A Tool for Predicting the Success of First-Line Antiretroviral - - PowerPoint PPT Presentation

A Tool for Predicting the Success of First-Line Antiretroviral Therapies

Alejandro Pironti

Computational Biology and Applied Algorithmics Max Planck Institute for Informatics April 28, 2010

April 28, 2010 Alejandro Pironti

Motivation

• The first antiretroviral regimen:

– Best chance of sustained virological suppression – Selection under consideration of transmitted drug resistance – Simplicity and side effects also important for success

Primary Drug Resistance Trends in the RESINA Study

5 10 15 20 2001 2002 2003 2004 2005 2006 2007 2008

Year Prevalence(% )

April 28, 2010 Alejandro Pironti

Motivation

• Available tools for assisting therapy selection:

– Designed for therapy-experienced patients – Therapy-naïve patients:

• Different mutations, e.g. T215Y →T215C
• A subset of regimens

April 28, 2010 Alejandro Pironti

The Data

• 2401 first-line antiretroviral therapies from

EuResist and the RESINA study including:

Counts

April 28, 2010 Alejandro Pironti

The Data

• 2401 first-line antiretroviral therapies from

EuResist and the RESINA Study including:

– PR and RT sequences – Various viral load measurements

• Linear interpolation of log VLs

to obtain values for week 36

Viral Load Measurements by Week

April 28, 2010 Alejandro Pironti

Dichotomization

• Failure:

– VL > 100 cp/ml at week 36 – Therapy stop before week 36

• Definition yielded

– 1527 (64%) successes – 874 (36%) failures

• Development set: 1981

therapies

• Test set: 483 therapies

10 20 30 40 50 60 70 % Virological Failure at Week 36 Other Failure Success

April 28, 2010 Alejandro Pironti

Prediction

• Linear support vector

machine was used to predict therapy success

• Training with

development set

• Features:

– Genotype – drug combination – drug interactions up to 3rd

• rder
• Feature selection:

z-score ≥ 2

Schematic Representation of a Support Vector Machine

Hyperplane M a r g i n

April 28, 2010 Alejandro Pironti

Performance

Test set. AUC = 0.7110 5-fold cross-validation on development set. AUC = 0.7135 EuResist Engine acheives AUC=0.5620 on the test set

April 28, 2010 Alejandro Pironti

Selected Features

• 70 out of 1280 features selected
• Protease Mutations:

– T12K I15L L19P K20V N37E C67S E79D T91A T91V I93M

• Reverse Transcriptase Mutations:

– K43R K43N A62V D67N L74V V90I A98G K102E Y144F K173V Q174N N175Y V179D D192N P197E T200E E203D Q207K R211A R211E T215C T215E D218E K219Q W229G K238N

• 7 single drugs, 23 two-way drug interactions and

4 three-way drug interactions

April 28, 2010 Alejandro Pironti

Tool Development Status

• Core algorithm of the tool

has been implemented

• Web interface will be

implemented and made available online by July 2010

• Tool will be part of

geno2pheno[resistance]

April 28, 2010 Alejandro Pironti

Example

• Case from the test set
• AZT 3TC LPV/r
• RT substitutions:

– 68G, 121H, 135T, 158S, 173Q, 200K, 211K, 214F, 215C

• PR substitutions:

– 3I, 12N, 12K, 19I, 35D, 37N, 63P, 77I

• Viral load > 100 cp/ml at week 36

April 28, 2010 Alejandro Pironti

Example

• Enter sequence into

geno2pheno[resistance]

• RT substitutions:

– 68G, 121H, 135T, 158S, 173Q, 200K, 211K, 214F, 215C

• PR substitutions:

– 3I, 12N, 12K, 19I, 35D, 37N, 63P, 77I

• WHO transmitted drug

resistance surveillance mutations: 215C

Geno2pheno[resistance] output

April 28, 2010 Alejandro Pironti

Compounds Success Probability TDF FTC SQV/r 0.82 TDF FTC EFV 0.76 TDF FTC ATV/r 0.76 LPV/r ABC 3TC 0.76 TDF FTC NVP 0.76 ABC 3TC SQV/r 0.76 TDF FTC LPV/r 0.76 ABC 3TC EFV 0.76 ABC 3TC NVP 0.75 AZT 3TC LPV/r 0.74 AZT 3TC FPV/r 0.73

Example

April 28, 2010 Alejandro Pironti

Acknowledgements

Max-Planck-Institut für Informatik

Thomas Lengauer André Altmann Joachim Büch

University of Düsseldorf

Björn Jensen

University of Cologne

Rolf Kaiser Marc Oette Melanie Balduin Saleta Sierra Aragon Finja Schweizer Elena Knops Maria Neumann-Fraune Eugen Schülter Eva Heger

University of Erlangen

Hauke Walter