This article is part of the supplement: Proceedings of the 6th International Conference of the Brazilian Association for Bioinformatics and Computational Biology (X-meeting 2010)
Cutoff Scanning Matrix (CSM): structural classification and function prediction by protein inter-residue distance patterns
1 Department of Biochemistry and Immunology, Universidade Federal de Minas Gerais, Belo Horizonte, 31270-901, Brazil
2 Department of Computer Science, Universidade Federal de Minas Gerais, Belo Horizonte, 31270-901, Brazil
3 Advanced Campus at Itabira, Universidade Federal de Itajubá, Itabira, 37500-903, Brazil
BMC Genomics 2011, 12(Suppl 4):S12 doi:10.1186/1471-2164-12-S4-S12Published: 22 December 2011
Additional file 1:
Additional figures and tables. Figure S1 - Performance metrics across EC classes. Figure S2 - Correlation between precision and minimum number of representatives. Figure S3 - The influence of Cα and Cβ distances in the performance. Figure S4 - Feature vector density distribution for proteins of different SCOP classes. Table S1 - Function prediction performance using naive Bayes for gold-standard dataset. Table S2 - Function prediction performance using random forest for the gold-standard dataset.
Format: PDF Size: 409KB Download file
This file can be viewed with: Adobe Acrobat Reader
Enzyme gold-standard dataset. List of PDB identifiers that compose the enzyme gold-standard dataset and its family and superfamily assignments.
Format: CSV Size: 15KB Download file