We think you have liked this presentation. If you wish to download it, please recommend it to your friends in any social system. Share buttons are a little bit lower. Thank you!
Presentation is loading. Please wait.
Published byJonas Bone
Modified about 1 year ago
© 2007 IBM Corporation EuResist From Data to Knowledge Integration of viral genomics with clinical data to predict response to anti-HIV treatment IBM Haifa Research Lab
© 2007 IBM Corporation Outline The Problem Present solutions The project –Vision, objectives, and value –Partners –Preliminary results Alignment with standards Collaborations Links
© 2007 IBM Corporation The problem
© 2007 IBM Corporation The problem HIV is a deadly virus Effective treatment available since 1996 –HAART = “Highly Active Antiretroviral Therapy” (combined use of 3 – 4 anti-HIV drugs) Anti-HIV drugs work, but the virus is not eradicated The virus replicates itself and generates variants with reduced suceptibility to anti-HIV drugs –Drug resistance Testing for drug resistance has been recommended in clinical practice since 2001
© 2007 IBM Corporation Present solutions How do we measure antiretroviral resistance? –Phenotypic test The virus “behavior” towards the drugs is observed “in vitro” –Pick the virus from the patient blood and replicate it in the lab in the presence of any single antiretroviral drug Costly, lengthy, complex – some drugs work “in vitro” and develop resistance “in vivo” Important for the formal characterization of drug resistance mutations, but not suitable for routine application
© 2007 IBM Corporation Present solutions How do we measure antiretroviral resistance? –Genotypic test The virus genetic make-up is investigated; its “behavior” is inferred –Pick the virus from the patient blood and read the virus’ genetic code, then infer its drug susceptibility profile based on our knowledge of the relationship between mutations and drug resistance Easier than phenotypic tests, but –We still have limited knowledge about the newest drugs –Some important mutations and interactions among mutations have not yet been identified Imperfect tool, but definitely the reference test for routine application
© 2007 IBM Corporation EuResist vision To predict the in-vivo efficacy of anti-retroviral drug regimens against a given HIV, based on the use of viral genotype data integrated with treatment response data derived from clinical practice
© 2007 IBM Corporation EuResist objectives Integrate biomedical information from three large genotype-response correlation databases –Karolinska –ARCA –Arevir Develop an array of engines for effective prediction of the response to treatment –Case-based reasoning –Machine learning (Bayesian networks, support vector machines) –Graph theory –Evolutionary models –Fuzzy logic Combine the engines into a predictive system publicly available on the web
© 2007 IBM Corporation EuResist value Largest resistance database in the world Innovative prediction system, based on state-of-the-art methods –Some of the methods were not applicable before due to insufficient amounts of data More effective care for patients –Harness the power of information technology Significant decrease in global therapy management costs A pilot for hepatitis (HCV and HBV) where development of drug resistance can be foreseen
© 2007 IBM Corporation EuResist partners Informa S.r.l., Italy, Rome Università degli Studi di Siena, Italy, Siena (ARCA database) Karolinska Institutet, Sweden, Stockholm (Karolinska database) University of Cologne – University hospital, Germany, Cologne (Arevir database) Max-Planck-Society for Advancement of Science, Germany Saarbrucken Research Institute for Particle and Nuclear Physics of the Hungarian Academy of Sciences, Hungary, Budapest European Federation of Pharmaceutical Industries and Associations (EFPIA) Kingston University, United Kingdom, Kingston upon Thames University of Roma TRE, Italy IBM Haifa Research Lab
© 2007 IBM Corporation EuResist at a glance EuResist database Training DB2 V9 ARCAArevirKarolinska Integrating Prediction System
© 2007 IBM Corporation Preliminary results Very encouraging preliminary results Integrating clinical, demographic and viral genomic data, and applying ML techniques improves the quality of treatment while significantly reducing costs –“The whole is more than its parts” Success rate of individual prediction engines varies between 75%- 78% Their combination gives a success rate of 80% –Clinical and demographic data significantly improves prediction Prediction based on clinical, demographic and viral genomic data outperforms predictions based solely on viral genomic data
© 2007 IBM Corporation Alignment with standards EuResist defines an HIV specific data-mart –Researchers run their analytical tools on this data- mart HL7 RIM based repository (e.g., IBM CG v3) –Provides a standard way of storing healthcare information –Supports HL7 v3 messages (e.g., CDA) Specialization vs. Generalization => Tension!
© 2007 IBM Corporation Alignment with standards EuResist infrastructure should be open and interoperable, supporting standard interfaces –EuResist HIV specific data-mart can be derived from HL7 RIM –EuResist defines a CDA template for HIV treatment
© 2007 IBM Corporation Alignment with standards CDA template for HIV treatment –Holds demographical and clinical data for a patient, as well as viral genomic data through links to the HL7 Clinical Genomics models –Provides a much-needed standard way for HIV scientists/caregivers to exchange information.
© 2007 IBM Corporation Alignment with standards What are the recommended tools for CDA template definition? –Authoring tools –Validation mechanism What is the recommended mechanism to disseminate a CDA template? –Implementation guides? –Balloting? –NIST/HL7 Registry?
© 2007 IBM Corporation Alignment with standards HL7 3.0 Msg HL7 RIM Repository EuResist Integrated database HL7 v3 Export/Import HL7 3.0 Msg CG v3 Mapping HL7 V3.0 Certified
© 2007 IBM Corporation Collaborations Retrovirology Laboratory Luxembourg –http://www.retrovirology.lu/ Stanford University –http://hidb.stanford.edu The Rega Institute, Katholieke Universiteit Leuven –http://www.kuleuven.be/rega/ Carlos III HIV resistance center –Reference national coordinating center for HIV resistance in Spain –http://www.fundacionies.com/
© 2007 IBM Corporation Links Official EuResist site –http://www.euresist.org/ IBM Haifa Research Lab –http://www.haifa.ibm.com/projects/software/euresist –http://www.haifa.ibm.com/projects/verification/ml_euresist
© 2007 IBM Corporation תודה Hebrew (Toda) Thank You! Merci Grazie Gracias Obrigado Danke French German Italian Spanish Brazilian Portuguese Tack Swedish Kös zö nö m Hungarian
EuResist? EuResist is an international project designed to improve the treatment of HIV patients by developing a computerized system that can recommend.
Introduction to HIV Databases Alejandro Pironti Dar es Salaam November 14 th, 2011.
Use of Bioisosteric Replacement Tools to Obtain Mutation- Resistant Antivirals Mattia CF Prosperi University of Roma TRE Faculty of Computer Science Engineering.
IBM Haifa Research Lab SPA a Platform for Hereditary Disease Management and Pedigree Analytics Rizzoli FOAK Alex Melament, July 2010.
HelsIT 2010 Alberto Sáez Torres Sacyl Interoperability Office Junta de Castilla y León Experience of ePrescription in Spain using HL7 V3 September 21 th,
Data mining in bioinformatics: problems and challenges Sorin Draghici WWW:
1 Intermountain Healthcare Clinical Genetics Institute Marc S. Williams, M.D. Director Grant M. Wood Senior IT Strategist Introduction to HL7 Clinical.
Clinical case 19 Lin, I-Yao (Sally). Case 19 Having been confined in the hospital for almost a month due recurrent pneumonia, Mr. XXX, 42 y/o, married,
HIV-1 Evolution and Drug Resistance Among Patients Receiving ART in San Mateo County, California, S. Dalai MSc, S. Sethi MSc, V. Levy MD, D.
What is “Biomedical Informatics”?. Biomedical Informatics Biomedical informatics (BMI) is the interdisciplinary field that studies and pursues.
Biomedical Informatics and Health. What is “Biomedical Informatics”?
Orphanet Europe State of the Art of Database and Services Polish activity Orphanet Europe State of the Art of Database and Services Polish.
Biological Signal Detection for Protein Function Prediction Investigators: Yang Dai Prime Grant Support: NSF Problem Statement and Motivation Technical.
Helping the Cause of Medical Device Interoperability Through Standards- based Test Tools DoC/NIST John J. Garguilo January 25,
Estimating fitness landscapes John Pinney
POPULATION PHARMACOKINETICS OF ANTIRETROVIRAL DRUGS IN HCV/HIV OR HBV/HIV CO-INFECTED INDIVIDUALS J.P. Cruz 1,2, D. Matias 1, C. Carvalho 1, J. Morais.
Mattia CF Prosperi, PhD Clinic of Infectious Diseases Catholic University of Sacred Heart Largo F. Vito, 1 – Rome, Italy.
6/28/00TPED1 Resistance Testing: What is it? What does it mean? How does drug resistance emerge? Overview of methods Advantages and disadvantages Current.
Systems interoperability for a better treatment and surveillance of infections ECCMID Symposium Interest of IT solutions to improve patient management.
GENOMICS TO COMBAT RESISTANCE AGAINST ANTIBIOTICS IN COMMUNITY-ACQUIRED LRTI IN EUROPE (GRACE) H. Goossens (Coordinator), K. Loens (Manager), M. Ieven.
IHIC 2011 – Orlando, FL Amnon Shabo (Shvo), PhD HL7 Clinical Genomics WG Co-chair and Modeling Facilitator HL7 Structured Documents WG.
The European Innovation Partnership for asthma: an opportunity for change Samantha Walker PhD, Asthma UK Project Coordinator, EARIP (European Asthma Research.
TripCom: Development of a patient summary at European level E. Della Valle, D. Cerizza, D. Foxvog, R. Krummenacher, L. J. B. Nixon, E.
Biomedical Research. What is Biomedical Research Biomedical research is the area of science devoted to the study of the processes of life; prevention.
1 Federal Health IT Ontology Project (HITOP) Group The Vision Toward Testing Ontology Tools in High Priority Health IT Applications October 5, 2005.
Newborn Screening Translational Research Network Coordinating Center Duane Alexander, M.D. Director, Eunice Kennedy Shriver National Institute of Child.
HL7 Clinical Genomics and Structured Documents Work Groups CDA Implementation Guide: Genetic Testing Report DRAFT PROPOSAL Amnon Shabo (Shvo), PhD
Clinical Collaboration Platform Overview ST Electronics (Training & Simulation Systems) 8 September 2009 Research Enablers Consulting Open Standards.
Supporting adherence to antiretroviral therapy with mobile phone reminders in South India Rashmi Rodrigues Jimmy Antony, Kristi Sidney, Karthika Arumugam,
IPlant cyberifrastructure to support ecological modeling Presented at the Species Distribution Modeling Group at the American Museum of Natural History.
A Presentation for the Enterprise Architect © 2008 IBM Corporation IBM Technology Day - SOA SOA Governance Miroslav Petrek IT Software Architect
The Pursuit of Better Medicines through Genetic Research Terri Arledge, DVM US Department Head Drug Development Genetics.
© 2009 IBM Corporation Let’s build a smarter planet: Healthcare 0 Smart healthcare: Achieve better quality and outcomes. SMART IS Establishing a strategic.
22 March 2012 Europe and ACP together against tuberculosis European Parliament, Rue Wiertz 60 BRUSSELS Charles S Mgone EDCTP Executive Director.
The TB Alliance-Bayer Moxifloxacin Deal Gerald J. Siuta, Ph.D. Business Development Rockville, MD July 25, 2006.
Dr. José M. Millán, PhD Deputy Director of CIBERER Universitary Hospital La Fe, Valencia, Spain Barriers and Challenges in Rare Diseases Research Centre.
© Gottfried Heider 1 The Austrian Use Case: eCard The eCard Project: giving an electronic card to everyone for accessing personal health record From patients.
EU rare diseases registry for Niemann-Pick Disease type A, B and C Tarekegn Hiwot Consultant in Inherited Metabolic Disorders University Hospital of Birmingham.
University of Pavia Dep. of Electrical, Computer and Biomedical Engineering Laboratory of Bioinformatics, Mathematical Modelling and Synthetic Biology.
Initial slides for Layered Service Architecture From existing materials: Practical Guide to SOA in Healthcare Part II IHE SOA Whitepaper.
26/05/2005 Research Infrastructures - 'eInfrastructure: Grid initiatives‘ FP INFRASTRUCTURES-71 DIMMI Project a DI gital M ulti M edia I nfrastructure.
Juha Mykkänen University of Kuopio, HIS R&D Unit Health Kuopio seminar Brussels, 5 November 2004 SerAPI project: Service-oriented architecture and Web.
CZ5225 Methods in Computational Biology Lecture 6: Drug resistance mutations and model developments CZ5225 Methods in Computational Biology.
Are people living with HIV less likely to pass HIV to others if they are on treatment? Exploring the use of treatment as prevention James Wilton Project.
1 Severe morbidity among HIV- infected patients : a comparison between a Brazilian and a French clinic based observational cohort FIOCRUZ: Prof B Grinsztejn.
Networking and Health Information Exchange Unit 5b Health Data Interchange Standards.
Summary Slide Presentation Are subtype differences important in HIV drug resistance? Lessells RJ, Katzenstein DK, de Oliveira T. Are subtype differences.
1. 2 Key Applications of Genetic and Genomic Testing (slide 1 of 2) Diagnosis of Disease: Whereby genetic or genomic tests are used to screen a patient.
© 2017 SlidePlayer.com Inc. All rights reserved.