Download wls-tamkang1-31may05..

Building Gene Networks
by Information
Extraction, Cleansing, &
Integration
Limsoon Wong
Institute for Infocomm Research
Singapore
Copyright © 2005 by Limsoon Wong
Plan
• Motivation for study of gene networks
• Example Efforts at I2R
– Disease Pathweaver
– Dragon ERG Solution
• Technical Challenges Involved
–
–
–
–
Name entity recognition
Co-reference resolution
Protein interaction extraction
Database cleansing
Copyright © 2005 by Limsoon Wong.
Motivation
Copyright © 2005 by Limsoon Wong
Some Useful Information Sources
• Disease-centric
resources
– OMIM [NCBI OMIM, 2004]
– Gene2Disease [Perez-Iratxeta
et al., Nature, 2002]
– MedGene [Hu et al., J. Proteome
Res., 2003]
• Emphasized direct genedisease relationships
– Provide lists of diseaserelated genes
– Do not provide info on
gene-gene interactions &
their networks
• Related interaction
resources
– KEGG [Kanehisa, NAR, 2000]
• Manually constructed
protein interaction
networks
• Mostly metabolic
pathways and few
disease pathways
– Only 7 disease pathways
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Zhou Zhang, Suisheng Tang, & See-Kiong Ng
Why Gene Network?
• Many common diseases are
– not caused by a genetic variation within a
single gene
• But are influenced by
– complex interactions among multiple genes
– environmental & lifestyle factors
Monogenic  Heterogenic
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Zhuo Zhang, Suisheng Tang, & See-Kiong Ng
Desired Outcome of
Gene Network Study
• Help scientists understand the mechanism of
complex diseases by
– Greatly reducing work load for primary study of
genetic diseases, broaden the scope of molecular
studies
– Easily identifying key players in the gene network,
help in finding potential drug targets
• Scalable framework
– Extend to many genetic diseases
– Include other resources of gene interactions
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Zhou Zhang, Suisheng Tang, & See-Kiong Ng
Some Gene Network
Study Efforts at I2R
• Disease Pathweaver
• Dragon ERG Solution
Copyright © 2005 by Limsoon Wong
Some Gene Network
Study Efforts at I2R
• Disease Pathweaver
• Dragon ERG Solution
Copyright © 2005 by Limsoon Wong
Disease Pathweaver, Zhang et al. APBC 2005
• Automatically
constructing disease
pathways
– Identify core genes
– Mine info on core genes
– Construct interaction
network betw core genes
• Data sources:
– Online literature
– High-thru’put biological
data
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Zhou Zhang, Suisheng Tang, & See-Kiong Ng
Disease Pathweaver:
The Portal
• Portal for human nervous diseases gene
networks
– http://research.i2r.a-star.edu.sg/NSDPath
• Statistics
– 37 Human Nervous System Disorders
– 7 ~ 60 core genes per disease
– 2 ~ 320 core interactions per disease
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Zhou Zhang, Suisheng Tang, & See-Kiong Ng
Disease Pathweaver:
A Tour
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Zhuo Zhang, Suisheng Tang, & See-Kiong Ng
Disease Pathweaver:
A Tour
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Zhuo Zhang, Suisheng Tang, & See-Kiong Ng
Disease Pathweaver:
A Tour
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Zhuo Zhang, Suisheng Tang, & See-Kiong Ng
Disease Pathweaver:
A Tour
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Zhuo Zhang, Suisheng Tang, & See-Kiong Ng
Disease Pathweaver:
DPW vs KEGG on Huntington Disease
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Zhuo Zhang, Suisheng Tang, & See-Kiong Ng
Some Gene Network
Study Efforts at I2R
• Disease Pathweaver
• Dragon ERG Solution
Copyright © 2005 by Limsoon Wong
Estrogen-Responsive Genes
• Why
– Affects human physiology
in many aspects
– Related to many diseases
– Widely used in clinic
• Challenges
– Multiple pathways
– Difficult to predict ERE
– Many estrogen-responsive
genes but only a few are
well-studied
– Difficult to keep up w/
speed of knowledge
accumulation
 Needed
– Tools to predict ERE &
estrogen-responsive genes
– Database of useful info
– Systems to predict impt
regulatory units, associate
gene functions, & generate
global view of gene network
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Suisheng Tang & Vlad Bajic
Dragon ERG Solution
ERE dependent
E2 dependent
E2 independent
ERE Finder
ERG Finder
ERE independent
ERs bind to other TFs
ERGDB
ERG Explorer
Coming
soon!
Membrane receptors
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Suisheng Tang & Vlad Bajic
Dragon ERG Solution:
Dragon ERE Finder,
Bajic et al, NAR, 2003
Predict functional ERE in genomic DNA
One prediction in 13.3k bp
Allow further analysis
http://sdmc.i2r.a-star.edu.sg/ERE-V2/index
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Suisheng Tang & Vlad Bajic
Dragon ERG Solution:
Dragon Estrogen-Responsive
Gene Finder, Tang et al, NAR, 2004a
Only for human genome
Using 117 bp ERE frame
Evaluated by PubMed & microarray data
http://sdmc.i2r.a-star.edu.sg/DRAGON/ERGP1_0
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Suisheng Tang & Vlad Bajic
Dragon ERG Solution:
Dragon Estrogen-Responsive
Genes Database, Tang et al, NAR, 2004b
Contains >1000 genes
Manually curated
Basic gene info
Experimental evidence
Full set of references
ERE sites annotated
http://sdmc.i2r.a-star.edu.sg/promoter/Ergdb-v11
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Suisheng Tang & Vlad Bajic
Dragon ERG Solution:
DEERGF
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Suisheng Tang & Vlad Bajic
Dragon ERG Solution:
Case-Specific TF relation
networks, Pan et al, NAR, 2004
• Analyse abstracts
• Stemming, POS tagging
• Use ANNs, SVM,
discriminant analysis
• Simplified rules for
sentence analysis
• Constraints on the forms
of sentences
• Sensitivity ~75%
• Precision ~82%
• Produce reports & direct
links to PubMed docs, &
graphical presentations
of entity links
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Vlad Bajic
Technical Challenges
Copyright © 2005 by Limsoon Wong
• Named entity recognition
• Co-reference resolution
• Protein interaction extraction
• Data cleansing
Technical Challenges
Copyright © 2005 by Limsoon Wong
• Named entity recognition
• Co-reference resolution
• Protein interaction extraction
• Data cleansing
Bio Entity Name Recognition,
Zhou et al., BioCreAtIvE, 2004
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Jian Su
Bio Entity Name Recognition:
Ensemble Classification Approach
• Features considered
– orthographic, POS,
morphologic, surface word,
trigger words (TW1: receptor,
enhancer, etc. TW2: activation, stimulation,
etc.)
• SVM
– Context of 7 words
– Each word gives 5 features,
plus its position
HMM1
balanced precision
& recall
HMM2
low precision
& high recall
Majority
Voting
SVM
high precision
& low recall
• HMMs
– 3 features used (orthographic,
POS, surface word)
– HMM1 & HMM2 use POS
taggers trained on diff corpora
Copyright © 2005 by Limsoon Wong.
Orthographic features:
• capital letters, numeric characters, & their combinations
Morphologic features:
• prefix, suffix, etc.
Bio Entity Name Recognition:
Performance at BioCreAtIvE 2004
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Zhou et al., BioCreAtIve 2004
Technical Challenges
Copyright © 2005 by Limsoon Wong
• Named entity recognition
• Co-reference resolution
• Protein interaction extraction
• Data cleansing
Co-Reference Resolution,
Yang et al., IJCNLP, 2004
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Yang et al., IJCNLP 2004
Co-Reference Resolution:
Baseline Features Used
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Yang et al., IJCNLP 2004
Co-Reference Resolution:
New Features Used & Performance
Base
Classifier:
C5.0
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Yang et al., IJCNLP 2004
Technical Challenges
Copyright © 2005 by Limsoon Wong
• Named entity recognition
• Co-reference resolution
• Protein interaction extraction
• Data cleansing
Protein Interaction Extraction,
Xiao et al, submitted
• The max entropy model:
• where
– o is the outcome
– h is the feature vector
– Z(h) is normalization
function
– fj are feature functions
– j are feature weights
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Xiao et al., IJCNLP 2004
Protein Interaction Extraction:
Features Used
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Xiao et al.
Protein Interaction Extraction:
Performance on IEPA Corpus
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Xiao et al.
Technical Challenges
Copyright © 2005 by Limsoon Wong
• Named entity recognition
• Co-reference resolution
• Protein interaction extraction
• Data cleansing
Data Cleansing, Koh et al, DBiDB, 2005
• 11 types & 28 subtypes
of data artifacts
– Critical artifacts (vector
contaminated sequences,
duplicates, sequence
structure violations)
– Non-critical artifacts
(misspellings, synonyms)
• > 20,000 seq records in
public contain artifacts
• Identification of these
artifacts are impt for
accurate knowledge
discovery
• Sources of artifacts
– Diverse sources of data
•
•
Repeated submissions of seqs to db’s
Cross-updating of db’s
– Data Annotation
•
•
•
Db’s have diff ways for data
annotation
Data entry errors can be introduced
Different interpretations
– Lack of standardized
nomenclature
•
•
Variations in naming
Synonyms, homonyms, & abbrevn
– Inadequacy of data quality
control mechanisms
•
Systematic approaches to data
cleaning are lacking
Copyright © 2005 by Limsoon Wong. Adapted w/ permission from Judice Koh, Mong Li Lee, & Vladimir Brusic
Data Cleansing:
A Classification of Errors
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
Invalid
values
Spelling errors
Format violation
ATTRIBUTE
Ambiguity
Data Cleansing:
Dubious
sequences
Example Spelling Errors
Vector
contaminated
sequence
Crossannotation
error
RECORD
Annotation
error
Sequence
structure
violation
SINGLE
SOURCE
DATABASE
• Usually typo errors
• Occurs in different fields of the record
• We identified 569 possible misspelled words affecting up to 20,505 nucleotide records in Entrez.
Misspellings
Corrections
Immunoglobin
Immunoglobulin
Cassete
Cassette
tranmembrane
transmembrane
asociated
associated
Sequence
redundancy
Data
Provenance
flaws
MULTIPLE
SOURCE
DATABASE
Erroneous data
transformation
Context of the misspellings
GenBank:AAD26534
nectin-1 [Rattus norvegicus]
TITLE Nectin/PRR: An Immunogloblin-like Cell Adhesion Molecule Recruited
to Cadherin-based Adherens Junctions through Interaction with
Afadin, a PDZ Domain-containing Protein
gi|4590334|gb|AAD26534.1
Patent Database:A76783
Sequence 11 from Patent WO9315210
CDS <1..150
/note="gene cassete encoding intercalating jun-zipper and
linker"
gi|6088638|emb|A76783.1||pat|WO|9315210|11[6088638]
Swiss-Prot:P03385
Env polyprotein precursor
DEFINITION Env polyprotein precursor [Contains: Surface protein (SU) (GP70);
Tranmembrane protein (TM) (p15E); R protein].
gi|119478|sp|P03385|ENV_MLVMO
EMBL:Y18050
E.faecium pbp5 gene
TITLE Modification of penicillin-binding protein 5 asociated with high
level ampicillin resistance in Enterococcus faecium
gi|1143442|emb|X92687.1|EFPBP5G
Incompatible
schema
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
Uninformative sequences
Invalid
values
Undersized sequences
ATTRIBUTE
Ambiguity
Data Cleansing:
Dubious
sequences
Example Meaningless Seqs
Vector
contaminated
sequence
Crossannotation
error
RECORD
Annotation
error
• Among the 5,146,255 protein records queried using Entrez to the major protein or translated nucleotide
databases , 3,327 protein sequences are shorter than four residues (as of Sep, 2004).
• In Nov 2004, the total number of undersized protein sequences increases to 3,350.
• Among 43,026,887 nucleotide records queried using Entrez to major nucleotide databases, 1,448 records
contain sequences shorter than six bases (as of Sep, 2004).
• In Nov 2004, the total number of undersized nucleotide sequences increases to 1,711.
Sequence
structure
violation
Undersized protein sequences in major databases
Sequence
redundancy
Data provenance
flaws
1015
1000
DDBJ
800
EMBL
600
400
200
GenBank
528
383
364
218
171
116
123
3 0
SwissProt
51
2 0
151
42
125
12 23
0
MULTIPLE
SOURCE
DATABASE
1
Erroneous data
transformation
PDB
2
Sequence Length
3
PIR
Number of records
SINGLE
SOURCE
DATABASE
Number of records
1200
Undersized nucleotide sequences in major
databases
233
228
250
200
DDBJ
150
100
50
115108
108
73
69
45
40
6
2
104
81
9
3
77
51
55
67
2
3
Sequence Length
Incompatible
schema
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
4
GenBank
PDB
24
0
1
EMBL
5
Invalid
values
ATTRIBUTE
Overlapping intron/exon
Data Cleansing:
Ambiguity
Example Overlapping Intron/Exon
Dubious
sequences
Vector
contaminated
sequence
Crossannotation
error
RECORD
Annotation
error
Sequence
structure
violation
SINGLE
SOURCE
DATABASE
Sequence
redundancy
Data
Provenance
flaws
MULTIPLE
SOURCE
DATABASE
Erroneous data
transformation
• Syn7 gene of putative polyketide synthase in NCBI TPA record BN000507 has
overlapping intron 5 and exon 6.
• rpb7+ RNA polymerase II subunit in GENBANK record AF055916 has overlapping exon 1
and exon 2.
Incompatible
schema
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
Replication of sequence information
Invalid
values
Different views
Overlapping annotations of the same sequence
ATTRIBUTE
Ambiguity
Dubious
sequences
Data Cleansing:
Example Seqs w/ Identical Info
• Submission of the same sequence to different databases
Vector
contaminated
sequence
Crossannotation
error
RECORD
• Repeated submission of the same sequence to the same database
• Initially submitted by different groups
• Protein sequences may be translated from duplicate nucleotide sequences
Annotation
error
Sequence
structure
violation
SINGLE
SOURCE
DATABASE
Sequence
redundancy
Data provenance
flaws
MULTIPLE
SOURCE
DATABASE
Erroneous data
transformation
Incompatible
schema
http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db
=protein&list_uids=11692005&dopt=GenPept
http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db
=protein&list_uids=11692005&dopt=GenPept
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
Invalid
values
Replication of sequence information
Different views
Overlapping annotations of the same sequence
ATTRIBUTE
Ambiguity
Data Cleansing:
Dubious
sequences
Overlapping Annotations
of the Same Seqs
Vector
contaminated
sequence
Crossannotation
error
RECORD
Annotation
error
Sequence
structure
violation
SINGLE
SOURCE
DATABASE
Sequence
redundancy
Data provenance
flaws
http://www.expasy.org/cgi-bin/niceprot.pl?Q95P69
MULTIPLE
SOURCE
DATABASE
Erroneous data
transformation
http://www.expasy.org/cgi-bin/niceprot.pl?Q9GNG8
Incompatible
schema
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
Trying our hands on a data
cleansing problem...
Spelling errors
Dictionary
lookup
Synonyms
Homonyms/Abbreviations
ATTRIBUTE
Uninformative sequences
Undersized sequences
Integrity
constraints
Format violation
Misuse of fields
Vector
screening
RECORD
Sequence
Structure
Parser
Schema
remapping
Vector contaminated sequences
Features do not correspond with sequence
Sequence structure violation
Concatenated values
Mis-fielded values
SINGLESOURCE
DATABASE
Replication of sequence information
Duplicate
detection
MULTISOURCE
DATABASE
Different views
Overlapping annotations of the same sequence
Fragments
Comparative
analysis
Putative features
Cross-annotation error
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
Association Rule Mining Approach
Select matching criteria
Compute similarity scores from known duplicate pairs
Generate association rules
Detect duplicates using the rules
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
Features
to Match
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
Association Rule Mining
AAG39642 AAG39643 AC0.9 LE1.0 DE1.0 DB1 SP1 RF1.0 PD0 FT1.0 SQ1.0
AAG39642 Q9GNG8 AC0.1 LE1.0 DE0.4 DB0 SP1 RF1.0 PD0 FT0.1 SQ1.0
Similarity scores
of known
duplicate pairs
P00599 PSNJ1W AC0.2 LE1.0 DE0.4 DB0 SP1 RF1.0 PD0 FT1.0 SQ1.0
P01486 NTSREB AC0.0 LE1.0 DE0.3 DB0 SP1 RF1.0 PD0 FT1.0 SQ1.0
O57385 CAA11159 AC0.1 LE1.0 DE0.5 DB0 SP1 RF0.0 PD0 FT0.1 SQ1.0
S32792 P24663 AC0.0 LE1.0 DE0.4 DB0 SP1 RF0.5 PD0 FT1.0 SQ1.0
P45629 S53330 AC0.0 LE1.0 DE0.2 DB0 SP1 RF1.0 PD0 FT1.0 SQ1.0
Association rule mining
Frequent item-set
with support
LE1.0 PD0 SQ1.0 (99.7%)
SP1 PD0 SQ1.0 (97.1%)
SP1 LE1.0 PD0 SQ1.0 (96.8%)
DB0 PD0 SQ1.0 (93.1%)
DB0 LE1.0 PD0 SQ1.0 (92.8%)
DB0 SP1 PD0 SQ1.0 (90.4%)
DB0 SP1 LE1.0 PD0 SQ1.0 (90.1%)
RF1.0 SP1 LE1.0 PD0 SQ1.0 (47.6%)
RF1.0 DB0 LE1.0 PD0 SQ1.0 (44.0%)
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
Dataset
Entrez (GenBank, GenPept,
SwissProt, DDBJ, PIR, PDB)
scorpion AND (venom OR toxin)
serpentes AND venom AND PLA2
Scorpion venom dataset
containing 520 records
Snake PLA2 venom dataset
containing 780 records
Expert annotation
251 duplicate pairs
444 duplicate pairs
695 duplicate pairs are collectively identified.
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
Results
Duplicates detected by association rules
60
49.4
FP% and FN%
50
40
36.3
32.7
30
20
10
6
2.4
1.8
5.7
3.8
0.3
9.4
7.9
7.5
5.2
0.1
0
le
Ru
1
le
Ru
2
le
Ru
3
le
Ru
4
le
Ru
5
le
Ru
6
le
Ru
7
Association rules
FP%
Exam 3 rules w/
highest support
FN% x 1000
Rule 1
S(Seq)=1 ^ N(Seq Length)=1 ^ M(PDB)=0 (99.7%)
Rule 2
S(Seq)=1 ^ M(PDB)=0 ^ M(Species)=1 (97.1%)
Rule 3
S(Seq)=1 ^ N(Seq Length)=1 ^ M(Species)=1 ^ M(PDB)=0 (96.8%)
Rule 4
S(Seq)=1^ M(PDB)=0 ^ M(DB)=0 (93.1%)
Rule 5
S(Seq)=1 ^ M(Seq Length)=1 ^ M(PDB)=0 ^ M(DB)=0 (92.8%)
Rule 6
S(Seq)=1 ^ M(Species)=1 ^ M(PDB)=0 ^ M(DB)=0 (90.4%)
Rule 7
S(Seq)=1 ^ N(Seq Length)=1 ^ M(Species)=1 ^ M(PDB)=0 ^ M(DB)=0 (90.1%)
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
Results
Rule 1 S(Seq)=1 ^ N(Seq Length)=1 ^ M(PDB)=0 (99.7%)
Identical sequences with the same sequence length and not originated from PDB
are 99.7% likely to be duplicates.
Rule 2 S(Seq)=1 ^ M(PDB)=0 ^ M(Species)=1 (97.1%)
Identical sequences with the same sequence length and of the same species are
97.1% likely to be duplicates.
Rule 3 S(Seq)=1 ^ N(Seq Length)=1 ^ M(Species)=1 ^ M(PDB)=0 (96.8%)
Identical sequences with the same sequence length, of the same species and not
originated from PDB are 96.8% likely to be duplicates.
What else do we learn?
Definition of the sequence records do not play
a role in identifying the record duplicates
Copyright © 2005 by Limsoon Wong. Adapted w/permision from Judice Koh, Mong Li Lee, & Vladimir Brusic
References
• Zhang et al., “Toward discovering disease-specific gene networks
from online literature”, APBC, 3:161-169, 2005
• Pan et al., “Dragon TF association miner: A system for exploring
transcription factor associations through text mining”, NAR,
32:W230-W234, 2004
• Tang et al., “Computational method for discovery of estrogenresponsive genes”, NAR, 32:6212-6217, 2004a
• Tang et al., “ERGDB: Estrogen-responsive genes database”,
NAR, 32:D533-D536, 2004b
• Bajic et al., “Dragon ERE finded ver.2: A tool for accurate detection
and analysis of estrogen-response elements in vertebrate
genomes”, NAR, 31:3605-3607, 2003
• Koh et al., “A Classification of Biological Data Artifacts”, DBiBD,
2005
Copyright © 2005 by Limsoon Wong.
References
• Zhou et al., “Recognition of protein and gene names from text
using an ensemble of classifiers and effective abbreviation
resolution”, Proc. BioCreAtIvE Workshop, pp 26-30, 2004
• Yang et al., “Improving Noun Phrase Co-reference Resolution by
Matching Strings”, IJCNLP, 1:226-333, 2004
• Xiao et al., “Protein-protein interaction extraction: A supervised
learning approach”, submitted
Copyright © 2005 by Limsoon Wong.
Acknowledgements
I2R
Data Cleansing:
Judice Koh, Vladimir Brusic,
Mong Li Lee, Asif M. Khan,
Paul T.J.
Tan, Heiny Tan,
Services
& Applications
Kenneth Lee, Wilson Goh,
Songsak Tongchusak,
Kavitha Gopalakrishnan
Infocomm
Security
Knowledge
Discovery
Communications & Devices
Context-Aware
Systems
Media
Media
Processing
Media
Semantics
Human Centric
Media
Pathweaver:
Zhuo Zhang, See-Kiong Ng,
Suisheng Tang, Chris Tan
Info Extraction:
Dragon ERG & TF Miner:
Embedded
Systems
Suisheng Tang, Vlad Bajic,
Radio Systems
Networking
Zuo Li, Pan Hong,
Vidhu Chaudhary, Raja Kangasa
Copyright © 2005 by Limsoon Wong
Guodong Zhou, Jian Su,
ChewLim Tan, Juan Xiao,
Xiaofeng Yang, Chris Tan,
Digital Wireless
Dan Shen, Lightwave
Jie Zhang