The Java Machine Learning Library is a set of reference implementations of machine learning algorithms. These algorithms are well documented, both in the source code as on the documentation site. Along with real machine learning algorithms, many supporting algorithms are provided: distance measures, evaluation criteria, data sets for validation purposes, and some sample code.
OpenAlea is a modeling and simulation framework in plant ecophysiology. It is based on the Python programming language and it provides different integration tools (for tasks such as installation and compilation), a visual programming interface, and different dedicated models and libraries.
Powua is a parallel super-computer consisting of many processors that work simultaneously. The Powua client lets users access this high computing power from wherever they are, directly on their computer, through a simple Internet connection. If your preferred software is supported, you can start using it immediately in Powua and speed up all those processes that would otherwise occupy your processor for a long time. Powua subdivides your operation and distributes it to many processors simultaneously.
Pipviewer is a visualizer for multiple alignments of genomic sequences. It highlights conserved regions and allows basic annotations. Its main goal is to find conserved probes for the construction of gene order data sets. Selected regions marked as 'probes' can be exported to fasta format. It can also retrieve gene annotations from the NBCI and display this information along the alignment. Pipviewer is not an aligner. You must compute the alignment with another tool like Clustal or Multi PIP Maker.
This package contains Virtual Hybridization tools. Virtual Hybridization uses sets of short probes to generate datasets for comparative genomics: given a DNA sequence and a set of probes, the typical output will give a sequence of oriented probe hits along the DNA sequence. Other tools are supplied to allow simple manipulations such as format conversion and extraction of permutations.
BioMAJ (BIOlogie Mises A Jour) is a workflow engine dedicated to data synchronization and processing. It automates the update cycle and the supervision of the locally mirrored data repository. The application is generalist, but was applied in the bioinformatics field for biological data bank management. The packaging includes workflow and indexing post-processing scripts for most used biological data banks. Developed in Java and Ant, the application is compatible with various Unix-based systems.
ThermonucleotideBLAST is a software program for searching a target database of nucleic acid sequences using an assay specific query that is based on biochemical assays (i.e. a pair of oligonucleotide sequences representing PCR primers or Padlock probes, a triplet of oligos representing PCR primers and a TaqMan probe, or a single oligo representing a hybridization probe). Unlike existing programs (i.e. BLAST) which use heuristic measures of sequence similarity for identifying matches between a query and target sequence, ThermonucleotideBLAST uses free energy and melting temperature.
The NCBI C++ Toolkit provides portable libraries and applications for assisting genetic science. These include libraries for networking, SQL and BerkeleyDB access, CGI and HTML handling, ASN.1 and XML handling, sequence alignment engines, sequence retrieval engines, BLAST database engines, FLTK and OpenGL graphics toolkits, and basic system utilities.