EMBER (Expectation Maximization of Binding and Expression pRofiles) employs unsupervised machine learning to elucidate patterns across a series of experiments that measure gene expression under different conditions, and these patterns can then be used to associate transcription factor binding sites with the genes that they regulate. See Maienschein-Cline et al. Bioinformatics 28, 206-213 (2011) for further information.
A version can also be found in the Galaxy Tool Shed

SiteSleuth SVM-PMM
This version of SiteSleuth is a linear support vector machine (SVM) classifier that is trained to distinguish transcription factor binding sites from background sequences based on local chemical and structural features of DNA. See Maienschein-Cline et al. Nucleic Acids Research 40, e175 (2012) for further information.

Enhanced Sampling Toolkit
The Enhanced Sampling Toolkit provides a flexible and extensible toolkit for rapidly prototyping rare event algorithms for use in simulations. The code is written entirely in Python and acts as a wrapper to various well-established molecular dynamics codes.

AFiNeS is a software package for simulations of a coarse-grained model of semiflexible filaments, crosslinkers, and motors that was developed to study cystokeletal materials. The code is written in C++.

Caulobacter crescentus data
Growth and division data for Fig. 2 of Iyer-Biswas et al. Proceedings of the National Academy of Sciences 111, 15912–15917 (2014).