Deep learning is a promising technology to accurately select individuals with high phenotypic values based on genotypic data. Genomic selection (GS) is a promising breeding strategy by which the phenotypes of plant individuals are usually predicted based on genome-wide markers of genotypes. In this study, we present a deep learning method, named DeepGS, to predict phenotypes from genotypes. Using a deep convolutional neural network, DeepGS uses hidden variables that jointly represent features in genotypes when making predictions; it also employs convolution, sampling and dropout strategies to reduce the complexity of high-dimensional genotypic data. We used a large GS dataset to train DeepGS and compared its performance with other methods. The experimental results indicate that DeepGS can be used as a complement to the commonly used RR-BLUP in the prediction of phenotypes from genotypes. The complementarity between DeepGS and RR-BLUP can be utilized using an ensemble learning approach for more accurately selecting individuals with high phenotypic values, even for the absence of outlier individuals and subsets of genotypic markers. The source codes of DeepGS and the ensemble learning approach have been packaged into Docker images for facilitating their applications in different GS programs.

The emergence of epitranscriptome opened a new chapter in gene regulation. 5-methylcytosine (m5C), as an important post-transcriptional modification, has been identified to be involved in a variety of biological processes such as subcellular localization and translational fidelity. Though high-throughput experimental technologies have been developed and applied to profile m5C modifications under certain conditions, transcriptome-wide studies of m5C modifications are still hindered by the dynamic nature of m5C and the lack of computational prediction methods. In this study, we introduced PEA-m5C, a machine learning-based m5C predictor trained with features extracted from the flanking sequence of m5C modifications. PEA-m5C yielded an average AUC (area under the receiver operating characteristic) of 0.939 in 10-fold cross-validation experiments based on known Arabidopsis m5C modifications. A rigorous independent testing showed that PEA-m5C (Accuracy [Acc] = 0.835, Matthews correlation coefficient [MCC] = 0.688) is remarkably superior to the recently developed m5C predictor iRNAm5C-PseDNC (Acc = 0.665, MCC = 0.332). PEA-m5C has been applied to predict candidate m5C modifications in annotated Arabidopsis transcripts. Further analysis of these m5C candidates showed that 4nt downstream of the translational start site is the most frequently methylated position. PEA-m5C is freely available to academic users at: https://github.com/cma2015/PEA-m5C.

Supplementary data are available at Bioinformatics online.

These results indicate that perceptual learning treatment for amblyopia had a positive effect on the visual cortex and temporal lobe visual areas in patients with anisometropic amblyopia.

Peptidoglycan (PGN), as the major components of the bacterial cell wall, is known to cause excessive proinflammatory cytokine production. Toll-like receptor 2 (TLR2) is abundantly expressed on immune cells and has been shown to be involved in PGN-induced signaling. Although more and more evidences have indicated that PGN is recognized by TLR2, the role of TLR2 PGN recognition is controversial. Mannan-binding lectin (MBL), a plasma C-type lectin, plays a key role in innate immunity. More and more evidences show that MBL could suppress the amplification of inflammatory signals. Whether MBL can alter PGN-elicited cellular responses through TLR2 in macrophages is still unknown, and possible mechanism underlying it should be investigated. In this study, we found that MBL significantly attenuated PGN-induced inflammatory cytokine production, including TNF-α and IL-6, in PMA-stimulated THP-1 cells at both mRNA and protein levels. The expression of TLR2 was strongly induced by PGN stimulation. Furthermore, the administration of TLR2-neutralized antibody effectively suppressed PGN-induced TNF-α and IL-6 expression. These results supplied the evidence that PGN from Saccharomyces cerevisiae could be recognized by TLR2. In addition, we also found that MBL decreased PGN-induced TLR2 expression and suppressed TLR2-mediated downstream signaling, including the phosphorylation of IκBα, nuclear translocation of NF-κBp65, and phosphorylation of MAPK p38 and ERK1/2. Administration of MBL alone did not have an effect on the expression of TLR2. Finally, our data showed that PGN-mediated immune responses were more severely suppressed by preincubation with MBL and indicated that MBL can combine with both TLR2 and PGN to block the inflammation cytokine expression induced by PGN. All these data suggest that MBL could downregulate inflammation by modulating PGN/TLR2 signaling pathways. This study supports an important role for MBL in immune regulation and signaling pathways involved in inflammatory responses.

Background Candida albicans (C. albicans), the most common human fungal pathogen, can cause fatal systemic infections under certain circumstances. Mannan-binding lectin (MBL),a member of the collectin family in the C-type lectin superfamily, is an important serum component associated with innate immunity. Toll-like receptors (TLRs) are expressed extensively, and have been shown to be involved in C. albicans-induced cellular responses. We first examined whether MBL modulated heat-killed (HK) C. albicans-induced cellular responses in phorbol 12-myristate 13-acetate (PMA)-activated human THP-1 macrophages. We then investigated the possible mechanisms of its inhibitory effect.Methodology/Principal FindingEnzyme-linked immunosorbent assay (ELISA) and reverse transcriptasepolymerase chain reaction (RT-PCR) analysis showed that MBL at higher concentrations (10–20 µg/ml) significantly attenuated C. albicans-induced chemokine (e.g., IL-8) and proinflammatory cytokine (e.g., TNF-α) production from PMA-activated THP-1 cells at both protein and mRNA levels. Electrophoretic mobility shift assay (EMSA) and Western blot (WB) analysis showed that MBL could inhibit C. albicans-induced nuclear factor-κB (NF-κB) DNA binding and its translocation in PMA-activated THP-1 cells. MBL could directly bind to PMA-activated THP-1 cells in the presence of Ca2+, and this binding decreased TLR2 and TLR4 expressions in C. albicans-induced THP-1 macrophages. Furthermore, the binding could be partially inhibited by both anti-TLR2 monoclonal antibody (clone TL2.1) and anti-TLR4 monoclonal antibody (clone HTA125). In addition, co-immunoprecipitation experiments and microtiter wells assay showed that MBL could directly bind to the recombinant soluble form of extracellular TLR2 domain (sTLR2) and sTLR4.Conclusions/SignificanceOur study demonstrates that MBL can affect proinflammatory cytokine and chemokine expressions by modifying C. albicans-/TLR-signaling pathways. This study supports an important role for MBL on the regulation of C. albicans-induced cellular responses.

Maximum power point tracking (MPPT) plays an important role in increasing the efficiency of a wind energy conversion system (WECS). In this paper, three conventional MPPT methods are reviewed: power signal feedback (PSF) control, decreased torque gain (DTG) control, and adaptive torque gain (ATG) control, and their potential challenges are investigated. It is found out that the conventional MPPT method ignores the effect of wind turbine inertia and wind speed fluctuations, which lowers WECS efficiency. Accordingly, an improved adaptive torque gain (IATG) method is proposed, which customizes adaptive torque gains and enhances MPPT performances. Specifically, the IATG control considers wind farm turbulences and works out the relationship between the optimal torque gains and the wind speed characteristics, which has not been reported in the literature. The IATG control is promising, especially under the ongoing trend of building wind farms with large-scale wind turbines and at low and medium wind speed sites.

The identification of genes associated with a given biological function in plants remains a challenge, although network-based gene prioritization algorithms have been developed for Arabidopsis thaliana and many non-model plant species. Nevertheless, these network-based gene prioritization algorithms have encountered several problems; one in particular is that of unsatisfactory prediction accuracy due to limited network coverage, varying link quality, and/or uncertain network connectivity. Thus, a model that integrates complementary biological data may be expected to increase the prediction accuracy of gene prioritization. Toward this goal, we developed a novel gene prioritization method named RafSee, to rank candidate genes using a random forest algorithm that integrates sequence, evolutionary, and epigenetic features of plants. Subsequently, we proposed an integrative approach named RAP (Rank Aggregation-based data fusion for gene Prioritization), in which an order statistics-based meta-analysis was used to aggregate the rank of the network-based gene prioritization method and RafSee, for accurately prioritizing candidate genes involved in a pre-specific biological function. Finally, we showcased the utility of RAP by prioritizing 380 flowering-time genes in Arabidopsis. The “leave-one-out” cross-validation experiment showed that RafSee could work as a complement to a current state-of-art network-based gene prioritization system (AraNet v2). Moreover, RAP ranked 53.68% (204/380) flowering-time genes higher than AraNet v2, resulting in an 39.46% improvement in term of the first quartile rank. Further evaluations also showed that RAP was effective in prioritizing genes-related to different abiotic stresses. To enhance the usability of RAP for Arabidopsis and non-model plant species, an R package implementing the method is freely available at http://bioinfo.nwafu.edu.cn/software.