hiv grade rules based genotypic hiv drug resistance
play

HIV-GRADE: Rules-Based Genotypic HIV Drug-Resistance Interpretation - PowerPoint PPT Presentation

HIV-GRADE: Rules-Based Genotypic HIV Drug-Resistance Interpretation under Consideration of Bioinformatic Knowledge Alejandro Pironti Computational Biology and Applied Algorithmics Max Planck Institute for Informatics April 18, 2013 What is


  1. HIV-GRADE: Rules-Based Genotypic HIV Drug-Resistance Interpretation under Consideration of Bioinformatic Knowledge Alejandro Pironti Computational Biology and Applied Algorithmics Max Planck Institute for Informatics April 18, 2013

  2. What is HIV-GRADE? • HIV G enotypic R esistance A lgorithm DE utschland • Rule set for drug-resistance interpretation • Platform for comparing HIV-GRADE’s interpretation with ANRS, HIVDB, Rega and geno2pheno [resistance] • http://www.hiv-grade.de Alejandro Pironti April 18, 2013

  3. How are HIV-GRADE rules established? Input Discussion by HIV- • Information extracted from GRADE Members clinical studies • Case reports from cooperating institutions • geno2pheno[resistance] weights for each drug Rule Proposal Output: Voting on Rules Consensus Rule Set Alejandro Pironti April 18, 2013

  4. geno2pheno[resistance] • Linear Support Vector Regression • Dataset: Up to 968 genotype-phenotype pairs for each drug • Raw prediction output: Resistance Factor (RF) • Z-score normalizes RF w.r.t. sequences from therapy-naïve patients Alejandro Pironti April 18, 2013

  5. Extracting Weights from geno2pheno [resistance] • Linear Support Vector Positive weights increase predicted resistance Negative weights decrease predicted resistance Regression is regularized. To estimate = β + β T f ( x ) x 0 we solve λ N ∑ − + β arg min E ( y f ( x )) i i 2 β = i 1 E: Error Function λ: Regularization Regularization term: Forces optimization to parameter find β with smallest coefficient absolute values possible Very similar to linear regression you know Alejandro Pironti April 18, 2013

  6. HIV-Grade Rules • Weights in • AZT_SP (Selective geno2pheno [resistance] have Pressure) Rules a strong influence of HIV- (excerpt): GRADE’s rules – 65R, 41L, 210W, 215YF → LS • AZT Rules: – 65R, 2 from {74V, 181C, – 151M → Resistant (R) 184VI}, 5 from {41L, 67N, – ≥ 3 from { 41L, 67N, 70R, 70R, 210W, 215FY, 210W, 215Y, 219QE } → R 219QE } and ≤ 2 from { 41L, – 2 from {41L, 67N, 70R, 210W, 215YF } → LS 210W, 215Y, 219QE } → intermediate Mutation with negative weight in geno2pheno – 2 from {41L, 67N, 70R, 210W, 215Y, 219QE } → Mutation with positive limited susceptibility (LS) weight in geno2pheno Alejandro Pironti April 18, 2013

  7. Acknowledgements University of Cologne Max-Planck-Institut für Informatik Rolf Kaiser Thomas Lengauer Mark Oette Nico Pfeifer Saleta Sierra Aragon Joachim Büch Finja Schweizer Elena Knops Maria Neumann-Fraune Eugen Schülter Medizinisches Labor Berg Eva Heger Hauke Walter Claudia Müller Martin Obermeier Institut für Immunologie und University of Düsseldorf Genetik Kaiserslautern Björn Jensen Martin Däumer Alexander Thielen Alejandro Pironti April 18, 2013

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend