Transcript A rule-based NLP pipeline for OWL

NLP pipeline for protein mutation
knowledgebase construction
Jonas B. Laurila, Nona Naderi, René Witte,
Christopher J.O. Baker
Background
• Knowledge about mutations is crucial for
many applications, e.g. Protein
engineering and Biomedicine.
• Protein mutations are described in
scientific literature.
• The amount of Information grow faster
than manual database curation can
handle.
• Automatic reuse of mutation impact
information from documents needed.
Example excerpts
"The W125F mutant showed only a slight reduction of activity (Vmax) and a
larger increase of Km with 1,2-dibromoethane."
• Mutation
• Directionality of impact
• Protein property
"Haloalkane dehalogenase (DhlA) from Xanthobacter autotrophicus
GJI0 hydrolyses terminally chlorinated and brominated n-alkanes to the
corresponding alcohols."
• Protein name
• Gene name
• Organism name
Mutation impact ontology
NLP framework
Named entity recognition
• Protein-, gene- and organism names
– Gazetteer lists based on SwissProt
– Mappings encoded in the MGDB
• Mutation mentions
– MutationFinder ~700 regular expressions
– normalize into wNm-format
Named entity recognition
Protein Properties
1. Protein functions
– Noun phrases extracted with MuNPEx
– Activity, binding, affinity, specificity as
head nouns
2. Kinetic variables
– Jape rules to extract Km, kcat and Km/kcat in
current implementation
Mutation grounding
Linking mutations positionally correct to target sequence
•
•
1.
2.
3.
Important for reuse of mutation
mentions
Levels of grounding:
mSTRAPviz
Structure annotation
visualization
Mutations extracted from
text visualized on the
protein structure for which
mutation grounding is a
prerequisite.
Protein function grounding
• Mentions of protein functions are
linked to correct Gene Ontology
concepts.
• Previously grounded proteins and
mutations provide us with hints.
• Grounding scored based on string
similarity (later used during impact
extraction)
Relation detection
• Impacts
– Words describing directionality + protein
properties
• Mutants
– Set of mutations giving rise to altered
proteins
• Mutant – Impacts
– The causal relation between mutants and
their impacts
OwlExporter
• Translates GATE Annotations to OWL
instances
• Application independent
• Literature Specifications added
automatically
• Used here to populate our Mutation
impact ontology to create a mutation
knowledgebase
Example query
Retrieve mutations that do not have an impact on
haloalkane dehalogenase activity (also retrieve the
Swissprot identifier of the protein beeing mutated).
Example query
Retrieve mutations on Haloalkane Dehalogenase that
do not impact negatively on the Michaelis Constant.
Evaluation
Mutation grounding performance
What’s next?
• Modularize into a set of web services
• Database (re-)creation
• Reuse in phenotype prediction
algorithms, (SNAP)*
*Bromberg and Rost, 2007
NLP pipeline for protein mutation
knowledgebase construction
Jonas B. Laurila
Acknowledgement
CSAS, UNB, Saint John
[email protected]
This research was funded in part by :
Nona Naderi
• New Brunswcik Innovation Foundation,
New Brunswick, Canada
CSE, Concordia University, Montréal
[email protected]
René Witte
CSE, Concordia University, Montréal
[email protected]
Christopher J.O. Baker
CSAS, UNB, Saint John
[email protected]
• NSERC, Discovery Grant, Canada
• Quebec -New Brunswick University
Co-operation in Advanced Education Research Program, Government of New
Brunswick, Canada