Bioinformatics-oriented Hierarchical Evolutionary Learning

BioHEL is an evolutionary learning system designed to handle with large-scale bioinformatic datasets. BioHEL is strongly influenced by the GAssist Pittsburgh LCS, inheriting from it some main mechanisms. However, the main learning paradigm differs from the LCS standards to make this system more suitable for large scale domains. Moreover, a novel meta-representation called AKLR and a CUDA-based evaluation process are used to speed up the evaluation process, making possible for this system to solve very large and complex real life problems in less time.


To learn how to compile, run and configure the BioHEL system read the tutorial. In addition to the installation basics it explains the advanced configuration of the system features useful in tweaking the data mining process towards better or more adequate results.

To improve the generality of the final BioHEL solutions you can use the Rule Post-processing Engine.


You can download the BioHEL C++ source code and compile it either for serial execution (CPU mode) or the parallel execution on GPU (up to 60x speedup, requires CUDA enabled graphics card to run). See the tutorial for details.

Project team


If you use BioHEL, please cite Bacardit2009 (serial version) and Franco2010 (parallel version).

We would also be happy to list your publications on BioHEL on this website, so feel free to contact us.