Data repositories are exponentially growing and the end is not in sight. Ever more sequencing information, biological data, generated images is becoming available both in public repos as internally with our customers. With this vast amount of information at hand, now is the time to try and learn from this data, to discover patterns driving future Life Science Research.
Machine learning is now being introduced in bioinformatics within the Life Science Research. Computer aided algorithm or mathematical model design, based on a training set, can be applied in order to make predictions or decisions. Multiple underlying algorithms exist and can be implemented dependent of the data at hand: (non)linear or logistic regression, classification as SVM, nearest neighbors or random forest, k-means or spectral clustering, dimensionality reduction, deep learning or neural networks.