Discoveries by GNS Healthcare Causal Machine Learning and Simulation Platform, REFS, Reveal Mechanisms Driving Key Clinical Outcomes in Multiple Myeloma

Ongoing Collaboration Leveraging the Multiple Myeloma Research
Foundation CoMMpass Study Reveals Drivers of High-Risk Disease and of
Durable Response

(GNS), a leading precision medicine company that
applies causal machine learning technology to massive and diverse data
streams to better match drugs and other health interventions to
individual patients, has announced the latest findings from its ongoing,
multi-year collaboration with The Multiple Myeloma Research Foundation
(the MMRF) leveraging the MMRF’s landmark CoMMpass Study™ (NCT0145429)
and revolutionary GNS causal machine learning and simulation platform
REFS™ (Reverse Engineering and Forward Simulation) to speed the
discovery of innovative treatments for patients with multiple myeloma.

Several drivers of clinical outcomes in multiple myeloma disease and
their associated molecular pathways, including some that are novel, were
revealed by GNS at the American Society of Hematology (ASH) 58th Annual
Meeting & Exposition in the session, “Bayesian
Network Models of Multiple Myeloma: Drivers of High Risk and Durable
.” The discoveries, from the largest and most comprehensive
computer models ever built of molecular and clinical interactions in
multiple myeloma disease, expand the existing understanding of key
subpopulations of multiple myeloma patients. They explain the underlying
causal mechanisms driving progression in patients with the high-risk
form of the disease and identify a previously unknown molecular pathway
driving the probability of a durable response to treatment.

“The MMRF’s collaboration with GNS is bearing fruit and helping us
fulfill our commitment to making rapid and meaningful progress toward a
cure for multiple myeloma,” said Daniel Auclair, PhD, Senior Vice
President of Research at the MMRF. “The discoveries being announced
today greatly expand our ability to identify treatment subgroups and
high-risk subgroups. These are significant steps forward in the
understanding of multiple myeloma.”

The specific discoveries include the identification of the genes CDK1,
PKMY1, MELK, and NEK2 as the top drivers of high-risk disease. Well
known to researchers focused on multiple myeloma and other forms of
cancer, these genes represent a pathway that contains known drug
targets, suggesting a validation strategy and the potential to employ
drugs in combination. Among these, the MELK inhibitor OTSSP167 has
recently been found to provide a synergistic effect with other drugs for
the treatment of multiple myeloma. In addition, the models identified
several novel pathways driving durable response, including a pathway of
ribosomal genes (RPL6, RPL23, RPL12), a pathway of translation
elongation factor EEF1A1 and associated pseudogenes, and a pathway of
regulatory noncoding genes MIR1302-9, RP11-946L20.4, RP11-346D14.1, and
RP11-506N2.1. Little is known about the connection of these genes to
multiple myeloma; however, a pathway that is central to ribosomal
biogenesis, ubiquitin-proteasome, is a major drug target in multiple

These discoveries deliver value for a range of healthcare stakeholders.
They may improve patient stratification and the overall efficiency of
clinical trials, accelerating the ability of pharmaceutical companies to
bring new and effective treatments to patients; lead to more
personalized treatment protocols, enhancing the ability of health
insurers and providers to offer the most beneficial treatment to
individual patients; result in new treatment strategies that employ
existing pharmaceuticals in combinations; and may represent targets for
drug discovery and development. Together, these capabilities improve the
ability to prevent progression of disease and address the continued
unmet treatment needs of patients with multiple myeloma.

The causal models are the product of large-scale, multi-modal patient
data from the MMRF CoMMpass Study and the revolutionary GNS causal
machine learning and simulation platform REFS. Results reflect an
analysis by REFS of the CoMMpass Interim Analysis 9 (IA9) dataset, which
is composed of extensive clinical and genomic data, including RNAseq
measurements, somatic copy numbers, single nucleotide variants, and
structural variants for a population of more than 600 enrolled patients.
GNS leveraged REFS to reverse-engineer the molecular pathways that
affect treatment outcomes in the CoMMpass population and to assess the
significance of these pathways in treatment response CoMMpass follows
1,000 newly diagnosed patients with active multiple myeloma for eight
years. Its objective is to map to clinical parameters each of these
patients’ myeloma cells genomic profiles, generated from specimens
collected at first presentation and at progression events, to develop a
more complete understanding of patient responses to treatments.

“The findings announced today underscore the power of causal models to
discover drug targets and pathways from the nearly infinite number of
possibilities,” said Iya Khalil, PhD, Chief Commercial Officer,
Executive Vice President and Co-Founder of GNS. “In combination with the
MMRF’s CoMMpass data, one of the richest datasets of its kind, we are
not only accelerating the discovery and development of new therapeutics,
but also helping patients and their providers with decisions about the
optimal use of existing and future therapies.”

GNS and the MMRF have made a number of significant discoveries since the
organizations began collaborating approximately two years ago, in the
fall of 2014. The 2016 ASH Annual Meeting & Exposition presentation
marks the second time in as many years that this effort combining data
from the MMRF CoMMpass Sudy with causal machine learning and simulation
technology has been featured at ASH. At the 2015 event, GNS and the MMRF
revealed the discovery of novel drivers of clinical outcomes.

About GNS Healthcare

GNS Healthcare applies causal machine learning and simulation technology
to predict which treatments will work for which patients, improving
individual patient outcomes and the health of populations, while
reducing the total cost of care. The GNS technology is based on its
MeasureBase™ data integration architecture and patented REFS™ (Reverse
Engineering and Forward Simulation) causal inference and simulation
engine. Health plans, bio-pharmaceutical companies, healthcare
providers, foundations, academic medical centers, and self-insured
employers use these cloud-based solutions to solve pressing and costly
problems including metabolic syndrome, medication adherence, end-of-life
care, preterm birth, personalized care pathways in specialty care,
oncology, and diabetes, new drug target discovery, patient
stratification in clinical trials, and more. GNS solutions focus on
reducing adverse events, slowing disease progression, and improving
therapeutic effectiveness through precision matching that maximizes
impact on individual patient health outcomes while reducing wasteful
spending and downstream medical costs.

Discovering what works. For whom.


GNS Healthcare
Gina Veazey, 703-254-6276