Motivation: The prediction of drug resistance and the identification of its mechanisms in bacteria such as Mycobacterium tuberculosis, the etiological agent of tuberculosis, is a challenging problem. Modern methods based on testing against a catalogue of previously identified mutations often yield poor predictive performance. On the other hand, machine learning techniques have demonstrated high predictive accuracy, but many of them lack interpretability to aid in identifying specific mutations which lead to resistance. We propose a novel technique, inspired by the group testing problem and Boolean compressed sensing, which yields highly accurate predictions and interpretable results at the same time. Results: We develop a modified version of the Boolean compressed sensing problem for identifying drug resistance, and implement its formulation as an integer linear program. This allows us to characterize the predictive accuracy of the technique and select an appropriate metric to optimize. A simple adaptation of the problem also allows us to quantify the sensitivity-specificity trade-off of our model under different regimes. We test the predictive accuracy of our approach on a variety of commonly used antibiotics in treating tuberculosis and find that it has accuracy comparable to that of standard machine learning models and points to several genes with previously identified association to drug resistance.

MOTIVATION: Constraint-based modeling of metabolic networks helps researchers gain insight into the metabolic processes of many organisms, both prokaryotic and eukaryotic. Minimal cut sets (MCSs) are minimal sets of reactions whose inhibition blocks a target reaction in a metabolic network. Most approaches for finding the MCSs in constrained-based models require, either as an intermediate step or as a byproduct of the calculation, the computation of the set of elementary flux modes (EFMs), a convex basis for the valid flux vectors in the network. Recently, Ballerstein et al. proposed a method for computing the MCSs of a network without first computing its EFMs, by creating a dual network whose EFMs are a superset of the MCSs of the original network. However, their dual network is always larger than the original network and depends on the target reaction. Here we propose the construction of a different dual network, which is typically smaller than the original network and is independent of the target reaction, for the same purpose. We prove the correctness of our approach, minimal coordinated support (MCS2), and describe how it can be modified to compute the few smallest MCSs for a given target reaction. RESULTS: We compare MCS2 to the method of Ballerstein et al. and two other existing methods. We show that MCS2 succeeds in calculating the full set of MCSs in many models where other approaches cannot finish within a reasonable amount of time. Thus, in addition to its theoretical novelty, our approach provides a practical advantage over existing methods. AVAILABILITY AND IMPLEMENTATION: MCS2 is freely available at https://github.com/RezaMash/MCS under the GNU 3.0 license. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Elemental balance, the property of having the same number of each type of atom on both sides of the equation, is a fundamental feature of chemical reactions. In metabolic network models, this property is typically verified on a reaction-by-reaction basis. In this paper we show how violations of elemental balance can be efficiently detected in an entire network, without the need for specifying the chemical formula of each of the metabolites, which enhances a modeler's ability to automatically verify that their model satisfies elemental balance. Our method makes use of duality theory, linear programming, and mixed integer linear programming, and runs efficiently on genome-scale metabolic networks (GSMNs). We detect elemental balance violations in 40 out of 84 metabolic network models in the BiGG database. We also identify a short list of reactions that are candidates for being elementally imbalanced. Out of these candidates, nearly half turn out to be truly imbalanced reactions, and the rest can be seen as witnesses of elemental balance violations elsewhere in the network. The majority of these violations involve a proton imbalance, a known challenge of metabolic network reconstruction. Our approach is efficient, easy to use and powerful. It can be helpful to metabolic network modelers during model verification. Our methods are fully integrated into the MONGOOSE software suite and are available at https://github.com/WGS-TB/MongooseGUI3.