Deep Learning in Proteomics Wen, Bo; Zeng, Wen‐Feng; Liao, Yuxing ...
Proteomics,
November 2020, Letnik:
20, Številka:
21-22
Journal Article
Recenzirano
Odprti dostop
Proteomics, the study of all the proteins in biological systems, is becoming a data‐rich science. Protein sequences and structures are comprehensively catalogued in online databases. With recent ...advancements in tandem mass spectrometry (MS) technology, protein expression and post‐translational modifications (PTMs) can be studied in a variety of biological systems at the global scale. Sophisticated computational algorithms are needed to translate the vast amount of data into novel biological insights. Deep learning automatically extracts data representations at high levels of ion from data, and it thrives in data‐rich scientific research domains. Here, a comprehensive overview of deep learning applications in proteomics, including retention time prediction, MS/MS spectrum prediction, de novo peptide sequencing, PTM prediction, major histocompatibility complex‐peptide binding prediction, and protein structure prediction, is provided. Limitations and the future directions of deep learning in proteomics are also discussed. This review will provide readers an overview of deep learning and how it can be used to analyze proteomics data.
In recent years, gas sensors have been increasingly used in industrial production and daily life. Metal oxide semiconductor gas sensing materials are favoured for their outstanding physical and ...chemical properties, low cost and simple preparation methods. However, the gas sensing mechanisms of metal oxide semiconductors have not been considered by researchers, resulting in omissions and errors in the interpretation of gas sensing mechanisms in many articles. This review organizes and introduces several common gas sensing mechanisms of metal oxide semiconductors in detail and classifies them into two categories. The scope and relationship of these mechanisms are clarified. In addition, this review selects four strategies for enhancing the gas sensing properties of metal oxide semiconductors and analyses the gas sensing mechanisms to highlight the importance of the gas sensing mechanism. Finally, some perspectives for future investigations on the gas sensing mechanisms of metal oxide semiconductors are discussed as well.
This review organizes and introduces several common gas sensing mechanisms of metal oxide semiconductors in detail and classifies them into two categories. The scope and relationship of these mechanisms are clarified.
As sessile organisms, plants must tolerate various environmental stresses. Plant hormones play vital roles in plant responses to biotic and abiotic stresses. Among these hormones, jasmonic acid (JA) ...and its precursors and derivatives (jasmonates, JAs) play important roles in the mediation of plant responses and defenses to biotic and abiotic stresses and have received extensive research attention. Although some reviews of JAs are available, this review focuses on JAs in the regulation of plant stress responses, as well as JA synthesis, metabolism, and signaling pathways. We summarize recent progress in clarifying the functions and mechanisms of JAs in plant responses to abiotic stresses (drought, cold, salt, heat, and heavy metal toxicity) and biotic stresses (pathogen, insect, and herbivore). Meanwhile, the crosstalk of JA with various other plant hormones regulates the balance between plant growth and defense. Therefore, we review the crosstalk of JAs with other phytohormones, including auxin, gibberellic acid, salicylic acid, brassinosteroid, ethylene, and abscisic acid. Finally, we discuss current issues and future opportunities in research into JAs in plant stress responses.
We report a hydrothermal synthesis of ZnO nanoparticles, nanoplates and nanoflowers, and investigate their gas-sensing behaviors. In addition, we also explore the effect of the concentration of ...surfactant CTAB on the ultimate morphology of the nanoflowers and propose the growth formation mechanism.
Display omitted
•ZnO nanoparticles, nanoplates and nanoflowers were successfully synthesized.•The nanoflowers architectures showed the best gas-sensing properties.•CTAB played a vital role in the ultimate morphology of the 3D hierarchical architectures.
ZnO nanoparticles, nanoplates and nanoflowers have been successfully synthesized via a facile hydrothermal route, and their microstructures and gas-sensing properties to ethanol were investigated. Among all the nanostructures, the nanoplates-assembled nanoflowers exhibited significantly higher gas-sensing performances than the others, which may ascribe to their hierarchical architectures with large specific area and abundant spaces for gas diffusion. Furthermore, we surprisingly found that the concentration of surfactant CTAB used had an essential effect on the ultimate morphology of the hierarchical nanoflowers. We hoped our findings could be in favor of further investigations on the fabrication of perfect hierarchical architectures.
We describe pLink 2, a search engine with higher speed and reliability for proteome-scale identification of cross-linked peptides. With a two-stage open search strategy facilitated by fragment ...indexing, pLink 2 is ~40 times faster than pLink 1 and 3~10 times faster than Kojak. Furthermore, using simulated datasets, synthetic datasets,
N metabolically labeled datasets, and entrapment databases, four analysis methods were designed to evaluate the credibility of ten state-of-the-art search engines. This systematic evaluation shows that pLink 2 outperforms these methods in precision and sensitivity, especially at proteome scales. Lastly, re-analysis of four published proteome-scale cross-linking datasets with pLink 2 required only a fraction of the time used by pLink 1, with up to 27% more cross-linked residue pairs identified. pLink 2 is therefore an efficient and reliable tool for cross-linking mass spectrometry analysis, and the systematic evaluation methods described here will be useful for future software development.
The cytotoxic T-lymphocyte-associated antigen 4 (CTLA-4)/B7 and programmed death 1 (PD-1)/ programmed cell death-ligand 1 (PD-L1) are two most representative immune checkpoint pathways, which ...negatively regulate T cell immune function during different phases of T-cell activation. Inhibitors targeting CTLA-4/B7 and PD1/PD-L1 pathways have revolutionized immunotherapies for numerous cancer types. Although the combined anti-CTLA-4/B7 and anti-PD1/PD-L1 therapy has demonstrated promising clinical efficacy, only a small percentage of patients receiving anti-CTLA-4/B7 or anti-PD1/PD-L1 therapy experienced prolonged survival. Regulation of the expression of PD-L1 and CTLA-4 significantly impacts the treatment effect. Understanding the in-depth mechanisms and interplays of PD-L1 and CTLA-4 could help identify patients with better immunotherapy responses and promote their clinical care. In this review, regulation of PD-L1 and CTLA-4 is discussed at the levels of DNA, RNA, and proteins, as well as indirect regulation of biomarkers, localization within the cell, and drugs. Specifically, some potential drugs have been developed to regulate PD-L1 and CTLA-4 expressions with high efficiency. Keywords: PD-L1, CTLA-4, Cancer immunotherapy, Regulatory mechanism, Drug intervention
Spectrum prediction using deep learning has attracted a lot of attention in recent years. Although existing deep learning methods have dramatically increased the prediction accuracy, there is still ...considerable space for improvement, which is presently limited by the difference of fragmentation types or instrument settings. In this work, we use the few-shot learning method to fit the data online to make up for the shortcoming. The method is evaluated using ten data sets, where the instruments includes Velos, QE, Lumos, and Sciex, with collision energies being differently set. Experimental results show that few-shot learning can achieve higher prediction accuracy with almost negligible computing resources. For example, on the data set from a untrained instrument Sciex-6600, within about 10 s, the prediction accuracy is increased from 69.7% to 86.4%; on the CID (collision-induced dissociation) data set, the prediction accuracy of the model trained by HCD (higher energy collision dissociation) spectra is increased from 48.0% to 83.9%. It is also shown that, the method is not critical to data quality and is sufficiently efficient to fill the accuracy gap. The source code of pDeep3 is available at http://pfind.ict.ac.cn/software/pdeep3.
Display omitted
•Synthesis of heterostructure NiO-ZnO nanodisks.•Utilization of NiO-ZnO nanodisks as gas sensor.•Fabrication of high sensitive and low-concentration sulfur dioxide gas sensor based on ...NiO-ZnO nanodisks.
This paper reports the synthesis and characterization of NiO-ZnO nanodisks synthesized through a facile hydrothermal method. The morphological characterizations confirmed the formation of well-defined nanodisks in high density with an average thickness of 60 ± 5 nm. The x-ray diffraction analysis confirmed the well incorporation of the NiO into the matrix of ZnO crystal and the average crystallite size for the NiO-ZnO nanodisks was found to be 39.71 nm. The compositional analysis revealed the formation of pure NiO-ZnO nanostructures. The synthesized NiO-ZnO nanodisks were used as electrode materials to fabricate Sulfur dioxide (SO2) gas sensors and the gas sensor response and recovery times were systematically analyzed with respect to the operating temperatures and the SO2 gas concentration. The observed sensor gas response, response time and recovery time of the fabricated NiO-ZnO nanodisks based gas sensor were 16.25, 52 s and 41 s, respectively, towards 20 ppm SO2 gas at an optimized temperature of 240 °C. Thus, it is believed that the NiO-ZnO nanodisks could be a promising candidate for the fabrication of efficient gas sensors towards toxic and hazardous gases.
Deep Convolutional Neural Networks (CNN) have drawn great attention in image super-resolution (SR). Recently, visual attention mechanism, which exploits both of the feature importance and contextual ...cues, has been introduced to image SR and proves to be effective to improve CNN-based SR performance. In this paper, we make a thorough investigation on the attention mechanisms in a SR model and shed light on how simple and effective improvements on these ideas improve the state-of-the-arts. We further propose a unified approach called "multi-grained attention networks (MGAN)" which fully exploits the advantages of multi-scale and attention mechanisms in SR tasks. In our method, the importance of each neuron is computed according to its surrounding regions in a multi-grained fashion and then is used to adaptively re-scale the feature responses. More importantly, the "channel attention" and "spatial attention" strategies in previous methods can be essentially considered as two special cases of our method. We also introduce multi-scale dense connections to extract the image features at multiple scales and capture the features of different layers through dense skip connections. Ablation studies on benchmark datasets demonstrate the effectiveness of our method. In comparison with other state-of-the-art SR methods, our method shows the superiority in terms of both accuracy and model size.
The recent revolution in computational protein structure prediction provides folding models for entire proteomes, which can now be integrated with large-scale experimental data. Mass spectrometry ...(MS)-based proteomics has identified and quantified tens of thousands of posttranslational modifications (PTMs), most of them of uncertain functional relevance. In this study, we determine the structural context of these PTMs and investigate how this information can be leveraged to pinpoint potential regulatory sites. Our analysis uncovers global patterns of PTM occurrence across folded and intrinsically disordered regions. We found that this information can help to distinguish regulatory PTMs from those marking improperly folded proteins. Interestingly, the human proteome contains thousands of proteins that have large folded domains linked by short, disordered regions that are strongly enriched in regulatory phosphosites. These include well-known kinase activation loops that induce protein conformational changes upon phosphorylation. This regulatory mechanism appears to be widespread in kinases but also occurs in other protein families such as solute carriers. It is not limited to phosphorylation but includes ubiquitination and acetylation sites as well. Furthermore, we performed three-dimensional proximity analysis, which revealed examples of spatial coregulation of different PTM types and potential PTM crosstalk. To enable the community to build upon these first analyses, we provide tools for 3D visualization of proteomics data and PTMs as well as python libraries for data accession and processing.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
PDF
