Study results are from the DREAM Challenge and are published in Leukemia
CAMBRIDGE, Mass.– May 28, 2020 – GNS Healthcare (GNS), a leading AI-driven precision medicine, announced results of a recently published collaboration that uncovered transcription factor PHF19 as a novel marker of aggressive multiple myeloma progression in newly diagnosed patients. By identifying PHF19, GNS and collaborators pave the way to potential improvements in clinical trial design and oncologists’ treatment decision-making for patients with newly diagnosed multiple myeloma. If further validated, the implication of a validated single gene test is clear – a simpler, faster way to understand multiple myeloma patient progression and risk.
“Identifying a robust prognostic signature will allow physicians to better treat the most high-risk patients with appropriate interventions earlier. Using PHF19, a single gene test, could make the process of identifying the right patients for intervention or for clinical trial design faster and simpler,” said Colin Hill, GNS Chairman, CEO, and Co-Founder. “This challenge was a great display of collaboration and shows that together we can not only break down data silos but move toward identifying previously unknown regulators of disease with the help of AI.”
The model resulting from the DREAM challenge has only four features: age, staging information and the expression of PHF19 and MMSET which can pave the way for a single gene test. To validate the marker, collaborators conducted cell line experiments and showed that knock down of PHF19 leads to decreased proliferation through cell cycle arrest in multiple myeloma.
Published in Leukemia, the study reported results from the DREAM competition which asked participants to submit algorithms to identify prognostic factors marking disease progression from gene expression data. With over 800 participants and nearly 200 algorithms submitted to the Challenge, GNS Healthcare’s algorithm was found to be the most accurate in predicting markers of aggressive disease progression, outperforming even those available in commercial tests such as UAMS70 and EMC92. The complex molecular datasets, contributed by the Multiple Myeloma Research Foundation (MMRF), M2Gen, Dana Farber Cancer Institute, University of Arkansas for Medical Sciences and the University of Heidelberg, included five microarray and three RNA-seq expression datasets annotated with clinical characteristics including gender, age, International Staging System and cytogenetics. The data was transformed using REFS, GNS’s AI and simulation platform, to build models of multiple myeloma.
The paper titled “Multiple Myeloma DREAM Challenge Reveals Epigenetic Regulator PHF19 as Marker of Aggressive Disease” was published in Leukemia on February 14, 2020 and is available here.
First author Fred Gruber, GNS Healthcare, collaborated with researchers from Sage Bionetworks, University of Arkansas for Medical Sciences, Genome Institute of Singapore, Celgene Corporation (Bristol-Myers Squibb), Virginia Polytechnic Institute and State University, University of Michigan Medical School, Shanghai Jiao Tong University, Stanford University School of Medicine, M2Gen, Rancho BioSciences, Moffitt Cancer Center & Research Institute, Universitätsklinikum Heidelberg, Nationales Centrum für Tumorerkrankungen, Institut Universitaire du Cancer Oncopole, Dana-Farber Cancer Institute, Harvard TH Chan School of Public Health, Erasmus MC Cancer Institute, VA Boston Healthcare System, Multiple Myeloma Research Foundation, Labor für Myelomforschung, and Indiana University on this paper.
About GNS Healthcare
GNS Healthcare is an AI-driven precision medicine company developing in silico patients from real world and clinical data. In silico patients reveal the complex system of interactions underlying disease progression and drug response, enabling the simulation of drug response at the individual patient level. This in turn enables the precise matching of therapeutics to patients and the rapid discovery of key insights across drug discovery, clinical development, commercialization, and payor markets. GNS REFS™ causal AI and simulation technology integrates and transforms a wide-variety of patient data types into in silico patients across oncology, auto-immune diseases, neurology, and cardio-metabolic diseases. GNS partners with the world’s leading biopharmaceutical companies and health plans and has validated its science and technology in over 50 peer-reviewed papers and abstracts. https://gnshealthcare.com
MacDougall Biomedical Communications