History-aware models for predicting outcomes of HIV combination - - PowerPoint PPT Presentation

Jasmina Bogojeska

AREVIR-GenaFor-Meeting 2011

History-aware models for predicting outcomes of HIV combination therapies

Problem setting

Prediction of the outcome of combination therapies given to HIV patients Develop methods that can deal with:

Different trends in treating patients Uneven therapy representation Current therapy Level of therapy experience

Data

Viral genotype Current treatment Treatment history Label (success or failure)

0 1 0 0 1 …

• ccurrence of

resistance mutations 1 1 0 0 1 … 1 0 0 1 0 … drugs used in current treatment drugs used in all previous treatments 1 or -1

6336 labeled samples with different 638 combination therapies

Treatment history-aware model

Problems in the available HIV data:

Only dominant strain sequenced- no information on latent virus population Uneven sample representation regarding level of therapy experience

Idea: use treatment history information

Extract knowledge on latent virus population Balance the data regarding level of therapy experience

How?

Quantify similarity of treatment histories by using drug resistance mutations

Similarity of treatment history

Treatment record ordered by therapy starting time => therapy sequence

Desired properties

Accounts for length of therapy history Order matters! Prediction targets current therapy

Adapt sequence alignment methods to align therapy sequences!

)} ( ) ( and ) ( ) ( | { ) ( t z t z z t patient patient start start r   

Therapy sequence alignment

Quantify pairwise therapy similarity

Use drug resistance mutations

Therapy sequence similarity

Treatment history-aware model

Train a separate model for each therapy sequence by using knowledge from similar therapy sequences

Sample weighted regularized logistic regression

loss function seq similarity







) , , , (

) ), , , , ( ( )) ( ), ( ( | | 1 max arg

D y T i i i i i

i i i i

y f l r r S D

h z x t t t w

w w w h z x t z

t





Time-oriented evaluation scenario

80% training 20% test

Special evaluation setup to address evolving trends in treatments

• ver time

Results

AUC performance stratified for the level of therapy experience

Results

AUC performance stratified for the therapy abundance

Results

Conclusions

Information extracted from treatment history enhances the performance for samples originating from both therapy-experienced patients and rare therapies Balance the uneven therapy-history representation in clinical data Time-aware evaluation setup to encounter changing trends in HIV treatment over time

Acknowledgements

Thomas Lengauer HIV group @ MPII Saarbrucken Joachim Büch Rolf Kaiser & Group

Thank You!

Results