Tensor-Based Least-Squares Solutions for Multirelational Signals and Applications.

The approach of least squares (LSs) has been quite popular and widely adopted for the common linear regression analysis, which can give rise to the solution to an arbitrary critically-, over-, or under-determined system. Such a linear regression analysis can be easily applied for linear estimation and equalization in signal processing for cybernetics. Nonetheless, the current LS approach for linear regression is unfortunately limited to the dimensionality of data, that is, the exact LS solution can involve only a data matrix. As the dimension of data increases and such data need to be represented by a tensor, the corresponding exact tensor-based LS (TLS) solution does not exist due to the lack of a pertinent mathematical framework. Lately, some alternatives such as tensor decomposition and tensor unfolding were proposed to approximate the TLS solutions to the linear regression problems involving tensor data, but these techniques cannot provide the exact or true TLS solution. In this work, we would like to make the first-ever attempt to present a new mathematical framework for facilitating the exact TLS solutions involving tensor data. To demonstrate the applicability of our proposed new scheme, numerical experiments regarding machine learning and robust speech recognition are illustrated and the associated memory and computational complexities are also studied.

Research on the Total Channel Capacities Pertaining to Two Coverage Layouts for Three-Dimensional, UAV-Assisted Ad Hoc Networks.

Unmanned aerial vehicles (UAVs) employed as airborne base stations (BSs) are considered the essential components in future sixth-generation wireless networks due to their mobility and line-of-sight communication links. For a UAV-assisted ad hoc network, its total channel capacity is greatly influenced by the deployment of UAV-BSs and the corresponding coverage layouts, where square and hexagonal cells are partitioned to divide the zones individual UAVs should serve. In this paper, the total channel capacities of these two kinds of coverage layouts are evaluated using our proposed novel computationally efficient channel capacity estimation scheme. The mean distance (MD) between a UAV-BS in the network and its served users as well as the MD from these users to the neighboring UAV-BSs are incorporated into the estimation of the achievable total channel capacity. We can significantly reduce the computational complexity by using a new polygon division strategy. The simulation results demonstrate that the square cell coverage layout can always lead to a superior channel capacity (with an average increase of 7.67% to be precise) to the hexagonal cell coverage layout for UAV-assisted ad hoc networks.

An integrated network representation of multiple cancer-specific data for graph-based machine learning.

Genomic profiles of cancer cells provide valuable information on genetic alterations in cancer. Several recent studies employed these data to predict the response of cancer cell lines to drug treatment. Nonetheless, due to the multifactorial phenotypes and intricate mechanisms of cancer, the accurate prediction of the effect of pharmacotherapy on a specific cell line based on the genetic information alone is problematic. Emphasizing on the system-level complexity of cancer, we devised a procedure to integrate multiple heterogeneous data, including biological networks, genomics, inhibitor profiling, and gene-disease associations, into a unified graph structure. In order to construct compact, yet information-rich cancer-specific networks, we developed a novel graph reduction algorithm. Driven by not only the topological information, but also the biological knowledge, the graph reduction increases the feature-only entropy while preserving the valuable graph-feature information. Subsequent comparative benchmarking simulations employing a tissue level cross-validation protocol demonstrate that the accuracy of a graph-based predictor of the drug efficacy is 0.68, which is notably higher than those measured for more traditional, matrix-based techniques on the same data. Overall, the non-Euclidean representation of the cancer-specific data improves the performance of machine learning to predict the response of cancer to pharmacotherapy. The generated data are freely available to the academic community at https://osf.io/dzx7b/ .

Novel Cooperative Automatic Modulation Classification Using Vectorized Soft Decision Fusion for Wireless Sensor Networks.

Cooperative automatic modulation classification (CAMC) using a swarm of sensors is intriguing nowadays as it would be much more robust than the conventional single-sensing-node automatic modulation classification (AMC) method. We propose a novel robust CAMC approach using vectorized soft decision fusion in this work. In each sensing node, the local Hamming distances between the graph features acquired from the unknown target signal and the training modulation candidate signals are calculated and transmitted to the fusion center (FC). Then, the global CAMC decision is made by the indirect vote which is translated from each sensing node's Hamming-distance sequence. The simulation results demonstrate that, when the signal-to-noise ratio (SNR) was given by η ≥ 0dB, our proposed new CAMC scheme's correct classification probability Pcc could reach up close to 100%. On the other hand, our proposed new CAMC scheme could significantly outperform the single-node graph-based AMC technique and the existing decision-level CAMC method in terms of recognition accuracy, especially in the low-SNR regime.

A Survey of Blind Modulation Classification Techniques for OFDM Signals.

Blind modulation classification (MC) is an integral part of designing an adaptive or intelligent transceiver for future wireless communications. Blind MC has several applications in the adaptive and automated systems of sixth generation (6G) communications to improve spectral efficiency and power efficiency, and reduce latency. It will become a integral part of intelligent software-defined radios (SDR) for future communication. In this paper, we provide various MC techniques for orthogonal frequency division multiplexing (OFDM) signals in a systematic way. We focus on the most widely used statistical and machine learning (ML) models and emphasize their advantages and limitations. The statistical-based blind MC includes likelihood-based (LB), maximum a posteriori (MAP) and feature-based methods (FB). The ML-based automated MC includes k-nearest neighbors (KNN), support vector machine (SVM), decision trees (DTs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) based MC methods. This survey will help the reader to understand the main characteristics of each technique, their advantages and disadvantages. We have also simulated some primary methods, i.e., statistical- and ML-based algorithms, under various constraints, which allows a fair comparison among different methodologies. The overall system performance in terms bit error rate (BER) in the presence of MC is also provided. We also provide a survey of some practical experiment works carried out through National Instrument hardware over an indoor propagation environment. In the end, open problems and possible directions for blind MC research are briefly discussed.

A Novel Protocol-Free Bandage-Cover Cryptographer.

Cyber security has become an important problem nowadays as almost everyone is often linked to the Internet for business and entertainment. Conventional cryptographers fail to address timely issues regarding cyber-attacks, such as cyber identity theft. In this work, we propose a novel idea, namely, a bandage-cover cryptographer (BCC), which is completely software-defined and protocol-free. Besides, this new cryptographic approach can enable camouflages to confuse data-mining robots, which are often encountered in the cyber world nowadays. Because all of the existing cryptographers aim to protect the entire data (document and file) altogether, they cannot have camouflagibility to mislead data-mining robots. Conversely, by our proposed novel BCC, one can select arbitrary contexts or parts of the data (related to individual identify and/or private confidential information) under protection. To evaluate such a first-ever cryptographer capable of misleading data-mining robots, we define two new metrics, namely: 1) vulnerability and 2) camouflage rates. The theoretical analyses of vulnerability rate and camouflage rate for our proposed new BCC are also presented in this article to demonstrate the corresponding effectiveness.

GraphDTI: A robust deep learning predictor of drug-target interactions from multiple heterogeneous data.

Traditional techniqueset identification, we developed GraphDTI, a robust machine learning framework integrating the molecular-level information on drugs, proteins, and binding sites with the system-level information on gene expression and protein-protein interactions. In order to properly evaluate the performance of GraphDTI, we compiled a high-quality benchmarking dataset and devised a new cluster-based cross-validation p to identify macromolecular targets for drugs utilize solely the information on a query drug and a putative target. Nonetheless, the mechanisms of action of many drugs depend not only on their binding affinity toward a single protein, but also on the signal transduction through cascades of molecular interactions leading to certain phenotypes. Although using protein-protein interaction networks and drug-perturbed gene expression profiles can facilitate system-level investigations of drug-target interactions, utilizing such large and heterogeneous data poses notable challenges. To improve the state-of-the-art in drug targrotocol. Encouragingly, GraphDTI not only yields an AUC of 0.996 against the validation dataset, but it also generalizes well to unseen data with an AUC of 0.939, significantly outperforming other predictors. Finally, selected examples of identified drug-target interactions are validated against the biomedical literature. Numerous applications of GraphDTI include the investigation of drug polypharmacological effects, side effects through off-target binding, and repositioning opportunities.

DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network.

Comprehensive characterization of ligand-binding sites is invaluable to infer molecular functions of hypothetical proteins, trace evolutionary relationships between proteins, engineer enzymes to achieve a desired substrate specificity, and develop drugs with improved selectivity profiles. These research efforts pose significant challenges owing to the fact that similar pockets are commonly observed across different folds, leading to the high degree of promiscuity of ligand-protein interactions at the system-level. On that account, novel algorithms to accurately classify binding sites are needed. Deep learning is attracting a significant attention due to its successful applications in a wide range of disciplines. In this communication, we present DeepDrug3D, a new approach to characterize and classify binding pockets in proteins with deep learning. It employs a state-of-the-art convolutional neural network in which biomolecular structures are represented as voxels assigned interaction energy-based attributes. The current implementation of DeepDrug3D, trained to detect and classify nucleotide- and heme-binding sites, not only achieves a high accuracy of 95%, but also has the ability to generalize to unseen data as demonstrated for steroid-binding proteins and peptidase enzymes. Interestingly, the analysis of strongly discriminative regions of binding pockets reveals that this high classification accuracy arises from learning the patterns of specific molecular interactions, such as hydrogen bonds, aromatic and hydrophobic contacts. DeepDrug3D is available as an open-source program at https://github.com/pulimeng/DeepDrug3D with the accompanying TOUGH-C1 benchmarking dataset accessible from https://osf.io/enz69/.

eToxPred: a machine learning-based approach to estimate the toxicity of drug candidates.

BACKGROUND: The efficiency of drug development defined as a number of successfully launched new pharmaceuticals normalized by financial investments has significantly declined. Nonetheless, recent advances in high-throughput experimental techniques and computational modeling promise reductions in the costs and development times required to bring new drugs to market. The prediction of toxicity of drug candidates is one of the important components of modern drug discovery. RESULTS: In this work, we describe eToxPred, a new approach to reliably estimate the toxicity and synthetic accessibility of small organic compounds. eToxPred employs machine learning algorithms trained on molecular fingerprints to evaluate drug candidates. The performance is assessed against multiple datasets containing known drugs, potentially hazardous chemicals, natural products, and synthetic bioactive compounds. Encouragingly, eToxPred predicts the synthetic accessibility with the mean square error of only 4% and the toxicity with the accuracy of as high as 72%. CONCLUSIONS: eToxPred can be incorporated into protocols to construct custom libraries for virtual screening in order to filter out those drug candidates that are potentially toxic or would be difficult to synthesize. It is freely available as a stand-alone software at https://github.com/pulimeng/etoxpred .

Novel tailoring algorithm for abrupt motion artifact removal in photoplethysmogram signals.

Photoplethysmogram (PPG) signals are widely used for wearable electronic devices nowadays. The PPG signal is extremely sensitive to the motion artifacts (MAs) caused by the subject's movement. The detection and removal of such MAs remains a difficult problem. Due to the complicated MA signal waveforms, none of the existing techniques can lead to satisfactory results. In this paper, a new framework to identify and tailor the abrupt MAs in PPG is proposed, which consists of feature extraction, change-point detection, and MA removal. In order to achieve the optimal performance, a data-dependent frame-size determination mechanism is employed. Experiments for the heart-beat-rate-measurement application have been conducted to demonstrate the effectiveness of our proposed method, by a correct detection rate of MAs at 98% and the average heart-beat-rate tracking accuracy above 97%. On the other hand, this new framework maintains the original signal temporal structure unlike the spectrum-based approach, and it can be further applied for the calculation of blood oxygen level (SpO2).

EphrinA5 suppresses colon cancer development by negatively regulating epidermal growth factor receptor stability.

Colon cancer is one of the most common human cancers worldwide. Owing to its aggressiveness and lethality, it is necessary to determine the mechanisms regulating the carcinogenesis of colon cancer. EphrinA5 has been reported to act as a putative tumor suppressor in glioma; however, little is known concerning the role of this protein in the context of colon cancer. To elucidate the biological significance of ephrinA5 in colon cancer, we examined ephrinA5 and epidermal growth factor receptor (EGFR) expression profiles in both colon cancer and normal tissues, using immunohistochemistry on a 96-spot tissue microarray. Gain-of-function and loss-of-function experiments were performed on the human colon cancer cell lines SW480 and WiDr to determine the biological effects of ephrinA5 in relation to cell proliferation, survival, and migration. It was found that ephrinA5 mRNA and protein levels were significantly reduced in colon cancer as compared with normal colon tissue specimens. EphrinA5 expression was also negatively associated with tumor differentiation and clinical stage. In colon cancer cell line models, ephrinA5 exerted an inhibitory effect on EGFR by promoting c-Cbl-mediated EGFR ubiquitination and degradation. EphrinA5 did not affect the transcriptional regulation of EGFR mRNA expression in colon cancer cells. Expression of ephrinA5 suppressed colon cancer cell proliferation, migration, and chemotherapeutic resistance. In conclusion, ephrinA5 inhibited colon cancer progression by promoting c-Cbl-mediated EGFR degradation. Our findings identify a novel mechanism that could be utilized to improve the therapeutic efficiency of EGFR-targeting strategies.

Soluble THSD7A is an N-glycoprotein that promotes endothelial cell migration and tube formation in angiogenesis.

BACKGROUND: Thrombospondin type I domain containing 7A (THSD7A) is a novel neural protein that is known to affect endothelial migration and vascular patterning during development. To further understand the role of THSD7A in angiogenesis, we investigated the post-translational modification scheme of THS7DA and to reveal the underlying mechanisms by which this protein regulates blood vessel growth. METHODOLOGY/PRINCIPAL FINDINGS: Full-length THSD7A was overexpressed in human embryonic kidney 293T (HEK293T) cells and was found to be membrane associated and N-glycosylated. The soluble form of THSD7A, which is released into the cultured medium, was harvested for further angiogenic assays. We found that soluble THSD7A promotes human umbilical vein endothelial cell (HUVEC) migration and tube formation. HUVEC sprouts and zebrafish subintestinal vessel (SIV) angiogenic assays further revealed that soluble THSD7A increases the number of branching points of new vessels. Interestingly, we found that soluble THSD7A increased the formation of filopodia in HUVEC. The distribution patterns of vinculin and phosphorylated focal adhesion kinase (FAK) were also affected, which implies a role for THSD7A in focal adhesion assembly. Moreover, soluble THSD7A increased FAK phosphorylation in HUVEC, suggesting that THSD7A is involved in regulating cytoskeleton reorganization. CONCLUSIONS/SIGNIFICANCE: Taken together, our results indicate that THSD7A is a membrane-associated N-glycoprotein with a soluble form. Soluble THSD7A promotes endothelial cell migration during angiogenesis via a FAK-dependent mechanism and thus may be a novel neuroangiogenic factor.

Blind multiridge detection for automatic nondestructive testing using ultrasonic signals.

Ultrasonic imaging has been a significant means for nondestructive testing (NDT). Recently the NDT techniques via the ultrasonic instrumentation have shown the striking capability of the quality control for the material fabrication industry. To the best of our knowledge, all existing signal processing methods require either the a priori information of the ultrasonic signature signals or the manual segmentation operation to achieve the reliable parameters that characterize the corresponding mechanical properties. In this paper, we first provide a general mathematical model for the ultrasonic signals collected by the pulse-echo sensors, then design a totally blind novel signal processing NDT technique relying on neither a priori signal information nor any manual effort. Based on the automatic selection of optimal frame sizes using a proposed new criterion in our scheme, the signature signal can be blindly extracted for further robust multiridge detection. The detected ridge information can be used to estimate the transmission and attenuation coefficients associated with any arbitrary material sample for the fabrication quality control.