About the Authors

2012 Psychological Science in the Public Interest  
Mining large datasets using machine learning approaches often leads to models that are hard to interpret and not amenable to the generation of hypotheses that can be experimentally tested. Finding 'actionable knowledge' is becoming more important, but also more challenging as datasets grow in size and complexity. We present 'Logic Optimization for Binary Input to Continuous Output' (LOBICO), a computational approach that infers small and easily interpretable logic models of binary input
more » ... that explain a binarized continuous output variable. Although the continuous output variable is binarized prior to optimization, the continuous information is retained to find the optimal logic model. Applying LOBICO to a large cancer cell line panel, we find that logic combinations of multiple mutations are more predictive of drug response than single gene predictors. Importantly, we show that the use of the continuous information leads to robust and more accurate logic models. LOBICO is formulated as an integer programming problem, which enables rapid computation on large datasets. Moreover, LOBICO implements the ability to uncover logic . CC-BY-NC-ND 4.0 International license peer-reviewed) is the author/funder. It is made available under a The copyright holder for this preprint (which was not . http://dx.doi.org/10.1101/036970 doi: bioRxiv preprint first posted online Jan. 15, 2016; models around predefined operating points in terms of sensitivity and specificity. As such, it represents an important step towards practical application of interpretable logic models. Consequently, misclassification of cell lines close to the binarization threshold does not considerably affect the optimization criterion, whereas there is a large penalty for misclassifying cell lines that are extremely sensitive or resistant to the drug. By default, the total weight associated with samples of each class is normalized in order to balance class importance. This is especially important for unbalanced classes as is often the case for the cell line panel, where we observed that, for most drugs, the bulk of cell lines are not . CC-BY-NC-ND 4.0 International license peer-reviewed) is the author/funder. It is made available under a
doi:10.1177/1529100612459637 fatcat:5ljm3kuabnbuzmvdbuwhhgyxqi