B IOMEDICAL T EXT M INING AND ITS A PPLICATION IN C ANCER R ESEARCH Henry Ikediego 118026.
-
Upload
dorthy-hopkins -
Category
Documents
-
view
213 -
download
0
Transcript of B IOMEDICAL T EXT M INING AND ITS A PPLICATION IN C ANCER R ESEARCH Henry Ikediego 118026.
OVERVIEW
Objectives
Introduction
Biomedical text mining phases and tasks
Data sets and tools for biomedical text mining
Application of biomedical text mining in cancer research
Cancer systems biology research with text mining approach
Future work and challenges
Conclusions
OBJECTIVES
After completing this presentation you should :
Know the phases and tasks in biomedical text mining.
Know the application of biomedical text mining in
cancer research.
The challenges of cancer research in biomedical text
mining
INTRODUCTION
Cancer is a malignant disease that has caused so
many deaths. The immense body and rapid growth of
biomedical text on cancer has led to the appearance
of large number of text mining techniques aimed at
extracting unique knowledge from scientific text.
Biomedical text mining on cancer research is
computationally automatic and high-throughput in
nature.
BIOMEDICAL TEXT MINING PHASES AND TASKS
The goal of text mining is to derive implicit knowledge that
hides in unstructured text and present it in an explicit form.
There are four phases in biomedical text mining:
Information retrieval: this aims at getting desired text on a
certain topic.
Information extraction: this system is used to extract
predefined types of information such as relation extraction.
Knowledge extraction: this system helps to extract
important knowledge from texts.
Hypothesis generation: this system infer unknown
biomedical facts based on texts.
GENERAL TASKS IN BIOMEDICAL TEXT MINING
There are four general tasks of biomedical text mining and they include:
Information retrieval
Named entity recognition and relation
extraction
Knowledge discovery
Hypothesis generation
DATA SETS AND TOOLS FOR BIOMEDICAL TEXT MINING
Examples of data set and tools used for biomedical text mining:
PubMed: this is one of the best known biomedical databases and
it contains more than 20 million citations on biomedical articles.
Textpresso: this uses an ontology, returns searching goals for
classes of biological concept (e.g., gene, cell), classes of
relations of objects (e.g., association, regulation), and related
description (biological process).
GoPubMed: this classifies literature abstracts according to a
Gene ontology and shows the ontology terms that are related to
the query words.
ETC.
APPLICATION OF BIOMEDICAL TEXT MINING IN CANCER RESEARCH
As a complex disease, cancer is related to a
large number of genes and proteins.
Biomedical researchers are interested in
mining cancer-related genes and proteins
from the literature to study cancer
diagnostics, treatment, and prevention.
CANCER SYSTEMS BIOLOGY RESEARCH WITH TEXT MINING APPROACH
Researchers tend to understand complex biological
systems from a systems biology viewpoint. Systems
biology-based networks cab be constructed by
aggregating previously reported associations from the
literature or various databases.
Generally, the conventional flow of text mining based
cancer systems biology research is text acquisition,
bio-entity terms recognition, complex relation
extraction, new knowledge discovery, and hypothesis
generation.
FUTURE WORK AND CHALLENGES
Challenges:
Application of biomedical text mining technologies in
the personalized medicine development.
Complex of cancer molecular mechanisms.
Application of text mining techniques in translational
medicine research.
The integration of the text information at molecule,
cell, tissue, organ. Individual and even population
levels to understand the complex biological systems.
The de-noising and testing of text mining results.
CONCLUSIONS
There are huge body of biomedical text and their rapid
growth makes it impossible for researchers to address
the information manually. Researchers can use
biomedical text mining to discover new knowledge.
Text mining has been used widely in cancer research.
However to fully utilize text mining , it is still
necessary to develop new methods for full text mining
and for highly complex text, as well as platforms for
integrating other biomedical knowledge bases.