Text Mining and Ontology Applications in Bioinformatics and GIS
 
                            Shamkant B. Navathe
                            College of Computing 
                       Georgia Institute Of Technology


Abstract:

This talk will present some general problem areas and solutions in two fields of applications 
of machine learning: bioinformatics and Geographic Information Systems (GIS). The bioinformatics 
arena is very broad and encompasses many problems such as gene finding in sequences, molecular 
pathway construction, protein structure prediction etc. We will outline our research on finding 
important keywords from the biomedical literature by statistical analysis and some natural 
language analysis. We have also incorporated ontologies such as UMLS (Unified Medical Language 
System) to determine relationships among biological and medical concepts. The primary goal of 
this work has been to interpret the long lists of genes that are derived in microarray experiments 
used to understand and treat diseases. We are able to cluster genes based on their functional 
similarity. We have also used lists of keywords as feature vectors to drive SVM models for a 
classification of literature. In particular, we have dealt with the classification of relevant 
literature for Public health at the CDC (Centers of Disease Control). We will briefly explain 
the discovery of biomarkers for cancer using a technique that combines SVM and gene ontology. 
In the latter part we address integration of geographic information to allow collaboration and 
exchange of data between private and public organization as well as the different levels of 
government.  Ontologies have been shown in research to enhance the conceptual modeling of 
geographic data and allow a more effective and efficient way of integrating multiple sources 
of information.  Different aspects such as fuzziness of the features, different levels of 
accuracy, precision and scale, heterogeneity of data models, generalization of concepts etc. 
may be resolved using ontologies. It still remains a challenge to use ontologies in order to 
automatically resolve the diverse geo-integration issues.  One area that we are investigating 
is to integrate data related to shelters and hospitals with appropriate diverse geo-information 
sources so as to improve emergency management during floods, hurricanes and natural disasters. 
Time permitting the speaker will also mention some recent work related to the modeling of 
circulation within buildings using better conceptual models of space and users and developing 
a constraint based approach to validate building designs.