Transcript drug interactions - BMI 205

Multiscale informatics for
understanding drug response
Russ B. Altman, MD, PhD
Departments of Bioengineering, Genetics,
Medicine & (by courtesy) Computer Science
Stanford University
PharmGKB, http://www.pharmgkb.org/
Outline of comments today
Our focus: drug action at molecular, cellular and
organismal level (for pharmacogenetics, mechanism,
repurposing, drug interactions)
Our toolkit: informatics tools and datasets for discovery and
for leveraging the investment.
1. Structural molecular data for drug repurposing
2. Expression data for understanding cellular responses to
drugs
3. Text information for predicting drug interactions
4. Population and clinical data to discover drug
interactions
Future prospects for systems pharmacology.
http://www.pharmgkb.org/
Summarizing clinical implications of molecular changes
PMID: 20435227
Beta 2 Adrenergic Receptor, a
G-protein coupled receptor
(GPCR), frequent
pharmacological target.
Beta 2 Adrenergic
Receptor in lipid
bilayer with
surrounding intraand extracellular
aqueous solution.
Molecular Data
• Structural genomics initiative: great increase
in “solved” 3D structures
• Includes many complexes of proteins with
small molecule ligands
Can we identify use this information to predict
new interactions between proteins and small
molecule drugs?
The FEATURE system for describing
molecular environments
Builds a statistical model of
microenvironments in proteins,
using occurrence of biophysical
and biochemical properties.
FEATURE1
Can detect remote similarities
in environments from different
proteins.
Atom Type
Atom Element
Residue Name
Residue Class
Partial Charge
Hydrophobicity
Aromatic
Etc.
FEATURE microenvironments detect
remote flexible FAD binding sites
FEATURE “sees” similarities in diverse kinase
structures (PIK3CG and SRC) = repurposing
opportunity (Liu & Altman, PLoS Comp Bio,
2011).
Validating kinase predictions from 40 tested
predictions (11 positive & 29 negative)
Pairs with high similarity
Validated
Highly interested
Mammalian
Liu & Altman, CPT: PSP, 2014
2
Moving from molecular to cellular data for
drug action
• Expression data universally available at
Gene Expression Omnibus
• Measures human gene expression in
thousands of conditions, cell types
• Recent examples of drug repurposing using
this information.
Can we understand drug action using this
data?
Independent Component Analysis (ICA) on all
human GEO data (~9K arrays)
component = hidden signal in data
Independent Component Analysis
Independent Component Analysis of GEO human data
yields ~420 fundamental components that explain
most variability in expression experiments.
(Engreitz et al, J Biomed Inform. 2010)
Analyzing response to a drug: gene
expression in response to parthenolide
•
•
•
CD34+ cells
12 AML patients
Samples before/after treatment
Key components expressed at different
levels in treated vs. untreated
373 = component with biggest difference
Highly weighted
Genes:
ICOS
GNA15
SOCS2
GCH1
ID3
NR4A3
PELI2
ID1
ZNF394
KHDRBS3
Diseases with high level of
component 373:
Pediatric T-ALL
Childhood ALL
AML
ALLL
Leukemia
Inteferon treatment of Hep C
Parthenolide effects NFKB signaling.
Pathways suggests new diseases and new
targets.
Parthenolide alters
expression of TNF, NFKB,
kinases.
Immediately suggests a way
to decide if Parthenolide is
appropriate for other
cancers, based on their
gene expression.
Augmenting the network of molecular and
cellular data with textual information.
• PubMed now holds more than 20 million
abstracts
• Most biomedical knowledge stored in the
published literature
Can we have computers “read” PubMed
abstracts and reason over them to predict new
drug-drug interactions?
Advances in natural language parsing enable
high fidelity extraction of relations
Sentence
SYNTAX
Word
Part Of
Speech
The
DT
ABCB1
NN
C3435T
NN
polymorphism
NN
influences
VBZ
methotrexate
JJ
sensitivity
NN
in
IN
rheumatoid
JJ
arthritis
NN
patients.
NNS
SEMANTICS
Named Entity
Recognition
Dependency Graph
Relation
Extraction
Relation
Normalization
ABCB1
polymorphism
ABCB1_
Variant
Genomic
Variation
influences
AFFECTS
relationship
methotrexate
sensitivity
methotrexate_
DrugSensitivity
Phenotype
Dependency
graph
gene
gene
variant
drug
disease
drug
sensitivity
disease
population
We can identify genes, drugs, phenotypes in
text using these technologies.… an ontology
to normalize
Sentence
SYNTAX
Word
Part Of
Speech
The
DT
ABCB1
NN
C3435T
NN
polymorphism
NN
influences
VBZ
methotrexate
JJ
sensitivity
NN
in
IN
rheumatoid
JJ
arthritis
NN
patients.
NNS
SEMANTICS
Named Entity
Recognition
Dependency Graph
Relation
Extraction
Relation
Normalization
ABCB1
polymorphism
ABCB1_
Variant
Genomic
Variation
influences
AFFECTS
relationship
methotrexate
sensitivity
methotrexate_
DrugSensitivity
Phenotype
gene
gene
variant
drug
drug
sensitivity
disease
disease
population
Coulet, Shah, Garten, Musen, Altman, JBI, 2010.
KEY: we map extracted entities to
standard terminologies
Sentence
SYNTAX
Word
Part Of
Speech
The
DT
ABCB1
NN
C3435T
NN
polymorphism
NN
influences
VBZ
methotrexate
JJ
sensitivity
NN
in
IN
rheumatoid
JJ
arthritis
NN
patients.
NNS
SEMANTICS
Named Entity
Recognition
Dependency Graph
Relation
Extraction
Relation
Normalization
ABCB1
polymorphism
ABCB1_
Variant
Genomic
Variation
influences
AFFECTS
relationship
methotrexate
sensitivity
methotrexate_
DrugSensitivity
Phenotype
gene
gene
variant
drug
drug
sensitivity
disease
disease
population
Coulet, Shah, Garten, Musen, Altman, JBI, 2010.
Semantic network of 170,598 normalized relations
from all PubMed abstracts.
CYP3A4
ACE
CYP2D
6
ABCB1 gene and verapamil drug
We chain together two gene-drug relationships
to create a drug-gene-drug relationship =
potential drug interaction!
Percha et al, Pacific Symposium on
Biocomputing, 2012.
Top
predicted
DDIs
from
text
processing
after training
on
known DDIs
drug pair
interact
fluoxetine-diazepam
tramadol-dextromethorphan
venlafaxine-dextromethorphan
naproxen-diazepam
paroxetine-dextromethorphan
metoprolol-dextromethorphan
lisinopril-enalapril
verapamil-omeprazole
dextromethorphan-codeine
omeprazole-naproxen
sertraline-dextromethorphan
omeprazole-diazepam
verapamil-fluconazole
verapamil-fexofenadine
verapamil-atorvastatin
naproxen-fluoxetine
warfarin-glibenclamide
warfarin-fluoxetine
verapamil-carvedilol
venlafaxine-tramadol
verapamil-clopidogrel
venlafaxine-paroxetine
verapamil-simvastatin
tramadol-paroxetine
warfarin-ibuprofen
omeprazole-dextromethorphan
fluoxetine-dextromethorphan
venlafaxine-metoprolol
venlafaxine-sertraline
tramadol-sertraline
dextromethorphan-citalopram
paroxetine-metoprolol
tramadol-metoprolol
verapamil-diazepam
dextromethorphan-aripiprazole
1*
1
1
0
1
0
1-0
11*
1**
1
1
0
1
1*
1*
1
1
1
11
1
1
1
0
1
1*
1
1
1**
1
0
10
npaths
avgvotes
p.glm
975
536
528
806
489
490
986
469
440
911
357
872
252
248
296
626
221
272
200
145
184
132
263
133
172
150
160
132
97
97
104
126
132
300
132
59.68%
95.27%
94.99%
65.60%
95.32%
90.17%
37.46%
87.30%
86.98%
40.09%
95.02%
38.84%
97.34%
93.28%
88.32%
52.50%
92.29%
86.93%
92.99%
98.45%
94.40%
99.18%
86.04%
98.42%
94.41%
96.36%
95.16%
94.89%
97.97%
97.84%
96.35%
93.79%
93.13%
76.30%
92.67%
0.608
0.533
0.523
0.506
0.489
0.441
0.410
0.395
0.367
0.366
0.365
0.322
0.296
0.262
0.261
0.240
0.236
0.234
0.227
0.227
0.226
0.223
0.222
0.219
0.218
0.216
0.215
0.196
0.194
0.193
0.188
0.186
0.186
0.185
0.183
LAB
1
0
1
1
1
0
0
1
0
Metoprolol
Class
Brand
Treats
Effects
Mech
Dextromethorphan
Beta blocker
Class
Non-opioid antitussive
Brand
Robitussin (+ tons of others)
Treats
Cough
Effects
Acts on central nervous system
to elevate threshold for
coughing
Mech
NMDA and glutamate antagonist
Blocks dopamine reuptake site
(?)
Lopressor, Toprol
High blood pressure
Angina (chest pain)
Heart attack (improves survival)
Heart failure
Relaxes blood vessels
Slows heart rate
Blocks beta receptors on
sympathetic nerves
Metoprolol
Dextromethorphan
metoprolol Drug isMetabolizedBy Gene CYP2D6…
Metoprolol
Dextromethorphan
… CYP2D6 Gene metabolizes Drug Dextromethorphan
DEEP DIVE for gene-drug-phenotype (Chris
Re, CS)
Using population-based and clinical data to
generate hypotheses
• FDA releases adverse event reports
regularly, but very complex data.
• Electronic Medical Records have
information about patient drug exposures?
Can we mine FDA and clinical EMR records to
discover new drug-drug interactions?
We built a statistical model able to recognize
glucose-altering drugs based on their
“adverse event signature”
Adverse Events reported by FDA
Diabetes
Drugs
Correlated
Indications
Fij = frequency of AEj for Drugi
Fij = frequency of AEj for Indicationi
The adverse event signature is able to
recall glucose-altering drugs
Model trained on single drug reports can be
used to classify drug pairs.
EXAMPLE: Glucose-homeostasis adverse
effects
Fij = frequency of AEj for Drugi
Drugs
Pairs
Pairs of drugs that match signature:
Paroxetine and Pravastatin each taken by approximately 15 million Americans.
We estimate 500,000 to 800,000 take both.
Pravastatin and paroxetine significantly increase
blood glucose by 20 mg/dl
Variable
N
Pravastatin and Paroxetine
Combination
10
Demographics
Age (mean ± SD)
Gender (% Female)
59.9 ± 11.09
90.0
Race (% of group)
White
50
African American
20
Hispanic
0
Other
30
Glucose (mg/dl mean ± SD)
Baseline (base)
114.08 ± 14.79
After treatment(s) (post)
133.96 ± 19.54
paired t-test (t: post - base)
Change (base to post)
N patients with increase
0.020
19.88 ± 21.04
8 (80)
Combination therapy increases glucose by 20
mg/dl; pravastatin and paroxetine effects alone
are modest
Site 2
(10 patients)
Replication sites validate combination findings
Vanderbilt
(18 patients)
Harvard Partners
(106 patients)
Combining all
three sites
Not a “class affect” of statins and SSRIs
Effect larger in diabetics
N = 177
Mice on two drugs also show increase
(Tatonetti et al, Clin Pharm Ther. 2011)
Web searches? Patient search for
pravastatin & paroxetine and DM-related
words more frequently.
White et al,
J Am Med
Inform
Assoc. 2013
May
1;20(3):4048
Conclusions
• Biomedical informatics provides powerful tools for discovery
at the molecular, cellular, and organismal levels.
• They operate on both primary data and processed
knowledge.
• They can individually contribute to understanding drug
action, effects and interactions.
• The combination & integration of these methods is likely to
be even more powerful going forward…
Combining text mining + FDA data
Orange
highlighted
predictions from
text
mining are also
predictions in
the FDA mining
effort!
drug pair
interact
fluoxetine-diazepam
tramadol-dextromethorphan
venlafaxine-dextromethorphan
naproxen-diazepam
paroxetine-dextromethorphan
metoprolol-dextromethorphan
lisinopril-enalapril
verapamil-omeprazole
dextromethorphan-codeine
omeprazole-naproxen
sertraline-dextromethorphan
omeprazole-diazepam
verapamil-fluconazole
verapamil-fexofenadine
verapamil-atorvastatin
naproxen-fluoxetine
warfarin-glibenclamide
warfarin-fluoxetine
verapamil-carvedilol
venlafaxine-tramadol
verapamil-clopidogrel
venlafaxine-paroxetine
verapamil-simvastatin
tramadol-paroxetine
warfarin-ibuprofen
omeprazole-dextromethorphan
fluoxetine-dextromethorphan
venlafaxine-metoprolol
venlafaxine-sertraline
tramadol-sertraline
dextromethorphan-citalopram
1*
1
1
0
1
0
1-0
11*
1**
1
1
0
1
1*
1*
1
1
1
11
1
1
1
0
1
1*
1
1
1**
npaths
avgvotes
p.glm
975
536
528
806
489
490
986
469
440
911
357
872
252
248
296
626
221
272
200
145
184
132
263
133
172
150
160
132
97
97
104
59.68%
95.27%
94.99%
65.60%
95.32%
90.17%
37.46%
87.30%
86.98%
40.09%
95.02%
38.84%
97.34%
93.28%
88.32%
52.50%
92.29%
86.93%
92.99%
98.45%
94.40%
99.18%
86.04%
98.42%
94.41%
96.36%
95.16%
94.89%
97.97%
97.84%
96.35%
0.608
0.533
0.523
0.506
0.489
0.441
0.410
0.395
0.367
0.366
0.365
0.322
0.296
0.262
0.261
0.240
0.236
0.234
0.227
0.227
0.226
0.223
0.222
0.219
0.218
0.216
0.215
0.196
0.194
0.193
0.188
LAB
1
0
1
1
1
0
Combining molecular & cellular data
Proteins with similar pockets can be associated with disease pathways
for repurposing.
Thus, the emerging network for drugs….
Cellular response &
pathways
Target structure
& dynamics
Drug recognition &
binding
Text mining of gene, drug,
phenotype associations
Clinical response
datamining
Population effect
reporting
Teri Klein
Michelle
Jesse
Guy
Roxana
Li
Mei
Grace Tang
Nick Tatonetti
Joan
Sara
Caroline
Beth Percha
Mark
Fen
Tianyun Liu
Ellie
Blanca
Jenn
Jesse Engreitz
Katrin
Jenelle
Yael Garten
Konrad
Ryan
But the database biases can kill you.
Corrects for *unmeasured* biasees
Tatonetti et al, Science STM, 2012
Thanks to PharmGKB Team
Teri Klein
Michelle Carrillo
Curators: Li Gong, Joan Hebert, Katrin
Sangkuhl, Laura Hodges, Connie Oshiro,
Caroline Thorn
Developers: Mark Woon, Ryan Whaley, Feng
Liu, Mei Gong, Rebecca Tang
Data Center: Tina Zhou, TC Truong
NIH: GM-61374
Key Papers
PharmGKB: a logical home for knowledge relating genotype to drug response phenotype. Altman RB. Nat Genet. 2007
Apr;39(4):426. No abstract available. PMID: 17392795 [PubMed - indexed for MEDLINE]
Independent component analysis: mining microarray data for fundamental human gene expression modules. Engreitz JM,
Daigle BJ Jr, Marshall JJ, Altman RB. J Biomed Inform. 2010 Dec;43(6):932-44. Epub 2010 Jul 7. PMID: 20619355
Detecting drug interactions from adverse-event reports: interaction between paroxetine and pravastatin increases blood
glucose levels. Tatonetti NP, Denny JC, Murphy SN, Fernald GH, Krishnan G, Castro V, Yue P, Tsao PS, Kohane I, Roden
DM, Altman RB. Clin Pharmacol Ther. 2011 Jul;90(1):133-42. doi: 10.1038/clpt.2011.83. Epub 2011 May 25. Erratum in: Clin
Pharmacol Ther. 2011 Sep;90(3):480. Tsau, P S [corrected to Tsao, P S]. PMID: 21613990
Using text to build semantic networks for pharmacogenomics.Coulet A, Shah NH, Garten Y, Musen M, Altman RB. J Biomed
Inform. 2010 Dec;43(6):1009-19. Epub 2010 Aug 17. PMID: 20723615 [PubMed - indexed for MEDLINE]
DISCOVERY AND EXPLANATION OF DRUG-DRUG INTERACTIONS VIA TEXT MINING. Percha B, Garten Y, Altman RB.
Pacific Symposium on Biocomputing 2012, in press. Available at http://psb.stanford.edu/psbonline/
A novel signal detection algorithm for identifying hidden drug-drug interactions in adverse event reports. Tatonetti NP,
Fernald GH, Altman RB. J Am Med Inform Assoc. 2011 Jun 14. [Epub ahead of print] PMID: 21676938
The FEATURE framework for protein function annotation: modeling new functions, improving performance, and extending to
novel applications. Halperin I, Glazer DS, Wu S, Altman RB. BMC Genomics. 2008 Sep 16;9 Suppl 2:S2. PMID: 18831785