No abstract

Motivation Prediction of peptide binding to the major histocompatibility complex (MHC) plays a vital role in the development of therapeutic vaccines for the treatment of cancer. Algorithms with improved correlations between predicted and actual binding affinities are needed to increase precision and reduce the number of false positive predictions. Results We present ACME (Attention-based Convolutional neural networks for MHC Epitope binding prediction), a new pan-specific algorithm to accurately predict the binding affinities between peptides and MHC class I molecules, even for those new alleles that are not seen in the training data. Extensive tests have demonstrated that ACME can significantly outperform other state-of-the-art prediction methods with an increase of the Pearson correlation coefficient between predicted and measured binding affinities by up to 23 percentage points. In addition, its ability to identify strong-binding peptides has been experimentally validated. Moreover, by integrating the convolutional neural network with attention mechanism, ACME is able to extract interpretable patterns that can provide useful and detailed insights into the binding preferences between peptides and their MHC partners. All these results have demonstrated that ACME can provide a powerful and practically useful tool for the studies of peptide–MHC class I interactions. Availability and implementation ACME is available as an open source software at https://github.com/HYsxe/ACME. Supplementary information Supplementary data are available at Bioinformatics online.

A simply fabricated microfluidic device using a green organic light emitting diode (OLED) and thin film interference filter as integrated excitation source is presented and applied to fluorescence detection of proteins. A layer-by-layer compact system consisting of glass/PDMS microchip, pinhole, excitation filter and OLED is designed and equipped with a coaxial optical fiber and for fluorescence detection a 300 microm thick excitation filter is employed for eliminating nearly 80% of the unwanted light emitted by OLEDs which has overlaped with the fluorescence spectrum of the dyes. The distance between OLED illuminant and microchannels is limited to approximately 1 mm for sensitive detection. The achieved fluorescence signal of 300 microM Rhodamine 6G is about 13 times as high as that without the excitation filter and 3.5 times the result of a perpendicular detection structure. This system has been used for fluorescence detection of Rhodamine 6G, Alexa 532 and BSA conjugates in 4% linear polyacrymide (LPA) buffer (in 1 x TBE, pH 8.3) and 1.4 fmol and 35 fmol mass detection limits at 0.7 nl injection volume for Alexa and Rhodamine dye have been obtained, respectively.

Purpose. To generate a signature based on anoikis-related genes (ARGs) for endometrial carcinoma (EC) patients and elucidate the molecular mechanisms in EC. Methods. On the basis of TCGA-UCEC dataset, we identified specific anoikis-related genes (ARGs) in EC. Cox-relative regression methods were used to generate an anoikis-related signature (ARS). The possible biological pathways of ARS-related genes were analyzed by GSEA. The clinical potency and immune status of ARS were analyzed by CIBERSORT method, ssGSEA algorithm, Tumor Immune Dysfunction and Exclusion (TIDE) analysis. Moreover, the expression patterns of ARS genes were verified by HPA database. Results. Seven anoikis genes (CDKN2A, E2F1, ENDOG, EZH2, HMGA1, PLK1, and SLC2A1) were determined to develop a prognostic ARS. Both genes of ARS were closely bound up with the prognosis of EC patients. The ARS could accurately classify EC cases with different clinical outcome and mirror the specific immune status of EC. We observed that ARS-high patients could not benefit from immunotherapy. Finally, all the hub genes of ARS were proved to be upregulated in EC tissues by immunohistology. Conclusion. ARS can be used to stratify the risk and forecast the survival outcome of EC patients and provide prominent reference for individualized treatment in EC.

Strigolactones (SL) fulfil important roles in plant development and stress tolerance. Here, we characterized the role of SL in the dark chilling tolerance of pea and Arabidopsis by analysis of mutants that are defective in either SL synthesis or signalling. Pea mutants (rms3, rms4, and rms5) had significantly greater shoot branching with higher leaf chlorophyll a/b ratios and carotenoid contents than the wild type. Exposure to dark chilling significantly decreased shoot fresh weights but increased leaf numbers in all lines. Moreover, dark chilling treatments decreased biomass (dry weight) accumulation only in rms3 and rms5 shoots. Unlike the wild type plants, chilling-induced inhibition of photosynthetic carbon assimilation was observed in the rms lines and also in the Arabidopsis max3-9, max4-1, and max2-1 mutants that are defective in SL synthesis or signalling. When grown on agar plates, the max mutant rosettes accumulated less biomass than the wild type. The synthetic SL, GR24, decreased leaf area in the wild type, max3-9, and max4-1 mutants but not in max2-1 in the absence of stress. In addition, a chilling-induced decrease in leaf area was observed in all the lines in the presence of GR24. We conclude that SL plays an important role in the control of dark chilling tolerance.