The following are a few sample collaborative projects that are currently 
taking place in the center.

(i) Fetal Alcohol Syndrome Diagnosis: As the Imaging Core 
of the NIH funded International Consortium for FASD (CIFASD), we are 
developing novel 3D surface image analysis techniques, using laser 
scanned facial image datasets, for effective early FSA diagnosis and the 
discovery of new FAS features and their biological relationships. This 
research has led to significant initial success in FAS diagnosis. 
Techniques developed here are not readily available elsewhere, and are 
the product of a unique marriage between medical research, clinical 
studies, and innovative 3D imaging technology.

(ii) Trusted Collaborative Computing (TCC) and Health/Medical 
Information System: We are working closely with colleagues from Veteran 
Affairs, IUSM and Regenstrief to build a seamless and trusted Medical 
Information Systems (MIS) to support mission-critical applications. The 
system combines security and reliability to ensure a highly secure and 
dependable collaborative communication environment. Our long term goal 
is developing and implementing a nationwide trusted health information 
system for nationwide deployment.

(iii) The BioSifter Project: BioSifter provides an information filtering 
system that helps biomedical researchers to more 
effectively search the Web for useful information and data such as 
protein and gene sequences. It is based on an agent-society framework 
where the elementary information services such as resource discovery and 
information retrieval, representation, and classification are carried 
out autonomously and collaboratively by independent software units 
(called agents). This project has been funded in the past by NSF, NIH 
Eli Lilly and Company.

(iv) Network Biology: We have developed a comprehensive 
collection of human protein interactome databases of biological sequence 
annotations, experimental functional genomics and proteomics data sets 
from both public and local sources. The large-scale network biology 
methods rely on a plethora of computing services, and the continued 
development of computational solutions such as Bio-GRID, biological data 
integration through semantic webs, and large-scale data mining.

(v) Integrating and Mining Human Disease Microarray and Clinical 
Databases: In collaboration with Eli Lilly and Company, we are 
developing a biological database (DGEM) that combines human disease 
microarray data and clinical data. New data mining and analysis 
techniques are developed for such hybrid bio-databases to identify genes 
that are differentially expressed between diseased and normal tissues, 
find associations between gene expressions and clinical markers, and 
build a gene expression profile-based survival predictor.