BIOKDD, 2005

5th Workshop on Data Mining in Bioinformatics

August 21st, 2005
Chicago, IL, USA

in conjunction with

11th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
(SIGKDD'2005)

Proceedings of the 5th ACM SIGKDD Workshop on Data Mining in Bioinformatics edited by Srini Parthasarathy, Wei Wang and Mohammed J. Zaki, (Click Here for PDF)

BIOKDD’05 Program Details

 

8:55 – 9:00    Introduction and Opening Comments  (Srini and Wei)

 

9:00 – 10:00  Session I:  Proteins   (Chair: Wei Wang)

                  

                   Motif Discovery for Proteins Using Subsequence Clustering

                   Hardik A. Sheth and Sun Kim (30 min)

                  

                   Graphical Models of Residue Coupling in Protein Families

                   John Thomas, Naren Ramakrishnan and Chris Bailey-Kellogg (30 min)

 

 

10:00 – 10:30  Coffee Break

 

10:30 – 12:00  Session II: Genomics and Health   (Chair: Srini Parthasarathy)

                                                                                                         

                        Invited Talk: Computational Approaches for Bridging

                                               Genomics  and Health

                                                        Aidong Zhang 

                   Abstract

                   Progress in biomedical research has reached a level that it is now
                   critical to merge the activities of computer scientist, mathematicians,
                   statisticians, and biomedical scientists for the purpose of addressing
                   grand challenges in medical research. In this talk, I will discuss 
                   research issues in biomedical computing which will contribute to
                   mid- and long-term research, development, and experimental

                   deployment of applications supporting the integration and analysis of

                   genomic, proteomic, and clinical data for diseases and treatment effects.
                   I will focus on the currect research trends in genomics and proteomics.
                   These research components and their correlations will help to
                   establish robust links between genomics/proteomics and human health

                   of a sort which can contribute to our knowledge of both diseases and
                   treatment of diseases.                                            (60 min)

 

 

 

 

                   Predicting Cancer Susceptibility from Single Nucleotide Polymorphism

                   Data: A Case Study in Multiple Myeloma 

                   Michael Waddell, David Page and John Shaughnessy Jr. (30 min)

 

12:00 – 1:30   Lunch

 

1:30   - 3:10   Session III: Sequences and Microarrays  (Chair: Chris Bailey-Kellogg)

 

                    Accelerating DNA Sequencing by Hybridization with Noises

                    Chen Chen, Dong Xin and Jiawei Han   (30 min)               

                   

                    On Discovery of Maximal Confident Rules Without Support Pruning in

                    Microarray Data 

                    Tara McIntosh and Sanjay Chawla (30 min)

           

                    A Data Mining Approach to Cell Population De-convolution from

                    Gene Expressions Using Particle Filters

                    Sushmita Roy, Terran Lane, Margaret Werner-Washburne, Chris Allen

                    and Anthony Aragon   (20 min)

 

                    siRNA Offtarget Search: A Hybrid q-gram Based Filtering Approach

                    WenZhong Zhao and Terran Lane (20 min)             

                 

3:10 – 3:30   Coffee Break

  

3:30 – 4:30    Session IV: Protein Interaction Networks and Bio-Entity Recognition (Chair: Chris Ding)

 

                    Analysis of Protein Interaction Networks Using Random Walks

                    Tolga Can, Orhan Camoglu and Ambuj K. Singh (20 min)

 

                    Finding Cliques in Protein Interaction Networks via Transitive Closure

                    of a Weighted Graph

                    Chris Ding, Xiofeng He  and Hanchuan Peng (20 min)

 

                    High Performance Bio-Entitiy Recognition by Combining Results from

                    Multiple Systems

                    Luo Si, Tapas Kungo and Xiangji Huang (20 min)

 

4:30 – 4:45    Program Chairs’ Report and Closing Comments (Srini and Wei)