Drug combinations has shown great promise in many diseases including cancer, HIV etc. Despite its empirical success, drug combination therapy is far from being theoretically understood. This is because very often efforts to discover synergistic drug combos by high throughput screening are not followed with an in depth investigation of how synergistic combinations work at a molecular level. In our recent paper, we study and try understand in depth how the molecular response of cells to each of two drugs combine when the two drugs are given in combination. Check it out here.

Recently, our paper on a new ensemble learning algorithm has been published in the Journal of Machine Learning Research (JMLR). In the paper, we propose an unsupervised ensemble learning algorithm, which we denote as SUMMA. The aim of ensemble learning is to combine multiple predictions to come up with a more robust predictors, i.e. similar to asking a question to many experts and coming up with the wisdom of the experts. With the availability of new algorithms almost every day and the heterogeneity of the data, it might be a wise approach to base our predictions not on a single algorithm but rather on an ensemble of algorithms. SUMMA achieves this in an unsupervised way. More details can be found here .

Recent decade brought a lot of excitement into molecular biology. With the advancements in measurement technology, we can now measure expression of thousands of genes simultaneously. This enabled us to develop biomarker sets predictive of diseases such as asthma. Although they have important prognostic value, biomarker sets are usually not very interpretable. In this work, we developed a novel algorithm, NeTFactor, that uses a computationally-inferred context-specific gene regulatory network and applies topological, statistical, and optimization methods to identify a minimal set of regulators underlying a biomarker set. The paper can be found here.

We have recently launched a new crowdsourcing challenge: The DREAM Malaria Challenge. The goal of the Malaria DREAM Challenge is to predict artemisinin drug-resistance levels for a test set of malaria parasites by using their in vitro transcription data and a training set consisting of published in vivo and unpublished in vitro transcriptomes. More info about the challenge can be found in the recent correspondence published in nature biotechnology.