BioWIC: Bioinformatics Workflows for Intensive Computation

The increasing flow of genomic data provided by the steadily improvement of new biotechnologies cannot be now efficiently exploited without a systematic in silico analysis. Data need to be filtered, curated, classified, annotated, validated, etc., to be actively used in a discovery process.

Such treatments can be very critical, especially in terms of time. The design of complex pipelines is a tedious and error-prone activity which requires consequent human resources. The execution time of several bioinformatics program can also be a major bottleneck when huge amount of data need to be processed. The BioWIC environment aims to save time in both directions.

• Minimizing the conception time of complex bioinformatics pipelines
• Parallelizing bioinformatics time-consuming algorithms

Both activities are matched by the design of a dedicated workflow environment targeting heterogeneous hardware such as parallel computers (clusters), reconfigurable accelerators (FPGA) or graphic processing units (GPU).

The BioWIC workflow environment provides an efficient way to easily connect standard bioinformatics programs with user data or common genomic banks. In addition, time-consuming programs can be substituted by their parallel version running on different parallel hardware accelerators according to the resources available on the platform.Both activities are matched by the design of a dedicated workflow environment targeting heterogeneous hardware such as parallel computers (clusters), reconfigurable accelerators (FPGA) or graphic processing units (GPU).