Manually validated proteins constitute the reference set of the database that contains over 590 yeast, 920 human, and 1020 mouse entries, and that is used for benchmarking the SVM score.
Subsequently, data preprocessing was performed to eliminate the effect of background noise and to normalize and summarize expression values per each probe set of the database.
These modifications are: Figure 18 New dimensioning and composition of the data sets of the FINO1 database.
Finally, some agents cannot benefit from processing an input set, e.g. if they operate on pre-computed sets of the full database.
Figure 8 Temporal evolution of the H s estimate made by the MLP-based method for the training and validation data sets of the Ekofisk database.
Comparing this database division with the one used originally (see Figure 7a), the following differences are found: Figure 16 New dimensioning and composition of the data sets of the Ekofisk database.
The Interpol package [ 28] was used to encode p2 sequences using all 531 descriptor sets of the AAindex database [ 29] and to normalize the feature length using a linear interpolation [ 30], resulting in 531 numerically encoded datasets.
The total database (35 plots) was systematically divided into two datasets: prediction or fitting set (70% of the database) and validation set (30% of the database).
Set A of the database is composed by 66 organisms (13 Archaea, 50 Bacteria and 3 unicellular Eukaryota) and set B by 4,873 COGs present in their genomes.
