Transcript Document

Functional Gene Clustering via Gene Annotation
Sentences, MeSH and GO Keywords from
Biomedical Literature
Dr. N. JEYAKUMAR, M.Sc., Ph.D.,
Bioinformatics Centre
School of Biotechnology
Madurai Kamaraj University
Madurai – 625021, INDIA
Purpose & Goals

Extracting gene specific functional ‘keywords’ from biological
literature




Augment extracted keywords with MeSH and GO keywords related
to gene
Compare the accuracy of results with a test data set in various
keyword extraction methods





2
From full-abstracts
Gene specific sentences
Full-abstracts
Gene specific sentences
Gene specific sentences + MeSH keywords
Gene specific sentences+ MeSH and GO keywords
Use the keyword extraction method to cluster the differentially
expressed gene clusters in a microarray experiments
Outline


Two Parts: I, and II
Part I: Text mining and keyword
extraction from literature


Our text mining methodology
Part II: Applications to microarrays

3
?
Functional keyword clustering of microarray
data
Part I: Text Mining
Text Mining:
Introduction and overview



5
Text mining aims to identify non-trivial, implicit, previously
unknown, and potentially useful patterns in text (e.g.
classification system, association rules, hyphothesis etc.)
includes more established research areas such as
 information retrieval (IR),
 natural language processing (NLP),
 information extraction (IE),
 and traditional data mining (DM)
relevant to bioinformatics because of
 explosive growth of biomedical literature (e.g. MEDLINE –
15 million records)
 availability of some information in textual form only, e.g.
clinical records
Text Mining:
System Architecture
MeSH /
GeneOntology
Microarray
Experiment
MedLine
Abstracts
Filtering
MeSH/GO
Your stuff here.
Keyword
Extraction
Gene List
Gene/Protein
Dictionary
Set of
Abstract
Sentence
Your stuff here.
Exctraction
Annotation
Keyword
Your stuff here.
Extraction
Patterns
Visualization
Feature Vector
Your stuff here.
Generation
Clustering
Experimental design of gene clustering with sentences-level, MeSH and GO keywords
6
Text Mining:
Keyword Extraction from Biomedical Literature
Steps to extract sentence-level keywords



Gene - Synonym dictionary – A special gene name synonym name dictionary
was created for human genes using Entrez-Gene
Gene-name normalization - This process replaces all the gene names in the
abstract with its unique canonical identifier (Entrez gene ID) using the genesynonym dictionary specially constructed for this study.
Sentence filtering – using corpus specific the regular expression as the following
example
($gene @{0,6} $action (of|with) @{0,2} $gene)



7
extracts sentences that match the structure shown below the expression. The notational construct ‘ A
 B  ...’ is interpreted as ‘A followed by B followed by ...’.
gene name  0-6 words  action verb  ‘of’ or ‘with’  0-2 words  gene name
Keyword extraction. – Next slide
Text Mining:
Keyword Extraction from biomedical literature
Table 1. An example set of regular expressions as nouns describing
agents and agents, and passive and active verbs
8
Name of Expression
Expression Pattern
Sentence Output
Nouns describing agents
($gene (is)? (the|an|a) @{0,2}$action of @{0,2}
$gene)
IL6, a known mediator of
STAT3 response
Nouns describing actions
($gene @{0,6} $action (of|with) @{0,1} $gene)
Passive verbs
($gene @{0.6} (is|was|be|are|were) @{0,1} $action
$(by|via|through) @{0,3} $gene)
abi5 domains required for
interaction with abi3
Protein kinase c (PKC) has
been shown to be activated
by parathyroid hormone
Active verbs
($gene $sub-action @{0,1} $action @{0,2} $gene)
Insulin mediated inhibition
of
hormone
sensitivity
lipase activity
Text Mining:
Keyword Extraction from Biomedical Literature
Keyword extraction Example

Sentence:


Brill-POS-tagged sentence:


associates, stimulates, transcription activity
Sentence keywords after manual curation:

9
BRCA1/NNP physically/RB associates/VBZ with/IN p53/NN and/CC
stimulates/VBZ its/PRP$ transcriptional/JJ activity/NN ./.
Sentence keywords:


BRCA1 physically associates with p53 and stimulates its transcriptional
activity.
transcription activity
Text Mining:
MeSH Keyword Extraction

MeSH keywords


MeSH keyword extraction


Extracted directly from gene specific abstracts via Perl scripts
MeSH keyword curation


MeSH keywords are subject index terms assigned to each scientific literature by
the Natural Library of Medicine (NLM) for purpose of subject indexing and
searching the journal articles via PubMed.
Using a MeSH keywords stop words dictionary (e.g., human, DNA, animal,
Support U.S Govt etc.).
For example the MeSH keywords associated with a gene ‘FOS’ in our
gene list are ‘oncogene, felypressin, transcription-factor, thermo-
receptors, DNA-binding, antibiosis, inflammatory-response, zinc-fingers,
gene-regulation, and neuronal-plasticity’.
10
Text Mining:
GO Keyword Extraction

GO keywords


GO keyword extraction



Gene Ontology (GO) is a hierarchical organization of gene and gene product
terms from various databases in which concepts at higher levels in the hierarchy
are more general than those further down
Out of the three GO annotation categories we included only molecular
function and biological process and left out cellular component as it is less
important for characterizing genes functions
Further, due to hierarchical nature of GO and multiple inheritance in the GO
structure, we consider with every ancestor up to the level 2 in the GO tree
For example the GO keywords associated with the gene ‘FOS’ in
our gene list are ‘protein-dimerization, DNA binding, RNA
polymerase, transcription factor, DNA methylation, and
inflammatory-response’.
11
Text Mining:
Keyword Representation and Calculation of Numeric Vectors


This process is concerned with computing the numeric
weight, wij, for each gene-keyword pair (gi, tj) (i = 1, 2,
… n and j = 1, 2, … k) to represent the gene’s
characteristics in terms of the associated keywords.
Common techniques for such numeric encoding include

Binary. The presence or absence of a keyword relative to a
gene.

Term frequency. The frequency of occurrence of a keyword
with a gene.

Term frequency / inverse document frequency (TF*IDF).
The relative frequency of occurrence of a keyword with a
gene compared to other genes
12
Text Mining:
TF*IDF Weighting




Most weighting scheme in information retrieval and text
classification method is the TFIDF (term frequency /
inverse document frequency) weighting scheme.
TF(w,d) (Term Frequency) is the number of times word
w occurs in a document d.
DF(w) (Document Frequency) is the number of
documents in which the word w occurs at least once.
The inverse document frequency is calculated as
IDF(w)  log(

13
|D|
DF ( w)
)
Where | D | is total number of documents in the corpus
Text Mining:
Keyword Representation and Calculation of Numeric vectors



In our study, as the keywords are extracted from gene
specific sentences but not from full abstracts, the
number of keywords associated with each gene is small.
Further, the frequency of occurance of most keywords
tended be one.
Therefore, the binary encoding scheme was adopted as
illustrated in Table 2 .
Table 2. Binary representation of gene * keywords
Genes / Terms
g1
g2
...
gn
14
t1
w11 = 0
w12 = 1
t2
w21 = 1
w22 = 1
...
...
w1n = 0
w2n = 0
...
...
...
...
...
tk
wk1 = 1
wk2 = 0
...
wkn = 1
Text Mining:
Gene Clustering



After, our binary coding scheme adopted in this study
consists of numeric row vectors representing genes (via
the associated biological functional keywords), and
numeric column vectors representing annotation terms
(via the associated genes)
Clustering can produce useful and specific information
about the biological characteristics of sets of genes
Clustering: Partition unlabeled examples into disjoint
subsets of clusters, such that:



15
Examples within a cluster are very similar
Examples in different clusters are very different
Discover new categories in an unsupervised manner.
Text Mining:
Test Set and Evaluation

The test set contains 20 genes and 10 abstracts for each
gene, resulting in a total of 200 abstracts in two cancer
categories (Table 3) was used evaluate usefulness of our
keyword extraction method
Table 3. Test set of 20 human genes manually grouped in to two cancer
categories
16
Genes
Category
ADAM23, DKK1, IGF2, LRRC4, L3MBTL, MMP9,
MSH2, PTPNS1, SFMBT1, ZIC1
Brain
Tumor
AMPH, ATM, BRCA1, BRCA2, CHEK2, CDH1, PHB,
TFF1, TSG101, XRCC3
Breast
Cancer
Text Mining:
Evaluation




17
Full abstract keywords (baseline). Extracts gene
annotation terms based on term frequencies *
inverse document frequencies (TF*IDF) within the
entire abstract without regard to sentence structure.
Sentence keywords. Extracts gene specific keywords
based sentence-level processing.
Sentence + MeSH keywords. As in (2) above plus
MeSH terms (see Section MeSH keywords
extraction).
Sentence + MeSH + GO keywords. As in (2) above
plus MeSH terms (see Section MeSH keywords
extraction) and GO terms (see Section GO keyword
extraction
Text Mining:
Evaluation
Results of various keyword extraction methods
Keywords Extraction
Method
18
Precisi
on
Recall
F-measure
(%)
Abstract keywords
(baseline)
0.31
0.24
27.05
Sentence keywords only
0.57
0.38
45.60
Sentence + MeSH
keywords
0.64
0.47
54.19
Sentence + MeSH + GO
keywords
0.78
0.72
74.88
Part II: Applications to Microarrays
Functional keyword Clustering of genes resulting
from microarray experiment
Applications to Microarrays
Data and Analysis


20
As an illustrative example, our keyword extraction methods
was applied to functional interpretation of cluster of genes
that were found differentially expressed in a microarray
experiment investigating the impact of two mitogenic protein
Epidermal growth factor (EGF) and Sphingosine 1-phosphate
(S1P) on glioblastoma cell lines
when compared to the resting state, 19 genes were
significantly differentially expressed as a response to EGF, 35
genes as a response to S1P and 30 genes as a response to
COM, i.e., combined stimuli of S1P and EGF. The three gene
lists are referred to as G(EGF), G(S1P) and G(COM),
respectively (Table 4).
Applications to Microarrays
Data and Analysis
Table 4. List of Differentially Expressed Genes
21
Gene List
Name of Genes
G(EGF)
(19 genes)
HRY, KLF2, ID1, JUN, DUSP6, IMPDH2, GP1BB, PNUTL1, CGI-96, CALD1,
TRIM15, FOS, SPRY4, CLU, SLC5A3, MRPS6, ABCA1, OLFM1,
PHLDA1
G(S1P)
(35 genes)
F3, NR4A1, KLF5, GADD45B, IL8, CITED2, CALD1, IL6, BCL6, LBH,
HRB2, KIAA0992, NFKBIA, TNFAIP3, CCL2, DSCR1, TXNIP, NAB1,
EHD1, GBP1, GLIPR1, MAP2K3, FZD7, RGS3, SOCS5, FOSL2, JAG1,
DOC1, NRG1, BTG1, PDE4C, KIAA1718, KIAA0346, SFRS3, PLAU
G(COM)
(30 genes)
MAFF, DUSP5, EGR3, SERPINE1, ZFP36, DUSP1, LIF, DTR, MYC,
GADD45B, RTP801, ATF3, JUNB, SNARK, WEE1, EGR2, TIEG,
SPRY2, CEBPD, SGK, GEM, NEDD9, LDLR, EGR1, C8FW, UGCG,
MCL1, ZYX, FOSL1, DIPA
Applications to Microarrays
Data and Analysis




22
Using these the three gene lists obtained from the microarray
experiment (Table 6) as query in MEDLINE returned the three
corresponding sets of abstracts A(EGF), A(S1P) and A(COM),
respectively (Table 5).
The abstracts were processed with the keyword extraction
method involving sentence-level augmented with MeSH and GO
keywords
The resulting keywords were encoded in binary weighting
scheme
The resulting representations were clustered using average
linkage hierarchical clustering algorithm.
Applications to Microarrays
Data and Analysis
Table 5. Three sets of abstracts, A(EGF), A(S1P), and A(COM),
retrieved via MEDLINE for this study
23
Gene List
# of Genes in
List
Retrieved Abstract
Set
# of Abstracts in
Set
G(EGF)
19
A(EGF)
28 913
G(S1P)
35
A(S1P)
19 705
G(COM)
30
A(COM)
39 890
Applications to Microarrays
Average Linkage Hierarchical Clustering Algorithm

Use average similarity across all pairs within the
merged cluster to measure the similarity of two
clusters.
sim(ci , c j ) 


24
 
1
sim
(
x
, y)






ci  c j ( ci  c j  1) x( ci c j ) y( ci c j ): y  x
Compromise between single and complete link.
Averaged across all ordered pairs in the merged
cluster instead of unordered pairs between the two
clusters.
TRIM15
GP1BB
SPRY4
MRPS6
IMPDH2
PNUTL1
OLFM1
PHLDA1
DUSP6
ID1
KLF2
CALD1
ABCA1
CLU
FOS
JUN
SLC5A3
HRY
25
antibiosis
osteoblasts
v-fos
fusion
sensation
immuno-reactivity
recombination
thermo-receptors
transition
clustering
intracellular
atherogeneses
glutamine-transport
DNA-methylation
felypressin
relaxation
tumorigenesis
desaturases
shape-regulation
assemble
secretion
biosynthesis
regulation
glycoprotein
androgens
odontogenesis
calmodulin-binding
trans-activators
zinc fingers
mitogenesis
inhibition
embryonic development
cell death
embryogenesis
ion binding
angiogenesis
neural tube defects
transcription factor
Applications to Microarrays
Results
Summary of analysis of EGF cluster
atherogenesis
mitogenesis
assemble
inflammation
angiogenesis
endocytosis
lymphocytes
pathogenesis
immune-response
DNA-dependent
focal-contact
DNA-damage
splicing
G1 phase
extracellular
motility
protein-binding
cos-cells
myosin
RNA localization
dose-response
anticodon
cytotoxicity
parasitophorous
G protein
demyelination
cytolysis
Ca release
locomotion
homeostasis
circulation
phosphorylation
synthesis
repair
protein kinase
endothelialization
organogenesis
cell-adhesion
mutagenesis
Applications to Microarrays
Results
Summary of analysis of S1P cluster
TNFAIP3
KLF5
BCL6
NAB1
BTG1
NFKBIA
NR4A1
SOCS5
CITED2
NRG1
JAG1
PLAU
CCL2
IL8
IL6
GLIPR1
F3
MAP2K3
EHD1
GBP1
DSCR1
HRB2
GADD45B
FOSL2
PDE4C
RGS3
FZD7
SFRS3
TXNIP
DOC1
CALD1
26
27
LDLR
SPRY2
GEM
ZYX
NEDD9
MYC
LIF
SERPINE1
DTR
MCL1
C8FW
MAFF
ATF3
RTP801
EGR1
JUNB
FOSL1
CEBPD
TIEG
EGR2
EGR3
ZFP36
WEE1
SNARK
SGK
GADD45B
DUSP1
DUSP5
UGCG
DIPA
DNA modification
DNA methylation
jun genes
G2-m transition
mRNA splicing
immortality
DNA recombination
microtubule
gene silencing
helix-loop-helix motifs
transcription factor
seizures
genome instability
DNA-binding
zinc fingers
repressor proteins
DNA-dependent
nucleus
transactivation
leucine zippers
transcription
gene expression regulation
oxidative stress
proto-oncogene
cell survival
signal transduction
maturation
endocytosis
differentiation
mitogenesis
mitosis
G2 phase
chemosensitivity
mutagenesis
lymphangiogenesis
ion binding
RNA processing
Applications to Microarrays
Results
Summary of analysis of COM cluster
Conclusions



28
An important topic in microarray data mining is to bind
transcriptionally modulated genes to functional pathways or
how transcriptional modulation can be associated with specific
biological events such as genetic disease phenotype, cell
differentiation etc.
However, the amount of functional annotation available with
each transcriptionaly modulated genes is still a limiting factor
because not all genes are well annotated
Further, Jenssen et al. (2001) earlier compiled a network of
human gene relationships from MEDLINE abstracts. These
compiled relationships were then compared to the gene
expression cluster results. This approach gives a very
interesting result: functionally related genes can show totally
different patterns, and hence belong to different clusters
(Jenssen, et al.: A literature network of human genes for highthroughput analysis of gene expression, Nat.Genet., 28, 21-28,
2001)
Conclusions



29
Our gene functional keyword clustering/ grouping will
enable to select functionally informative genes from
differentially expressed genes for further investigations.
Our evaluation suggests that this approach will provide
more specific and useful information than typical
approaches using abstract-level information. This is
particularly the case when the sentence-level terms are
augmented by MeSH and GO keywords
As the current text mining scenario is on full-text mining
As full-text contains large number of irreverent
sentences compare to abstracts this approach is
more appropriate for full-text study as it filters
irrelevant sentences before clustering.
Acknowledgments




30
Eric G. Bremer, Brain Tumor Research Program, Children’s
Memorial Research Center, Chicago, IL, USA, and James R.
van Brocklyn, Division of Neuropathology, Department of
Pathology, The Ohio State University, Columbus, Ohio, USA
for the microarray data set
Dr. Daniel Berrar, Bioinformatics Research Group, University
of Ulster, UK
Members of Bioinformatics Centre, Madurai Kamaraj
University, India
Dept of Biotechnology, Govt. of India for Bioinformatics
facilities
THANK YOU
31