SlideShare a Scribd company logo
Combining Syntactic Information and
domain-specific Lexical Patterns to
Extract Drug-Drug Interactions from
Biomedical texts
Isabel Segura-Bedmar, Paloma Martínez, César de Pablo-Sánchez,
CS Department, Universidad Carlos III de Madrid, Spain
October 26, 2010
Toronto, Ontorio, Canada
DTMBIO'10
2
Outline
Introduction
I
State of the Art
Proposal
Evaluation
Conclusions and Future Work
DrugDDI Corpus
IE processes for DDI Extraction: DrugDDI prototype
3
What is a Drug-Drug Interaction (DDI)?
Introduction
4
Beneficial
Introduction
Ritonavir + Lopinavir → Effective antiretroviral
Nifedipine + propranolol → Antianginal drug
5
DANGER!!!
Introduction
Aspirin + Heparin → Bleeding
Aspirin + Acetazolamide → Death
6
 47.8% of adverse
eventes are due to
drugs, of which 3.5%
result from DDI1.
 Medication errors kill
7,000 patients per
annum in USA2.
 High incidence in certain
patient groups (3-20%).
 Increase the Healthcare
costs
Things can get complicated...
1. APEAS Estudio sobre la seguridad de los pacientes en Atención primaria de salud.
Madrid: Ministerio de Sanidad y Consumo, 2008
2. Kohn et al., 2000. “To Err is Human”.
Introduction
How do healthcare
professionals
avoid drug-drug interactions?
Introduction
8
Drug interaction Resources
Introduction
Drug Interactions Resources
Medical and Pharmaceutical Research 
Publications
? ?
Most effective source:
Medical Literature.
9
How does Information Extraction help?
A possible interaction resulting in acute
renal failure has been reported
in a few subjects when indomethacin,
a nonsteroidal anti-inflammatory agent,
was given with triamterene.
DDI ( INDOMETHACIN, TRIAMTERENE)
Introduction
10
Objectives
Creation of an annotated corpus of DDI.
Introduction
Study the main approaches for biomedical RE.
Combine the resolution of complex syntactic
constructions and a set of lexical patterns
defined by a pharmacist in order to extract
DDIs.
State of the Art
State of the Art
Approaches
12
State of the Art
Relation 
Extraction
In biomedicine
1
Linguistic­based 
approaches
2
3
Pattern­based 
approaches
Machine Learning­
based approaches
4
Hybrid approaches
Proposal
14
Proposal
Create an
annotated corpus
to study the
extraction of DDI
An Information
Extraction (IE)
System for DDI
Proposal
15
Proposal
Create an
annotated corpus
to study the
extraction of DDI
An Information
Extraction System
for DDI
Proposal: Corpus DrugDDI
Building a corpus for DDI
DrugBank
HTML To Text
Wrapper
Corpus TXT
Drug Name Recognition
MetaMap UMLS:
Text analysis
String Matching
Algorithm
2006AA
UMLSKS
WHOINN
affixes
DDI Extraction
XML annotated with drugs and other
biomedical concepts
XML annotated with drugs
interactions
Proposal: Corpus DrugDDI
DrugBank
HTML To Text
Wrapper
Corpus TXT
Proposal: Corpus DrugDDI
18
Text Analysis by MetaMap program
Corpus TXT
XML annotated with shallow
syntactic and semantic
information from UMLS
UMLS MetaMap
(MMTx):
Text analysis
Unified
Medical
Language
System
(UMLS)
Proposal: Corpus DrugDDI
DrugBank
19
Sentence splitting
Proposal: Corpus DrugDDI
20
Shallow parsing
Proposal: Corpus DrugDDI
21
Tokenization
Proposal: Corpus DrugDDI
22
UMLS Semantic Information
(concepts and semantic types)
Proposal: Corpus DrugDDI
23
Example of DDI annotation
Proposal: Corpus DrugDDI
24
Corpus DrugDDI
Total
Avg . 
per 
doc
DDIs 3,160 5.5
Sentences  5,806 10.2
Sentences with at least one DDI 2,044 3.5
Drugs 14,930 25.7
Documents 579
Proposal: Corpus DrugDDI
(http://labda.inf.uc3m.es/DrugDDI/)
Create an
annotated corpus
to study the
Extraction of DDI
Build a
Pattern-based
method to
Extract DDI
Proposal: DDI extraction
26
IE System for DDI
Corpus TXT
Text analysis
XML annotated 
with shallow 
syntactic and 
semantic 
information
Drug Name 
Recognition
Anaphora 
Resolution
DDI Extraction
+
drugs and other 
biomedical 
concepts 
+
anaphoras
+
Drug 
interactions
Biomedical Resources
Proposal: DrugDDI prototype
whoole
27
Drug Name Recognition (DrugNer)
Corpus TXT
+
drugs and other 
biomedical 
concepts 
+
anaphoras
+
Drug­Drug 
interactions
WHOINN
affixes
UMLS
XML annotated 
with shallow 
syntactic and 
semantic 
information
Proposal: DrugDDI prototype
Drug Name 
Recognition
Anaphora 
Resolution
DDI Extraction
Text analysis
28
Drug Anaphora Resolution
Corpus TXT
Biomedical Resources
Proposal: DrugDDI prototype
Drug Name 
Recognition
Anaphora 
Resolution
DDI Extraction
Text analysis
+
drugs and other 
biomedical 
concepts 
+
anaphoras
+
Drug­Drug 
interactions
XML annotated 
with shallow 
syntactic and 
semantic 
information
29
Drug-Drug Interaction Extraction
Corpus TXT
Biomedical Resources
Proposal: DrugDDI prototype
Drug Name 
Recognition
Anaphora 
Resolution
DDI Extraction
Text analysis
+
drugs and other 
biomedical 
concepts 
+
anaphoras
+
Drug­Drug 
interactions
XML annotated 
with shallow 
syntactic and 
semantic 
information
30
Syntactic Information + Lexical
Patterns
Proposal: DrugDDI prototype
XML annotated with 
shallow syntactic and 
semantic information, 
drugs and other 
biomedical concepts, 
anaphoras
Drug­Drug  
interactions
Detection of 
coordinate structures
Detection of 
appositions
Pattern 
Matching
Clause Splitting
Rules for sentence 
simplification
31
Pharmacological patterns
Patterns defined by our pharmacist.
<DRUG>  INTERACT(S) WITH <DRUG>.
<DRUG> (INCREASE(S)|DECREASE(S)|...) <DRUG EFFECTS>
<DRUG> INTERFERE(S) WITH <DRUG PROPERTIES>
CONCURRENT USE OF <DRUG> WITH <DRUG> (INCREASE(S)|
DECREASE(S)|...) <DRUG PROPERTIES>
<DRUG> INHIBIT(S) <DRUG PROPERTIES>
CO­ADMINISTRATION OF <DRUG> AND <DRUG> RESULT IN 
<DRUG PROPERTIES>
<DRUG EFFECTS> OF <DRUG> BE (ENHANCED|REDUCED|...) BY 
<DRUG>
Proposal: DrugDDI prototype
Allopurinol interacts with anisindione, azathioprine and cyclosporine
How does syntactic information help?
Detecting coordinate structures
Proposal: DrugDDI prototype
Allopurinol interacts with anisindione, azathioprine and cyclosporine
Detection of
Coordinate structures
COORD := ([NP|PP|AJD|UNK],)* [NP|PP|
ADJ|UNK] CONJ [NP|PP|ADJ|UNK]
Allopurinol interact with COORD
Detecting coordinate structures
Proposal: DrugDDI prototype
How does syntactic information help?
Allopurinol interacts with anisindione, azathioprine and cyclosporine
Detection of
Coordinate structures
COORD := ([NP|PP|AJD|UNK],)* [NP|PP|
ADJ|UNK] CONJ [NP|PP|ADJ|UNK]
Allopurinol interacts with COORD
Drug Name Recognition
DRUG.1 interacts with COORD
Detecting coordinate structures
Proposal: DrugDDI prototype
How does syntactic information help?
Allopurinol interacts with anisindione, azathioprine and cyclosporine
DDI := <DRUG1|COORD|APPOSITION>
INTERACTS WITH
<DRUG2|COORD|APPOSITION>.
Detection of
Coordinate structures
Pattern Matching
COORD := ([NP|PP|AJD|UNK],)* [NP|PP|
ADJ|UNK] CONJ [NP|PP|ADJ|UNK]
Allopurinol interacts with COORD
Drug Name Recognition
DRUG.1 interacts with COORD
Detecting coordinate structures
Proposal: DrugDDI prototype
How does syntactic information help?
Allopurinol interacts with anisindione, azathioprine and cyclosporine
DDI := <DRUG1|COORD|APPOSITION>
INTERACTS WITH
<DRUG2|COORD|APPOSITION>.
Detection of
Coordinate structures
Pattern Matching
DRUG-DRUG INTERACTION:
Drug 1: Allopurinol
Drug 2: anisindione
COORD := ([NP|PP|AJD|UNK],)* [NP|PP|
ADJ|UNK] CONJ [NP|PP|ADJ|UNK]
Allopurinol interacts with COORD
Drug Name Recognition
DRUG.1 interacts with COORD
DRUG-DRUG INTERACTION:
Drug 1: Allopurinol
Drug 2: azathioprine
DRUG-DRUG INTERACTION:
Drug 1: Allopurinol
Drug 2: cyclosporine
Detecting coordinate structures
Proposal: DrugDDI prototype
How does syntactic information help?
Catecholamine-depleting drugs, such as reserpine, may have an additive
effect when given with beta-blocking agents.
DDI := <DRUG1|APPOSITION>
(HAVE|INCREASE|...) <EFFECT>
WHEN GIVEN WITH
<DRUG2|APPOSITION>.
Detection of
Appositions
Pattern Matching
DRUG-DRUG INTERACTION:
Drug 1: Catecholamine-depleting drugs
Drug 2: beta-blocking agents
Property|Effect: additive
DRUG-DRUG INTERACTION:
Drug 1: Reserpine
Drug 2: beta-blocking agents
Property|Effect: additive
APPOSITION may have an additive effect when given with DRUG.
APPOSITION := <APPOSITIVE>
MARKER <APOSITIVE>
How syntactic information helps?
Proposal: DrugDDI prototype
Detecting appositions
Concomitant administration of corticosteroids with Aspirin may increase the risk of
gastrointestinal ulceration and may reduce serum salicylate levels.
Concomitant administration of
corticosteroids with Aspirin may
increase the risk of
gastrointestinal ulceration
Concomitant administration of
corticosteroids with Aspirin may
reduce serum salicylate levels.
PATTERN: ADMINISTRATION
OF <DRUG1> WITH
<DRUG2>
MAY (INCREASE|REDUCE)...
Clause splitting
Pattern Matching
DRUG-DRUG INTERACTION:
Drug 1: Corticosteroids
Drug 2: Aspirin
Action: increase
Property|Effect: Gastrointestinal
ulceration
DRUG-DRUG INTERACTION:
Drug 1: Corticosteroids
Drug 2: Aspirin
Action: reduce
Property|Effect: serum salicylate
levels
Proposal: DrugDDI prototype
Detecting clauses
How syntactic information helps?
Evaluation
40
1st
Baseline Experiment
Evaluation
Pair of drugs in the same sentence => DDI.
41
2nd Experiment: Lexical Patterns
Evaluation
XML annotated with 
shallow syntactic and 
semantic information, 
drugs and other 
biomedical concepts, 
anaphoras
Drug­Drug  
interactions
Pattern 
Matching
42
3th Experiment: Coordinate structures
and appositions
XML annotated with 
shallow syntactic and 
semantic information, 
drugs and other 
biomedical concepts, 
anaphoras
Drug­Drug  
interactions
Detection of 
coordinate structures
Detection of 
appositions
Pattern 
Matching
Clause Splitting
Rules for sentence 
simplification
Evaluation
43
4th Experiment: Coordinate structures,
appositions and clauses
XML annotated with 
shallow syntactic and 
semantic information, 
drugs and other 
biomedical concepts, 
anaphoras
Drug­Drug  
interactions
Detection of 
coordinate structures
Detection of 
appositions
Pattern 
Matching
Clause Splitting
Rules for sentence 
simplification
Evaluation
44
Evaluation
Precision Recall F-measure
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
0.11
1
0.19
0.67
0.14
0.23
0.48
0.26
0.34
0.49
0.25
0.33
Baseline
Only patterns
Coordinatives & Appositions
Coordinatives & Appositions &
Clauses
Experiments:
Evaluation
Conclusions and
Future Work
Contributions
46
Conclusions
First annotated corpus with DDI.
First approximation for DDI extraction
Future Work
47
Conclusions
Treatment of negation and modality.
Integrate the drug anaphora resolution in the
DDI extraction.
Improve the clause splitting process.
Handle the mistakes made by MetaMap.
Future Work
48
Conclusions
Use the SPINDEL [De Pablo-Sánchez et al., 2009]
system to acquire new patterns.
Evaluate Machine learning techniques.
Increase the quality of the DrugDDI corpus.
Future Work
49
Conclusions
Extract relevant information about each DDI.
Improve drug interaction resources.
User-oriented evaluation.
Drug Drug Interaction detection is a
promising application for Text Mining
(http://labda.inf.uc3m.es/DrugDDI/)
Proposal: Corpus DrugDDI
Projects
52
Conclusions
This work has been partially supported by the Spanish research
projects:
MAVIR consortium (S-0505/TIC-0267, www.mavir.net), a network
of excellence funded by the Madrid Regional Government.
ISSE: Semantic Interoperability in Electronic Healthcare (FIT-
350300-2007-75).
BRAVO: Advanced Multimodal and Multilingual Question
Answering. (TIN2007-67407-C03-01).
MULTIMEDICA.
53
WHO affixes
for identifying and classifying drugs
Affixes 
WHOINN
Drug Family  Pattern Drugs
­pristin Antibacterials,
pristinamycin
derivatives
[A­Za­z0­9]*[pristin] Efepristin
­gatran  Antithrombotic
agents
[A­Za­z0­9]*[gatran] Dabigatran
-tinib Antineoplastic
agents
[A­Za­z0­9]*[tinib] Dasatinib,
Sunitinib,
Nilotinib
-mycin -Antibiotics [A­Za­z0­9]*[mycin] Tanespimycin
Proposal: DrugDDI prototype
Drug name recognition
and classification
in biomedical texts
(Segura-Bedmar et al., 2008)
Score-based approach for
Anaphora Resolution in Drug-
Drug Interacion Documents
(Segura-Bedmar et al., 2009a)
NLDB 2009
DrugNerAR: Linguistic Rule-
Based Anaphora Resolution for
DDI Extraction in
pharmacological documents
(Segura-Bedmar et al., 2009b
To appear in DTMBIO 2009
56
How does Information Extraction help?
Triamterene, metformin and amiloride
should be administered with care
as they might increase dofetilide levels.
DDI ( TRIAMTERENE, DOFETILIDE)
DDI ( METFORMIN, DOFETILIDE)
DDI ( AMILORIDE, DOFETILIDE)
Introduction
Proposal: Corpus DrugDDI

More Related Content

Viewers also liked

Compensation claim nsw
Compensation claim nswCompensation claim nsw
Compensation claim nsw
Paramount Lawyers
 
Q4 and 5
Q4 and 5 Q4 and 5
Q4 and 5
Molly Dickerson
 
Perfluorocyclohexenyl aryl ether polymers via polycondensation
Perfluorocyclohexenyl aryl ether polymers via   polycondensationPerfluorocyclohexenyl aryl ether polymers via   polycondensation
Perfluorocyclohexenyl aryl ether polymers via polycondensation
Babloo Sharma, Ph.D.
 
Ultra low dielectric, self-cleansing and highly oleophobic POSS-PFCP aryl eth...
Ultra low dielectric, self-cleansing and highly oleophobic POSS-PFCP aryl eth...Ultra low dielectric, self-cleansing and highly oleophobic POSS-PFCP aryl eth...
Ultra low dielectric, self-cleansing and highly oleophobic POSS-PFCP aryl eth...
Babloo Sharma, Ph.D.
 
Detecting Semantic Relations between Nominals using Support Vector Machines a...
Detecting Semantic Relations between Nominals using Support Vector Machines a...Detecting Semantic Relations between Nominals using Support Vector Machines a...
Detecting Semantic Relations between Nominals using Support Vector Machines a...
Grupo HULAT
 
Negara Maju Dan Berkembang
Negara Maju Dan BerkembangNegara Maju Dan Berkembang
Negara Maju Dan Berkembang
arisokta
 
DINTO An Ontology for Drug-Drug Interactions
DINTO An Ontology for Drug-Drug InteractionsDINTO An Ontology for Drug-Drug Interactions
DINTO An Ontology for Drug-Drug Interactions
Grupo HULAT
 
Bis-perfluorocycloalkenyl (PFCA) aryl ether monomers towards a versatile clas...
Bis-perfluorocycloalkenyl (PFCA) aryl ether monomers towards a versatile clas...Bis-perfluorocycloalkenyl (PFCA) aryl ether monomers towards a versatile clas...
Bis-perfluorocycloalkenyl (PFCA) aryl ether monomers towards a versatile clas...
Babloo Sharma, Ph.D.
 
Solving 1 step equations
Solving 1 step equationsSolving 1 step equations
Solving 1 step equations
sgaster
 
Perfluorocyclopentenyl (PFCP) Aryl Ether Polymers via Polycondensation of Oct...
Perfluorocyclopentenyl (PFCP) Aryl Ether Polymers via Polycondensation of Oct...Perfluorocyclopentenyl (PFCP) Aryl Ether Polymers via Polycondensation of Oct...
Perfluorocyclopentenyl (PFCP) Aryl Ether Polymers via Polycondensation of Oct...
Babloo Sharma, Ph.D.
 
The Citizen Card - Improving Voluntary Tax Compliance in Ghana
The Citizen Card - Improving Voluntary Tax Compliance in GhanaThe Citizen Card - Improving Voluntary Tax Compliance in Ghana
The Citizen Card - Improving Voluntary Tax Compliance in Ghana
Yaw Osei-Tutu
 
CV-updated-ÒÕÓ
CV-updated-ÒÕÓCV-updated-ÒÕÓ
CV-updated-ÒÕÓIlya Ganeev
 
Infrastructure is Dead - Pepijn Palmans
Infrastructure is Dead -  Pepijn PalmansInfrastructure is Dead -  Pepijn Palmans
Infrastructure is Dead - Pepijn Palmans
Housingcenter
 

Viewers also liked (17)

Compensation claim nsw
Compensation claim nswCompensation claim nsw
Compensation claim nsw
 
Q4 and 5
Q4 and 5 Q4 and 5
Q4 and 5
 
Perfluorocyclohexenyl aryl ether polymers via polycondensation
Perfluorocyclohexenyl aryl ether polymers via   polycondensationPerfluorocyclohexenyl aryl ether polymers via   polycondensation
Perfluorocyclohexenyl aryl ether polymers via polycondensation
 
Ultra low dielectric, self-cleansing and highly oleophobic POSS-PFCP aryl eth...
Ultra low dielectric, self-cleansing and highly oleophobic POSS-PFCP aryl eth...Ultra low dielectric, self-cleansing and highly oleophobic POSS-PFCP aryl eth...
Ultra low dielectric, self-cleansing and highly oleophobic POSS-PFCP aryl eth...
 
1Lezione inventor
1Lezione inventor1Lezione inventor
1Lezione inventor
 
Detecting Semantic Relations between Nominals using Support Vector Machines a...
Detecting Semantic Relations between Nominals using Support Vector Machines a...Detecting Semantic Relations between Nominals using Support Vector Machines a...
Detecting Semantic Relations between Nominals using Support Vector Machines a...
 
Protecting the brand
Protecting the brandProtecting the brand
Protecting the brand
 
Negara Maju Dan Berkembang
Negara Maju Dan BerkembangNegara Maju Dan Berkembang
Negara Maju Dan Berkembang
 
DINTO An Ontology for Drug-Drug Interactions
DINTO An Ontology for Drug-Drug InteractionsDINTO An Ontology for Drug-Drug Interactions
DINTO An Ontology for Drug-Drug Interactions
 
Bis-perfluorocycloalkenyl (PFCA) aryl ether monomers towards a versatile clas...
Bis-perfluorocycloalkenyl (PFCA) aryl ether monomers towards a versatile clas...Bis-perfluorocycloalkenyl (PFCA) aryl ether monomers towards a versatile clas...
Bis-perfluorocycloalkenyl (PFCA) aryl ether monomers towards a versatile clas...
 
Solving 1 step equations
Solving 1 step equationsSolving 1 step equations
Solving 1 step equations
 
Perfluorocyclopentenyl (PFCP) Aryl Ether Polymers via Polycondensation of Oct...
Perfluorocyclopentenyl (PFCP) Aryl Ether Polymers via Polycondensation of Oct...Perfluorocyclopentenyl (PFCP) Aryl Ether Polymers via Polycondensation of Oct...
Perfluorocyclopentenyl (PFCP) Aryl Ether Polymers via Polycondensation of Oct...
 
The Citizen Card - Improving Voluntary Tax Compliance in Ghana
The Citizen Card - Improving Voluntary Tax Compliance in GhanaThe Citizen Card - Improving Voluntary Tax Compliance in Ghana
The Citizen Card - Improving Voluntary Tax Compliance in Ghana
 
CV-updated-ÒÕÓ
CV-updated-ÒÕÓCV-updated-ÒÕÓ
CV-updated-ÒÕÓ
 
Infrastructure is Dead - Pepijn Palmans
Infrastructure is Dead -  Pepijn PalmansInfrastructure is Dead -  Pepijn Palmans
Infrastructure is Dead - Pepijn Palmans
 
RERA
RERARERA
RERA
 
CV-updated
CV-updatedCV-updated
CV-updated
 

Similar to Combining Syntactic Information and domain-specific Lexical Patterns to Extract Drug-Drug Interactions from Biomedical texts

Application of Information Extraction techniques to pharmacological domain: E...
Application of Information Extraction techniques to pharmacological domain: E...Application of Information Extraction techniques to pharmacological domain: E...
Application of Information Extraction techniques to pharmacological domain: E...
Grupo HULAT
 
Extraction of Drug-Drug Interactions from Biomedical Texts
Extraction of Drug-Drug Interactions from Biomedical TextsExtraction of Drug-Drug Interactions from Biomedical Texts
Extraction of Drug-Drug Interactions from Biomedical Texts
Grupo HULAT
 
Towards a foundational representation of potential drug-drug interaction know...
Towards a foundational representation of potential drug-drug interaction know...Towards a foundational representation of potential drug-drug interaction know...
Towards a foundational representation of potential drug-drug interaction know...
Mathias Brochhausen
 
GtoPdb ELIXIR-All Hands 2018
GtoPdb ELIXIR-All Hands 2018GtoPdb ELIXIR-All Hands 2018
GtoPdb ELIXIR-All Hands 2018
Guide to PHARMACOLOGY
 
Computer aided drug designing (CADD)
Computer aided drug designing (CADD)Computer aided drug designing (CADD)
Computer aided drug designing (CADD)
Aakshay Subramaniam
 
RxpredictPresentation.pdf
RxpredictPresentation.pdfRxpredictPresentation.pdf
RxpredictPresentation.pdf
DanikaGupta
 
MOLECULAR DOCKING AND RELATED DRUG DESIGN ACHIEVEMENTS
MOLECULAR DOCKING AND RELATED DRUG DESIGN ACHIEVEMENTS MOLECULAR DOCKING AND RELATED DRUG DESIGN ACHIEVEMENTS
MOLECULAR DOCKING AND RELATED DRUG DESIGN ACHIEVEMENTS
santosh Kumbhar
 
Integration of knowledge for personalized medicine: a pharmacogenomics...
Integration of knowledge for personalized medicine: a pharmacogenomics...Integration of knowledge for personalized medicine: a pharmacogenomics...
Integration of knowledge for personalized medicine: a pharmacogenomics...cancerdrg
 
IUPHAR/BPS Guide to Pharmacology
IUPHAR/BPS Guide to PharmacologyIUPHAR/BPS Guide to Pharmacology
IUPHAR/BPS Guide to Pharmacology
Guide to PHARMACOLOGY
 
GtoPdb June 2019 poster
GtoPdb June 2019 posterGtoPdb June 2019 poster
GtoPdb June 2019 poster
Chris Southan
 
IUPHAR/BPS Guide to Pharmacology in 2018
IUPHAR/BPS Guide to Pharmacology in 2018IUPHAR/BPS Guide to Pharmacology in 2018
IUPHAR/BPS Guide to Pharmacology in 2018
Guide to PHARMACOLOGY
 
Sorting bioactive wheat from database chaff: Challenges of discerning correct...
Sorting bioactive wheat from database chaff: Challenges of discerning correct...Sorting bioactive wheat from database chaff: Challenges of discerning correct...
Sorting bioactive wheat from database chaff: Challenges of discerning correct...
Guide to PHARMACOLOGY
 
Sorting bioactive wheat from database chaff
Sorting bioactive wheat from database chaffSorting bioactive wheat from database chaff
Sorting bioactive wheat from database chaff
Chris Southan
 
Embase.pdf
Embase.pdfEmbase.pdf
Embase.pdf
AntonellaDiNisio1
 
Talk at Yale University April 26th 2011: Applying Computational Models for To...
Talk at Yale University April 26th 2011: Applying Computational Modelsfor To...Talk at Yale University April 26th 2011: Applying Computational Modelsfor To...
Talk at Yale University April 26th 2011: Applying Computational Models for To...
Sean Ekins
 
The DDI (Drug-Drug Interaction) Corpus
The DDI (Drug-Drug Interaction) CorpusThe DDI (Drug-Drug Interaction) Corpus
The DDI (Drug-Drug Interaction) Corpus
Grupo HULAT
 
Finland Helsinki Drug Research slides 2011
Finland Helsinki Drug Research slides 2011Finland Helsinki Drug Research slides 2011
Finland Helsinki Drug Research slides 2011
Sean Ekins
 
Molecular docking
Molecular dockingMolecular docking
Molecular docking
Maakasaikumar
 
Guide to Pharmacology Poster - ELIXIR All Hands 2020
Guide to Pharmacology Poster - ELIXIR All Hands 2020Guide to Pharmacology Poster - ELIXIR All Hands 2020
Guide to Pharmacology Poster - ELIXIR All Hands 2020
Guide to PHARMACOLOGY
 
The Principle of Rational Design of Drug Combination and Personalized Therapy...
The Principle of Rational Design of Drug Combination and Personalized Therapy...The Principle of Rational Design of Drug Combination and Personalized Therapy...
The Principle of Rational Design of Drug Combination and Personalized Therapy...Jianghui Xiong
 

Similar to Combining Syntactic Information and domain-specific Lexical Patterns to Extract Drug-Drug Interactions from Biomedical texts (20)

Application of Information Extraction techniques to pharmacological domain: E...
Application of Information Extraction techniques to pharmacological domain: E...Application of Information Extraction techniques to pharmacological domain: E...
Application of Information Extraction techniques to pharmacological domain: E...
 
Extraction of Drug-Drug Interactions from Biomedical Texts
Extraction of Drug-Drug Interactions from Biomedical TextsExtraction of Drug-Drug Interactions from Biomedical Texts
Extraction of Drug-Drug Interactions from Biomedical Texts
 
Towards a foundational representation of potential drug-drug interaction know...
Towards a foundational representation of potential drug-drug interaction know...Towards a foundational representation of potential drug-drug interaction know...
Towards a foundational representation of potential drug-drug interaction know...
 
GtoPdb ELIXIR-All Hands 2018
GtoPdb ELIXIR-All Hands 2018GtoPdb ELIXIR-All Hands 2018
GtoPdb ELIXIR-All Hands 2018
 
Computer aided drug designing (CADD)
Computer aided drug designing (CADD)Computer aided drug designing (CADD)
Computer aided drug designing (CADD)
 
RxpredictPresentation.pdf
RxpredictPresentation.pdfRxpredictPresentation.pdf
RxpredictPresentation.pdf
 
MOLECULAR DOCKING AND RELATED DRUG DESIGN ACHIEVEMENTS
MOLECULAR DOCKING AND RELATED DRUG DESIGN ACHIEVEMENTS MOLECULAR DOCKING AND RELATED DRUG DESIGN ACHIEVEMENTS
MOLECULAR DOCKING AND RELATED DRUG DESIGN ACHIEVEMENTS
 
Integration of knowledge for personalized medicine: a pharmacogenomics...
Integration of knowledge for personalized medicine: a pharmacogenomics...Integration of knowledge for personalized medicine: a pharmacogenomics...
Integration of knowledge for personalized medicine: a pharmacogenomics...
 
IUPHAR/BPS Guide to Pharmacology
IUPHAR/BPS Guide to PharmacologyIUPHAR/BPS Guide to Pharmacology
IUPHAR/BPS Guide to Pharmacology
 
GtoPdb June 2019 poster
GtoPdb June 2019 posterGtoPdb June 2019 poster
GtoPdb June 2019 poster
 
IUPHAR/BPS Guide to Pharmacology in 2018
IUPHAR/BPS Guide to Pharmacology in 2018IUPHAR/BPS Guide to Pharmacology in 2018
IUPHAR/BPS Guide to Pharmacology in 2018
 
Sorting bioactive wheat from database chaff: Challenges of discerning correct...
Sorting bioactive wheat from database chaff: Challenges of discerning correct...Sorting bioactive wheat from database chaff: Challenges of discerning correct...
Sorting bioactive wheat from database chaff: Challenges of discerning correct...
 
Sorting bioactive wheat from database chaff
Sorting bioactive wheat from database chaffSorting bioactive wheat from database chaff
Sorting bioactive wheat from database chaff
 
Embase.pdf
Embase.pdfEmbase.pdf
Embase.pdf
 
Talk at Yale University April 26th 2011: Applying Computational Models for To...
Talk at Yale University April 26th 2011: Applying Computational Modelsfor To...Talk at Yale University April 26th 2011: Applying Computational Modelsfor To...
Talk at Yale University April 26th 2011: Applying Computational Models for To...
 
The DDI (Drug-Drug Interaction) Corpus
The DDI (Drug-Drug Interaction) CorpusThe DDI (Drug-Drug Interaction) Corpus
The DDI (Drug-Drug Interaction) Corpus
 
Finland Helsinki Drug Research slides 2011
Finland Helsinki Drug Research slides 2011Finland Helsinki Drug Research slides 2011
Finland Helsinki Drug Research slides 2011
 
Molecular docking
Molecular dockingMolecular docking
Molecular docking
 
Guide to Pharmacology Poster - ELIXIR All Hands 2020
Guide to Pharmacology Poster - ELIXIR All Hands 2020Guide to Pharmacology Poster - ELIXIR All Hands 2020
Guide to Pharmacology Poster - ELIXIR All Hands 2020
 
The Principle of Rational Design of Drug Combination and Personalized Therapy...
The Principle of Rational Design of Drug Combination and Personalized Therapy...The Principle of Rational Design of Drug Combination and Personalized Therapy...
The Principle of Rational Design of Drug Combination and Personalized Therapy...
 

More from Grupo HULAT

Interaccion 2019 lourdes moreno
Interaccion 2019 lourdes morenoInteraccion 2019 lourdes moreno
Interaccion 2019 lourdes moreno
Grupo HULAT
 
Low vision interaccion2018v4
Low vision interaccion2018v4Low vision interaccion2018v4
Low vision interaccion2018v4
Grupo HULAT
 
Exploring language technologies to provide support to WCAG 2.0 and E2R guidel...
Exploring language technologies to provide support to WCAG 2.0 and E2R guidel...Exploring language technologies to provide support to WCAG 2.0 and E2R guidel...
Exploring language technologies to provide support to WCAG 2.0 and E2R guidel...
Grupo HULAT
 
Babelfy: Entity Linking meets Word Sense Disambiguation.
Babelfy: Entity Linking meets Word Sense Disambiguation.Babelfy: Entity Linking meets Word Sense Disambiguation.
Babelfy: Entity Linking meets Word Sense Disambiguation.
Grupo HULAT
 
Integration of Accessibility Requirements in the Design of Multimedia User Ag...
Integration of Accessibility Requirements in the Design of Multimedia User Ag...Integration of Accessibility Requirements in the Design of Multimedia User Ag...
Integration of Accessibility Requirements in the Design of Multimedia User Ag...
Grupo HULAT
 
New Approaches to Interactive Multimedia Content Retrieval from different Sou...
New Approaches to Interactive Multimedia Content Retrieval from different Sou...New Approaches to Interactive Multimedia Content Retrieval from different Sou...
New Approaches to Interactive Multimedia Content Retrieval from different Sou...
Grupo HULAT
 
Presentation "Spanish Resources in Trendminer Project"
Presentation "Spanish Resources in Trendminer Project"Presentation "Spanish Resources in Trendminer Project"
Presentation "Spanish Resources in Trendminer Project"
Grupo HULAT
 
Mujeres, ciencia y tecnología. Encuesta sobre la percepción de las dificultad...
Mujeres, ciencia y tecnología. Encuesta sobre la percepción de las dificultad...Mujeres, ciencia y tecnología. Encuesta sobre la percepción de las dificultad...
Mujeres, ciencia y tecnología. Encuesta sobre la percepción de las dificultad...
Grupo HULAT
 
Lessons from the Drug-Drug Interaction Extraction Task
Lessons from the Drug-Drug Interaction Extraction TaskLessons from the Drug-Drug Interaction Extraction Task
Lessons from the Drug-Drug Interaction Extraction Task
Grupo HULAT
 
BioSEPLN 2010 Workshop on Language Technology applied to biomedical and heal...
BioSEPLN 2010 Workshop on Language Technology applied to biomedical and heal...BioSEPLN 2010 Workshop on Language Technology applied to biomedical and heal...
BioSEPLN 2010 Workshop on Language Technology applied to biomedical and heal...
Grupo HULAT
 
Building a Graph of Names and Contextual Patterns for Named Entity Classifica...
Building a Graph of Names and Contextual Patterns for Named Entity Classifica...Building a Graph of Names and Contextual Patterns for Named Entity Classifica...
Building a Graph of Names and Contextual Patterns for Named Entity Classifica...
Grupo HULAT
 
Accessibility to mobile interfaces for older people
Accessibility to mobile interfaces for older peopleAccessibility to mobile interfaces for older people
Accessibility to mobile interfaces for older people
Grupo HULAT
 
Toward an integration of Web accessibility into testing processes
Toward an integration of Web accessibility into testing processesToward an integration of Web accessibility into testing processes
Toward an integration of Web accessibility into testing processes
Grupo HULAT
 
Revisión de los requisitos de accesibilidad en la interacción del usuario anc...
Revisión de los requisitos de accesibilidad en la interacción del usuario anc...Revisión de los requisitos de accesibilidad en la interacción del usuario anc...
Revisión de los requisitos de accesibilidad en la interacción del usuario anc...
Grupo HULAT
 
Formación y tecnologías en accesibilidad para la Universidad
Formación y tecnologías en accesibilidad para la UniversidadFormación y tecnologías en accesibilidad para la Universidad
Formación y tecnologías en accesibilidad para la Universidad
Grupo HULAT
 
Requisitos de accesibilidad web en los reproductores multimedia
Requisitos de accesibilidad web en los reproductores multimediaRequisitos de accesibilidad web en los reproductores multimedia
Requisitos de accesibilidad web en los reproductores multimedia
Grupo HULAT
 
Integrating HCI in a Web accessibility engineering approach
Integrating HCI in a Web accessibility engineering approachIntegrating HCI in a Web accessibility engineering approach
Integrating HCI in a Web accessibility engineering approach
Grupo HULAT
 
A MDD approach for modelling web accessibility
A MDD approach for modelling web accessibilityA MDD approach for modelling web accessibility
A MDD approach for modelling web accessibility
Grupo HULAT
 
Inclusive Usability Techniques in Requirements Analysis of Accessible Web App...
Inclusive Usability Techniques in Requirements Analysis of Accessible Web App...Inclusive Usability Techniques in Requirements Analysis of Accessible Web App...
Inclusive Usability Techniques in Requirements Analysis of Accessible Web App...
Grupo HULAT
 
Adaptation Rules for Accessible Media Player Interface
Adaptation Rules for Accessible Media Player Interface Adaptation Rules for Accessible Media Player Interface
Adaptation Rules for Accessible Media Player Interface
Grupo HULAT
 

More from Grupo HULAT (20)

Interaccion 2019 lourdes moreno
Interaccion 2019 lourdes morenoInteraccion 2019 lourdes moreno
Interaccion 2019 lourdes moreno
 
Low vision interaccion2018v4
Low vision interaccion2018v4Low vision interaccion2018v4
Low vision interaccion2018v4
 
Exploring language technologies to provide support to WCAG 2.0 and E2R guidel...
Exploring language technologies to provide support to WCAG 2.0 and E2R guidel...Exploring language technologies to provide support to WCAG 2.0 and E2R guidel...
Exploring language technologies to provide support to WCAG 2.0 and E2R guidel...
 
Babelfy: Entity Linking meets Word Sense Disambiguation.
Babelfy: Entity Linking meets Word Sense Disambiguation.Babelfy: Entity Linking meets Word Sense Disambiguation.
Babelfy: Entity Linking meets Word Sense Disambiguation.
 
Integration of Accessibility Requirements in the Design of Multimedia User Ag...
Integration of Accessibility Requirements in the Design of Multimedia User Ag...Integration of Accessibility Requirements in the Design of Multimedia User Ag...
Integration of Accessibility Requirements in the Design of Multimedia User Ag...
 
New Approaches to Interactive Multimedia Content Retrieval from different Sou...
New Approaches to Interactive Multimedia Content Retrieval from different Sou...New Approaches to Interactive Multimedia Content Retrieval from different Sou...
New Approaches to Interactive Multimedia Content Retrieval from different Sou...
 
Presentation "Spanish Resources in Trendminer Project"
Presentation "Spanish Resources in Trendminer Project"Presentation "Spanish Resources in Trendminer Project"
Presentation "Spanish Resources in Trendminer Project"
 
Mujeres, ciencia y tecnología. Encuesta sobre la percepción de las dificultad...
Mujeres, ciencia y tecnología. Encuesta sobre la percepción de las dificultad...Mujeres, ciencia y tecnología. Encuesta sobre la percepción de las dificultad...
Mujeres, ciencia y tecnología. Encuesta sobre la percepción de las dificultad...
 
Lessons from the Drug-Drug Interaction Extraction Task
Lessons from the Drug-Drug Interaction Extraction TaskLessons from the Drug-Drug Interaction Extraction Task
Lessons from the Drug-Drug Interaction Extraction Task
 
BioSEPLN 2010 Workshop on Language Technology applied to biomedical and heal...
BioSEPLN 2010 Workshop on Language Technology applied to biomedical and heal...BioSEPLN 2010 Workshop on Language Technology applied to biomedical and heal...
BioSEPLN 2010 Workshop on Language Technology applied to biomedical and heal...
 
Building a Graph of Names and Contextual Patterns for Named Entity Classifica...
Building a Graph of Names and Contextual Patterns for Named Entity Classifica...Building a Graph of Names and Contextual Patterns for Named Entity Classifica...
Building a Graph of Names and Contextual Patterns for Named Entity Classifica...
 
Accessibility to mobile interfaces for older people
Accessibility to mobile interfaces for older peopleAccessibility to mobile interfaces for older people
Accessibility to mobile interfaces for older people
 
Toward an integration of Web accessibility into testing processes
Toward an integration of Web accessibility into testing processesToward an integration of Web accessibility into testing processes
Toward an integration of Web accessibility into testing processes
 
Revisión de los requisitos de accesibilidad en la interacción del usuario anc...
Revisión de los requisitos de accesibilidad en la interacción del usuario anc...Revisión de los requisitos de accesibilidad en la interacción del usuario anc...
Revisión de los requisitos de accesibilidad en la interacción del usuario anc...
 
Formación y tecnologías en accesibilidad para la Universidad
Formación y tecnologías en accesibilidad para la UniversidadFormación y tecnologías en accesibilidad para la Universidad
Formación y tecnologías en accesibilidad para la Universidad
 
Requisitos de accesibilidad web en los reproductores multimedia
Requisitos de accesibilidad web en los reproductores multimediaRequisitos de accesibilidad web en los reproductores multimedia
Requisitos de accesibilidad web en los reproductores multimedia
 
Integrating HCI in a Web accessibility engineering approach
Integrating HCI in a Web accessibility engineering approachIntegrating HCI in a Web accessibility engineering approach
Integrating HCI in a Web accessibility engineering approach
 
A MDD approach for modelling web accessibility
A MDD approach for modelling web accessibilityA MDD approach for modelling web accessibility
A MDD approach for modelling web accessibility
 
Inclusive Usability Techniques in Requirements Analysis of Accessible Web App...
Inclusive Usability Techniques in Requirements Analysis of Accessible Web App...Inclusive Usability Techniques in Requirements Analysis of Accessible Web App...
Inclusive Usability Techniques in Requirements Analysis of Accessible Web App...
 
Adaptation Rules for Accessible Media Player Interface
Adaptation Rules for Accessible Media Player Interface Adaptation Rules for Accessible Media Player Interface
Adaptation Rules for Accessible Media Player Interface
 

Recently uploaded

Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)
TravisMalana
 
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
ukgaet
 
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
NABLAS株式会社
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP
 
The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...
jerlynmaetalle
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单
ewymefz
 
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
axoqas
 
Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project PresentationPredicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Boston Institute of Analytics
 
Machine learning and optimization techniques for electrical drives.pptx
Machine learning and optimization techniques for electrical drives.pptxMachine learning and optimization techniques for electrical drives.pptx
Machine learning and optimization techniques for electrical drives.pptx
balafet
 
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
vcaxypu
 
Opendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptxOpendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptx
Opendatabay
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
Subhajit Sahu
 
一比一原版(TWU毕业证)西三一大学毕业证成绩单
一比一原版(TWU毕业证)西三一大学毕业证成绩单一比一原版(TWU毕业证)西三一大学毕业证成绩单
一比一原版(TWU毕业证)西三一大学毕业证成绩单
ocavb
 
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
Tiktokethiodaily
 
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
nscud
 
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
slg6lamcq
 
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Subhajit Sahu
 
SOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape ReportSOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape Report
SOCRadar
 
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
slg6lamcq
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghh
ArpitMalhotra16
 

Recently uploaded (20)

Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)Malana- Gimlet Market Analysis (Portfolio 2)
Malana- Gimlet Market Analysis (Portfolio 2)
 
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
一比一原版(UVic毕业证)维多利亚大学毕业证成绩单
 
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
【社内勉強会資料_Octo: An Open-Source Generalist Robot Policy】
 
Criminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdfCriminal IP - Threat Hunting Webinar.pdf
Criminal IP - Threat Hunting Webinar.pdf
 
The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...The affect of service quality and online reviews on customer loyalty in the E...
The affect of service quality and online reviews on customer loyalty in the E...
 
一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单一比一原版(NYU毕业证)纽约大学毕业证成绩单
一比一原版(NYU毕业证)纽约大学毕业证成绩单
 
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
哪里卖(usq毕业证书)南昆士兰大学毕业证研究生文凭证书托福证书原版一模一样
 
Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project PresentationPredicting Product Ad Campaign Performance: A Data Analysis Project Presentation
Predicting Product Ad Campaign Performance: A Data Analysis Project Presentation
 
Machine learning and optimization techniques for electrical drives.pptx
Machine learning and optimization techniques for electrical drives.pptxMachine learning and optimization techniques for electrical drives.pptx
Machine learning and optimization techniques for electrical drives.pptx
 
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
一比一原版(RUG毕业证)格罗宁根大学毕业证成绩单
 
Opendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptxOpendatabay - Open Data Marketplace.pptx
Opendatabay - Open Data Marketplace.pptx
 
Adjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTESAdjusting primitives for graph : SHORT REPORT / NOTES
Adjusting primitives for graph : SHORT REPORT / NOTES
 
一比一原版(TWU毕业证)西三一大学毕业证成绩单
一比一原版(TWU毕业证)西三一大学毕业证成绩单一比一原版(TWU毕业证)西三一大学毕业证成绩单
一比一原版(TWU毕业证)西三一大学毕业证成绩单
 
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
1.Seydhcuxhxyxhccuuxuxyxyxmisolids 2019.pptx
 
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
一比一原版(CBU毕业证)卡普顿大学毕业证成绩单
 
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide毕业证书)阿德莱德大学毕业证如何办理
 
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
Algorithmic optimizations for Dynamic Levelwise PageRank (from STICD) : SHORT...
 
SOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape ReportSOCRadar Germany 2024 Threat Landscape Report
SOCRadar Germany 2024 Threat Landscape Report
 
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
一比一原版(UniSA毕业证书)南澳大学毕业证如何办理
 
standardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghhstandardisation of garbhpala offhgfffghh
standardisation of garbhpala offhgfffghh
 

Combining Syntactic Information and domain-specific Lexical Patterns to Extract Drug-Drug Interactions from Biomedical texts

  • 1. Combining Syntactic Information and domain-specific Lexical Patterns to Extract Drug-Drug Interactions from Biomedical texts Isabel Segura-Bedmar, Paloma Martínez, César de Pablo-Sánchez, CS Department, Universidad Carlos III de Madrid, Spain October 26, 2010 Toronto, Ontorio, Canada DTMBIO'10
  • 2. 2 Outline Introduction I State of the Art Proposal Evaluation Conclusions and Future Work DrugDDI Corpus IE processes for DDI Extraction: DrugDDI prototype
  • 3. 3 What is a Drug-Drug Interaction (DDI)? Introduction
  • 4. 4 Beneficial Introduction Ritonavir + Lopinavir → Effective antiretroviral Nifedipine + propranolol → Antianginal drug
  • 5. 5 DANGER!!! Introduction Aspirin + Heparin → Bleeding Aspirin + Acetazolamide → Death
  • 6. 6  47.8% of adverse eventes are due to drugs, of which 3.5% result from DDI1.  Medication errors kill 7,000 patients per annum in USA2.  High incidence in certain patient groups (3-20%).  Increase the Healthcare costs Things can get complicated... 1. APEAS Estudio sobre la seguridad de los pacientes en Atención primaria de salud. Madrid: Ministerio de Sanidad y Consumo, 2008 2. Kohn et al., 2000. “To Err is Human”. Introduction
  • 7. How do healthcare professionals avoid drug-drug interactions? Introduction
  • 9. 9 How does Information Extraction help? A possible interaction resulting in acute renal failure has been reported in a few subjects when indomethacin, a nonsteroidal anti-inflammatory agent, was given with triamterene. DDI ( INDOMETHACIN, TRIAMTERENE) Introduction
  • 10. 10 Objectives Creation of an annotated corpus of DDI. Introduction Study the main approaches for biomedical RE. Combine the resolution of complex syntactic constructions and a set of lexical patterns defined by a pharmacist in order to extract DDIs.
  • 12. State of the Art Approaches 12 State of the Art Relation  Extraction In biomedicine 1 Linguistic­based  approaches 2 3 Pattern­based  approaches Machine Learning­ based approaches 4 Hybrid approaches
  • 14. 14 Proposal Create an annotated corpus to study the extraction of DDI An Information Extraction (IE) System for DDI Proposal
  • 15. 15 Proposal Create an annotated corpus to study the extraction of DDI An Information Extraction System for DDI Proposal: Corpus DrugDDI
  • 16. Building a corpus for DDI DrugBank HTML To Text Wrapper Corpus TXT Drug Name Recognition MetaMap UMLS: Text analysis String Matching Algorithm 2006AA UMLSKS WHOINN affixes DDI Extraction XML annotated with drugs and other biomedical concepts XML annotated with drugs interactions Proposal: Corpus DrugDDI
  • 17. DrugBank HTML To Text Wrapper Corpus TXT Proposal: Corpus DrugDDI
  • 18. 18 Text Analysis by MetaMap program Corpus TXT XML annotated with shallow syntactic and semantic information from UMLS UMLS MetaMap (MMTx): Text analysis Unified Medical Language System (UMLS) Proposal: Corpus DrugDDI DrugBank
  • 22. 22 UMLS Semantic Information (concepts and semantic types) Proposal: Corpus DrugDDI
  • 23. 23 Example of DDI annotation Proposal: Corpus DrugDDI
  • 24. 24 Corpus DrugDDI Total Avg .  per  doc DDIs 3,160 5.5 Sentences  5,806 10.2 Sentences with at least one DDI 2,044 3.5 Drugs 14,930 25.7 Documents 579 Proposal: Corpus DrugDDI (http://labda.inf.uc3m.es/DrugDDI/)
  • 25. Create an annotated corpus to study the Extraction of DDI Build a Pattern-based method to Extract DDI Proposal: DDI extraction
  • 26. 26 IE System for DDI Corpus TXT Text analysis XML annotated  with shallow  syntactic and  semantic  information Drug Name  Recognition Anaphora  Resolution DDI Extraction + drugs and other  biomedical  concepts  + anaphoras + Drug  interactions Biomedical Resources Proposal: DrugDDI prototype whoole
  • 27. 27 Drug Name Recognition (DrugNer) Corpus TXT + drugs and other  biomedical  concepts  + anaphoras + Drug­Drug  interactions WHOINN affixes UMLS XML annotated  with shallow  syntactic and  semantic  information Proposal: DrugDDI prototype Drug Name  Recognition Anaphora  Resolution DDI Extraction Text analysis
  • 28. 28 Drug Anaphora Resolution Corpus TXT Biomedical Resources Proposal: DrugDDI prototype Drug Name  Recognition Anaphora  Resolution DDI Extraction Text analysis + drugs and other  biomedical  concepts  + anaphoras + Drug­Drug  interactions XML annotated  with shallow  syntactic and  semantic  information
  • 29. 29 Drug-Drug Interaction Extraction Corpus TXT Biomedical Resources Proposal: DrugDDI prototype Drug Name  Recognition Anaphora  Resolution DDI Extraction Text analysis + drugs and other  biomedical  concepts  + anaphoras + Drug­Drug  interactions XML annotated  with shallow  syntactic and  semantic  information
  • 30. 30 Syntactic Information + Lexical Patterns Proposal: DrugDDI prototype XML annotated with  shallow syntactic and  semantic information,  drugs and other  biomedical concepts,  anaphoras Drug­Drug   interactions Detection of  coordinate structures Detection of  appositions Pattern  Matching Clause Splitting Rules for sentence  simplification
  • 32. Allopurinol interacts with anisindione, azathioprine and cyclosporine How does syntactic information help? Detecting coordinate structures Proposal: DrugDDI prototype
  • 33. Allopurinol interacts with anisindione, azathioprine and cyclosporine Detection of Coordinate structures COORD := ([NP|PP|AJD|UNK],)* [NP|PP| ADJ|UNK] CONJ [NP|PP|ADJ|UNK] Allopurinol interact with COORD Detecting coordinate structures Proposal: DrugDDI prototype How does syntactic information help?
  • 34. Allopurinol interacts with anisindione, azathioprine and cyclosporine Detection of Coordinate structures COORD := ([NP|PP|AJD|UNK],)* [NP|PP| ADJ|UNK] CONJ [NP|PP|ADJ|UNK] Allopurinol interacts with COORD Drug Name Recognition DRUG.1 interacts with COORD Detecting coordinate structures Proposal: DrugDDI prototype How does syntactic information help?
  • 35. Allopurinol interacts with anisindione, azathioprine and cyclosporine DDI := <DRUG1|COORD|APPOSITION> INTERACTS WITH <DRUG2|COORD|APPOSITION>. Detection of Coordinate structures Pattern Matching COORD := ([NP|PP|AJD|UNK],)* [NP|PP| ADJ|UNK] CONJ [NP|PP|ADJ|UNK] Allopurinol interacts with COORD Drug Name Recognition DRUG.1 interacts with COORD Detecting coordinate structures Proposal: DrugDDI prototype How does syntactic information help?
  • 36. Allopurinol interacts with anisindione, azathioprine and cyclosporine DDI := <DRUG1|COORD|APPOSITION> INTERACTS WITH <DRUG2|COORD|APPOSITION>. Detection of Coordinate structures Pattern Matching DRUG-DRUG INTERACTION: Drug 1: Allopurinol Drug 2: anisindione COORD := ([NP|PP|AJD|UNK],)* [NP|PP| ADJ|UNK] CONJ [NP|PP|ADJ|UNK] Allopurinol interacts with COORD Drug Name Recognition DRUG.1 interacts with COORD DRUG-DRUG INTERACTION: Drug 1: Allopurinol Drug 2: azathioprine DRUG-DRUG INTERACTION: Drug 1: Allopurinol Drug 2: cyclosporine Detecting coordinate structures Proposal: DrugDDI prototype How does syntactic information help?
  • 37. Catecholamine-depleting drugs, such as reserpine, may have an additive effect when given with beta-blocking agents. DDI := <DRUG1|APPOSITION> (HAVE|INCREASE|...) <EFFECT> WHEN GIVEN WITH <DRUG2|APPOSITION>. Detection of Appositions Pattern Matching DRUG-DRUG INTERACTION: Drug 1: Catecholamine-depleting drugs Drug 2: beta-blocking agents Property|Effect: additive DRUG-DRUG INTERACTION: Drug 1: Reserpine Drug 2: beta-blocking agents Property|Effect: additive APPOSITION may have an additive effect when given with DRUG. APPOSITION := <APPOSITIVE> MARKER <APOSITIVE> How syntactic information helps? Proposal: DrugDDI prototype Detecting appositions
  • 38. Concomitant administration of corticosteroids with Aspirin may increase the risk of gastrointestinal ulceration and may reduce serum salicylate levels. Concomitant administration of corticosteroids with Aspirin may increase the risk of gastrointestinal ulceration Concomitant administration of corticosteroids with Aspirin may reduce serum salicylate levels. PATTERN: ADMINISTRATION OF <DRUG1> WITH <DRUG2> MAY (INCREASE|REDUCE)... Clause splitting Pattern Matching DRUG-DRUG INTERACTION: Drug 1: Corticosteroids Drug 2: Aspirin Action: increase Property|Effect: Gastrointestinal ulceration DRUG-DRUG INTERACTION: Drug 1: Corticosteroids Drug 2: Aspirin Action: reduce Property|Effect: serum salicylate levels Proposal: DrugDDI prototype Detecting clauses How syntactic information helps?
  • 40. 40 1st Baseline Experiment Evaluation Pair of drugs in the same sentence => DDI.
  • 41. 41 2nd Experiment: Lexical Patterns Evaluation XML annotated with  shallow syntactic and  semantic information,  drugs and other  biomedical concepts,  anaphoras Drug­Drug   interactions Pattern  Matching
  • 42. 42 3th Experiment: Coordinate structures and appositions XML annotated with  shallow syntactic and  semantic information,  drugs and other  biomedical concepts,  anaphoras Drug­Drug   interactions Detection of  coordinate structures Detection of  appositions Pattern  Matching Clause Splitting Rules for sentence  simplification Evaluation
  • 43. 43 4th Experiment: Coordinate structures, appositions and clauses XML annotated with  shallow syntactic and  semantic information,  drugs and other  biomedical concepts,  anaphoras Drug­Drug   interactions Detection of  coordinate structures Detection of  appositions Pattern  Matching Clause Splitting Rules for sentence  simplification Evaluation
  • 44. 44 Evaluation Precision Recall F-measure 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 0.11 1 0.19 0.67 0.14 0.23 0.48 0.26 0.34 0.49 0.25 0.33 Baseline Only patterns Coordinatives & Appositions Coordinatives & Appositions & Clauses Experiments: Evaluation
  • 46. Contributions 46 Conclusions First annotated corpus with DDI. First approximation for DDI extraction
  • 47. Future Work 47 Conclusions Treatment of negation and modality. Integrate the drug anaphora resolution in the DDI extraction. Improve the clause splitting process. Handle the mistakes made by MetaMap.
  • 48. Future Work 48 Conclusions Use the SPINDEL [De Pablo-Sánchez et al., 2009] system to acquire new patterns. Evaluate Machine learning techniques. Increase the quality of the DrugDDI corpus.
  • 49. Future Work 49 Conclusions Extract relevant information about each DDI. Improve drug interaction resources. User-oriented evaluation.
  • 50. Drug Drug Interaction detection is a promising application for Text Mining
  • 52. Projects 52 Conclusions This work has been partially supported by the Spanish research projects: MAVIR consortium (S-0505/TIC-0267, www.mavir.net), a network of excellence funded by the Madrid Regional Government. ISSE: Semantic Interoperability in Electronic Healthcare (FIT- 350300-2007-75). BRAVO: Advanced Multimodal and Multilingual Question Answering. (TIN2007-67407-C03-01). MULTIMEDICA.
  • 53. 53 WHO affixes for identifying and classifying drugs Affixes  WHOINN Drug Family  Pattern Drugs ­pristin Antibacterials, pristinamycin derivatives [A­Za­z0­9]*[pristin] Efepristin ­gatran  Antithrombotic agents [A­Za­z0­9]*[gatran] Dabigatran -tinib Antineoplastic agents [A­Za­z0­9]*[tinib] Dasatinib, Sunitinib, Nilotinib -mycin -Antibiotics [A­Za­z0­9]*[mycin] Tanespimycin Proposal: DrugDDI prototype
  • 54. Drug name recognition and classification in biomedical texts (Segura-Bedmar et al., 2008)
  • 55. Score-based approach for Anaphora Resolution in Drug- Drug Interacion Documents (Segura-Bedmar et al., 2009a) NLDB 2009 DrugNerAR: Linguistic Rule- Based Anaphora Resolution for DDI Extraction in pharmacological documents (Segura-Bedmar et al., 2009b To appear in DTMBIO 2009
  • 56. 56 How does Information Extraction help? Triamterene, metformin and amiloride should be administered with care as they might increase dofetilide levels. DDI ( TRIAMTERENE, DOFETILIDE) DDI ( METFORMIN, DOFETILIDE) DDI ( AMILORIDE, DOFETILIDE) Introduction

Editor's Notes

  1. Ok, I am the next speaker. My name is Isabel Segura Bedmar from the University Carlos III of Madrid. I&amp;apos;m going to talk about an approach for the extraction of drug-drug interactions from biomedical texts. This approach combines syntactic information and a set of lexical patterns to extract these interactions from text. Of course, the method is not novel, but it is the problem of extraction drug interactions. Maybe after you have listened to me, you may are interested in working in this novel domain.
  2. Ok, this is the typical outline /autline/. Firstly, I am going to explain /iks&amp;apos;plein/ why the extraction of DDI /didiai/ from texts is important. Secondly, I&amp;apos;m going to talk about the main approaches in biomedical relation extraction, Thirdly, I&amp;apos;m going to describe our hybrid approach and finally, I am going to present the results /&amp;apos;risolts/ and main conclusions.
  3. So, what is a drug-drug interactiong? A DDI occurs /a&amp;apos;curs/ when a drug influences /in&amp;apos;fluensis/ the level or the activity of another drug. In other words /wuerds/, it&amp;apos;s a reaction between two or more drugs taken concurrently.
  4. Some interactions can be beneficial, in fact, it&amp;apos;s very common to combine several drugs in order to obtain more effective drugs. For example, the combination of retrovirals like ritonavir and lopinavir achieves a more potent /po&amp;apos;tnt/ antiretrovial. /Sam interakshons can be benefishol, in fact, it&amp;apos;s very kamon to com-bain sevral drags in order to obtein more iffektive drags. For exampol, the combinesion of re&amp;apos;trovirals like ritonavir and lopinavir achieves a more potent antiretroviral/.
  5. But unfortunatly, many interactions are very dangerous. For example, aspirin and heparin taken concurrently can cause a bleeding. /Bat anfortunatli, meni interakshons are very den&amp;apos;yeras/. For igsam&amp;apos;pol, asprin and heparin teikin cancurrentli can co:s a bli:din/ Or, Aspirin and Acetazolamide can cause the death of the patient. Or, asprin and acetazolamide can co:s the dez of the peishent.
  6. In fact, several studies have shown that drug interactions are a serious problem for the patient safety. In fact, sevral stadis hav shon dat drag interakshons are a sirias problem for the peishent seifti. In addition, drug interactions increase the healthcare costs. In adision, drug interakshons incri:s the helzker costs. Therefore, it&amp;apos;s very important to develop resources for healthcare professionals in order to detect these drug interactions. Derefor, its very important to dive&amp;apos;lop risoursis for helzker professionals in order to ditekt thiis drug interakshons. j
  7. So, hau do helzker proffesionasl avoid /&amp;apos;avoid/ drug-drug interarkshons
  8. There are several resources that contain information about drug-drug interactions (for example, micromedex or drugbank databases /deitabesis/), but unfortunatly, they are not comprehensive, because many interactions are only reported in medical journal or in drug safety reports. Therefore, healthcare professionals have to spend a long time in reading them. /There are sevral risoursis that contein informashon abaut drag-drag interakshons, bat anfortunatli, dei are not compre&amp;apos;jensive, because meni interakshons are only reportid in medical yurnal or riports. Helzker professionals have to spend a long time in ri:din them/
  9. For this reason, we think that Information Extraction can help to improve the early detection of drug interactions and to reduce the time spent by healthcare proffessionals on reading the drug safety reports and medical journals, /for dis ri&amp;apos;son, wi think that informeison extrakson can help to impruv the erli detekshon of drag interakshons and to ridus the taim spent by helzker profesionals on riiding the medical journals and riports/. For example, you can see this sentence “A possible interaction resulting in acute renal failure has been reported in a few subjects when indomethacin, a nonsteroidal anti-inflammatory agent, was given with triamterene” /for igsampol, yu can sii dat dis sentens “a posibol interakshon risalting in akiut rinal feilier has biin riportid in a fiu sabjects when indometazin, a nonsteroidal anti-inflamatori agent, was given with triamteren/ The final goal of our method is to identify the drugs (indomethacin and tramteren) and to detect the interaction between them. /the fainal gol of auer mezod is to identifai de drags (indometazin and tramteren) and to ditect the interakshon bituin dem/
  10. In more detail /di&amp;apos;teil/, the objectives of this work are: First, we must study the main approaches for biomedical relation /rileshon/ extraction. Second, we need to build an annotated /a&amp;apos;noteitid/ corpus to evaluate /ivalueti/ the approach. Third, we are combining the resolution /risolusion/ of complex syntactic constructions /canstrakshons/ and a set of lexical patterns defined /difainid/ by a pharmacist in order to extract drug interactions.
  11. The goal /gol/ of biomedical relation /rileishon/ extraction is to detect /di&amp;apos;tekt/ occurrences /a&amp;apos;kurensis/ of a predefined /pridifainid/ type of relationship between a pair /per/ of given entity types (like genes, proteins or drugs) in text. During the last years /yirs/, many works /wurks/ have addressed /a-drest/ this task, in particular, the extraction of protein interactions, however /hau&amp;apos;var/, no approach has been proposed /propoust/ to solve /solf/ the problem of extracting DDIs in biomedical texts.
  12. Current /ka-rent/ approaches to biomedical relation extraction may be classified in four main categories: Linguistic approaches are based /beist/ on the application of linguistic technology /teknology/. Patterns approaches apply rules to detect the relationships. Approaches that use machine learning techniques /tekniks/. Of course, many works combine these approaches. In general, the approaches show poor results. In fact, the best system for PPI extraction in BioCreative workshop in last year achieve an f-measure of 30%. Few approaches have dealt with the complexity /&amp;apos;campleksity/ of biomedical sentences. However, language structures /strakchurs/ such as appositions /a&amp;apos;posishons/, coordinations and complex sentences are very common in the biomedical literature /&amp;apos;literachur/. In our case, for this first approximation for DDI extraction, we decided to combine shallow parsing and pattern matching.
  13. Ok, Now, I&amp;apos;m goint to describe our proposal. First of all, we built an annotated corpus with DDI to evaluate our method.
  14. First, I&amp;apos;m going to describe the creation of the first corpus annotated with DDI, and then, I&amp;apos;m goint to present our system for DDI extraction.
  15. We are talking about the construction of a corpus for drug interactions and the developtment of a system for drug drug interaction extraction.
  16. For building the corpus, we used the pharmacological database DrugBank that contains information about almost five thousand drugs. For bildin the corpus, wiyus the pharmacological databeis DragBank dat conteins informations about olmost faiv zausand drags.
  17. In particular, for each drug, DrugBank also contains a text document with information about its drug interactions. For example, this text shows interactions for Heparin. In the last paragraph, the sentence: Digitalis, tetracyclines, nicotine, or antihistamines may partially counteract the anticoagulant action of heparin sodium. Contains several interactions with heparin sodium. We have used these text documents to build our corpus. /En particular, for ich drag, DragBank olso conteins a text document with information about its drug interakshons/ For example, this text shous the interakshons for heparin. In the last paragraf, the sentens: Digitalis, tetracyclines, nicotine, or antihistamines mei parshali kaunterakt di anticoagualnt acsion of heparin sodium. Contains sevral interakshons wiz heparin sodium/ Wi haev ju:st thi:s text documents to bild aur corpus.
  18. Then, We used the MetaMap tool for parsing the texts. This tool provides shallow syntactic information and semantic information from the biomedical UMLS ontology. You can see an example:
  19. First, MetaMap splits the text into sentences.
  20. Then, MetaMap makes shallow parsing.
  21. Also, Metamap performs tokenization
  22. Finally, for each phrase, MetaMap tries to look for a concept in the UMLS ontology. For example, for the phrase &amp;apos;Aspirin&amp;apos;. MetaMap found the UMLS concept with the identifier C0004057. Also, MetaMap provides semantic types to classify the phrases, for example, the phrase &amp;apos;Aspirin&amp;apos; was classified by MetaMap as a pharmacological substance and as organic chemical.
  23. Once /guans/ we have collected /kolektid/ and processed the corpus, we annotated the documents with the assistant of a pharmacist For example, in this case, we annotated the three interactions between Aspirin and these three drugs. Each drug interaction is represened in a DDI element that contains attributes for the name of the drugs that interact and its phrase id.
  24. The corpus consists of almost six hundred documents and contains around of fifteen thousands drugs, and three thousand drug interactions. In a future, we would like to work with more pharmacists in order to assess the agreement among /aman/ several annotators /anoteitars/
  25. Ok, I have just described the process of construction of the corpus. And, now, I&amp;apos;m going to explain our hybrid approach for the extraction of drug-drug interactions. .
  26. You can see our system that consits of four main modules. I have just describe the first process for obtaining the syntactic and semantic information by the MetaMap tool. The second process tries ecognizes and classifies the drug names. The third process is an anaphora resolver. But in this presentation, I focuns on the fourth process for the extraction of DDI.
  27. Regarding the drug name recognition, we used the semantic information provided by MetaMap in order to identify drug names.
  28. The third process tries to resolve the pronominal and drug nominal anaphors occuring in the texts by a set of linguistic heuristics.
  29. Now, we are going to explain the most important process to extract DDIs from texts.
  30. The basic idea is to detect linguistic complex structures such as coordinations, appositions and clauses /closis/ becuase they are very common in biomedical texts. The method proposes a set of syntactic patterns to detect the structures and then applies a set of rules for sentence simplification. Finally, relations are extracted from simple sentences by a pattern matching
  31. Despite the richness of natural language expressions, in practice, DDI are often expressed by a limited number of constructions. This fact favors the use of patterns as an excellent method for their extraction. Based on her professional experience and the corpus observation, our pharmacist defined a set of lexical patterns (see Table 6) to capture the various language constructions used to express DDI in pharmacological texts. Moreover, the pharmacist provided a set of synonyms for the verbs that can indicate a possible DDI.
  32. Now, I am going to explain by an example why the resolution of these structures is important. For example, you can see the following sentence:
  33. Our method, first, is able to identify the coordination by this pattern.
  34. In a similar way, our method identifies appositions and applies pattern matching to detect DDIs.
  35. For the clause splitting, we use a set of clues (for example, the use of relative pronouns, subordinators, coordinators, commas) to detect the clause boundaries /baundris/ Once the bondaries /baundris/ have been detected, new simple sentences are generated from these clauses by a set of simplification rules
  36. Now, I&amp;apos;m going to describe the experiments that we have performed.
  37. Our baseline experiment considers every pair of drugs as a DDI. This baseline achives the maximum recall but a low precision.
  38. In our 2nd experiment, we have only applied the lexical pattern on the sentences in the corpus DrugDDI, without performing syntactic processing.
  39. In our 3rd experiment, we first resolve coordinatives and appositions by a set of syntactic patterns, as I have just described, and then, we applied the lexical patterns on the sentences in order to detect the DDIs.
  40. In our last experiment, we also detected the clause boundaries /clos baundris/ by a clause splitting algorithm and split the complex and compound /com-pound/ sentences into simple sentences. Finally, we applied lexical pattern matching /maching/ on these simple sentences.
  41. This graph compares the three experiments. You can see that the baseline achieves a very low precision (only 11%).(the green bars) Llexical patterns achieve the best precision (67%), however, obtain a low recall (14%). (the blue bars) The detection of coordinatives and appositions helps to improve the recall to 26%, but the precision decreases to 48%. (the red bars) Finally, you can see that the clause splitting and sentence simplification do not achieve our second experiment. (the yellow bars) This is mainly due to two reasons: first, our method for clause splitting is too much basic and is not able to detect the boundaries, but on the other hand, many interactions often span several clauses and our lexical patterns are not able to capture them.
  42. So to conclude...
  43. Our main contributions are: We have created the first annotated corpus with drug-drug interactions. and we have developed the first approximation for DDI extraction based on the use of syntactic information and lexical patterns. Also, we have performed several experiments. We can conclude that the resolution of complex linguistic constructions and pattern matching can help to detect DDI, although we know that there is lot of work to do yet.
  44. Future directions include to improve the DrugDDI corpus. Also, we will improve the resolution of the syntactic constructions by the handling of the mistakes made by Metamap. Other important point, is the integration of the drug anaphora resolver in order to extract DDIs that span several sentences.
  45. Of course, we must improve our clause splitting process and the treatment of negation and modality. We will apply a bootstraping method called Spindel to acquire new patterns. Also, we will consider to apply machine learning techniques.
  46. We will also detect relevant information such as the severity, mechanism /mekanisim/, dosage drugs /dosich drags/, time course that will help to improve the quality of drug interaction resources. Also, we think that it is very important to carry out an user-oriented evaluation.
  47. Debo decir que este proyecto se ha desarrollado en el marco de dos proyectos de investigación: el proyecto ISSE sobre interoperabilidad semántica en el dominio de la salud y el proyecto BRAVO. También agradecer al consorcio MAVIR su apoyo durante este trabajo.
  48. And also, we applied a set of affixes to identify and classify drugs that are not detected by MetaMap.
  49. You can see a more detailed /diteld/ description of this drug name recogniton taks in our paper “Drug name recognition and classification in biomedical texts” \
  50. We have developed two different approaches for anaphora resolution. We believe that they are the fisrt works for the pharmacological domain. The first approach uses syntactic and semantic features to score the antecedents. This approach has been published in NLDB conference, held in saarbrucken. The second approach uses a set of linguistic rules (based on the centering theory) in order to find the antecedents. This work has been submitted to the DTMBIO workshop. \textcolor{blue}{\textit{ We have di-vilop two different a-ppro-ches for anaphora ri-so-lusson. We bi-liv that they are the first works for the pharmacological domein. The first approach uses syn-tac-tic and si-man-tic features to score the antecedents. This approch has been published in the NLDB (en-el-di-bi) conference, held in saabrucken, this year.} The second approach ius a set of linguistic ruuls based, on the sente-ring zeo-ri, in order to faind the antecedents}
  51. For this reason, we think that the information extraction can improve the early detection of drug interactions. We are developing a system that provides a more effective access to this information. This is a very simple sentence &amp;apos;Aspirin may decrease the effects of probenecid, sulfinpyrazone and phenylbutazone&amp;apos;. It contains three interactions. So, the goal of our system is to identify the drug names and extract the interactions between them.
  52. DrugBank is an online and free database. You can seach /serch/ any drug, for example, heparin. DragBank isan online and fri databeis. Yu can serch ani drug, for igsampol, heparin, and then, drugbank shows pharmacological and kemical information about this drug.