ The disease field generally requires an value that is known to the Disease Ontology database. (Kibbe et al. 2015) The Disease Ontology (DO) database provides an open-sourced ontology for the integration of biomedical data that is associated with human disease. Within the CIViC database, the disease should be the cancer or cancer subtype that is associated to the described Molecular Profile (variant or ensemble of variants) by the evidence being curated. The disease selected should be as specific as possible and should reflect the disease type described in the source that supports the evidence statement. In CIViC, Disease is largely synonymous with cancer type or sub-type. Curating Diseases¶ The disease field will autofill based on existing diseases in the Disease Ontology (DO) database and the most specific disease subtype should be selected, if possible. Only a single disease can be associated with an evidence item. If the Molecular Profile and clinical evidence is implicated in multiple diseases in the source that is being curated, then multiple evidence items should be created. If the disease cannot be identified in the Disease Ontology database, the curator can add this new disease to CIViC during the curation of the associated Evidence Item (Figure 1). Alternatively, new DO terms, definitions, suggestions and questions in regard the Disease Ontology can be submitted to the DO Term Tracker. Figure 1: A new disease term can be added to CIViC during the Evidence Item curation process The current Diseases (cancer types) with associated with Evidence, Assertions and other information in CIViC can be explored on the CIViC Disease Page. Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/about/citations.html",
"title": "citations",
"contents": "Citations — CIViC documentation About CIViC Participating Meetings & Events FAQ Instructional Videos Scientific Advisory Board Domain Experts AI Editorial Policies Partners Data Clients Figures and Graphics Acknowledgements Citations CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » About CIViC » Citations View page source Citations¶ The following publications are directly related to the CIViC project. Project Organization Title Link(s) CIViC public proposal WashU / Scripps Organizing knowledge to enable personalization of medicine in cancer PubMed: 25222080(2014. Genome Biology) CIViC original publication WashU CIViC is a community knowledgebase for expert crowdsourcing the clinical interpretation of variants in cancer PubMed: 28138153(2017. Nature Genetics) Standards for variant sharing Multi-institution initiative / ClinGen Somatic Working Group ClinGen Cancer Somatic Working Group standardizing and democratizing access to cancer molecular diagnostic data to drive translational research PubMed: 29218886(2018. PSB) Minimum variant level data Multi-institution initiative / ClinGen Somatic Working Group Adapting crowdsourced clinical cancer curation in CIViC to the ClinGen minimum variant level data community‐driven standards PubMed: 30311370(2018. Human Mutation) CIViC SOP WashU Standard operating procedure for curation and clinical interpretation of variants in cancer PubMed: 31779674(2019. Genome Medicine) CIViCmine Canada’s Michael Smith Genome Sciences Centre Text-mining clinically relevant cancer biomarkers for curation into the CIViC database PubMed: 31796060(2019. Genome Medicine) OpenCAP WashU Open-Sourced CIViC Annotation Pipeline to Identify and Annotate Clinically Relevant Variants Using Single-Molecule Molecular Inversion Probes PubMed: 31618044(2019. JCO Clinical Cancer Informatics) CIViCpy WashU CIViCpy: a Python software development and analysis toolkit for the CIViC knowledgebase PubMed: 32191543(2020. JCO Clinical Cancer Informatics) Virtual Molecular Tumor Board Multi-institution initiative / GA4GH (VICC) Collaborative, Multidisciplinary Evaluation of Cancer Variants Through Virtual Molecular Tumor Boards Informs Local Clinical Practices PubMed: 32644817(2020. JCO Clinical Cancer Informatics) Meta-knowledgebase Multi-institution initiative / GA4GH (VICC) A harmonized meta-knowledgebase of clinical interpretations of somatic genomic variants in cancer PubMed: 32246132(2020. Nature Genetics) CIViC community approach Multi-institution WashU / ClinGen / GA4GH (VICC) A community approach to the cancer variant interpretation bottleneck PubMed: 35624339(2022. Nature Cancer) CIViC update 2022 (NAR) Multi-institution WashU / ClinGen / GA4GH (VICC) Evolution of the open-access CIViC knowledgebase is driven by the needs of the cancer variant interpretation community PubMed: 36373660(2022. Nucleic Acids Research) Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
}
]
CIViC Bot
01:21 AM
Tool Call
search_docs(query: "CIViC Genes HGNC 'gene' 'HGNC' 'Entrez' site:civic.readthedocs.io")
Tool Result
01:21 AM
Tool Result
Click to expand
[
{
"link": "https://civic.readthedocs.io/en/latest/model/genes/name.html",
"title": "name",
"contents": "Gene Name — CIViC documentation About CIViC CIViC Knowledge Model Evidence Items Assertions Features Molecular Profiles Variants Genes Gene Name Understanding Gene Names Curating Gene Names Summary MyGene.info Fusions Factors Variant Groups Sources Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » CIViC Knowledge Model » Genes » Gene Name View page source Gene Name¶ The CIViC Gene Name utilizes official Entrez Gene Names from the Entrez Gene database. Understanding Gene Names¶ The CIViC Gene Name utilizes official Entrez Gene Names from the Entrez Gene database, which are approved by the HUGO Gene Nomenclature Committee (HGNC). Curators must enter a valid Entrez Gene Name (e.g., TP53) and should verify the correct entry against the Entrez Gene ID automatically displayed by the CIViC interface. Alternative Gene Names (Aliases/Synonyms) are imported from Entrez and are searchable throughout the database. Curating Gene Names¶ Only Entrez Gene Names are accepted for the CIViC Gene Name field. Curators should verify the correct entry against the Entrez Gene ID automatically displayed by the CIViC interface. Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/model/evidence/gene.html",
"title": "gene",
"contents": "Gene — CIViC documentation About CIViC CIViC Knowledge Model Evidence Items Evidence Overview Gene Curating Genes Molecular Profile Statement Evidence Level Type Direction Significance Origin Disease Therapy Associated Phenotype Source Clinical Trial Evidence Rating Assertions Features Molecular Profiles Variants Genes Fusions Factors Variant Groups Sources Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » CIViC Knowledge Model » Evidence Items » Gene View page source Gene¶ The Gene Name identifies the gene(s) associated with a Molecular Profile (simple or complex variant) implicated by the Evidence Item. Curating Genes¶ Gene Names are associated with evidence through their inclusion in the associated Molecular Profile (MP). Each Evidence Item must be associated with an MP and each MP must have one or more gene and variant. The CIViC Gene Name utilizes the HGNC official gene symbol as provided by Entrez, where applicable, which are approved by the HUGO Gene Nomenclature Committee (HGNC). As the MP (Simple or Complex) is created, the Gene Name field will auto-fill using type-ahead search for genes in the Entrez database or their associated Aliases. Curators must enter a valid Entrez Gene Name (e.g., TP53) and should verify the correct entry against the Entrez Gene ID automatically displayed by the CIViC interface. Alternative Gene Names (Aliases/Synonyms) are imported from Entrez and are searchable throughout the database. Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/model/genes.html",
"title": "genes",
"contents": "Genes — CIViC documentation About CIViC CIViC Knowledge Model Evidence Items Assertions Features Molecular Profiles Variants Genes Gene Name Summary MyGene.info Fusions Factors Variant Groups Sources Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » CIViC Knowledge Model » Genes View page source Genes¶ The gene entity within the CIViC database includes several useful features for assessing the clinical relevance of variants (Figure 1). The first is a human curated gene-level summary describing the gene’s clinical relevance with associated sources. The second feature is an external link to The Drug Gene Interaction Database, which can be selected to learn more about specific drug-gene interactions and the druggable genome. The third feature is an external link to the ProteinPaint resource allowing a view of variant recurrence data for the gene in the context of alternative transcripts, known protein domains, etc. The fourth feature includes gene-level details (e.g., gene aliases, domains, pathways) pulled in from MyGene.info with a link to additional details. Understanding Genes In order to be listed in CIViC a Gene must have at least one clinical Evidence Item that has been curated from the literature and associated with at least one Molecular Profile (variant) of the gene. A new Gene record will be created automatically when the first Evidence Item is assigned to the Gene. The official gene name according to Entrez Gene (assigned by HGNC) is used. Alternative gene names or “aliases” are autopopulated from MyGeneInfo and searchable throughout the database. However, new Evidence Items must be associated with an official gene symbol to prevent ambiguity. Figure 1: A CIViC Gene's attributes, associations, computed properties Gene Attributes Attribute Description Source Name Entrez symbol of the gene. EntrezDB Summary User-defined summary of the clinical relevance of this Gene. Curation efforts should aim to concisely summarize the relevance of Molecular Profiles (simple or complex variants) in this gene to treatment prediction, prognosis, diagnosis, predisposition, oncogenicity and function. The summary should also provide an overview of the most relevant cancer types. The summary may also include relevant mechanistic information such as pathway interactions, functional alterations caused by variants within this Gene (i.e., activating, loss-of-function, etc.), and normal functions key to its oncogenic properties. CIViC Sources (PubMed IDs) A list of PubMed IDs referring to evidence supporting statements made in the Gene’s description. Source descriptions (e.g. ‘Weisberg et al., 2007, Nat. Rev. Cancer’) are pulled from the PubMed database at the time of submission, and are not editable. CIViC (PubMed) MyGene.Info MyGene Info Data retrieved from MyGene.Info using the HGNC symbol as the query. Includes synonyms, protein domains, and pathways with additional data displayed by clicking the “Details” button. MyGene.Info Curating Genes Most of the information within the Gene entity is automatically imported after the gene is created. These automatically generated fields include: 1) information from MyGene.info and 2) link to DGIdb details, 3) link to ProteinPaint. Curators can add gene-level summaries and sources associated with the gene-level summaries. These clinical summaries should include relevant cancer subtypes, specific treatments for the gene’s associated variants, pathway interactions, functional alterations caused by the variants in the gene, and normal/abnormal functions of the gene with associated roles in oncogenesis. The sources used for gene-level summaries should correspond to Pubmed IDs. Gene Name Understanding Gene Names Curating Gene Names Summary Understanding Gene Summaries Curating Gene Summaries MyGene.info Understanding MyGene.info Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/generated/civic.docs-aliases.html",
"title": "civic.docs-aliases",
"contents": "<no title> — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » <no title> View page source Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
}
]
CIViC Bot
01:21 AM
Tool Call
search_docs(query: "site:civic.readthedocs.io Phenotype CIViC phenotype ontology 'Human Phenotype Ontology' 'HPO'")
Tool Result
01:22 AM
Tool Result
Click to expand
[
{
"link": "https://civic.readthedocs.io/en/latest/generated/civic.docs-aliases.html",
"title": "civic.docs-aliases",
"contents": "<no title> — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » <no title> View page source Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/model/assertions/associated_phenotypes.html",
"title": "associated_phenotypes",
"contents": "Associated Phenotypes — CIViC documentation About CIViC CIViC Knowledge Model Evidence Items Assertions Assertions Overview Fields Shared with Evidence Associated Phenotypes Curating Associated Phenotypes NCCN Guideline FDA Companion Test Summary and Description Features Molecular Profiles Variants Genes Fusions Factors Variant Groups Sources Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » CIViC Knowledge Model » Assertions » Associated Phenotypes View page source Associated Phenotypes¶ Associated Phenotypes for an Assertion are phenotypes that have been observed and recorded in patients documented to have the specific variant for which the Assertion has been created. The Associated Phenotypes field is hand curated and terms are drawn from the Human Phenotype Ontology (HPO). Curating Associated Phenotypes¶ Associated Phenotypes for an Assertion are a collection of the Associated Phenotypes taken from the Assertion’s supporting Evidence Items. Any phenotypes added to an Assertion’s Associated Phenotypes field must occur in at least one of the supporting Evidence Items (EIDs). Note that when an HPO term is added to an EID, it has been reported in the specific evidence source for that EID in a patient with the specific CIViC Variant for that EID. Supporting EIDs for a given Assertion may be drawn from categories of different generality (i.e. an EID for “Cancer” may support an Assertion for melanoma). Therefore, curators should be careful to only draw HPO terms to use in the Assertion from EIDs that strictly match the Assertion Disease and Variant in a highly specific manner. Note that the HPO Terms chosen for Associated Phenotypes for an Assertion do not give quantitative data. For instance a given HPO term may be found in multiple supporting EIDs for an Assertion, while a second HPO term may occur only once in the collection of supporting EIDs. In the Assertion, both terms will occur only once. Therefore the information on frequency of phenotype observation is not carried over into the Assertion. While the collection of evidence supporting an Assertion should do a good job of covering the field for that given variant, CIViC Clinical Significance, and disease, the system of publishing on variants and noting Associated Phenotypes may not yet be reliable enough to use literature curation as a measure for phenotype frequency, especially when the numbers are small. For variants with larger bodies of curated literature in CIViC, advanced search functions can give statistics on phenotype frequency occurring in literature for a given variant. Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/model/evidence/associated_phenotype.html",
"title": "associated_phenotype",
"contents": "Associated Phenotype — CIViC documentation About CIViC CIViC Knowledge Model Evidence Items Evidence Overview Gene Molecular Profile Statement Evidence Level Type Direction Significance Origin Disease Therapy Associated Phenotype Curating Associated Phenotypes Source Clinical Trial Evidence Rating Assertions Features Molecular Profiles Variants Genes Fusions Factors Variant Groups Sources Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » CIViC Knowledge Model » Evidence Items » Associated Phenotype View page source Associated Phenotype¶ Associated Phenotypes can be added to any evidence item. Phenotypes standardize symptoms or abnormalities that are encountered in human disease (e.g., pheochromocytoma) and each phenotype is taken from the Human Phenotype Ontology database. This field is optional and evidence items can be submitted without associated phenotypes. Associated Phenotypes should provide additional information beyond what is implied by the Disease field. Phenotypes should be particularly considered for Predisposing Evidence Items whereby the variant is associated with a non-binary phenotype or syndrome for a particular genotype. Curating Associated Phenotypes¶ The Associated Phenotypes field should be curated when the literature or abstract source specifically mentions the given phenotype being observed in a patient with the Molecular Profile (variant) of interest. If the phenotype was seen in a group of patients with related Molecular Profiles, then the Associated Phenotypes field should be left blank. If the curator has knowledge that the given phenotype is often associated with the Molecular Profile, but this association is not specifically noted in an observed patient being reported in the specific literature source used for creation of the EID, then the Associated Phenotype field should be left blank. The current Associated Phenotypes linked to Evidence Items and Assertions in CIViC can be explored on the CIViC Phenotypes Page. Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/genindex.html",
"title": "genindex",
"contents": "Index — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Index Index Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
}
]
CIViC Bot
01:22 AM
Tool Call
search_docs(query: "CIViC drugs ontology 'Drug' 'DrugBank' 'ChEMBL' 'PubChem' site:civic.readthedocs.io")
Tool Result
01:22 AM
Tool Result
Click to expand
[
{
"link": "https://civic.readthedocs.io/en/latest/generated/civic.docs-aliases.html",
"title": "civic.docs-aliases",
"contents": "<no title> — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » <no title> View page source Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/genindex.html",
"title": "genindex",
"contents": "Index — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Index Index Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/search.html",
"title": "search",
"contents": "Search — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Search Please activate JavaScript to enable the search functionality. Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); }); jQuery(function() { Search.loadIndex(\"searchindex.js\"); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/about/citations.html",
"title": "citations",
"contents": "Citations — CIViC documentation About CIViC Participating Meetings & Events FAQ Instructional Videos Scientific Advisory Board Domain Experts AI Editorial Policies Partners Data Clients Figures and Graphics Acknowledgements Citations CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » About CIViC » Citations View page source Citations¶ The following publications are directly related to the CIViC project. Project Organization Title Link(s) CIViC public proposal WashU / Scripps Organizing knowledge to enable personalization of medicine in cancer PubMed: 25222080(2014. Genome Biology) CIViC original publication WashU CIViC is a community knowledgebase for expert crowdsourcing the clinical interpretation of variants in cancer PubMed: 28138153(2017. Nature Genetics) Standards for variant sharing Multi-institution initiative / ClinGen Somatic Working Group ClinGen Cancer Somatic Working Group standardizing and democratizing access to cancer molecular diagnostic data to drive translational research PubMed: 29218886(2018. PSB) Minimum variant level data Multi-institution initiative / ClinGen Somatic Working Group Adapting crowdsourced clinical cancer curation in CIViC to the ClinGen minimum variant level data community‐driven standards PubMed: 30311370(2018. Human Mutation) CIViC SOP WashU Standard operating procedure for curation and clinical interpretation of variants in cancer PubMed: 31779674(2019. Genome Medicine) CIViCmine Canada’s Michael Smith Genome Sciences Centre Text-mining clinically relevant cancer biomarkers for curation into the CIViC database PubMed: 31796060(2019. Genome Medicine) OpenCAP WashU Open-Sourced CIViC Annotation Pipeline to Identify and Annotate Clinically Relevant Variants Using Single-Molecule Molecular Inversion Probes PubMed: 31618044(2019. JCO Clinical Cancer Informatics) CIViCpy WashU CIViCpy: a Python software development and analysis toolkit for the CIViC knowledgebase PubMed: 32191543(2020. JCO Clinical Cancer Informatics) Virtual Molecular Tumor Board Multi-institution initiative / GA4GH (VICC) Collaborative, Multidisciplinary Evaluation of Cancer Variants Through Virtual Molecular Tumor Boards Informs Local Clinical Practices PubMed: 32644817(2020. JCO Clinical Cancer Informatics) Meta-knowledgebase Multi-institution initiative / GA4GH (VICC) A harmonized meta-knowledgebase of clinical interpretations of somatic genomic variants in cancer PubMed: 32246132(2020. Nature Genetics) CIViC community approach Multi-institution WashU / ClinGen / GA4GH (VICC) A community approach to the cancer variant interpretation bottleneck PubMed: 35624339(2022. Nature Cancer) CIViC update 2022 (NAR) Multi-institution WashU / ClinGen / GA4GH (VICC) Evolution of the open-access CIViC knowledgebase is driven by the needs of the cancer variant interpretation community PubMed: 36373660(2022. Nucleic Acids Research) Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
}
]
CIViC Bot
01:22 AM
Tool Call
search_docs(query: "site:civic.readthedocs.io 'Drug' 'curation' 'ontology' 'Drug Ontology' 'ChEMBL' 'PubChem' 'Drugbank' CIViC drugs 'Drug' page")
Tool Result
01:22 AM
Tool Result
Click to expand
[
{
"link": "https://civic.readthedocs.io/en/latest/generated/civic.docs-aliases.html",
"title": "civic.docs-aliases",
"contents": "<no title> — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » <no title> View page source Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/search.html",
"title": "search",
"contents": "Search — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Search Please activate JavaScript to enable the search functionality. Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); }); jQuery(function() { Search.loadIndex(\"searchindex.js\"); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/genindex.html",
"title": "genindex",
"contents": "Index — CIViC documentation About CIViC CIViC Knowledge Model Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » Index Index Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
},
{
"link": "https://civic.readthedocs.io/en/latest/model/evidence/disease.html",
"title": "disease",
"contents": "Disease — CIViC documentation About CIViC CIViC Knowledge Model Evidence Items Evidence Overview Gene Molecular Profile Statement Evidence Level Type Direction Significance Origin Disease Curating Diseases Therapy Associated Phenotype Source Clinical Trial Evidence Rating Assertions Features Molecular Profiles Variants Genes Fusions Factors Variant Groups Sources Curating CIViC User Interface and Data CIViC API Get Help CIViC Docs » CIViC Knowledge Model » Evidence Items » Disease View page source Disease¶ The disease field generally requires an value that is known to the Disease Ontology database. (Kibbe et al. 2015) The Disease Ontology (DO) database provides an open-sourced ontology for the integration of biomedical data that is associated with human disease. Within the CIViC database, the disease should be the cancer or cancer subtype that is associated to the described Molecular Profile (variant or ensemble of variants) by the evidence being curated. The disease selected should be as specific as possible and should reflect the disease type described in the source that supports the evidence statement. In CIViC, Disease is largely synonymous with cancer type or sub-type. Curating Diseases¶ The disease field will autofill based on existing diseases in the Disease Ontology (DO) database and the most specific disease subtype should be selected, if possible. Only a single disease can be associated with an evidence item. If the Molecular Profile and clinical evidence is implicated in multiple diseases in the source that is being curated, then multiple evidence items should be created. If the disease cannot be identified in the Disease Ontology database, the curator can add this new disease to CIViC during the curation of the associated Evidence Item (Figure 1). Alternatively, new DO terms, definitions, suggestions and questions in regard the Disease Ontology can be submitted to the DO Term Tracker. Figure 1: A new disease term can be added to CIViC during the Evidence Item curation process The current Diseases (cancer types) with associated with Evidence, Assertions and other information in CIViC can be explored on the CIViC Disease Page. Next Previous Visit the CIViC resource at civicdb.org. Disclaimer: CIViC is intended for purely research purposes. It should not be used for emergencies or medical or professional advice. CIViC by The McDonnell Genome Institute at Washington University School of Medicine is licensed under a Creative Commons Public Domain Dedication (CC0 1.0 Universal) jQuery(function () { SphinxRtdTheme.Navigation.enable(true); });",
"document_type": "read_the_docs"
}
]
CIViC Bot
01:22 AM
Short answer
- CIViC uses these external ontologies/controlled vocabularies for curation and the data model:
- Disease Ontology (DO) — used for the Evidence/Assertion disease field.
- Sequence Ontology (SO) — used for Variant Type(s).
- Human Phenotype Ontology (HPO) — used for Associated Phenotypes on Evidence and Assertions.
Excerpts from the CIViC documentation
-
Disease (Disease Ontology): “The disease field generally requires an value that is known to the Disease Ontology database. (Kibbe et al. 2015)”)” [1]
-
Variant Types (Sequence Ontology): “Variant Type(s) are used to classify variants by Sequence Ontology terms. Variant Types permit advanced searching for categories of variants in the CIViC interface and downstream semantic analyses of CIViC variants.” [2]
-
Associated Phenotypes (Human Phenotype Ontology): “…terms are drawn from the Human Phenotype Ontology (HPO).” [3]
Notes / related controlled vocabularies used by CIViC (not strictly ontologies)
-
Gene symbols / gene identifiers: CIViC requires official Entrez/HGNC gene symbols (Entrez Gene IDs are used as the canonical gene identifier in CIViC). Example excerpt: “The CIViC Gene Name utilizes official Entrez Gene Names from the Entrez Gene database… Curators must enter a valid Entrez Gene Name (e.g., TP53) and should verify the correct entry against the Entrez Gene ID automatically displayed by the CIViC interface.” [4]
-
CIViC also links out to other external resources (e.g., MyGene.info, DGIdb, ProteinPaint) for gene/drug annotations, but those are external databases/services rather than ontologies (see gene page). [4]
If you want, I can: (a) list the exact fields in the CIViC API or data model where each ontology is enforced/used, or (b) provide direct links to the ontology term pickers / UI screenshots in the docs.