Extra resources for after the workshop - QCB-Collaboratory/W17.MachineLearning GitHub Wiki

Here are some resources to keep you advancing your studies and find everything you need to apply Machine Learning by yourself in your research.

If you find anything interesting and would like to add to the list below, please leave us a message!

Article published on Forbes, What Is The Future Of Machine Learning In Biology?, by Isabelle Guyon. Here's an interesting quote:

Current practice in biology and medicine, based on statistical testing loosely (or not at all) taking into account the problem of multiple testing, lead to many false discoveries, as notes by Professor Ioannidis. Dealing with big data requires new tools and a deep understanding of modern statistics, as taught by Vapnik, Hastie, Tibshirani, and others. Once properly understood by biologist and doctors, ML will considerably accelerate research in these areas.

Are you a biology major (or a B.A. in a field not related to computer science) and are you struggling with learning more advanced topics related to data analysis and statistics? You are not alone. In Addressing the digital divide in contemporary biology: Lessons from teaching UNIX, by Mangul et al., this issue is discussed and a methodology to teach command-line tools is proposed based on the authors' experience.

The following figure is from Mangul's paper:

• Machine Learning and Its Applications to Biology, by Tarca et al (Plos Comp Biol)

• Machine learning in bioinformatics, by Larranaga et at (Briefings in Bioinformatics)

• Machine learning in cell biology – teaching computers to recognize phenotypes, by Sommer & Gerlich (J Cell Science)

• Machine learning applications in cancer prognosis and prediction, by K. Kourou et al (Comp Struct Biotech J)

• Support Vector Machines and Kernels for Computational Biology, by Ben-Hur (Plos Comp Biol.)

• What's a support vector machine?, by W. Noble

• What are decision trees?, by C. Kingsford and S. Salzberg

• What are artificial neural networks?, by A. Krogh

• How does gene expression clustering work?, by P. D'haeseleer