Home
 

What is PexSPAM

PexSPAM is a Java standalone program that I wrote for protein sequence feature extraction. PexSPAM was originally designed to be a "feature factory" for secondary structure classification problem in integral membrane proteins. PexSPAM extends the SPAM (Ayres et al, 2002) method by incorporating gap and regular expression constraints into mining procedure. The details of the method are described in a COMAD 2005b paper.

Snapshots


The main frame for selecting various parameters for mining sequential patterns.


The output frame that displays all output sequences. Users can define filtering and sorting criteria here.


The tree-browsing frame. The tree contains all the extracted high-support sequences.

Licence

Copyright 2005 - 2008 by The University of Sydney. All rights reserved.

Permission is granted to use PexSPAM© provided no fee is charged and the copyright is honoured. Intended commercial use of the program requires prior permission and may incur a fee. The University of Sydney makes no warranties, either expressed or implied, with respect to PexSPAM© and its suitability for a particular purpose.

Under no circumstances will the authors or the University of Sydney be liable for indirect or consequential damages, including, without limitation, loss of income or use of information.

Download

Publications

  • Ho J, Lukov L, Chawla S (2005) Sequential Pattern Mining with Constraints on Large Protein Databases. In Chakrabarti S, Sudarshan S, Radha Krishnan P (Eds) Proceedings of the 12th International Conference on Management of Data (COMAD 2005b), 89-100. (PDF)

Contact

Ayres J, Flannick J, Gehrke J, Yiu T (2002) Sequential pattern mining using a bitmap representation. KDD 2002, 429-435

© Copyright 2008. Joshua Ho (Last updated on 29 January 2008)