drug target prediction using semantic linked data

39
DRUG TARGET PREDICTION USING SEMANTIC LINKED DATA Bin Chen Ph.D. candidate School of Informatics and Computing, Indiana University [email protected] http://cheminfo.informatics.indiana.edu/~binchen CSHALS, Feb 23, 2012

Upload: bin-chen

Post on 12-May-2015

720 views

Category:

Health & Medicine


1 download

DESCRIPTION

beyond data integration, what else can we do? this presentation shows how we use semantic linked data for drug target prediction.

TRANSCRIPT

Page 1: drug target prediction using semantic linked data

DRUG TARGET PREDICTION USING SEMANTIC LINKED DATA

Bin Chen Ph.D. candidate School of Informatics and Computing, Indiana University

[email protected] http://cheminfo.informatics.indiana.edu/~binchen

CSHALS, Feb 23, 2012

Page 2: drug target prediction using semantic linked data

Beyond Data Integration

Chem2Bio2RDF.ORG

Page 3: drug target prediction using semantic linked data

What is Drug Target?

Page 4: drug target prediction using semantic linked data

Why Drug Target Prediction?

Page 5: drug target prediction using semantic linked data

How to predict drug target?

Page 6: drug target prediction using semantic linked data

?

• Substructure• Side effect• Chemical ontology• Gene expression profile

Drug 1 Target 1

bind

Drug 2From Ligand (drug) perspective

Page 7: drug target prediction using semantic linked data

?

• Sequence• 3D structure• Gene Ontology• Ligand

Drug 1 Target 1

bind

Target 2

From target perspective

Page 8: drug target prediction using semantic linked data

Troglitazone

PPARG

ACSL4

bind

PPARA

bind

bind

Rosiglitazone Pioglitazo

ne

hypoglycemic drug

Chemical ontology

Chemical ontology

Chemical ontology

bindbind

PPAR signaling pathway

Eicosapentaenoic Acid

Response to nutrient

pathway

bind

bind

GO

GO

pathway

Page 9: drug target prediction using semantic linked data

troglitazone

troglitazone

Semantic Linked Network

Page 10: drug target prediction using semantic linked data

Topology is important for association

Cmpd 1Protein

1 Cmpd 2

Cmpd 1Protein

1 Cmpd 2

hasSubstructure

hasSubstructure

hasSubstructure

hasSubstructure

bind

bind

Page 11: drug target prediction using semantic linked data

Protein2

Cmpd1

Cmpd 2Protein

1

Protein2

Cmpd1Protein

1

hasGOhasGO

Protein2

Cmpd1Protein

1bind PPI

Cmpd1Protein

1Cmpd 2 bindhasSideeffect hasSide ffect

Cmpd1Protein

1Cmpd 2 bindhasSubstructure hasSubstructure

Semantic is important for association

GO:00001

hypertension

substructure1

bind

bind bind bind

Page 12: drug target prediction using semantic linked data

(Semantic Link Association Prediction)

Page 13: drug target prediction using semantic linked data

Data schema

Page 14: drug target prediction using semantic linked data

Path finding

Drug: Troglitazone

Target :PPARG>300k nodes, >1million edges

Page 15: drug target prediction using semantic linked data

Statistical Model---edge weight

Target I

Target JPPI

PPI

PPI

hasGOhasGO

hasPathway

bind

P(i j) =1/3

Page 16: drug target prediction using semantic linked data

Statistical Model---path raw score

Target2

Cmpd1 (s)

Target

1 (t)

e1 e2e4 e3

Page 17: drug target prediction using semantic linked data

Protein2

Cmpd1

Cmpd1

Protein1

Path pattern

bind bind bind

Protein

Cmpd

Cmpd

Protein

bind bind bind

Protein1

Cmpd3

Cmpd4

Protein5

bind bind bind

Path examples:

Path pattern:

Page 18: drug target prediction using semantic linked data

• Randomly sample 100,000 drug target pairs, yielding 453,087 paths, 35 patterns

• Plot Path pattern score distribution

• Convert path score to path z score

Path Pattern Score Distribution

Statistical Model---path z score

Page 19: drug target prediction using semantic linked data

Statistical Model---association score

Fit association scores of random pairs to normal distribution

Page 20: drug target prediction using semantic linked data

Association Score distribution among different pairs

Page 21: drug target prediction using semantic linked data

Comparing SLAP with link prediction methods in social science

ROC curve

AUC=0.92

Page 22: drug target prediction using semantic linked data

Drug polypharmacology profiles

Polypharmacology profile comprises of association scores of one drug against over one thousand targets

Moexipril

Rescinnamine

Benazepril

Quinapril

Fosinopril

Trandolapril

Enalapril

Chlorthalidone

Metolazone

Trichlormethiazide

Betaxolol

Alprenolol

Acebutolol

Nadolol

Bisoprolol

Page 23: drug target prediction using semantic linked data

Drug similarity network

• Nodes present drugs

• Two nodes are linked if they are similar in terms of biological function.

• Nodes are colored by their therapeutic indications

Page 24: drug target prediction using semantic linked data

Insomnia related drugs

Dissimilar Drugs have same indication

Page 25: drug target prediction using semantic linked data

Drug repurposing

Anti-Parkinson

allergic rhinitis

http://www.ebi.ac.uk/chebi/searchId.do?chebiId=3398

?

Page 26: drug target prediction using semantic linked data

Summary

Semantic Link association can be assessed by topology and semantics of the network

Domain knowledge plays an important role!

Page 27: drug target prediction using semantic linked data

Team

Prof. Ying Ding Prof. David Wild

Page 28: drug target prediction using semantic linked data

http://chem2bio2rdf.org/slap

Page 29: drug target prediction using semantic linked data

Thanks!

Page 30: drug target prediction using semantic linked data

Backup slides

Page 31: drug target prediction using semantic linked data

SLAP Pipeline

Path filtering

Page 32: drug target prediction using semantic linked data

Chen, B., Dong. X., Jiao, D., Wang, H., Zhu, Q., Ding, Y., Wild, D.J. Chem2Bio2RDF: a semantic framework for linking and data mining chemogenomic and systems chemical biology data. BMC Bioinformatics, 2010, 11:255

Chem2Bio2RDF Datasets

Chem2Bio2RDF data

Other data venderscompoundprotein/genechemogenomicsliteratureothers

http://chem2bio2rdf.org

Page 33: drug target prediction using semantic linked data

Ranking Target associated chemicals

Randomly select three targets Select all target associated

chemicals as positive link Randomly select equal number of

chemicals that are not associated with the target

Compare with Naïve bayes using Molecular Weight, ALogP, number of hydrogen bond acceptors and donors, the number of rotatable bonds and FCFP_6 as descriptors

Leave one out validation

Page 34: drug target prediction using semantic linked data

Two objects are related if they are related to same objects

Coauthorship

Same Target

Page 35: drug target prediction using semantic linked data

Two objects are related if their related objects are related

Page 36: drug target prediction using semantic linked data
Page 37: drug target prediction using semantic linked data
Page 38: drug target prediction using semantic linked data

Similar Drugs have distinct indications

Levodopa: dopaminergic agentAnti-parkinson drug

Methyldopa : antiadrenergicAntihypertensive drug

Slap similarity: p value>0.05Tanimoto coefficient=0.89

Page 39: drug target prediction using semantic linked data

Direct: drug target interacts with each other physicallyIndirect: indirect interaction (e.g., change gene expression)Random: random drug target pairs

Association Score distribution among different pairs