The Release 2 of GeneXproTools 4.0 introduces a powerful Logistic Regression Framework. This new framework builds on the models GeneXproTools generates with its evolutionary algorithms and then applies the canonical logistic regression technique to estimate probabilities for each model score. The Logistic Regression Framework includes tools for Quantile Analysis and Regression, ROC Curve and Cutoff Points analyses, Gains and Lift charts, Logistic Regression and Logistic Fit, and both tabular and stacked Confusion Matrixes.

This version of GeneXproTools can process an unlimited number of samples. In practice this means that you can create models using several dozens of thousands samples thus increasing the level of trust of the models by exposing them to a large set of cases. This is valid for all editions of GeneXproTools and applies to training data, testing data and scoring data. GeneXproTools can easily handle a few million cells of data with much improved data load times and a new more compact file format.

All GeneXproTools 4.0 editions have an expanded number of variables (when compared with APS 3.0) and the new Enterprise Edition supports an unlimited number of variables. This is especially useful for the classification of DNA Microarrays, for example. GeneXproTools produces excellent models in a few seconds or minutes using sets well in excess of 25,000 variables on any modern desktop computer. This new capability provides very interesting possibilities in the realms of data filtering and feature selection.

The Standard Edition of GeneXproTools 4.0 was expanded from 5 independent variables to 16, whereas the Advanced Edition was expanded from 20 to 64 independent variables. Furthermore, a new Academic Enterprise supporting unlimited variables is also available.

Brand new implementation of gene expression programming for Logic Synthesis problems suitable for the optimization and size reduction of complex logic circuits. The code generation includes two specialty languages (VHDL and Verilog) using six different logical systems: All Gates, Not-And-Or gates, Nand gates, Nor gates, Mux System, and Reed-Muller system.

A complete rewrite of the Custom Fitness now opens new possibilities for the implementation of more complex functions. The new implementation removes most of the overhead caused by the data transfer into the scripting environment and introduces new features that allow your fitness functions to influence the size and contents of the models.

There are now in GeneXproTools 4.0 36 built-in fitness functions for Function Finding and Time Series Prediction and 30 for Classification and Logic Synthesis. This enlarged spectrum of fitness functions allows you to judge your models using the measures you are most comfortable working with. Most standard statistical measures are covered and for each of them there is a counterpart with parsimony pressure. The new functions also allow the exploration of different fitness landscapes increasing the chance of finding an excellent model for your problem.

A much larger pool of operations are now accessible to your models including dozens of new functions and an expanded section of decision rules with 2-4 arguments. The new Logic Synthesis algorithm includes all the one and two argument logical functions and dozens of rules with three and four arguments including dozens of interesting Universal Logical Modules. The User Defined Functions and Dynamically Defined Functions also benefited from the new script environment with noticeable increases in performance. The new Functions panel includes random function selection, function search and blanket weight changes.

The Function Selection facility of GeneXproTools 4.0 allows you to experiment with different function sets very quickly either by pressing the Random button or by selecting certain sub-sets of functions.

New algorithm that dynamically adjusts the number of functions to the data environment compensating for very wide datasets. Coupled with finer adjustments at the function level through individual function weighting this feature simplifies the selection of appropriate function sets and provides better defaults for generic model creation.

New optimization mode that reduces the size of a model while improving its accuracy at the same time. The Simplify Method reduces the redundancy in the model to an absolute minimum creating very lean models that are easier to study and less computer intensive in production environments. When used with Logic Synthesis it reduces the number of gates needed for the logic circuit, reducing costs and memory footprint.

Easier data access with direct connections to Excel files and an enhanced column manipulation that is also used for database access.

The new Scoring panel replaces the scoring screen in APS 3.0 and adds easier text data access and improved database and Excel files feature selection. Also new in this panel is the preview window that simplifies small scoring operations and provides feedback on data correctness from inside GeneXproTools.

The models created by GeneXproTools can be translated into as many as 16 programming languages (Ada, C, C++, C#, Fortran, Java, Java Script, Matlab, Pascal, Perl, PHP, Python, Visual Basic, VB.Net, Verilog, and VHDL) including specialty languages like VHDL and Verilog and languages relevant to the bio-informatics field like Perl and Python and the simulation fields like Ada. The model’s code is also improved reducing the amount of code you must add to use the model in production environments.

The new charts provide invaluable information about the model and an insight into the algorithm inner workings. The charts show what variables are being used and which have a heavier weight, the model’s size and its tendency over time and the exciting new curve-fitting chart shows how the models are fitting the data. Also new are charts with the size of each sub-program and the total program size and charts with the sizes and fitness of all the models.

A new and fresh look with improved access to all the areas of GeneXproTools and more navigation and organization options including a fully customizable toolbar. The wizards benefited from simplification and a reduction in the number of steps to create a new run and many new useful features were introduced at the panel level to help with the day-to-day operations.

This version includes brand new target/model comparison plots for Classification problems and new chart types in the Results/Predictions panel for all categories. The Data panel is especially reformatted to improve visualization and the new and more scalable grid includes column selection tools for feature extraction especially useful for DNA microarrays studies.