Fu Zhu

An investigation about the acetylation of cellulose fibers extracted by acidified sodium chlorite and sodium hydroxide from corn straw was undertaken to examine its potential for use as sorbents in oil spill cleanup. The extent of acetylation was measured by weight percent gain (WPG), which increased with the extent of reaction time and reaction temperature. According to WPG and oil sorption capacity of the acetylated cellulose fibers, the optimum acetylated condition for cellulose fibers was at 120 °C for 7 h. As shown by the adsorption kinetic experiments, more than 90% of the diesel oil was absorbed by the acetylated cellulose fibers within the first 5 min and the adsorption kinetic was consistent with the simulated-second-order model. Characterization of the acetylated and unmodified cellulose fibers was performed by Fourier transform infrared spectroscopy (FT-IR), scanning electron microscopy (SEM), X-ray diffraction (XRD), and contact angle analysis. The results showed that the acetylated cellulose fibers were significantly oleophilic and did not get wet with water. Therefore, the acetylated cellulose fibers provided potential for the better utilization of agricultural residues as natural sorbents in oil cleanup.

Enantioselective analysis of biological thiols, including cysteine (Cys) and glutathione (GSH), is extremely important because of their unique role in bioentities. Here we demonstrated that the end-to-end assemblies of plasmonic gold nanorods with chiral Cys or GSH can be used as a distinctive chiroptical sensor for reliable determination of the absolute configuration of Cys and GSH at the visible light region. The end-to-end assemblies of Au nanorods induced by Cys or GSH exhibit strong circular dichroism (CD) signals in the region of 500-850 nm, which is attributed to chiral current inside Au nanorods induced by the mixed biothiols. The CD intensity of the assemblies shows good linearity with the amount of Cys and GSH. The limit of detection for Cys and GSH using end-to-end assemblies is at micromolar concentrations. In addition, the sensing system exhibits good selectively toward Cys and GSH in the presence of other amino acids.

DNA-binding proteins perform an indispensable function in the maintenance and processing of genetic information and are inefficiently identified by traditional experimental methods due to their huge quantities. On the contrary, machine learning methods as an emerging technique demonstrate satisfactory speed and accuracy when used to study these molecules. This work focuses on extracting four different features from primary and secondary sequence features: Reduced sequence and index-vectors (RS), Pseudo-amino acid components (PseAACS), Position-specific scoring matrix-Auto Cross Covariance Transform (PSSM-ACCT), and Position-specific scoring matrix-Discrete Wavelet Transform (PSSM-DWT). Using the LASSO dimension reduction method, we experiment on the combination of feature submodels to obtain the optimized number of top rank features. These features are respectively input into the training Ensemble subspace discriminant, Ensemble bagged tree and KNN to predict the DNA-binding proteins. Three different datasets, PDB594, PDB1075, and PDB186, are adopted to evaluate the performance of the as-proposed approach in this work. The PDB1075 and PDB594 datasets are adopted for the five-fold cross-validation, and the PDB186 is used for the independent experiment. In the five-fold cross-validation, both the PDB1075 and PDB594 show extremely high accuracy, reaching 86.98% and 88.9% by Ensemble subspace discriminant, respectively. The accuracy of independent experiment by multi-classifiers voting is 83.33%, which suggests that the methodology proposed in this work is capable of predicting DNA-binding proteins effectively.

Deep learning (DL) has widespread applications and has revolutionized many industries. Although automated machine learning (AutoML) can help us away from coding for DL models, the acquisition of lots of high-quality data for model training remains a main bottleneck for many DL projects, simply because it requires high human cost. Despite many works on weak supervision ( i.e. , adding weak labels to seen data) and data augmentation ( i.e. , generating more data based on seen data), automatically acquiring training data, via smartly searching a pool of training data collected from open ML benchmarks and data markets, is not explored. In this demonstration, we demonstrate a new system, automatic data acquisition (AutoData), which automatically searches training data from a heterogeneous data repository and interacts with AutoML. It faces two main challenges. (1) How to search high-quality data from a large repository for a given DL task? (2) How does AutoData interact with AutoML to guide the search? To address these challenges, we propose a reinforcement learning (RL)-based framework in AutoData to guide the iterative search process. AutoData encodes current training data and feedbacks of AutoML, learns a policy to search fresh data, and trains in iterations. We demonstrate with two real-life scenarios, image classification and relational data prediction, showing that AutoData can select high-quality data to improve the model.