Rapid advances in cancer treatments have led to the generation of large quantities of data. Collecting, organizing, and understanding this rapidly growing amount of data and rapidly evolving types of data is a challenge to the modern bioinformatician and/or medical informatician. As "Big Data" becomes significantly impactful in the cancer treatment landscape, it is imperative to maintain a robust and flexible data pipeline. GenomOncology’s APIs and analytics tools allow institutions to integrate both our data curation and analytics functionalities into their existing infrastructures.
Solutions for Cancer Informatics include...
GO Application Programming Interfaces
GenomOncology Application Programming Interfaces (API) provide REST-based interfaces for the GenomOncology Knowledge Management System (KMS). Examples of functionality provided by the KMS and API include...
- Variant data file parsers (VCF, XML, MAF, etc.) enable importing case variants
- Comprehensive biomarker grammar for region-based and implied biomarker matching
- High-throughput of HGVS nomenclature (g. c. and p.) for the calculation of variants
- Annotation of variants using open source and licensed data sets.
- Classification of variants using AMP and ACMG guidelines by disease/phenotype
- Data Sharing APIs for approving and submitting variants to ClinGen, GENIE, etc.
- Disease ontology provides a hierarchy curated by the My Cancer Genome team that can be mapped into existing ontologies
- Matching of therapies, prognoses, and clinical trials using molecular and clinical data
- Institution and geolocation-based clinical trial filtering and sorting.
- Curation of custom annotations, classifications, therapies, prognoses, and trials
- HTML and PDF Report rendering from customizable templates.
- Analytics API for cohort analysis and visualization
The annotator is a high-throughput, parallel processing tool that injects annotations into a copy of a VCF file at the rate of 2000 Variants per second.
- Highly configurable command-line tool that should fit into most data pipelines without customization
- Billions of annotation data points are loaded into its flexible architecture in order to ease implementation
- Seamlessly provides hundreds of data points for files ranging from small-panel VCFs to whole exome VCFs.
- The Annotations API which drives the annotator is additionally able to perform a variety of bioinformatic calculations such as HGVS, exon distance, exon numbering, mutation type, etc.
- Base annotations include datasets such as ExAC, EVS, dbSNFP, dbSNP, ClinVar, GNOMAD, 1000 Genomes, SIFT, COSMIC, Mutation Taster, etc.
- Flexibility and extensibility of our system allows for the loading of any additional licensed materials into the system with custom parsers (VCF, TSV, CSV, JSON, XML, etc.)
"Big Data" analysis of patient data in context.
GenomAnalytics is a visualization and statistical analysis software suite composed of reusable widgets that allow users to design analyses and dashboards without any coding. GenomAnalytics utilizes GenomOncology's Knowledge Management System to enable users to analyze any molecular, clinical, demographic, or recommendation data housed within. The system incorporates basic summarization widgets; clinical analysis widgets such as survival curves; data specific widgets such as heatmaps for expression data, and statistical clustering; and grouping widgets. The integration with R and Python-based data science tools is available, along with an integrated Jupyter Notebook environment.
Integration of discrete genomic data into the EMR using standards based HL7 messages.
- The increasing importance of DNA sequence data to cancer therapeutic decision making has illuminated the need to make discrete genomic information available in the Electronic Health Record
- It has been thought that this would require new technologies, like FHIR, and therefore, will not become widely available for some years
- To accelerate this process, GenomOncology, working in collaboration with the University of Nebraska Medical Center, has developed GO Connect, a technology that generates standard HL7 Observation Results messages that describe somatic mutations, thereby providing integration with today’s Electronic Health Records
- GO Connect can accept biomarker data in a variety of formats from a variety of sources, including industry standard “vcf” files, Foundation Medicine XML files, and, of course, files from the GO Pathology Workbench
- GO Connect uses services provided by the GO Knowledge Management System (KMS) to transform data into HL7, including adding additional annotations, providing filtering capabilities, etc.
- GO Connect can also accept HL7 formatted orders and convert them into formats acceptable to a variety of laboratories