Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Matrix Factorization-Based Data Fusion for Drug-Induced Liver Injury Prediction

Talk at CAMDA'13 Conference, ISMB'13, Berlin, Germany.
by

Marinka Zitnik

on 24 June 2014

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Matrix Factorization-Based Data Fusion for Drug-Induced Liver Injury Prediction

Matrix Factorization-Based
Data Fusion for Drug-Induced Liver
Injury Prediction

Marinka Zitnik and Blaz Zupan

University of Ljubljana, Slovenia
Data Fusion Configuration
14 types of objects
29 data sources
134,113,951 non-zero data entries
DILI Potential
CUR matrix decomposition
Data collapsing
Fold change
Quantile normalization
Compound batch correction
FARMS summarization
Random
forests
Gradient
boosting
trees
Stacking w.
logistic
regression
PCA
Stacking w.
logistic
regression
Mahoney and Drineas, 2009.
Leverage scores
C
U = C A R
R
A
+
+
Gene Expression
Protein-Protein
Interactions
Gene Ontology Annotations
Metadata on Arrays
Input
Output
Fusion
Data Fusion
AUC of 0.82 > 0.78 Standard ML
AUC of 0.82 > 0.66 CAMDA 2012
In vitro single
Rat gene
Dose Level
In vivo single
In vivo repeated
In vitro single
Human gene
ACSL1
Dose
Sacrifice Period
Animal Age
Sex Type
Test Type
Species
RBC, Neutrophil, Eosinophil,
Basophil, Monocyte, Lymphocyte
Terminal body weight
Liver weight,
Relative liver weight
ALP, Cl, TC, Ca, TG, IP, PL, TP, TBIL, RALB, DBIL, A/G GLC, AST (GOT), BUN, ALT (GPT), CRE, LDH, Na, gamma-GTP, K
ketoconazole
Drug Interactions
Drug Targets
Block-based
data representation
Equations
Hematology
Blood Chemistry
Liver Weight
Chemical Structure
10-fold cross-validation
Input Data + Circumstantial Evidence = Gain in Accuracy
Replace animal studies with in vitro assays (AUC = 0.799)
Predict liver injury in humans from animal data (AUC = 0.811)
Thanks to...
Blaz Zupan, PhD
Organizing committee
''Non-standard''
''Standard''
Multi-Classifiers
with
Feature Selection

Data Fusion
arXiv:1307.0803
DILI Potential
Prediction

Baseline
Full transcript