Methodology article
Gene prediction in metagenomic fragments: A large scale machine learning approach
-
* Corresponding author: Katharina J Hoff katharina@gobics.de
1 Abteilung Bioinformatik, Georg-August-Universität Göttingen, Goldschmidtstr. 1, 37077 Göttingen, Germany
2 Abteilung Genomische und Angewandte Mikrobiologie, Georg-August-Universität Göttingen, Goldschmidtstr. 1, 37077 Göttingen, Germany
BMC Bioinformatics 2008, 9:217 doi:10.1186/1471-2105-9-217
Published: 28 April 2008Additional files
Additional file 1:
Tables with training genomes, discriminant weights, and network parameters. The tables list all genomes that were used for training the neural network (1), present the discriminant weights that were learned for all monocodons (2), and give neural network parameters (3, 4).
Format: PDF Size: 65KB Download file
This file can be viewed with: Adobe Acrobat Reader
Additional file 2:
Supplementary figures. The figures show the area under precision recall curve for discriminant validation using different λ values (1), the neural network performance with increasing numbers of nodes (2), the percentage of complete genes within all annotated genes per fragment for different fragment lengths (3), and gene prediction performance on fragments ranging from 5000 to 60000 bp (4).
Format: PDF Size: 58KB Download file
This file can be viewed with: Adobe Acrobat Reader