PMID- 27585838
OWN - NLM
STAT- MEDLINE
DCOM- 20171016
LR  - 20190610
IS  - 1752-0509 (Electronic)
IS  - 1752-0509 (Linking)
VI  - 10 Suppl 3
IP  - Suppl 3
DP  - 2016 Aug 26
TI  - Leveraging syntactic and semantic graph kernels to extract pharmacokinetic drug 
      drug interactions from biomedical literature.
PG  - 67
LID - 10.1186/s12918-016-0311-2 [doi]
LID - 67
AB  - BACKGROUND: Information about drug-drug interactions (DDIs) supported by 
      scientific evidence is crucial for establishing computational knowledge bases for 
      applications like pharmacovigilance. Since new reports of DDIs are rapidly 
      accumulating in the scientific literature, text-mining techniques for automatic 
      DDI extraction are critical. We propose a novel approach for automated 
      pharmacokinetic (PK) DDI detection that incorporates syntactic and semantic 
      information into graph kernels, to address the problem of sparseness associated 
      with syntactic-structural approaches. First, we used a novel all-path graph 
      kernel using shallow semantic representation of sentences. Next, we statistically 
      integrated fine-granular semantic classes into the dependency and shallow 
      semantic graphs. RESULTS: When evaluated on the PK DDI corpus, our approach 
      significantly outperformed the original all-path graph kernel that is based on 
      dependency structure. Our system that combined dependency graph kernel with 
      semantic classes achieved the best F-scores of 81.94 % for in vivo PK DDIs and 
      69.34 % for in vitro PK DDIs, respectively. Further, combining shallow semantic 
      graph kernel with semantic classes achieved the highest precisions of 84.88 % for 
      in vivo PK DDIs and 74.83 % for in vitro PK DDIs, respectively. CONCLUSIONS: We 
      presented a graph kernel based approach to combine syntactic and semantic 
      information for extracting pharmacokinetic DDIs from Biomedical Literature. 
      Experimental results showed that our proposed approach could extract PK DDIs from 
      literature effectively, which significantly enhanced the performance of the 
      original all-path graph kernel based on dependency structure.
FAU - Zhang, Yaoyun
AU  - Zhang Y
AD  - School of Biomedical Informatics, University of Texas Health Science Center at 
      Houston, Houston, TX, 77030, USA.
FAU - Wu, Heng-Yi
AU  - Wu HY
AD  - School of Medicine, Indiana University, Indianapolis, IN, 46202, USA.
FAU - Xu, Jun
AU  - Xu J
AD  - School of Biomedical Informatics, University of Texas Health Science Center at 
      Houston, Houston, TX, 77030, USA.
FAU - Wang, Jingqi
AU  - Wang J
AD  - School of Biomedical Informatics, University of Texas Health Science Center at 
      Houston, Houston, TX, 77030, USA.
FAU - Soysal, Ergin
AU  - Soysal E
AD  - School of Biomedical Informatics, University of Texas Health Science Center at 
      Houston, Houston, TX, 77030, USA.
FAU - Li, Lang
AU  - Li L
AD  - School of Medicine, Indiana University, Indianapolis, IN, 46202, USA. 
      lali@iu.edu.
FAU - Xu, Hua
AU  - Xu H
AD  - School of Biomedical Informatics, University of Texas Health Science Center at 
      Houston, Houston, TX, 77030, USA. hua.xu@uth.tmc.edu.
LA  - eng
GR  - R01 AG025152/AG/NIA NIH HHS/United States
GR  - R01 GM104483/GM/NIGMS NIH HHS/United States
GR  - R01 LM011945/LM/NLM NIH HHS/United States
GR  - UL1 TR001108/TR/NCATS NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
PT  - Research Support, Non-U.S. Gov't
DEP - 20160826
PL  - England
TA  - BMC Syst Biol
JT  - BMC systems biology
JID - 101301827
SB  - IM
MH  - *Biomedical Research
MH  - Computational Biology/*methods
MH  - *Computer Graphics
MH  - Data Mining
MH  - *Drug Interactions
MH  - *Pharmacokinetics
MH  - *Publications
MH  - *Semantics
PMC - PMC5009562
EDAT- 2016/09/03 06:00
MHDA- 2017/10/17 06:00
PMCR- 2016/08/26
CRDT- 2016/09/03 06:00
PHST- 2016/09/03 06:00 [entrez]
PHST- 2016/09/03 06:00 [pubmed]
PHST- 2017/10/17 06:00 [medline]
PHST- 2016/08/26 00:00 [pmc-release]
AID - 10.1186/s12918-016-0311-2 [pii]
AID - 311 [pii]
AID - 10.1186/s12918-016-0311-2 [doi]
PST - epublish
SO  - BMC Syst Biol. 2016 Aug 26;10 Suppl 3(Suppl 3):67. doi: 
      10.1186/s12918-016-0311-2.