DNN-PNN: A parallel deep neural network model to improve anticancer drug sensitivity.

With the rapid development of deep learning techniques and large-scale genomics database, it is of great potential to apply deep learning to the prediction task of anticancer drug sensitivity, which can effectively improve the identification efficiency and accuracy of therapeutic biomarkers. In this study, we propose a parallel deep learning framework DNN-PNN, which integrates rich and heterogeneous information from gene expression and pharmaceutical chemical structure data. With the proposal of DNN-PNN, a new and more effective drug data representation strategy is introduced, that is, the correlation between features is represented by product, which alleviates the limitations of high-dimensional discrete data in deep learning. Furthermore, the framework is optimized to reduce the time complexity of the model. We conducted extensive experiments on the CCLE datasets to compare DNN-PNN with its variant DNN-FM representing the traditional feature correlation model, the component DNN or PNN alone, and the common machine learning models. It is found that DNN-PNN not only has high prediction accuracy, but also has significant advantages in stability and convergence speed.

Filter paper supported nZVI for continuous treatment of simulated dyeing wastewater.

In this study, polyacrylic acid modified filter paper (FP/PAA) was synthesized by in-situ polymerization of acrylic acid, which was used as a matrix to chelate nano-scale zero valent iron (nZVI). The loading content of nZVI in the filter paper reached 24.8%. The fabricated composite FP/PAA/nZVI was characterized by SEM, FT-IR and TGA respectively. Moreover, it was used for the removal of methyl blue and methylene blue as model anionic and cationic dyes. The effect of initial dye concentration on decolorization efficiency was investigated. The results showed that FP/PAA/nZVI enhanced the removal of dye from the simulated dye wastewater and the decolorization efficiency exceeded 95% for the dye solutions lower than 20 mg/L. More importantly, the filter paper supported nZVI realized the continuous treatment of simulated dye wastewater by a simple filtration process. This study hopes to serve as a basis for the application of nZVI in textile wastewater treatment.

Poly(l-lactic acid) bio-composites reinforced by oligo(d-lactic acid) grafted chitosan for simultaneously improved ductility, strength and modulus.

PLA bio-composites reinforced by oligo(d-lactic acid) grafted chitosan has been developed for simultaneously improved ductility, strength and modulus. Brittleness problem greatly limits the applications of PLA, a polymer derived from corn. Various methods have been developed to solve the brittleness problem. Unfortunately, these methods have their limitations, such as sacrifice of strength and modulus of PLA, use of toxic chemicals and high costs. Bio-based elastomers such as chitosan also have poor compatibility with PLA, leading to poor mechanical properties. The hypothesis for this research is that CS-g-oligo(D-LA) particles with good ductility could form strong interfacial interactions with PLLA matrix. Reinforcing effect of CS-g-oligo(D-LA) particles on PLLA matrix was systematically studied. Compatibility and intermolecular interactions between CS-g-oligo(D-LA) particles and PLLA matrix were studied by SEM, DSC and 13C NMR analyses. The reinforcing mechanism was summarized. Due to effective transfer of stress from PLLA matrix to the strong but ductile skeletons of CS-g-oligo(D-LA), ductility, strength and modulus of PLLA bio-composites were substantially improved. This novel reinforcing strategy via formation of strong interactions between enantiomeric lactyl units would enrich the fabrication and exploration of high-performance PLA-based bio-composites.

Degradation and regeneration of feather keratin in NMMO solution.

Chicken feather, a potential source of keratin, is often disposed as waste material. Although some methods, i.e., hydrolysis, reduction, and oxidation, have been developed to isolate keratin for composites, it has been limited due to the rising environmental concerns. In this work, a green solvent N-methylmorpholine N-oxide (NMMO) was used to extract keratin from chicken feather waste. Eighty-nine percent of keratin was extracted using 75% NMMO solution. However, the result from size exclusion HPLC showed that most of the keratin degraded into polypeptide with molecular weight of 2189 and only 25.3% regenerated keratin was obtained with molecular weight of 14,485. Analysis of amino acid composition showed a severe damage to the disulfide bonds in keratin during the extraction procedure. Oxidization had an important effect on the reconstitution of the disulfide bonds, which formed a stable three-dimensional net structure in the regenerated keratins. Besides, Raman spectra, NMR, FT-IR, XRD, and TGA were used to characterize the properties of regenerated keratin and raw chicken feather. In the end, a possible mechanism was proposed based on the results.