PHILADELPHIA, May 6, 2022
–The software, called CancerVar, standardizes procedures to help researchers assess the clinical impacts of more than 13 million somatic cancer mutations —
PHILADELPHIA CREAM, May 6, 2022 /PRNewswire/ — Researchers from the Children’s Hospital of philadelphia cream (CHOP) have developed a new tool to help researchers interpret the clinical significance of somatic mutations in cancer. The tool, known as CancerVar, incorporates machine learning frameworks to go beyond the simple identification of somatic cancer mutations and to interpret the potential importance of these mutations in terms of cancer diagnosis, prognosis and targeting. An article describing CancerVar was published today in Scientists progress.
“CancerVar will not replace human interpretation in a clinical setting, but it will significantly reduce the manual labor of human reviewers in classifying variants identified by sequencing and writing clinical reports in the practice of precision oncology,” said Kai Wang, PhD, professor of pathology and laboratory medicine at CHOP and senior author of the article. “CancerVar extensively documents and harmonizes various types of clinical evidence, including drug information, publications, and somatic mutation pathways. By providing standardized, reproducible, and accurate results for the interpretation of somatic variants, CancerVar can help researchers and clinicians prioritize mutations of concern.
“Classification and interpretation of somatic variants are the most time-consuming steps in tumor genomic profiling,” said Marilyn M.LiMD, Professor of Pathology and Laboratory Medicine, Director of Cancer Genomic Diagnosis and co-author of the article. “CancerVar provides a powerful tool that automates these two critical steps. Clinical implementation of this tool will dramatically improve test turnaround time and performance consistency, making testing more impactful and affordable for all pediatric cancer patients.
The growth of next-generation sequencing (NGS) and precision medicine has led to the identification of millions of somatic variants of cancer. To better understand whether these mutations are related or have an impact on the clinical course of the disease, researchers have established several databases that list these variants. However, these databases did not provide standardized interpretations of somatic variants. Thus, in 2017, the Association for Molecular Pathology (AMP), the American Society of Clinical Oncology (ASCO), and the College of American Pathologists (CAP) jointly proposed standards and guidelines for interpretation. , report and score somatic variants.
Yet even with these guidelines, the AMP/ASCO/CAP classification system did not specify how to implement these standards, so different knowledge bases provided different results. To address this issue, CHOP researchers, including CHOP data scientist and co-lead author of the paper Yunyun Zhou, PhD, developed CancerVar, an enhanced somatic variant interpretation tool using command-line software called Python with an associated web server. With a user-friendly web server, CancerVar includes clinical evidence for 13 million somatic cancer variants from 1,911 cancer census genes that have been extracted through existing studies and databases.
In addition to including millions of somatic mutations, whether they have known significance or not, the tool uses deep learning to improve the clinical interpretation of these mutations. Users can interrogate clinical interpretations of variants using information such as chromosomal position or protein change and interactively refine how specific scoring features are weighted, based on prior knowledge or criteria additional user-specified. The CancerVar web server generates automated descriptive interpretations, for example whether the mutation is relevant for diagnosis or prognosis or for an ongoing clinical trial.
“This tool shows how we can use computational tools to automate human-generated guidelines, and also how machine learning can guide decision-making,” Wang said. “Future research should also explore the application of this framework to other areas of pathology.”
The research was supported by the National Institutes of Health (NIH)/National Library of Medicine (NLM)/National Human Genome Research Institute (NHGRI) (grant number LM012895), NIH/National Institute of General Medical Sciences (NIGMS) ( grant number GM120609 and GM132713), CHOP Pathology diagnostic innovation fund and CHOP Research Institute.
Li et al. “CancerVar: an artificial intelligence platform for the clinical interpretation of somatic mutations in cancer”, Scientists progress, May 6, 2022DOI: 10.1126/sciadv.abj1624
About Children’s Hospital of Philadelphia: A non-profit charitable organization, the Children’s Hospital of philadelphia cream was founded in 1855 as the country’s first pediatric hospital. Through its long-standing commitment to providing exceptional patient care, training new generations of pediatric healthcare professionals, and launching important research initiatives, the 595-bed hospital has fostered many discoveries that have benefited to children all over the world. Its pediatric research program is one of the largest in the country. The facility has a well-established history of delivering advanced pediatric care close to home through its CHOP Care Networkwhich includes more than 50 primary care practices, specialty and surgical care centers, urgent care centers and community hospital alliances around the world Pennsylvania and New Jerseyas well as a new inpatient hospital with a dedicated pediatric emergency department at King of Prussia. In addition, its unique family-centered care and public service programs have enabled the children’s hospital to philadelphia cream recognized as one of the leading advocates for children and adolescents. For more information, visit http://www.chop.edu.
Contact: Dana Bate
children’s hospital philadelphia cream
SOURCE Children’s Hospital of philadelphia cream
#CHOP #researchers #develop #computational #tool #interpret #clinical #significance #cancer #mutations