Helomics : AI Pharma :
CoRE Case Studies

CoRE™ case studies

Case study 1

Reduced experimentation cost to develop accurate predictive models.

Two Pharma companies wanted to compare the cost and accuracy of predictive models developed using CoRE’s active machine learning methods, to those using standard industry methods.  EPA’s ToxCast dataset was used as a simulated “experimental space” for the test.

  • A predictive model of the experimental space was developed using the current industry standard analytic methods. Using several machine
    learning approaches – RandomForest and LASSO regression– it was
    necessary to explore 80% of the experimental space to reach the
    maximum predictive accuracy when compounds were chosen for
    experimentation based on their chemical diversity.

  • However, it only took 10% of the experimental space for CoRE to reach this level of predictive accuracy.

Given the EPA estimate that $6M was spent on the experiments to develop ToxCast, when dollarized, current industry methods would have cost $4.8M to explore and achieve the level of accuracy that CoRE™ would have achieved for $600K. An 87% savings!

Any further experimentation directed by CoRE™ resulted in an accuracy that was better than standard machine learning methods regardless of experiment selection methods.

Case study 2

Reduced experimentation by leveraging historical experimental results.

A large pharma wanted to  compare the efficiency of CoRE’s active machine learning methods to standard industry methods for predicting hepatotoxicity.  Their high content screening (HCS) data from a recently published study was used.

  • A predictive model of the experimental space was developed using the current industry standard analytic methods. About 50% of the
    experiments executed in the Study were needed to create the most
    accurate predictive model.

  • By comparison, it took only 30% of the experimental space for CoRE to reach this same level of accuracy predicting hepatotoxicity.

While it took 40% less experimentation, the savings could not be estimated as costs were not made available. More interestingly, collaborators then suggested that methods be tested for predicting toxicity without using “new” experimental results from HCS screens. This is as if the models were developed entirely in silico without novel experimentation. In order to use only our extensive database of prior research (CoRE knowledgebase) on this problem, a new, sophisticated method was designed that works with extremely sparse data sets. Using this method with the dataset and no current experimental results, CoRE™ developed a model with higher accuracy than any methods previously tested. This shows that the knowledge gathered in their new HCS experiments was actually already in the CoRE knowledgebase, but it had been gathered in different experiments, testing different compounds. The active learning methods used by CoRE™ enabled us to capture that knowledge effectively.

Case study 3

Reduced compound synthesis required to discover promising drug leads.

A smaller pharma specializing in CNS drug development wished to assess how well CoRE would have performed on a completed drug discovery campaign had it been used to direct experimentation. The pharma company conducted the campaign and identified a lead to advance after synthesizing a large number of compounds.  In our simulations, CoRE™ used their historical data to simulate an active learning approach as if it was directing compound synthesis.  So all of their data was hidden from CoRE™ and only revealed when CoRE™ recommended a batch of compound be “synthesized.” Random selection required that on average 42 compounds be synthesized in order to predict the ideal compound.  The “industry standard approach” required on average 25 compounds to be synthesized to produce an optimal lead.  CoRE™ required an average of only 18 compounds be synthesized to produce the optimal lead to advance.

This represents a 30-50% reduction in the number of synthesized compounds that would have needed to be made.

CoRE and Active Learning publications:

Publications

  • Josh D. Kangas, Naik, Armaghan W., & Murphy, Robert. F., Efficient Discovery of Responses of Proteins to Compounds Using Active Learning, BMC Bioinformatics, 15(1), 143, May, 2014.

  • Armaghan W. Naik, Kangas, Joshua D., Langmead, Christopher J. & Murphy, Robert F., Efficient Modeling and Active Learning Discovery of Biological Responses. PLoS ONE 8(12) e83996, December 2013.

  • Robert F. Murphy, An Active Role for Machine Learning in Drug Development, Nature Chemical Biology, June 2011.

Posters

  • J. D. Kangas, Naik, A. W. & Murphy, R. F., Active Learning to Improve Efficiency of Drug Discovery and Development, SLAS 2014 poster describing the capabilities and uses of the CoRE™.

  • ​​R. J. Brennan, Kangas, J. D., Schmidt, F., Khan-Malek, R. & Keller, D. A., Applying an Active Machine Learning Process to Build Predictive Models of In Vivo Toxicity from ToxCast Screening Data, ToxCast Data Summit, September 2014. Additional Information

Lawrence J. DeLucas, PhD

VP, OPERATIONS,
Predictive Oncology
Site Leader, Soluble Biotech
At Predictive Oncology

Dr. DeLucas is the Vice president of Operations for Predictive Oncology and President and co-founder of Soluble Biotech, Inc. DeLucas is currently working to complete development of GMP facilities at Soluble Biotech and at TumorGenesis. In addition, he oversees Soluble Biotech’s solubility and stability contracts for numerous pharmaceutical/biotech companies.

Before Predictive Oncology

From 1981-2016 Dr. DeLucas was a faculty member at the University of Alabama at Birmingham (UAB) where he served as a Professor in the School of Optometry, Senior Scientist and Director of the Comprehensive Cancer Center X-ray Shared Facility, and Director of the Center for Structural Biology. Dr. DeLucas received five degrees from UAB culminating in a Doctor of Optometry degree and a Ph.D. degree in Biochemistry. He also received honorary Doctor of Science degrees from The Ohio State University, Ferris State University, the State University of New York (SUNY), and the Illinois College of Optometry. He has published 164 peer-reviewed research articles in various scientific journals, co-authored and edited several books on protein crystal growth and membrane proteins and is a co-inventor on 43 patents involving protein crystal growth, novel biotechnologies and structure-based drug design. DeLucas was a payload specialist NASA astronaut and member of the 7-person crew of Space Shuttle Columbia for Mission “STS-50”, called the United States Microgravity Laboratory-1 (USML-1) Spacelab mission. Columbia launched on June 25, 1992, returning on July 9.  In 1994 and 1995, Dr. DeLucas served as the Chief Scientist for the International Space Station at NASA Headquarters in Washington, D.C. In 1999, Dr. DeLucas was recognized as one of the scientists who could shape the 21st century in an article published by “The Sunday Times” of London titled “The Brains Behind the 21st Century”.  In 2004, he was recognized as a Top Ten Finalist for the Entrepreneur of the Year award from the Birmingham Business Journal. 

“ Soluble Biotech is continually demonstrating to pharmaceutical and biotech companies the significant value of its novel HSC technology for optimizing protein therapeutic formulations to treat a variety of chronic and infectious diseases. ”

Education
  • Five degrees from Univ. of Alabama at Birmingham (UAB): B.S. Chemistry, M.S. Chemistry, B.S. Physiological Optics, O.D. Optometry, PhD Biochemistry

  • Published 164 peer-reviewed research articles in various scientific journals

  • 1993-2016: Director of the UAB Comprehensive Cancer Center X-ray Shared Facility, and Director of the Center for Structural Biology.

  • NASA Astronaut, flew on Columbia Space

  • 994-1995: Appointed Chief Scientist for the International Space Station at NASA HQ
  • CoRE Case Studies

    CHIEF EXECUTIVE OFFICER
    Predictive Oncology
    At Predictive Oncology
    This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO.
    Before Predictive Oncology
    This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO. This paragraph will outline the executive’s role at PO.

    “ Eliminating cancer is our overall goal.  This is not an easy task.  We are working hard every day to make this happen, using our novel technology and talented team of employees. ”

     

     

    Education

    University of Southern California
    School of Business
    MBA, Finance

    University of Colorado Boulder
    BS, Accounting

    Richard Gabriel, BS, MBA

    SVP, RESEARCH & DEVELOPMENT
    Predictive Oncology
    Site Leader, TumorGenesis
    At Predictive Oncology
    My role at Predictive Oncology is to bring the business sense to managing Research and Development programs at all our companies. To seek new ways and opportunities to commercialize exciting new technologies that we have built, licensed, acquired, or are developing through our own research and development. The success of any company is to get the research off the bench and to the customers. That is what I do at POAI and help the other companies as well.
    Before Predictive Oncology
    Prior to starting his first company in 1984 and registering with the FDA a pilot plant facility to make pharmaceutical actives, Mr. Gabriel managed a $50 million product line for W.R. Grace, developed new marketing and sales strategies for Ventron a Division of Morton Thiokol, research work at Ashland Chemical for pressure sensitive adhesives and plant scale-up. Since then, he ran a genetics company, built three GMP/Research facilities, and helped 5 drugs reach their markets in AIDS and cancer. Real expertise in cGMP process scale-up and compliance. Completely understand the needs of an API manufacturing facility and build processes that are scalable, environmentally acceptable, and safe. 3 FDA inspections with no 483’s, ISO certification, DEA registration, DoD compliance, NCI contractor and inventor. Has also broad-based experience in start-up companies and how to make them operational and profitable. 7 years of Team set-up, R&D management, and implementation for 165-person (85 PhD’s and Engineers) company (Pharm-Eco) and lecturer on cGMP and Teams within the Pharmaceutical Industry.
    “ Patients are always first, is our driving force. Oncology is a tough space, and we are determined to bring the best validated science to help cancer patients and as our CEO says; “Eliminate Cancer”. You first must know your enemy before you can defeat them. That takes teamwork and a lot of smart hard-working people, our team members at POAI are up to the challenge. ”

     

     

    Education
    Suffolk University
    Executive MBA Program

    Ohio Dominican College
    BS, Chemistry

    Ohio State University
    Microbiology and Virology

    University of Cincinnati
    Associates Degree, Liberal Arts

    Mark A Collins, Ph.D

    SCIENTIFIC/CUSTOMER DEVELOPMENT
    Predictive Oncology
    Chief Technical Officer, Helomics
    At Predictive Oncology

    Mark is currently Chief Technical Officer at Predictive Oncology. Using the power of AI, Mark is responsible for leveraging Helomics’ vast repository of physical and digital tumor samples, to build multi-omic predictive models of tumor drug response and outcome. Such models can be applied to the discovery of new targeted therapies for cancer as well as used in clinical decision support to help oncologists individualize  treatment.

    Before Predictive Oncology

    Dr. Mark Collins embarked on a career in the pharmaceutical industry following his postdoctoral work. Pursuing a passion for both biology and computing, Mark has held multiple executive roles in a variety of discovery, informatics and bioinformatics functions within global pharma, and founded three startup software companies in the artificial intelligence (AI) machine learning (ML) and drug discovery space. Mark relocated to the USA in 2001 to work for Cellomics (now part of Thermo Fisher Scientific), where he played a pivotal role in establishing the High-Content cell analysis market, building, and commercializing several key informatics and bioinformatics products.

    Since leaving Thermo Fisher, Mark has focused on developing and commercializing informatics solutions for clinical and translational research, specifically in the specimen tracking, ‘omics data management and NGS analysis space, through key roles at BioFortis, Global Specimen Solutions and Genedata

    “ I have been pursuing a vision since the late 1990s that AI will help deliver better patient therapies. I firmly believe at POAI we will deliver on that vision. ”

    Education
    University of Surrey, UK
    Ph.D., Microbiology

    University of Wolverhampton, UK
    Undergraduate Degree, Applied Science

    Bob Myers

    CHIEF FINANCIAL OFFICER
    Predictive Oncology
    Site Leader, Skyline Medical
    At Predictive Oncology

    Executive officer, Compliance Officer, Corporate Secretary, and member of the Senior Leadership Team. Responsible for Finance, Administration, Human Resources, Investor Relations, and IT. Skyline Medical Site Leader.

    Before Predictive Oncology

    Numerous years as CEO/Controller consultant including medical devices companies. Executive positions with CES Computer Solutions, Computer Accomplishments, Hi-Tech Stationary & Printing, Capital Distributors Corp, International Creative Management American Express, Showtime Entertainment and public accounting with Laventhol & Horwath, CPA’s.

    “ It’s a privilege to work with a highly talented team to pursue oncology advances, while protecting and increasing shareholder value. ”

    Education

    Adelphi University
    MBA, Finance

    Hofstra University
    BBA, Public Accounting 

    J. Melville (“Mel”) Engle

    CHIEF EXECUTIVE OFFICER
    & CHAIRMAN OF THE BOARD
    Predictive Oncology
    At Predictive Oncology
    Mr. Engle became POAI’s CEO in 2021 and was appointed to the POAI Board of Directors in 2016. He was elected Chairman of the Board in 2020.
    Before Predictive Oncology
    Between 2012 and 2021, he was CEO of Engle Strategic Solutions, a consulting and coaching company focused on CEO issues. From 2009 to 2012, he was CEO and Chairman of Thermogenesis, a cell separation company. From 2002 to 2007, he was Regional Head/Director, North America at Merck Generics and CEO of Dey Laboratories, a respiratory company From 1996 to 2001, he was CEO and Chairman of Anika Therapeutics, an orthobiologics company From 1980 to 1995, he was with Allergan, Inc., an eye and skin care company, where he served as CFO, Managing Director (living in Toronto), and other positions with the firm

    “ Eliminating cancer is our overall goal.  This is not an easy task.  We are working hard every day to make this happen, using our novel technology and talented team of employees. ”

    Education

    University of Southern California
    School of Business
    MBA, Finance

    University of Colorado Boulder
    BS, Accounting