Here, we introduce a “simple to use” yet efficient and panoptic software to addresses shotgun proteomic data analysis. PatternLab offers easy and unified access to a variety of feature selection (i.e. t-test, SVM-RFE, Golubs Index, etc..) and normalization strategies, each having its own niche.  Additionally, graphing tools are available to aid in high throughput experimental data analysis. The initial contributions from this project comprised to new data analysis tools; the first method addresses experimental designs that comprise three or more replicate readings from each state and is referred to as nSVM (natural support vector machines) because of its roots in evolutionary computing and in statistical learning theory. Our observations suggest that nSVM’s niche comprises projects aiming the selection of a minimum set of proteins for classification problems.  An example would be to aid in selecting a minimal but optimal combination of bona fide markers to develop an early detection kit for a given pathology. The other method, ACFold, addresses experiments with less than three replicates from each state (class) or having few assays acquired by different protocols and can supply a "birds eye" over differential protein expression. These methods were published in BMC Bioinformatics in 2008. A subsequent upgrade to the project was the TFold, simmilar to the ACFold, but with the t-test engine, when 3 or more replicates are present.

We have currently expanded the project offering two new tools. The first one is the Gene Ontology Explorer (GOEx), to aid in the interpretation of shotgun proteomic data. Besides its nifty GUI, it stands out for providing data such as the global protein fold changes for the GO groups.

Another recent upgrade is the Charge Prediction Machine (CPM) . This software predicts the charge states of precursor ions of low resolution ETD MS2 spectra and is useful for speeding up protein identification.