Highlights d A selective, orally bioavailable Menin-MLL inhibitor, VTP50469, is developed d Displacement of Menin from chromatin leads to loss of MLL from specific loci d Treatment with VTP50469 leads to suppression of a subset of MLL fusion target genes d Treatment with VTP50469 improves survival in PDX models of MLL-r ALL

No abstract

The identification of a subset of genes having the ability to capture the necessary information to distinguish classes of patients is crucial in bioinformatics applications. Ensemble and bagging methods have been shown to work effectively in the process of gene selection and classification. Testament to that is random forest which combines random decision trees with bagging to improve overall feature selection and classification accuracy. Surprisingly, the adoption of these methods in support vector machines has only recently received attention but mostly on classification not gene selection. This paper introduces an ensemble SVM-Recursive Feature Elimination (ESVM-RFE) for gene selection that follows the concepts of ensemble and bagging used in random forest but adopts the backward elimination strategy which is the rationale of RFE algorithm. The rationale behind this is, building ensemble SVM models using randomly drawn bootstrap samples from the training set, will produce different feature rankings which will be subsequently aggregated as one feature ranking. As a result, the decision for elimination of features is based upon the ranking of multiple SVM models instead of choosing one particular model. Moreover, this approach will address the problem of imbalanced datasets by constructing a nearly balanced bootstrap sample. Our experiments show that ESVM-RFE for gene selection substantially increased the classification performance on five microarray datasets compared to state-of-the-art methods. Experiments on the childhood leukaemia dataset show that an average 9% better accuracy is achieved by ESVM-RFE over SVM-RFE, and 5% over random forest based approach. The selected genes by the ESVM-RFE algorithm were further explored with Singular Value Decomposition (SVD) which reveals significant clusters with the selected data.

This study provided new insights regarding the energy efficiency of hollow fibre forward osmosis modules for seawater desalination; and as a consequence an approach was developed to improve the process performance. Previous analysis overlooked the relationship between the energy efficiency and operating modes of the hollow fibre forward osmosis membrane when the process was scaled-up. In this study, the module length and operating parameters were incorporated in the design of an energy-efficient forward osmosis system. The minimum specific power consumption for seawater desalination was calculated at the thermodynamic limits.Two FO operating modes: (1) draw solution in the lumen and (2) feed solution in the lumen, were evaluated in terms of the desalination energy requirements at a minimum draw solution flow rate. The results revealed that the operating mode of the forward osmosis membrane was important in terms of reducing the desalination energy. In addition, the length of the forward osmosis module was also a significant factor and surprisingly increasing the length of the forward osmosis module was not always advantageous in improving the performance. The study outcomes also showed that seawater desalination by the forward osmosis process was less energy efficient at low and high osmotic draw solution concentration and performed better at 1.2 to 1.4 M sodium chloride draw solution concentrations. The findings of this study provided a platform to the manufacturers and operators of hollow fibre forward 2 osmosis membrane to improve the energy efficiency of the desalination process.