Cancer is a well-known killer of human beings, which has led to countless deaths and misery. Anticancer peptides open a promising perspective for cancer treatment, and they have various attractive ...advantages. Conventional wet experiments are expensive and inefficient for finding and identifying novel anticancer peptides. There is an urgent need to develop a novel computational method to predict novel anticancer peptides. In this study, we propose a deep learning long short-term memory (LSTM) neural network model, ACP-DL, to effectively predict novel anticancer peptides. More specifically, to fully exploit peptide sequence information, we developed an efficient feature representation approach by integrating binary profile feature and k-mer sparse matrix of the reduced amino acid alphabet. Then we implemented a deep LSTM model to automatically learn how to identify anticancer peptides and non-anticancer peptides. To our knowledge, this is the first time that the deep LSTM model has been applied to predict anticancer peptides. It was demonstrated by cross-validation experiments that the proposed ACP-DL remarkably outperformed other comparison methods with high accuracy and satisfied specificity on benchmark datasets. In addition, we also contributed two new anticancer peptides benchmark datasets, ACP740 and ACP240, in this work. The source code and datasets are available at https://github.com/haichengyi/ACP-DL.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Abstract
Graph is a natural data structure for describing complex systems, which contains a set of objects and relationships. Ubiquitous real-life biomedical problems can be modeled as graph ...analytics tasks. Machine learning, especially deep learning, succeeds in vast bioinformatics scenarios with data represented in Euclidean domain. However, rich relational information between biological elements is retained in the non-Euclidean biomedical graphs, which is not learning friendly to classic machine learning methods. Graph representation learning aims to embed graph into a low-dimensional space while preserving graph topology and node properties. It bridges biomedical graphs and modern machine learning methods and has recently raised widespread interest in both machine learning and bioinformatics communities. In this work, we summarize the advances of graph representation learning and its representative applications in bioinformatics. To provide a comprehensive and structured analysis and perspective, we first categorize and analyze both graph embedding methods (homogeneous graph embedding, heterogeneous graph embedding, attribute graph embedding) and graph neural networks. Furthermore, we summarize their representative applications from molecular level to genomics, pharmaceutical and healthcare systems level. Moreover, we provide open resource platforms and libraries for implementing these graph representation learning methods and discuss the challenges and opportunities of graph representation learning in bioinformatics. This work provides a comprehensive survey of emerging graph representation learning algorithms and their applications in bioinformatics. It is anticipated that it could bring valuable insights for researchers to contribute their knowledge to graph representation learning and future-oriented bioinformatics studies.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Intense infiltration of tumour-associated macrophages (TAMs) facilitates malignant growth of glioblastoma (GBM), but the underlying mechanisms remain undefined. Herein, we report that TAMs secrete ...abundant pleiotrophin (PTN) to stimulate glioma stem cells (GSCs) through its receptor PTPRZ1 thus promoting GBM malignant growth through PTN-PTPRZ1 paracrine signalling. PTN expression correlates with infiltration of CD11b
/CD163
TAMs and poor prognosis of GBM patients. Co-implantation of M2-like macrophages (MLCs) promoted GSC-driven tumour growth, but silencing PTN expression in MLCs mitigated their pro-tumorigenic activity. The PTN receptor PTPRZ1 is preferentially expressed in GSCs and also predicts GBM poor prognosis. Disrupting PTPRZ1 abrogated GSC maintenance and tumorigenic potential. Moreover, blocking the PTN-PTPRZ1 signalling by shRNA or anti-PTPRZ1 antibody potently suppressed GBM tumour growth and prolonged animal survival. Our study uncovered a critical molecular crosstalk between TAMs and GSCs through the PTN-PTPRZ1 paracrine signalling to support GBM malignant growth, indicating that targeting this signalling axis may have therapeutic potential.
The key to modern drug discovery is to find, identify and prepare drug molecular targets. However, due to the influence of throughput, precision and cost, traditional experimental methods are ...difficult to be widely used to infer these potential Drug-Target Interactions (DTIs). Therefore, it is urgent to develop effective computational methods to validate the interaction between drugs and target.
We developed a deep learning-based model for DTIs prediction. The proteins evolutionary features are extracted via Position Specific Scoring Matrix (PSSM) and Legendre Moment (LM) and associated with drugs molecular substructure fingerprints to form feature vectors of drug-target pairs. Then we utilized the Sparse Principal Component Analysis (SPCA) to compress the features of drugs and proteins into a uniform vector space. Lastly, the deep long short-term memory (DeepLSTM) was constructed for carrying out prediction.
A significant improvement in DTIs prediction performance can be observed on experimental results, with AUC of 0.9951, 0.9705, 0.9951, 0.9206, respectively, on four classes important drug-target datasets. Further experiments preliminary proves that the proposed characterization scheme has great advantage on feature expression and recognition. We also have shown that the proposed method can work well with small dataset.
The results demonstration that the proposed approach has a great advantage over state-of-the-art drug-target predictor. To the best of our knowledge, this study first tests the potential of deep learning method with memory and Turing completeness in DTIs prediction.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Accumulating evidence suggests that formation of peroxynitrite (ONOO–) in the cerebral vasculature contributes to the progression of ischemic damage, while the underlying molecular mechanisms remain ...elusive. To fully understand ONOO– biology, efficient tools that can realize the real-time tracing of endogenous ONOO– fluxes are indispensable. While a few ONOO– fluorescent probes have been reported, direct visualization of ONOO– fluxes in the cerebral vasculature of live mice remains a challenge. Herein, we present a fluorescent switch-on probe (NP3) for ONOO– imaging. NP3 exhibits good specificity, fast response, and high sensitivity toward ONOO– both in vitro and in vivo. Moreover, NP3 is two-photon excitable and readily blood–brain barrier penetrable. These desired photophysical and pharmacokinetic properties endow NP3 with the capability to monitor brain vascular ONOO– generation after injury with excellent temporal and spatial resolution. As a proof of concept, NP3 has enabled the direct visualization of neurovascular ONOO– formation in ischemia progression in live mouse brain by use of two-photon laser scanning microscopy. Due to these favorable properties, NP3 holds great promise for visualizing endogenous peroxynitrite fluxes in a variety of pathophysiological progressions in vitro and in vivo.
Full text
Available for:
IJS, KILJ, NUK, PNG, UL, UM
The interactions between non-coding RNAs (ncRNAs) and proteins play an important role in many biological processes, and their biological functions are primarily achieved by binding with a variety of ...proteins. High-throughput biological techniques are used to identify protein molecules bound with specific ncRNA, but they are usually expensive and time consuming. Deep learning provides a powerful solution to computationally predict RNA-protein interactions. In this work, we propose the RPI-SAN model by using the deep-learning stacked auto-encoder network to mine the hidden high-level features from RNA and protein sequences and feed them into a random forest (RF) model to predict ncRNA binding proteins. Stacked assembling is further used to improve the accuracy of the proposed method. Four benchmark datasets, including RPI2241, RPI488, RPI1807, and NPInter v2.0, were employed for the unbiased evaluation of five established prediction tools: RPI-Pred, IPMiner, RPISeq-RF, lncPro, and RPI-SAN. The experimental results show that our RPI-SAN model achieves much better performance than other methods, with accuracies of 90.77%, 89.7%, 96.1%, and 99.33%, respectively. It is anticipated that RPI-SAN can be used as an effective computational tool for future biomedical researches and can accurately predict the potential ncRNA-protein interacted pairs, which provides reliable guidance for biological research.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
The concept of the OOS of spacecraft can be traced back to the 1960s, when the main focus was on providing the necessary maintenance to advance the lifetime of spacecraft and extending the scale and ...function through on-orbit assembly. During the past decades, the Hubble Space Telescope has made great contributions to the fields of astronomy and physics through both observational data and the success of five OOS missions to overcome big challenges. That included an initial flaw of its primary mirror and subsequent obstacles associated with replacing and upgrading its science instruments. Furthermore, many programs have been carried out in the area of the OOS of spacecraft with successful operations in space. It could be exemplified by the assembly of the International Space Station, service verification of ETS-VII and Orbital Express, and detailed research for future applications including servicer and client satellites and particularly large space systems. This paper attempts to summarize all reported programs of the OOS in terms of engineering developments and provide an overall perspective for investigators in this field. Based on the reviewed programs, an analysis is carried out to elucidate the logical architectures of the mission and technology of the OOS of spacecraft. Further attention is paid to discussions of the enabling technologies that support the development of the OOS and related spacecraft. As an outlook, the future development and challenges of the OOS and the application of novel technologies are finally discussed to extend the present review work.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Alcoholic liver disease (ALD) is a major cause of chronic liver disease worldwide. Macrophages exhibit different functional states and are classified as classically activated (M1) and alternatively ...activated (M2) macrophages. However, the mechanisms that govern M1/M2 polarization in chronic ALD remain to be elucidated. Prostacyclin (PGI2) synthase (PTGIS) is an enzyme of the prostaglandin pathway which catalyzes the conversion of Prostaglandin H2 (PGH2) to PGI2. PTGIS has anti-inflammatory properties. However, the function of PTGIS in ALD has not yet been determined. In this study, we demonstrated that PTGIS was downregulated in ALD and forced PTGIS expression in vivo using recombinant adeno-associated viral vector-packed PTGIS overexpression plasmid, which alleviated the inflammatory response and suppressed the macrophage M1 phenotype in mice. Loss- and gain-of function-experiments demonstrated that forced PTGIS expression inhibited the macrophage switch to the M1 phenotype and promoted M2 polarization. Furthermore, we identified the genes regulated by PTGIS through RNA-sequencing (RNA-seq) analysis. Gene ontology and KEGG pathway analyses showed that PTGIS regulates many genes involved in the immune response and is enriched in the Janus kinase/signal transducers and activators of transcription (JAK/STAT) signal transduction pathway, which plays an important role in regulating macrophage polarization. The proteins interacting with JAKs were predicted using the STRING database. The overlap between the RNA-seq and the STRING database was interleukin-6; this indicated that it was involved in macrophage polarization regulated by JAK/STAT signaling. We further explored the microRNAs that could regulate the expression of PTGIS through TargetScan. The results of luciferase assay illustrated that the expression of PTGIS was regulated by miR-140-3p.1. These results imply that PTGIS plays a pivotal role in ALD, partly by influencing macrophage polarization.
Prostacyclin synthase (PTGIS) levels are decreased by elevated miR-140-3p.1 expression in chronic alcoholic liver disease. Inducing PTGIS expression alleviates chronic alcohol-induced liver injury by promoting macrophage M2 polarization and inhibiting the M1 phenotype through the JAK/STAT pathway. Interestingly, inducing PTGIS expression also increases IL-6 expression, which has not yet been explained.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
The invasion of malignant glioma cells into the surrounding normal brain tissues is crucial for causing the poor outcome of this tumor type. Recent studies suggest that glioma stem-like cells (GSLCs) ...mediate tumor invasion. However, it is not clear whether microenvironment factors, such as tumor-associated microglia/macrophages (TAM/Ms), also play important roles in promoting GSLC invasion. In this study, we found that in primary human gliomas and orthotopical transplanted syngeneic glioma, the number of TAM/Ms at the invasive front was correlated with the presence of CD133(+) GSLCs, and these TAM/Ms produced high levels of TGF-β1. CD133(+) GSLCs isolated from murine transplanted gliomas exhibited higher invasive potential after being cocultured with TAM/Ms, and the invasiveness was inhibited by neutralization of TGF-β1. We also found that human glioma-derived CD133(+) GSLCs became more invasive upon treatment with TGF-β1. In addition, compared with CD133(-) committed tumor cells, CD133(+) GSLCs expressed higher levels of type II TGF-β receptor (TGFBR2) mRNA and protein, and downregulation of TGFBR2 with short hairpin RNA inhibited the invasiveness of GSLCs. Mechanism studies revealed that TGF-β1 released by TAM/Ms promoted the expression of MMP-9 by GSLCs, and TGFBR2 knockdown reduced the invasiveness of these cells in vivo. These results demonstrate that TAM/Ms enhance the invasiveness of CD133(+) GSLCs via the release of TGF-β1, which increases the production of MMP-9 by GSLCs. Therefore, the TGF-β1 signaling pathway is a potential therapeutic target for limiting the invasiveness of GSLCs.
In this study, the electrodeposition (ED) of ultrathin, compact TiO2 blocking layers (BLs) on fluorine-doped tin oxide (FTO) glass for perovskite solar cells (PSCs) is evaluated. This bottom-up ...method allows for controlling the morphology and thickness of TiO2 films by simply manipulating deposition conditions. Compared with BLs produced using the spin-coating (SC) method, BLs produced using ED exhibit satisfactory surface coverage, even with a film thickness of 29 nm. Evidence from cyclic voltammetry shows that an ED BL suppresses interfacial recombination more profoundly than an SC BL does, consequently improving the photovoltaic properties of the PSC significantly. A PSC equipped with an ED TiO2 BL having a 13.6% power conversion efficiency is demonstrated.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK