Each dataset that was created using a different target labeling protocol or different batch of MTRC was processed separately with RMA.
This protocol was successful but cannot be applied to the numerous Affymetrix (3'IVT) expression arrays, because these arrays are constructed with probes of the opposite strand to the Whole-Transcript Expression arrays, thus they use a different target labeling procedure altogether.
The Pre-diagnosis model found only about a third of actual target class observations, but it was correct most of the time when it did predict a target class label.
The same dataset was also imported into RapidMiner software (RapidMiner 5.0.001, Rapid-I GmbH, Dortmund, Germany) and the type of metal transporter (categorized as hyperaccumulator or tolerant) was set as a target or label attribute.
Manual labeling: A target detector was trained on a set of target labeled samples.
An edge was drawn to link a compound node (labeled by the PubChem compound identifier: CID) and a target node (labeled by the NCBI protein identifier: GI) if the compound is active against the target.
We performed complementary DNA synthesis and labeling and array hybridization by following the Affymetrix user's manual with a one-cycle target labeling and control reagent kit (Affymetrix, Santa Clara, CA, USA) with 0.4 μg of mRNA as the template material.
Double-stranded cDNA and biotin-labeled cRNA were synthesized from 1 to 5 µg of total RNA using a two-cycle target labeling kit [36].
