Arevir Meeting, Bonn, 22-23 April 2010 M. Zazzi on behalf of the - - PowerPoint PPT Presentation

▶
arevir meeting bonn 22 23 april 2010 m zazzi on behalf of
SMART_READER_LITE
LIVE PREVIEW

Arevir Meeting, Bonn, 22-23 April 2010 M. Zazzi on behalf of the - - PowerPoint PPT Presentation

May 24, 2023 12 likes •336 views

Arevir Meeting, Bonn, 22-23 April 2010 M. Zazzi on behalf of the EuResist Network (www.euresist.org) EuResist status Funded by the EU JAN-06 to JUN-08, then set as a European Network (legal entity) GOAL: to develop and make freely

slide-1
SLIDE 1

Arevir Meeting, Bonn, 22-23 April 2010

  • M. Zazzi
  • n behalf of the EuResist Network

(www.euresist.org)

slide-2
SLIDE 2

EuResist status

Funded by the EU JAN-06 to JUN-08, then set as a European Network (legal entity)

GOAL: to develop and make freely available an on-line expert system for prediction of response to antiretroviral treatment

Data collected from ~40,000 patients (Italy, Germany, Sweden, Luxembourg, Belgium, Spain)

Data modeling by IBM Israel, Max Planck Institute for Informatics, Informa & Rome TRE University

slide-3
SLIDE 3

Integration of clinical and laboratory data from multiple sources PATIENTS Patient ID Gender Year

  • f

birth Country

  • f
  • rigin

Risk group HCV status HBV status THERAPY PatientID Treatment regimen Date of start Date of stop Reason for change/stop GENOTYPE PatientID Date Sequence Method CD4 PatientID Date CD4/cmm CD4% HIV RNA PatientID Date Copies/ml <LLD (undetectable) Method AIDS EVENTS PatientID Event Date STATUS PatientID Date Followed Lost Died

EuResist – type of data collected

slide-4
SLIDE 4

Baseline GENOTYPE, viral load, CD4, ... Follow-up viral load, CD4, ...

CD4 HIV RNA

Model training

Treatment switch

From genotype to response

slide-5
SLIDE 5

EuResist – Treatment Change Episode (TCE) definition

time Genotype Treatment switch Viral load 0 to 12 weeks Short-term model: 4-12 weeks Viral load Pre-therapy HIV RNA CD4 Patient demographics (age, gender, race, route of infection) Past genotypes Past treatments Past AIDS diagnosis

slide-6
SLIDE 6

EuResist – labeling therapies

Baseline data HIV genotype at 0 to 12 weeks before treatment VL at 0 to 12 weeks before treatment Additional variables when available Treatment switch VL at 4 to 12 weeks (8-week outcome)

SUCCESS Undetectable or >2 log decrease VL FAILURE Detectable and not >2 log decrease VL

slide-7
SLIDE 7

The data funnel…

slide-8
SLIDE 8

EuResist – HIV clades distribution

slide-9
SLIDE 9

EuResist – engines

Three prediction engines developed independently

Generative-Discriminative (by IBM)

Evolutionary (by Max-Planck Institute)

Mixed effects (by Rome TRE & Informa)

Then, combined into a unique engine and made freely available on the web

slide-10
SLIDE 10

EuResist Generative/Discriminative engine

Model response to treatment in the absence of genotype with a Bayesian network For any defined regimen, compute a probability of success (Generative step) Use the probability as an additional feature for logistic regression together with genotype and

  • ther covariates (Discriminative

step)

slide-11
SLIDE 11

EuResist Evolutionary engine

Model HIV evolution under therapy from longitudinal and cross-sectional sequence data For any defined genotype, neighbor mutants can be computed in silico and the contribution of the expected mutants to resistance can be calculated Functions weight for probability and expected time for mutants to occur Probability to remain susceptible to a drug (below a defined phenotypic threshold) GENETIC BARRIER

Altmann et al, AVT 2007

slide-12
SLIDE 12

EuResist Mixed-Effects engine

Focuses on interactions among variables

  • drug x drug
  • drug x drug x drug
  • drug x mutation
  • drug x previous drug class exposure
  • drug x previous drug exposure
  • mutation x mutation
slide-13
SLIDE 13

The EuResist combined engine

3143 therapies, Short-term outcome (8 weeks)

Rosen-Zvi, Bioinformatics 2008

slide-14
SLIDE 14

EuResist Combined engine

The combination (mean) of the engines performs equal to or better than the individual engines

The combined engine learns faster, i. e. it is more accurate when trained on limited data sets

Altmann et al, PLoS ONE 2008

slide-15
SLIDE 15

Virtual response on the web

Remote users Web server

RESPONSE Ordered list of the best treatments for that patient

OUTPUT

QUESTION What treatment(s) will be successful for my patient?

INPUT

slide-16
SLIDE 16

Feeding DBs from different countries

D D D I I I L L L S S S Merged EuResist DB Merged EuResist DB Merged EuResist DB

Combined predictive system Web interface Individual engines End users

Connections used during project life and then for system updates Connections used by the final users

slide-17
SLIDE 17

INPUT

slide-18
SLIDE 18

INPUT OUTPUT

slide-19
SLIDE 19
slide-20
SLIDE 20

The Computerworld Honors Program

Honoring Those Who Use Information Technology to Benefit Society

EuResist

  • Laureate Award

plus

  • Special Recognition
slide-21
SLIDE 21

EuResist vs. Expert interpretation

(EVE study)

Form the invitation letter: The requested response include a categorical (C) answer and a quantitative (Q) estimate: C) Given this HIV genotype and patient information, will the indicated therapy be successful (i. e. will it make HIV RNA decrease by at least 2 logs or to undetectable levels in 8 weeks) ? Q) Given this HIV genotype and patient information, what probability

  • f success would you estimate for the indicated therapy?
slide-22
SLIDE 22

Distribution of wrong and correct calls

25 HAART cases randomly selected form the EuResist db:

  • Obsolete therapies excluded
  • Wild type genotype excluded
  • All clinical and virological

information available 12 experts enrolled, response

  • btained from 10:
  • On‐line anonymous rating
  • Only European (E) vs. non‐

European (N) setting traceable

  • Use of any interpretation

system allowed (and declared)

slide-23
SLIDE 23

Why do we err (so much)?

Limitations in the definition of success can “create” prediction errors (e. g. success at a later time point)

Expected adherence cannot be accounted for based on presently available training data set

Genotype shortcomings

Impact of past mutations

Short-term drug activity on partially resistant strains (e. g. 215 revertants, Y181C with EFV)

Subtype differences?

Unweighted factors (host genetics)

slide-24
SLIDE 24

Prediction based on treatment history vs. genotype

Preliminary analysis

Further work warranted in the setting of missing genotype information

Based on HIV genotype Based on treatment history

slide-25
SLIDE 25

EuResist – Data sources

Data regularly refreshed from original sources & later contributors

Belgium, Italy, Germany, Luxembourg, Spain

Data from new countries

Other European countries (Greece, Portugal)

Non-European countries

Data format conversion and upload provided by IBM as EuResist contractor

slide-26
SLIDE 26

EuResist – Accessibility

Official website www.euresist.org

Interface in Russian now available

Incorporated into InfCare, the Swedish HIV data management and remote consulting system

Used in all Scandinavia and Baltic states, being adopted in several low-middle income countries

EuResist on Facebook (coming soon)

EuResist entry in Wikipedia (coming soon)

slide-27
SLIDE 27

EuResist within InfCARE

slide-28
SLIDE 28

EuResist engine update

From ~3,000 to >5,000 TCEs

Small increase in accuracy

AUC from 0.76 to 0.78

○

Upper bound of accuracy already reached?

Outperforms HIVdb with the training set (AUC 0.69)

List of regimens considered in output expanded from 100 to >400

Tipranavir, Darunavir, Etravirine now computed

○

Lower accuracy, AUC 0.70 (HIVdb 0.63)

○

Data from clinical trials coming!

slide-29
SLIDE 29

EuResist

A treasure for collaborative research

Extraordinary collection of clinical and virological data

Ideal for resistance related investigations but suitable also for other research topics

Data available for the scientific community

Many requests already satisfied

○

Networks (Virolab, CHAIN, CORONET) as well as single research units

Cooperation preferred over the simple task of providing data

slide-30
SLIDE 30

EuResist Partners

Expectations & opportunities

Partnership regulations set (see web site)

Benefits for the prediction engine

Increased size of training data set

Expanded representation of different scenarios (e. g. drug prescriptions, HIV clades, different epidemiology & demographics)

Testing the system in different geographic areas

Benefit for clinical research

Role as data providers

Role as investigators

slide-31
SLIDE 31

EuResist Partners & Scientific Board

The EuResist Network offers partnership to new parties of proved or potential scientific value

All partners become members of the EuResist Network Scientific Board

The EuResist Network Scientific Board evaluates the scientific adequacy of research proposals, made by third parties, that require the access to the data stored in the EuResist Integrated Data Base (EIDB) and takes decisions on approval or rejection of such research proposals

slide-32
SLIDE 32

EuResist Partners

Partner’s activities and data are protected by the data and authorship policies

Data provided by a partner always remain the property of the partner

Data providers are acknowledged in all publications

Authorship is built based on the proportion of cases contributed for a specific study. Credits are saved and used subsequently