Numerate to join ATOM Consortium to Rapidly Accelerate Preclinical Drug Development

Taken from the official press release from ATOM:

Computational drug design company Numerate has signed a letter of intent to join an open consortium of scientists staffed from two U.S. national laboratories, industry, and academia working to transform drug discovery and development into an approach that is rapid, integrated and with better patient outcomes.

Accelerating Therapeutics for Opportunities in Medicine (ATOM) formed in October 2017 with the goal of reducing preclinical drug discovery from six years to just one, using cancer as the exemplar disease.

ATOM is integrating high-performance computing and biological, chemical, preclinical, and clinical data from public and industry sources to create an active learning platform that considers all aspects of drug discovery and pharmacology. ATOM will integrate emerging high-fidelity, data-rich experimental technologies, and cutting-edge software into the approach.

“This will create an ecosystem which will foster the rapid and dynamic collaboration needed to advance precision medicine and tremendously benefit patients,” wrote Guido Lanza, president and CEO of Numerate, and Brandon Allgood, CTO, in the letter signed April 3, 2018.

“Our organization’s business priorities and directions are strongly aligned with the fundamental elements of ATOM … and we look forward to outlining the specific contributions we can make to the ATOM consortium as collaborators,” they wrote.

John Baldoni, ATOM founder and governing board co-chair, and senior vice president for R&D at GSK, said Numerate is well-known for its innovative software approach to drug discovery.

“This collaboration provides Numerate with extensive and unique data sources and computer power with which they can optimize their drug discovery algorithms,” Baldoni said. “This letter of intent signals how cutting-edge private-sector organizations can benefit in this public/private consortium.”

Numerate joins the founding members of ATOM: GSK, the National Cancer Institute’s Frederick National Laboratory for Cancer Research (FNLCR), the University of California, San Francisco (UCSF), and the Department of Energy/National Nuclear Security Administration (NNSA)’s Lawrence Livermore National Laboratory (LLNL), which is contributing supercomputer resources and cognitive simulation expertise to the ATOM consortium. ATOM headquarters is located in the Mission Bay neighborhood of San Francisco.

ATOM seeks other organizations to join the consortium to bring their expertise into this new environment.

“We are excited to see the addition of industry leaders to the consortium and to the effort to bring effective new drugs to cancer patients more rapidly,” said Eric Stahlberg, director of high performance computing at the Frederick National Laboratory.

The partners agree to work together to develop, test, and validate a multidisciplinary approach to drug discovery where science, technology and engineering, supercomputing simulations, data science, and artificial intelligence are integrated into a drug-discovery platform, ultimately to be shared with the drug development community at large.

 

DTRA Renews Contract to Support Continued Development of Numerate’s Predictive Toxicity System

Numerate and partner CUBRC receive three-year contract to continue to improve and validate Numerate’s ToxTool system that characterizes potential chemical threats

We would like to announce that, in collaboration with CUBRC, a leading research, development, testing and system integration company, we have received a three-year contract renewal worth $1.23 million from Defense Threat Reduction Agency (DTRA) within the Department of Defense (DoD).
Under the contract Numerate will be extending the capabilities of and, in collaboration with CUBRC, validating and deploying our ToxTool system, developed and validated with CUBRC under two previous contracts with DTRA (under Prime Contracts FA8075-14-C-0092 and SP00700-00D-3180).
The ToxTool system is a computational assessment tool that can determine potential compound toxicity and guide the laboratory characterization of new chemical threat agents. At its core, ToxTool uses Numerate’s proprietary AI technology that has the capability to build highly predictive and generalizable ligand based models of compound-target activity, as well as absorption, distribution, metabolism, and elimination (ADME) properties with small amounts of publicly available data, which is often very noisy and biased. The current version of the tool contains over 6,600 mechanism-of-action based target models and around 1,600 surrogate models, used for protein targets without any publicly disclosed data. The tool also incorporates cellular pathway information, allowing researchers to quickly understand the implications of a predicted target hit, and ADME models, further helping the researchers understand whether a prediction is going to be clinically relevant.
Brandon Allgood, Ph.D., Chief Technology Officer at Numerate, will lead the software development efforts and work closely with David Mangino, VP, Chemical, Biological & Medical Sciences at CUBRC, who will lead the laboratory validations of the tools predictions.
“We are excited to continue working with DTRA and CUBRC to further advance the capabilities of ToxTool,” said Dr. Brandon Allgood, CTO at Numerate. “These new developments will help to better inform and guide the researchers working to characterize new chemical threats and protect the warfighter. At the same time, these advancements will further improve our capabilities to develop new drugs that will having a much lower potential for off-target side effects in the clinic.”
During the first year of the renewal, the key advancement will be a more integrated ADME system using protein and RNA expression data to develop a protein map. Using this map and a number of newly developed ADME models, the tool will be able to qualify the clinical relevance of a target activity prediction. For example, if a compound is predicted to hit a CNS target, but the blood brain barrier model predicts that it won’t get into the CNS the threat level will be automatically downgraded. Previously, the system relied on the user’s understanding of biology for this determination. Other improvements also included in this year are user adjustable threat levels and incorporation of automatic pKa adjustment. In the following years, the tool will be equipped with the ability to incorporate new data in to existing models as researchers collect it, enabling them to add classified data to classified deployments. It will also include models of more routes of exposure.
“We are very pleased to continue our work with DTRA and our collaboration with Numerate supporting the development and testing of the ToxTool. In silico predictive assessments provide a critical contribution to the overall characterization of potential chemical threats and to the understanding of the clinical relevance of specific compounds,” said David Mangino, Vice President of CUBRC’s Chemical, Biological & Medical Sciences Sector.
This work is being supported by subcontract 08064S1 through a CUBRC Task Order under Prime Contract FA8075-14-D-0003.

About CUBRC

CUBRC is an independent not-for-profit research and development company specializing in the areas of Chemical, Biological and Medical Defense, Data Science and Information Fusion and Aeronautics. CUBRC serves as prime contractor and systems integrator for the US Government and has over 30 years of experience combining innovative ideas and state-of-the-art technology and test facilities to help solve some of the most critical and challenging problems facing our Defense, Intelligence and Homeland Security communities. CUBRC is headquartered in Buffalo, New York. For more information, visit www.cubrc.org.

National Institutes of Health Awards Grant to Numerate to Develop Compounds that Enhance Bone Integration of Orthopedic Devices

Numerate will collaborate with researchers at Mayo Clinic on the discovery of compounds for surface coating of endoprosthetic devices

We would like to announce that the National Institute of Arthritis and Musculoskeletal and Skin Diseases (NIAMS) of the National Institutes of Health (NIH) awarded Numerate a grant to improve outcomes for patients who need an orthopedic implant surgery.

The project titled, “EZH2 inhibitors as endoprosthetic device coatings that induce osteogenesis and promote implant osseointegration” is expected to identify potential drug options that will ultimately help patients undergoing implant surgeries.

Uwe Klein, Ph.D., Vice President, Biology at Numerate, will lead the discovery efforts and serve as Principal Investigator with co-investigator Andre J. van Wijnen, Ph.D., professor of Biochemistry and Molecular Biology, and Orthopedic Surgery at the Mayo Clinic.

The project is based on work in Dr. van Wijnen’s laboratory that demonstrated a key role of the epigenetic enzyme ‘Enhancer of Zeste homolog 2’ (EZH2) in skeletal development and the differentiation of osteoblasts, the cells critical for new bone formation. Dr. van Wijnen has shown that inhibition of EZH2 results in the stimulation of new bone formation by activation of the osteogenic pathway in mesenchymal stem cells1. Surface coating of orthopedic implants used in hip and knee replacement procedures with such compounds is expected to facilitate integration of existing bone with the device. Better device/bone integration may reduce complications stemming from poor anchoring of implants and improve implant life-time, especially in patients suffering from bone disorders such as osteoporosis, arthrosis or osteopenia.

“We are pleased to receive this award from the NIH and are excited to work with Dr. van Wijnen, a renowned expert in bone biology, to build upon his work and discover an important new drug for use in a drug/device combination for orthopedic indications, addressing a significant medical need in the aging population in the United States,” said Uwe Klein, Ph.D., Vice President, Biology at Numerate.

With an aging population and increased life span, the number of patients requiring reconstructive joint surgeries or joint replacements continues to increase. Many patients undergoing arthroplasty procedures suffer from bone disorders such as osteoporosis, severe arthrosis or osteopenia, with a bony matrix that impedes firm anchoring of implants to existing bone. This results in poor implant osseointegration and aseptic loosening, and requires revision surgeries in many patients. The need and opportunity exists for new therapeutic strategies that improve bone-implant contact and device osseointegration2.

“The NIAMS funding will allow us to further explore the therapeutic utility of EZH2 inhibition to treat bone disorders,” said Dr. Andre van Wijnen. “We hope that this work will allow us to offer better treatment options for patients who need short-term augmentation of bone formation including those requiring endoprosthetic device implants.”

John Griffin, Ph.D., Chief Scientific Officer of Numerate, added, “Our AI-based drug discovery platform has the potential to accelerate the discovery and development of novel small molecule compounds with optimized properties for use in combination with a device, and with minimized systemic toxicity. We are looking forward to collaborating with Dr. van Wijnen and his team at Mayo Clinic”.

This works is being supported by the Small Business Innovation Research (SBIR) Phase I grant (1R43AR073051-01), awarded by the National Institute of Arthritis and Musculoskeletal and Skin Diseases (NIAMS) of the National Institutes of Health (NIH).

Numerate Enhances Platform Through Acquisition of DeepCrystal Technology

San Bruno, CA – Numerate, Inc., the world’s leading computational drug design company applying artificial intelligence (AI) at cloud scale to transform small molecule drug discovery has acquired DeepCrystal’s small molecule design platform. The platform is used to build models of compound activity and ADME based on advances in graph-valued deep-learning technology.  These methods will augment Numerate’s existing AI platform by compressing timelines to facilitate the discovery of next generation therapeutics.

As part of the acquisition, Patrick Hop, the Founder of DeepCrystal, will join Numerate as Principal Engineer of Deep Learning. At DeepCrystal, Mr. Hop was responsible for the development of its core technology and platform, as well as leading the company into strategic partnerships with top pharmaceutical companies to advance in-silico modeling. He holds a B.A in Applied Mathematics from UC Berkeley, and serves as a mentor to River Accelerator.

“We are excited to have Patrick join our team and bring his extensive experience in applying deep learning to drug discovery,” said Brandon Allgood, Ph.D., Chief Technology Officer at Numerate. “His research and insights combined with our expertise of applying AI to drug discovery will be synergistic.”

“I’m excited to begin working with the world-class engineering and scientific teams at Numerate,” said Mr. Hop. “Among the groups working in this space, I believe Numerate is the one striking the right balance of AI technology, and classical drug-discovery experience which, combined with the deep-learning technology from DeepCrystal, will help identify new therapies for patients faster and with less capital investment than ever before.”

CSO Report: Collaborating with academic investigators to unlock emerging biology

A most distinctive and valuable application of our AI platform is to rapidly advance small molecule therapeutic programs that exploit exciting insights as they emerge from basic biomedical research.  Our ability to learn accurate, scaffold-hopping predictive models from small, non-diverse and noisy training sets enables us to initiate and accelerate work against new targets from an early stage, e.g., from the point where an academic group has identified a small number of tool compounds having an activity of interest in a complex high-content/low-throughput assay that exists only in that laboratory.  Many promising projects that have the potential to address major unmet medical needs and opportunities languish at just this point because they cannot be adapted to traditional pharmaceutical screening and lead design processes.  We are able to unlock these projects, leveraging our AI to bootstrap the limited information content of initial training sets into models that we then use to screen large (107-109) compound libraries in silico to quickly (and with high laboratory-validated accuracy) expand the number and diversity of active compounds.  This sets the stage for AI-driven Hit-to-Lead and Lead Optimization.

We have published some of the results we have obtained in collaboration with leading academic laboratories.  With Prof. Chaitan Khosla and his group at Stanford, we demonstrated our ability to identify and improve upon new inhibitors of transglutaminase 2 (TG2).  Here, we built useful predictive models from a small training set comprising two very different chemotypes that were later found to bind to different binding sites on, and different conformational states of, TG2.  With Prof. Carl Nathan and his colleagues at Weill Cornell Medical College, we highlighted the scaffold-hopping capabilities of our models to identify structurally distinct new inhibitors of protein kinase R, including a potent, non-cytotoxic inhibitor suitable for use as a biological probe of PKR function.

More recently, we applied our AI to identify new stabilizers of the cardiac ryanodine receptor (RYR2), and licensed them to Servier.  Our work on this project benefitted from a very productive interaction with Prof. Wayne Chen at University of Calgary.  We also enjoyed a very productive collaboration with Prof. Robert Mahley of the J. David Gladstone Institutes where, with financial support from a Seeding Drug Discovery Award from the Wellcome Trust, we designed multiple series of ApoE4 structure correctors as potential leads for treating Alzheimer’s disease.  These became core assets for E-Scape, the founding and financing of which was recently announced.

Applying advanced AI in conjunction with cutting-edge biomedical science to produce scarce, first-in-class therapeutic assets sits at the core of Numerate’s business.  We believe that recognition of the value of translating insights into assets for compelling yet challenging targets, by Pharma partners and venture investors, has validated our strategy.  We look forward to continuing and expanding work with investigators from leading research institutions, as in our recently announced, NIH-funded collaboration with UCLA’s Cardiovascular Research Laboratory, where we are seeking to unlock an exciting new approach to preventing fatal heart arrhythmias.

National Institutes of Health Awards Innovation Research Grant to Numerate to Accelerate Discovery of Novel Antiarrhythmic Drug Candidates

Numerate and the UCLA Cardiovascular Research Laboratory will focus efforts on identifying therapy for the treatment and prevention of ventricular tachycardias and fibrillation (VT/VF)

San Bruno, CA – Numerate, Inc., a computational drug design company applying artificial intelligence (AI) at cloud scale to transform small molecule drug discovery, announced that the National Heart, Lung, and Blood Institute (NHLBI) of the National Institutes of Health (NIH) has awarded Numerate a Small Business Innovation Research (SBIR) Phase I grant.  Numerate, working with members of the UCLA Cardiovascular Research Laboratory (CVRL), will use the funds to initiate a drug discovery program targeting cardiac arrhythmias.

The project targets the discovery of small molecule drug candidates that address the need for a novel well-tolerated antiarrhythmic therapy for the treatment and prevention of ventricular tachycardias and fibrillation (VT/VF). Uwe Klein, Ph.D., Vice President, Biology at Numerate, will lead the discovery efforts and serve as Principal Investigator for the project titled, “Peripherally restricted α2/δ-1 subunit ligands that modulate CaV channel gating as novel antiarrhythmic drugs.” The project is funded under Grant Number 1R43HL139143-01.

The co-investigators include esteemed members of the UCLA Cardiovascular Research Laboratory, including:

  • Hrayr S. Karagueuzian, Ph.D., Professor of Medicine at the David Geffen School of Medicine at UCLA, Director of Translational Arrhythmias Research Section
  • Riccardo Olcese, Ph.D., Professor of Anesthesiology and Physiology at UCLA, Division of Molecular Medicine

“We are pleased to receive this award from the NIH and thrilled to be working with Drs. Karagueuzian and Olcese at the CVRL to build upon their existing work and discover an important new medicine for treatment of life-threatening arrhythmias,” said Dr. Klein.

John Griffin, Ph.D., Chief Scientific Officer of Numerate, added, “Our AI-based drug discovery platform has the potential to accelerate the rapid discovery and development of novel small molecule therapeutics and we are looking forward to collaborating with these two renowned cardiac pathobiology experts”.

“The NHLBI funding will expand upon our innovative research to manage cardiac arrhythmias with novel small molecule drugs that specifically block the arrhythmogenic late inward calcium current without altering other cardiac ionic currents,” said Dr. Karagueuzian. “I look forward to working with the scientists at Numerate who have developed highly sophisticated approaches using data driven machine learning and cloud computing to discover and develop a new antiarrhythmic drug therapy.”

“It’s a very exciting time for the fight against cardiac arrhythmias as my laboratory, which uses the quantitative rigor of biophysics to understand aberrant cardiac excitability, will benefit greatly from the application of artificial intelligence that Numerate brings to the table,” said Dr. Riccardo Olcese. “Numerate is the ideal partner to complement my laboratory’s expertise and with the generous support from the NHLBI, we are ready to evaluate the capabilities of rationally designed next-generation antiarrhythmics.”

About Cardiac Arrhythmias

According to the Mayo Clinic, more than 4 million Americans, most over age 60, experience heart arrhythmias (abnormal heart rhythms)[i]. Arrhythmias are caused by problems with the electrical system that regulates the steady heartbeat. The heart rate may be too slow or too fast; it may stay steady or become irregular and disorganized[ii]. The most serious and life-threatening arrhythmia is ventricular fibrillation (VF), which is an erratic disorganized firing of impulses in the lower chambers of the heart, called the ventricles. VF result in the heart being unable to pump blood, and is the most common cause of sudden cardiac death, claiming the lives of about 300,000 adults in the United States each year[iii].

AI Pharma Summit Meeting

Guido Lanza (CEO) and Brandon Allgood (CTO) attended the AI Pharma Summit in Boston last week.  The meeting brought together both large and small companies pushing the boundaries of AI in Pharma R&D.  Overall the discussions were productive, but there is a lot of work to be done and that is exciting! Below is the technical keynote given by Brandon at the meeting.

Numerate and Takeda Enter Agreement to Generate Novel Clinical Candidates Using AI-Driven Drug Discovery

Numerate, Inc., a computational drug design company applying artificial intelligence (AI) at cloud scale to transform small molecule drug discovery, announced the formation of a multi-year agreement with Takeda Pharmaceutical Company Limited (TSE: 4502) under which Numerate will identify and deliver multiple clinical candidates.

Under the agreement, Numerate will drive discovery programs aimed at identifying clinical candidates for use in Takeda’s core therapeutic areas: oncology, gastroenterology, and central nervous system disorders. The projects will rely on Numerate leveraging its AI-driven platform, from hit finding and expansion through lead design/optimization and ADME (absorption, distribution, metabolism and excretion)/toxicity modeling.

“This is an ideal arrangement for Numerate because our team will be working largely independently while having the opportunity to leverage Takeda’s global experience, therapeutic area insights, and unique R&D capabilities,” said Guido Lanza, President and CEO of Numerate. “We expect to produce multiple clinical candidates, while also continuing to refine, validate and expand our proprietary AI-driven platform as we work across a broad range of target types and drug design challenges.”

Financial terms of the current agreement were not disclosed, but include a combination of milestone payments and royalties that reflect the value of the clinical candidates being delivered.

“We are excited to partner with Numerate. Numerate has established an impressive track record of leveraging their AI platform to overcome drug design challenges, both for its own pipeline and in pharma/biotech collaborations,” said David Weitz, Head of Takeda California and Global Research Externalization. “By having Numerate select projects that align with Takeda’s strategy we expect the partnership to yield multiple assets that Takeda can develop into truly transformative medicines for patients.”

Numerate and Servier Establish Collaboration to Advance First-in-Class Ryanodine Receptor 2 Candidates for Cardiovascular Diseases

Numerate, Inc., a computational drug design company applying artificial intelligence (AI) at cloud scale to transform small molecule drug discovery, and Servier, an independent international pharmaceutical company, today announced a collaboration to pursue the design of small molecule modulators of ryanodine receptor 2 (RyR2), a target identified as physiologically important in cardiovascular diseases, but whose drug-ability has proven highly challenging. This collaboration could lead to potential first-in-class therapies for cardiovascular diseases, including heart failure and arrhythmias.

Ryanodine receptor dysfunction is known to be involved in the defects in calcium handling associated with cardiovascular diseases. The design of novel ryanodine receptor modulators remains challenging to address with traditional drug discovery methods, largely because of the complexity of the underlying biology.

Numerate’s disruptive, proprietary algorithm-driven drug discovery platform has overcome these challenges to successfully identify a series of novel RyR2 modulators. This collaboration will include the modeling of all aspects of small molecule drug discovery, leveraging all available chemical and biological data and using Numerate’s AI-driven process to accelerate the path to the clinical phase.

“We are very pleased to be working with Servier, a global leader in cardiovascular medicine,” said Guido Lanza, President and CEO of Numerate. “Their long-standing appreciation for the complexity and the promise of this target made the power of our approach and the success we were having with our internal discovery program appealing. Our agreement forges an ideal combination of capabilities and expertise to advance these assets.”

“Numerate’s platform has literally cracked the code on rapidly identifying diverse, potent, and functionally active modulators of the ryanodine receptor,” said Dr. Isabelle Tupinon-Mathieu, Vice President of Research and Development and Head of Cardiovascular and Metabolism Therapeutic Innovation Poles. “This collaboration will also integrate with our ongoing and very productive partnership with Professor Andrew Marks and ARMGO, and accelerate the design of novel molecules to advance our cardiovascular program toward clinical development.”

Under the agreement, Servier has licensed Numerate’s RyR2 program including the novel compounds it identified. Numerate will also support efforts in assay development, lead design and optimization. Financial terms of the agreement were not disclosed.

About Servier

Servier is an international pharmaceutical company governed by a non-profit foundation with its headquarters based in Suresnes (France). With a strong international presence in 148 countries and a turnover of 4 billion euros in 2016, Servier employs 21,000 people worldwide. Corporate growth is driven by Servier’s constant search for innovation in five areas of excellence: cardiovascular diseases, diabetes, cancers, immune-inflammatory diseases, and neurodegenerative diseases, as well as by its activities in high-quality generic drugs. Being completely independent, the Group reinvests 25% of turnover (excluding generics) in research and development and uses all its profits for growth. A key player in cardiology and hypertension for the last 20 years, Servier has 12 major products on the market with a total turnover of more than 1.6 billion euro in 2016. Currently, there are 12 new fixed-dose combinations and 10 new molecular entities in research or development, mainly targeting heart failure. This portfolio of innovative treatments is being developed with partners worldwide. For more information, visit www.servier.com.

Forbes article by our CTO on what you need to know about AI

Scan today’s headlines and it seems that every business is adopting artificial intelligence (AI), or more accurately, machine learning. Everyone is being told that they need AI, but few know why — and even fewer know how to use it. The truth is, AI is complex in nature. As the CTO of a company with a foundation in AI, trust me when I tell you that it’s harder to implement than you might think.

AI and machine learning are not commonplace today because we still lack a few essential building blocks…

What You Need To Know Before Incorporating AI Into Your Business Model