Nonlinear Spiking Neural Systems With Autapses for Predicting Chaotic Time Series.

Spiking neural P (SNP) systems are a class of distributed and parallel neural-like computing models that are inspired by the mechanism of spiking neurons and are 3rd-generation neural networks. Chaotic time series forecasting is one of the most challenging problems for machine learning models. To address this challenge, we first propose a nonlinear version of SNP systems, called nonlinear SNP systems with autapses (NSNP-AU systems). In addition to the nonlinear consumption and generation of spikes, the NSNP-AU systems have three nonlinear gate functions, which are related to the states and outputs of the neurons. Inspired by the spiking mechanisms of NSNP-AU systems, we develop a recurrent-type prediction model for chaotic time series, called the NSNP-AU model. As a new variant of recurrent neural networks (RNNs), the NSNP-AU model is implemented in a popular deep learning framework. Four datasets of chaotic time series are investigated using the proposed NSNP-AU model, five state-of-the-art models, and 28 baseline prediction models. The experimental results demonstrate the advantage of the proposed NSNP-AU model for chaotic time series forecasting.

A Novel and Highly Selective Epidermal Growth Factor Receptor Inhibitor, SMUZ106, for the Treatment of Glioblastoma.

Targeting the epidermal growth factor receptor (EGFR) is one of the potential ways to treat glioblastoma (GBM). In this study, we investigate the anti-GBM tumor effects of the EGFR inhibitor SMUZ106 in both in vitro and in vivo conditions. The effects of SMUZ106 on the growth and proliferation of GBM cells were explored through MTT and clone formation experiments. Additionally, flow cytometry experiments were conducted to study the effects of SMUZ106 on the cell cycle and apoptosis of GBM cells. The inhibitory activity and selectivity of SMUZ106 to the EGFR protein were proved by Western blotting, molecular docking, and kinase spectrum screening methods. We also conducted a pharmacokinetic analysis of SMUZ106 hydrochloride following i.v. or p.o. administration to mice and assessed the acute toxicity level of SMUZ106 hydrochloride following p.o. administration to mice. Subcutaneous and orthotopic xenograft models of U87MG-EGFRvIII cells were established to assess the antitumor activity of SMUZ106 hydrochloride in vivo. SMUZ106 could inhibit the growth and proliferation of GBM cells, especially for the U87MG-EGFRvIII cells with a mean IC50 value of 4.36 µM. Western blotting analyses showed that compound SMUZ106 inhibits the level of EGFR phosphorylation in GBM cells. It was also shown that SMUZ106 targets EGFR and presents high selectivity. In vivo, the absolute bioavailability of SMUZ106 hydrochloride was 51.97%, and its LD50 exceeded 5000 mg/kg. SMUZ106 hydrochloride significantly inhibited GBM growth in vivo. Furthermore, SMUZ106 inhibited the activity of U87MG-resistant cells induced by temozolomide (TMZ) (IC50: 7.86 µM). These results suggest that SMUZ106 hydrochloride has the potential to be used as a treatment method for GBM as an EGFR inhibitor.

Gated Spiking Neural P Systems for Time Series Forecasting.

Spiking neural P (SNP) systems are a class of neural-like computing models, abstracted by the mechanism of spiking neurons. This article proposes a new variant of SNP systems, called gated spiking neural P (GSNP) systems, which are composed of gated neurons. Two gated mechanisms are introduced in the nonlinear spiking mechanism of GSNP systems, consisting of a reset gate and a consumption gate. The two gates are used to control the updating of states in neurons. Based on gated neurons, a prediction model for time series is developed, known as the GSNP model. Several benchmark univariate and multivariate time series are used to evaluate the proposed GSNP model and to compare several state-of-the-art prediction models. The comparison results demonstrate the availability and effectiveness of GSNP for time series forecasting.

Multivariate time series forecasting method based on nonlinear spiking neural P systems and non-subsampled shearlet transform.

Multivariate time series forecasting remains a challenging task because of its nonlinear, non-stationary, high-dimensional, and spatial-temporal characteristics, along with the dependence between variables. To address this limitation, we propose a novel method for multivariate time series forecasting based on nonlinear spiking neural P (NSNP) systems and non-subsampled shearlet transform (NSST). A multivariate time series is first converted into the NSST domain, and then NSNP systems are automatically constructed, trained, and predicted in the NSST domain. Because NSNP systems are used as nonlinear prediction models and work in the NSST domain, the proposed prediction method is essentially a multiscale transform (MST)-based prediction method. Therefore, the proposed prediction method can process nonlinear and non-stationary time series, and the dependence between variables can be characterized by the multiresolution features of the NSST transform. Five real-life multivariate time series were used to compare the proposed prediction method with five state-of-the-art and 28 baseline prediction methods. The comparison results demonstrate the effectiveness of the proposed method for multivariate time-series forecasting.

A Time Series Forecasting Approach Based on Nonlinear Spiking Neural Systems.

Nonlinear spiking neural P (NSNP) systems are a recently developed theoretical model, which is abstracted by nonlinear spiking mechanism of biological neurons. NSNP systems have a nonlinear structure and the potential to describe nonlinear dynamic systems. Based on NSNP systems, a novel time series forecasting approach is developed in this paper. During the training phase, a time series is first converted to frequency domain by using a redundant wavelet transform, and then according to the frequency data, an NSNP system is automatically constructed and adaptively trained in frequency domain. Then, the well-trained NSNP system can automatically generate sequence data for future time as the prediction results. Eight benchmark time series data sets and two real-life time series data sets are utilized to compare the proposed approach with several state-of-the-art forecasting approaches. The comparison results demonstrate availability and effectiveness of the proposed forecasting approach.

Design, synthesis, biological evaluation and molecular modeling of novel 2-amino-4-(1-phenylethoxy) pyridine derivatives as potential ROS1 inhibitors.

With the aim of discovering potential and selective inhibitors targeting ROS1 kinase, we rationally designed, synthesized and evaluated two series of novel 2-amino-pyridine derivatives with 1-phenylethoxy at C-3 and C-4 position. The enzymic assays results indicated that six of the new compounds 13b-13d and 14a-14c showed remarkably higher inhibitory activities against ROS1 kinase. The most promising compounds, 13d and 14c displayed the most desired ROS1 inhibitory activity with IC50 values of 440 nM and 370 nM respectively. Furthermore, 13d and 14c displayed ROS1 inhibitory selectivity of about 7-fold and 12-fold, relative to that of ALK sharing about 49% amino acid sequence homology in the kinase domains. They also showed good anti-proliferative effects against ROS1-addicted HCC78 cell lines with the IC50 values of 8.1 µM and 65.3 µM, respectively. Moreover, molecular docking and molecular dynamics simulation studies disclosed that compound 14c and 13d shared similar binding poses with Crizotinib except the selective binding site of ROS1. It also gave a probable molecular explanation for their activity and selectivity, which the methoxyl group in benzene ring was the crucial to the selectivity to ROS1 versus ALK.