Exploring Surface-Enhanced Raman Spectroscopy (SERS) Characteristic Peaks Screening Methods for the Rapid Determination of Chlorpyrifos Residues in Rice.

Surface-enhanced Raman spectroscopy (SERS), coupled with characteristic peak screening methods, was developed for analyzing chlorpyrifos (CM) pesticide residues in rice. Au nanoparticles (AuNPs) were prepared as Raman signal enhancement. Magnesium sulfate (MgSO4), primary secondary amine (PSA), and C18 were used to purify the rice extraction. A successive projections algorithm (SPA) was performed to identify the optimal characteristic peaks of CM in rice from full Raman spectroscopy. Support vector machine (SVM) and partial least squares (PLS) were implemented to investigate the quantitative analysis models. The results demonstrated that six Raman peaks such as 671, 834, 1016, 1114, 1436, and 1444 cm-1 were selected by the SPA and SVM models and had better performance using six peaks (only 0.92% of the full spectra variables) with R2p = 0.97, RMSEP = 2.89 and RPD = 4.26, and the experiment time for a sample was accomplished within 10 min. Recovery for five unknown concentration samples was 97.45-103.96%, and T-test results also displayed no obvious differences between the measured value and the predicted value. The study stated that SERS, combined with characteristic peak screening methods, can be applied to rapidly monitor the chlorpyrifos residue in rice.

Cloning southern corn rust resistant gene RppK and its cognate gene AvrRppK from Puccinia polysora.

Broad-spectrum resistance has great values for crop breeding. However, its mechanisms are largely unknown. Here, we report the cloning of a maize NLR gene, RppK, for resistance against southern corn rust (SCR) and its cognate Avr gene, AvrRppK, from Puccinia polysora (the causal pathogen of SCR). The AvrRppK gene has no sequence variation in all examined isolates. It has high expression level during infection and can suppress pattern-triggered immunity (PTI). Further, the introgression of RppK into maize inbred lines and hybrids enhances resistance against multiple isolates of P. polysora, thereby increasing yield in the presence of SCR. Together, we show that RppK is involved in resistance against multiple P. polysora isolates and it can recognize AvrRppK, which is broadly distributed and conserved in P. polysora isolates.

A teosinte-derived allele of a MYB transcription repressor confers multiple disease resistance in maize.

Natural alleles that control multiple disease resistance (MDR) are valuable for crop breeding. However, only one MDR gene has been cloned in maize, and the molecular mechanisms of MDR remain unclear in maize. In this study, through map-based cloning we cloned a teosinte-derived allele of a resistance gene, Mexicana lesion mimic 1 (ZmMM1), which causes a lesion mimic phenotype and confers resistance to northern leaf blight (NLB), gray leaf spot (GLS), and southern corn rust (SCR) in maize. Strong MDR conferred by the teosinte allele is linked with polymorphisms in the 3' untranslated region of ZmMM1 that cause increased accumulation of ZmMM1 protein. ZmMM1 acts as a transcription repressor and negatively regulates the transcription of specific target genes, including ZmMM1-target gene 3 (ZmMT3), which functions as a negative regulator of plant immunity and associated cell death. The successful isolation of the ZmMM1 resistance gene will help not only in developing broad-spectrum and durable disease resistance but also in understanding the molecular mechanisms underlying MDR.

Towards Robust and Accurate Multi-View and Partially-Occluded Face Alignment.

Face alignment acts as an important task in computer vision. Regression-based methods currently dominate the approach to solving this problem, which generally employ a series of mapping functions from the face appearance to iteratively update the face shape hypothesis. One keypoint here is thus how to perform the regression procedure. In this work, we formulate this regression procedure as a sparse coding problem. We learn two relational dictionaries, one for the face appearance and the other one for the face shape, with coupled reconstruction coefficient to capture their underlying relationships. To deploy this model for face alignment, we derive the relational dictionaries in a stage-wised manner to perform close-loop refinement of themselves, i.e., the face appearance dictionary is first learned from the face shape dictionary and then used to update the face shape hypothesis, and the updated face shape dictionary from the shape hypothesis is in return used to refine the face appearance dictionary. To improve the model accuracy, we extend this model hierarchically from the whole face shape to face part shapes, thus both the global and local view variations of a face are captured. To locate facial landmarks under occlusions, we further introduce an occlusion dictionary into the face appearance dictionary to recover face shape from partially occluded face appearance. The occlusion dictionary is learned in a data driven manner from background images to represent a set of elemental occlusion patterns, a sparse combination of which models various practical partial face occlusions. By integrating all these technical innovations, we obtain a robust and accurate approach to locate facial landmarks under different face views and possibly severe occlusions for face images in the wild. Extensive experimental analyses and evaluations on different benchmark datasets, as well as two new datasets built by ourselves, have demonstrated the robustness and accuracy of our proposed model, especially for face images with large view variations and/or severe occlusions.

HCP: A Flexible CNN Framework for Multi-label Image Classification.

Convolutional Neural Network (CNN) has demonstrated promising performance in single-label image classification tasks. However, how CNN best copes with multi-label images still remains an open problem, mainly due to the complex underlying object layouts and insufficient multi-label training images. In this work, we propose a flexible deep CNN infrastructure, called Hypotheses-CNN-Pooling (HCP), where an arbitrary number of object segment hypotheses are taken as the inputs, then a shared CNN is connected with each hypothesis, and finally the CNN output results from different hypotheses are aggregated with max pooling to produce the ultimate multi-label predictions. Some unique characteristics of this flexible deep CNN infrastructure include: 1) no ground-truth bounding box information is required for training; 2) the whole HCP infrastructure is robust to possibly noisy and/or redundant hypotheses; 3) the shared CNN is flexible and can be well pre-trained with a large-scale single-label image dataset, e.g., ImageNet; and 4) it may naturally output multi-label prediction results. Experimental results on Pascal VOC 2007 and VOC 2012 multi-label image datasets well demonstrate the superiority of the proposed HCP infrastructure over other state-of-the-arts. In particular, the mAP reaches 90.5% by HCP only and 93.2% after the fusion with our complementary result in [44] based on hand-crafted features on the VOC 2012 dataset.