MethTools--a toolbox to visualize and analyze DNA methylation data.

The Bisulfite Genomic Sequencing technique has found wide acceptance for the generation of DNA-methylation maps with single-base resolution. The method is based on the selective deamination of cytosine to uracil (and subsequent conversion to thymine via PCR), whereas 5-methylcytosine residues remain unchanged. Methylation maps are created by the comparison of bisulfite converted sequences with the untreated genomic sequence. 'MethTools' is a collection of software tools that replaces the time-consuming manual comparison process, generates graphical outputs of methylation patterns and methyl-ation density, estimates the systematic error of the experiment and searches for conserved methylated nucleotide patterns. The programs are written in Perl 5 and C, and the source code can be downloaded. All tools run independently but the programs are interfaced. Thus, a script can perform the entire analysis procedure automatically. In addition, a web-based remote analysis service is offered. Both the source code and the remote analysis are available at http://genome.imb-jena.de/methtools/

A parallel neural network simulator on the connection machine CM-5.

We here present a parallel implementation of artificial neural networks on the connection machine CM-5 and compare it with other parallel implementations on SIMD and MIMD architectures. This parallel implementation was developed with the goal of efficiently training large neural networks with huge training pattern sets for applications in molecular biology, in particular the prediction of coding regions in DNA sequences. The implementation uses training pattern parallelism and makes use of the parallel I/O facilities of the CM-5 and its efficient reduction operations available within the control network to achieve a high scalability. The parallel simulator obtains a maximum speed of 149.25 MCUPS for training feedforward networks with backpropagation on a 512 processor CM-5 system without using the CM-5 vector facility. The implementation poses no restriction on the type of network topology and works with different batch training algorithms like BP. Quickprop and Rprop.