Research article
Predictive models for anti-tubercular molecules using machine learning on high-throughput biological screening datasets
-
* Corresponding authors: Abdul UC Jaleel jaleel.uc@gmail.com - Vinod Scaria drvinod@gmail.com
1 GN Ramachandran Knowledge Center for Genome Informatics, CSIR Institute of Genomics and Integrative Biology (CSIR-IGIB), Mall Road, Delhi - 110007, India
2 Department of Cheminformatics, Malabar Christian College, Calicut - 673001, Kerala, India
3 Open Source Drug Discovery Consortium, Council of Scientific and Industrial Research (CSIR), Anusandhan Bhavan, 2 Rafi Marg, Delhi 110001, India
BMC Research Notes 2011, 4:504 doi:10.1186/1756-0500-4-504
Published: 18 November 2011Additional files
Additional file 1:
List of descriptors before and after data processing. Microsoft DOC file containing a table on detailed list of descriptors before and after data processing for all the three datasets
Format: DOC Size: 34KB Download file
This file can be viewed with: Microsoft Word Viewer
Additional file 2:
ROC plot of SMO, J48 and NB. Microsoft DOC file containing ROC graphs of SMO, J48 and NB
Format: DOC Size: 1.3MB Download file
This file can be viewed with: Microsoft Word Viewer
Additional file 3:
Dataset details. Microsoft DOC file containing a table on number of compounds in each dataset and their minority class ratios used in present analysis.
Format: DOC Size: 29KB Download file
This file can be viewed with: Microsoft Word Viewer
Additional file 4:
List of descriptors. Microsoft DOC file enlisting the descriptive account of various descriptors calculated for each dataset using PowerMV [22]
Format: DOC Size: 28KB Download file
This file can be viewed with: Microsoft Word Viewer
Additional file 5:
Comparative account of molecular descriptors. Contribution of each descriptor to molecular properties of all compounds
Format: TIFF Size: 41KB Download file