In this study, we proposed an ensemble learning method, simultaneously integrating a low-rank matrix completion model and a ridge regression model to predict anticancer drug response on cancer cell lines. The model was applied to two benchmark datasets, including the Cancer Cell Line Encyclopedia (CCLE) and the Genomics of Drug Sensitivity in Cancer (GDSC). As previous studies suggest, the dual-layer integrated cell line-drug network model was one of the best models by far and outperformed most state-of-the-art models. Thus, we performed a head-to-head comparison between the dual-layer integrated cell line-drug network model and our model by a 10-fold crossvalidation study. For the CCLE dataset, our model has a higher Pearson correlation coefficient between predicted and observed drug responses than that of the dual-layer integrated cell line-drug network model in 18 out of 23 drugs. For the GDSC dataset, our model is better in 26 out of 28 drugs in the phosphatidylinositol 3-kinase (PI3K) pathway and 26 out of 30 drugs in the extracellular signal-regulated kinase (ERK) signaling pathway, respectively. Based on the prediction results, we carried out two types of case studies, which further verified the effectiveness of the proposed model on the drug-response prediction. In addition, our model is more biologically interpretable than the compared method, since it explicitly outputs the genes involved in the prediction, which are enriched in functions, like transcription, Src homology 2/3 (SH2/3) domain, cell cycle, ATP binding, and zinc finger.

The NdFeB permanent magnet is a critical material in digital electronics and clean energy industry. Traditional recovery processes based on the solvent extraction technique would consume high energy and large amounts of chemicals as well as resulting in abundant secondary organic wastes. In this work, a green process using deep eutectic solvents (DESs) in the selective leaching technology was designed to recover NdFeB permanent magnets. Nine kinds of DESs composed of guanidine were prepared and screened as the leachants. The guanidine hydrochloride–lactic acid (GUC–LAC) combined DES achieved the highest separation factor (>1300) between neodymium and iron through simple dissolution of their corresponding oxide mixture. The mass concentration of Nd dissolved in the GUC–LAC DES could reach 6.7 × 104 ppm. The viscosity of this type of DES at 50 °C was 36 cP, which was comparable to many common organic solvents. In a practical recovery of roasted magnet powders, the Nd2O3 product with 99% purity was facilely obtained with only one dissolution step, followed by a stripping process with oxalic acid. Even after 3 cycles, the GUC–LAC DES kept the same dissolution property and chemical stability. With such superior performances in selective leaching of rare earth elements from transition metals, the GUC–LAC DES is greatly promising in the rare earth element recovery field.

BackgroundAccurate prediction of anticancer drug responses in cell lines is a crucial step to accomplish the precision medicine in oncology. Although many popular computational models have been proposed towards this non-trivial issue, there is still room for improving the prediction performance by combining multiple types of genome-wide molecular data.ResultsWe first demonstrated an observation on the CCLE and GDSC datasets, i.e., genetically similar cell lines always exhibit higher response correlations to structurally related drugs. Based on this observation we built a cell line-drug complex network model, named CDCN model. It captures different contributions of all available cell line-drug responses through cell line similarities and drug similarities. We executed anticancer drug response prediction on CCLE and GDSC independently. The result is significantly superior to that of some existing studies. More importantly, our model could predict the response of new drug to new cell line with considerable performance. We also divided all possible cell lines into “sensitive” and “resistant” groups by their response values to a given drug, the prediction accuracy, sensitivity, specificity and goodness of fit are also very promising.ConclusionCDCN model is a comprehensive tool to predict anticancer drug responses. Compared with existing methods, it is able to provide more satisfactory prediction results with less computational consumption.Electronic supplementary materialThe online version of this article (10.1186/s12859-019-2608-9) contains supplementary material, which is available to authorized users.

Leveraging metal–organic framework (MOF) to eliminate radioactive contaminants has invariably received much attention, but low preparation efficiency and poor selectivity have still limited its actual application. Herein, it is found that a fourfold interpenetrated cationic MOF (Ag‐TPPE) can be rapidly synthesized by only mixing, stirring, or sonication at room temperature. More impressively, the preparation process can be completed in <1 min. Up to now, this is the first report that cationic MOFs can be obtained by directly mixing the corresponding raw materials at room temperature. In addition to holding the rare merits of structural stability in extremely strong bases (8 m NaOH), Ag‐TPPE can selectively remove TcO4− in the presence of large excess SO42− or NO3−. Based on its ultra‐high selectivity, Ag‐TPPE exhibits exceptional removal rate for TcO4− from simulated Hanford and Savannah River Site waste streams, which refreshes the record of selective sorption of TcO4− at low solid/liquid ratio, overcoming the drawback of overused sorbent in treatment of radioactive waste solution. Such superior sorption capabilities are thoroughly elucidated by the density functional theory calculations on a molecular level, clearly disclosing that TcO4− can enter into the framework through breathing effect and is trapped in the large cavity through dense hydrogen bonds.