Advances in high ‐ throughput sequencing technologies led to an enormous increase in the amount of data stored in public databases. The experimental annotation of this data however remains a challenging task, thus widening the sequence ‐ to ‐ annotation gap. Reliable computational prediction methods of protein function could counter this trend; they are becoming invaluable in the analysis and annotation of biological data. In this presentation I will give an introduction to Machine Learning and its applications in Bioinformatics. On the example of protein sub ‐ cellular localization prediction, I will discuss a typical workflow for applying Machine Learning methods and provide code samples.