Search

Development of novel anti-cancer treatments requires not only a comprehensive knowledge of cancer processes and drug mechanisms of action, but also the ability to accurately predict the response of various cancer cell lines to therapeutics. Numerous computational methods have been developed to address this issue, including algorithms employing supervised machine learning. Nonetheless, high prediction accuracies reported for many of these techniques may result from a significant overlap among training, validation, and testing sets, making existing predictors inapplicable to new data. To address these issues, we developed CancerOmicsNet, a graph neural network with sophisticated attention propagation mechanisms to predict the therapeutic effects of kinase inhibitors across various tumors. Emphasizing on the system-level complexity of cancer, CancerOmicsNet integrates multiple heterogeneous data, such as biological networks, genomics, inhibitor profiling, and gene-disease associations, into a unified graph structure. The performance of CancerOmicsNet, properly cross-validated at the tissue level, is 0.83 in terms of the area under the receiver operating characteristics, which is notably higher than those measured for other approaches. CancerOmicsNet generalizes well to unseen data, i.e., it can predict therapeutic effects across a variety of cancer cell lines and inhibitors. CancerOmicsNet is freely available to the academic community at https://github.com/pulimeng/CancerOmicsNet.

Nowadays, the sufficient quality-of-service (QoS) provision for multimedia mobile applications remains a major challenge to any wireless network. Conventional sufficient QoS provision techniques using resource allocation, data scheduling, and cross-layer optimization have been proposed to tackle this problem. Nevertheless, due to the unpredictable nature of wireless channel conditions, the QoS improvements resulting from the aforementioned approaches are often unsatisfactory. In this paper, we would like to further exploit our previous concept, namely user-placement ushering (UPU). A mobile user can be relocated to an optimal, or at least a better place to boost the QoS for a given application. The QoS is measured by the packet-success rate (PSR), which can be further computed from the code-block error-rate (CBER). Novel fast algorithms are devised here to usher (guide) a mobile user to an appropriate spot with sufficient QoS, which is nearby. We address the UPU problem to accommodate the realistic complex indoor environments, where obstacles are present. Our simulation results have demonstrated that our new fast UPU algorithms are capable of finding new appropriate locations satisfying the required QoSs for different wireless network applications.The preliminary results are presented in [1] .

In this paper, we propose a novel hierarchical radio-frequency identification (RFID) tag-recognition method based on blind source separation (BSS), graph-based automatic modulation classification (AMC), and direct-sequence spread-spectrum (DSSS). In our proposed method, RFID tags can be modulated using different modulation schemes according to different scenarios (e.g., different users or different tag devices). For each modulation scheme, the direct-sequence spread-spectrum strategy is employed to allow simultaneous transmissions of multiple commands. In the signal separation phase, BSS is employed to separate different transmitted signals. Then in the first hierarchy of the recognition phase, different modulation types are adopted to distinguish different users, the graph-based AMC is built upon the periodicity of the modulated signals: the cyclic spectrum of the received signal is established; the graph representation is then constructed according to the cyclic spectrum. Ultimately, robust features are extracted from the graph representation. In the second hierarchy of the recognition phase, the DSSS scheme is utilized to differentiate the control or sensed data carried by individual tags; the signature sequence set with low cross-correlations can be generated from Kasami sequences. In the third hierarchy of the recognition phase, the information data are thus spread by these signature sequences. In our proposed new RFID framework, multiple tags can transmit signals simultaneously in the same frequency band where each tag signal can still be separated and identified and its carried information can be recovered. Monte Carlo simulation results demonstrate the promising performance of our proposed new RFID scheme.

Computational modeling is an essential component of modern drug discovery. One of its most important applications is to select promising drug candidates for pharmacologically relevant target proteins. Because of continuing advances in structural biology, putative binding sites for small organic molecules are being discovered in numerous proteins linked to various diseases. These valuable data offer new opportunities to build efficient computational models predicting binding molecules for target sites through the application of data mining and machine learning. In particular, deep neural networks are powerful techniques capable of learning from complex data in order to make informed drug binding predictions. In this communication, we describe Pocket2Drug, a deep graph neural network model to predict binding molecules for a given a ligand binding site. This approach first learns the conditional probability distribution of small molecules from a large dataset of pocket structures with supervised training, followed by the sampling of drug candidates from the trained model. Comprehensive benchmarking simulations show that using Pocket2Drug significantly improves the chances of finding molecules binding to target pockets compared to traditional drug selection procedures. Specifically, known binders are generated for as many as 80.5% of targets present in the testing set consisting of dissimilar data from that used to train the deep graph neural network model. Overall, Pocket2Drug is a promising computational approach to inform the discovery of novel biopharmaceuticals.

Binding sites are concave surfaces on proteins that bind to small molecules called ligands. Types of molecules that bind to the protein determine its biological function. Meanwhile, the binding process between small molecules and the protein is also crucial to various biological functionalities. Therefore, identifying and classifying such binding sites would enormously contribute to biomedical applications such as drug repurposing. Deep learning is a modern artificial intelligence technology. It utilizes deep neural networks to handle complex tasks such as image classification and language translation. Previous work has proven the capability of deep learning models handle binding sites wherein the binding sites are represented as pixels or voxels. Graph neural networks (GNNs) are deep learning models that operate on graphs. GNNs are promising for handling binding sites related tasks - provided there is an adequate graph representation to model the binding sties. In this communication, we describe a GNN-based computational method, GraphSite, that utilizes a novel graph representation of ligand-binding sites. A state-of-the-art GNN model is trained to capture the intrinsic characteristics of these binding sites and classify them. Our model generalizes well to unseen data and achieves test accuracy of 81.28% on classifying 14 binding site classes.

This paper proposes a novel indoor device-free localization and tracking approach using the received signal-strength indicators (RSSIs) of WiFi signals. The RSSI feature-vectors simulated by a channel-propagation emulator software are adopted as the training data for our proposed scheme. Prevalent discriminative machine-learning methods are used to predict the locations of a moving human-object. Hidden Markov models (HMMs) are also incorporated with such machine-learning techniques for robust and reliable indoor tracking. In this work, we partition the given indoor geometry into several equi-sized zones and then convert the underlying localization/tracking problem to the classical multi-classification problem. Simulation results demonstrate that the gradient boosting decision-tree (GBDT) classifier in conjunction with the Viterbi algorithm over hidden Markov models leads to the highest localization-accuracies of 83.9% for eight zones and 71.4% for sixteen zones. As a result, our proposed new indoor localization and tracking scheme can be very promising for many indoor device-free surveillance applications in the future.

Traditional techniques 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 target 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 protocol. 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 drugtarget interactions are validated against the biomedical literature. Numerous applications of GraphDTI include the investigation of drug polypharmacological effects, side effects through offtarget binding, and repositioning opportunities.

Advances in several engineering fields have led to a trend toward miniaturization and portability of wearable biosensing devices, which used to be confined to large tools and clinical settings. Various systems to continuously measure electrophysiological activity through electrical and optical methods are one category of such devices. Being wearable and intended for prolonged use, the amount of noise introduced on sensors by movement remains a challenge and requires further optimization. User movement causes motion artifacts that alter the overall quality of the signals obtained, hence corrupting the resulting measurements. This paper introduces a fully wearable optical biosensing system to continuously measure pulse oximetry and heart rate, utilizing a reflectance-based probe. Furthermore, a novel data-dependent motion artifact tailoring algorithm is implemented to eliminate noisy data due to the motion artifact and measure oxygenation level with high accuracy in real time. By taking advantages of current wireless transmission and signal processing technologies, the developed wearable photoplethysmography device successfully captures the measured signals and sends them wirelessly to a mobile device for signal processing in real time. After applying motion artifact tailoring, evaluating accuracy with a continuous clinical device, the blood oxygenation measurements obtained from our system yielded an accuracy of at least 98%, when compared to a range of 93.6%-96.7% observed before from the same initial data. Additionally, heart rate accuracy above 97% was achieved. Motion artifact tailoring and removal in real time, continuous systems will allow wearable devices to be truly wearable and a reliable electrophysiological monitoring and diagnostics tool for everyday use.

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. 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%. 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 .

This paper introduces a new indoor-localization approach using a deep-learning network for which the received signal-strength indicator (RSSI) is adopted as the radiofrequency fingerprint. In our proposed scheme, the RSSIs which are estimated by a channel-propagation emulator software, are adopted as the input features for deep learning. This approach is measurement-free and thus it is very cost-effective and convenient to users. A multilayer perceptron (MLP) is constructed to predict the location(s) of the mobile object(s). The time evolution of the predicted locations of an object will form the predicted trajectory thereby. Because deep-learning networks require tremendous training data to achieve good prediction accuracy, we propose to partition the indoor geometry of interest (ex., a room) into several zones. Preliminary simulation results demonstrate that the AUC (area under the receiver-operating characteristic curve) can reach up to 0.89 for a room partitioned into eight zones. Our proposed new indoor-localization scheme in this work can be a rare but promising localization technology, which is neither passive nor active as other existing prevalent localization methods.

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 treatment with drugs. 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. High prediction accuracies reported in the literature likely result from significant overlaps among training, validation, and testing sets, making many predictors inapplicable to new data. To address these issues, we developed GraphGR, a graph neural network with sophisticated attention propagation mechanisms to predict the therapeutic effects of kinase inhibitors across various tumors. Emphasizing on the system-level complexity of cancer, GraphGR integrates multiple heterogeneous data, such as biological networks, genomics, inhibitor profiling, and genedisease associations, into a unified graph structure. In order to construct diverse and information-rich cancer-specific networks, we devised a novel graph reduction protocol based on not only the topological information, but also the biological knowledge. The performance of GraphGR, properly cross-validated at the tissue level, is 0.83 in terms of the area under the receiver operating characteristics, which is notably higher than those measured for other approaches on the same data. Finally, several new predictions are validated against the biomedical literature demonstrating that GraphGR generalizes well to unseen data, i.e. it can predict therapeutic effects across a variety of cancer cell lines and inhibitors. GraphGR is freely available to the academic community at https://github.com/pulimeng/GraphGR.

Motivation Fast and accurate classification of ligand-binding sites in proteins with respect to the class of binding molecules is invaluable not only to the automatic functional annotation of large datasets of protein structures but also to projects in protein evolution, protein engineering and drug development. Deep learning techniques, which have already been successfully applied to address challenging problems across various fields, are inherently suitable to classify ligand-binding pockets. Our goal is to demonstrate that off-the-shelf deep learning models can be employed with minimum development effort to recognize nucleotide- and heme-binding sites with a comparable accuracy to highly specialized, voxel-based methods. Results We developed BionoiNet, a new deep learning-based framework implementing a popular ResNet model for image classification. BionoiNet first transforms the molecular structures of ligand-binding sites to 2D Voronoi diagrams, which are then used as the input to a pretrained convolutional neural network classifier. The ResNet model generalizes well to unseen data achieving the accuracy of 85.6% for nucleotide- and 91.3% for heme-binding pockets. BionoiNet also computes significance scores of pocket atoms, called BionoiScores, to provide meaningful insights into their interactions with ligand molecules. BionoiNet is a lightweight alternative to computationally expensive 3D architectures. Availability and implementation BionoiNet is implemented in Python with the source code freely available at: https://github.com/CSBG-LSU/BionoiNet. Supplementary information Supplementary data are available at Bioinformatics online.

We consider the use of multiple mobile agents to explore an unknown area. The area is orthogonal, such that all perimeter lines run both vertically and horizontally. The area may consist of unknown rectangular holes which are non-traversable internally. For the sake of analysis, we assume that the area is discretized into N points allowing the agents to move from one point to an adjacent one. Mobile agents communicate through face-to-face communication when in adjacent points. The objective of exploration is to develop an online algorithm that will explore the entire area while reducing the total work of all k agents, where the work is measured as the number of points traversed. We propose splitting the exploration into two alternating tasks, perimeter and room exploration. The agents all begin with the perimeter scan and when a room is found they transition to room scan after which they continue with perimeter scan until the next room is found and so on. Given the total traversable points N, our algorithm completes in total O ( N ) work with each agent performing O ( N / k ) work, namely the work is balanced. If the rooms are hole-free the exploration time is also asymptotically optimal, O ( N / k ) . To our knowledge, this is the first agent coordination algorithm that considers simultaneously work balancing and small exploration time.

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/., Author summary Small organic ligands bind to the locations of chemical specificity and affinity on their protein targets, called binding sites. A typical ligand-binding site is a small pocket formed by a few residues while the remaining protein structure acts as a framework providing the correct orientation of binding residues. Annotating ligand-binding sites is complicated by a fact that the same small molecule often binds to similar pockets but located in different proteins. In order to improve the detection and classification of binding pockets in proteins, we developed a new computational tool, DeepDrug3D. Our algorithm employs a convolutional neural network, a class of deep learning already commonly used in visual imagery analysis, recommender systems, and natural language processing. DeepDrug3D is able to accurately classify binding sites by learning the patterns of specific molecular interactions between ligands and their protein targets, such as hydrogen bonds, aromatic and hydrophobic contacts. Although the current proof-of-concept implementation is limited to a few most abundant functional classes, the repertoire of pocket types handled by DeepDrug3D will significantly be expanded in the near future.

Nowadays, automatic object-size measurement (AOSM) techniques are in high demand since there are numerous applications including three-dimensional multimedia entertainment games, cyber-physical interaction, and real-time geographical survey. When a scene is complex with many objects, the AOSM problem is quite challenging because it is very hard to describe the object of interest a priori. In this paper, we present a novel efficient automatic human-height measurement scheme using a single camera. Our proposed new scheme is very robust so that the heights of multiple persons within the scene can be estimated automatically and simultaneously. The experimental results demonstrate that the average error percentage is less than 2% in general.

In this paper, we propose a new hierarchical radio-frequency identification (RFID) tag- recognition method based on the graph-based automatic modulation classification (AMC) and direct-sequence spread-spectrum (DSSS). In our proposed method, RFID tags can be modulated using different modulation schemes according to different scenarios (e.g., different users or different devices). For each modulation scheme, the direct-sequence spread-spectrum strategy is employed to allow simultaneous transmissions of multiple tags. In the first hierarchy, different modulation types are employed to distinguish different users, the graph-based AMC is built upon the periodicity of the modulated signals. The cyclic spectrum of the received signal is first established. The graph representation is then constructed according to the cyclic spectrum. Ultimately, robust features are extracted from the graph representation. In the second hierarchy, the DSSS scheme is utilized to differentiate the control or sensed data carried by individual tags, the signature sequence set with low cross- correlations is generated from Gold and Kasami sequences. In the third hierarchy, the information data sequences are thus spread by these signature sequences. In our proposed new RFID framework, multiple tags can transmit the signals simultaneously in the same frequency band where the dominant tag signal will be identified and its carried information can be recovered. Monte Carlo simulation results demonstrate the promising performance of our proposed new scheme.

Quick Response (QR) code is a two-dimensional bar-code, which is quite popular due to its excellent storage capacity and error resilience. Generally, QR codes are widely used to store text information such as URL links, geographical coordinates, name cards, inventory information, authorship, etc. To reach the current limit of QR codes, in this paper, we would like to propose an innovative multimedia archiving technique, which is built upon the advanced signal processing scheme to tackle the multiple QR codes all at once. The multimedia data often include texts, images, audio data, special-purpose codes, etc. The recently proposed software-defined multiplexing code (SDMC) can be applied to combine all of them even though each type of data would have the individual data format different from others. Our proposed new archiving technique involves two phases, namely multimedia-amalgamation (MA) and multimedia-detachment (MD). In the MA phase, the multimedia data, regardless of their data format, can be converted to the binary streams; then the SDMC will be employed to aggregate them together in a longer binary stream; such an ultimate long binary stream will be converted to the QR codes. The QR codes, protected by the inherent error-correction mechanism, will thus be placed on a sheet or multiple sheets with a uniform spacing. The sheet(s) containing multiple QR codes can thus be archived in soft (PDF) or hard (print-out) copies. In the MD (recovery) phase, one can scan these PDF files and employ our designed signal processing algorithms to separate the individual QR codes; then the corresponding QR decoder can convert these QR codes back to the original binary stream. Finally the unstuffing algorithm in the SDMC can detach the individual data from the long binary stream composed by the multimedia mixture.

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).

Nowadays, the sufficient quality-of-service (QoS) provision for mobile applications remains a major challenge in any wireless network. Conventional sufficient QoS provision techniques using resource allocation, data scheduling, and cross-layer optimization have been proposed to tackle this problem. Nevertheless, due to the unpredictable nature of wireless channel conditions, the QoS improvements resulting from the aforementioned approaches are often unsatisfactory. In this paper, we would like to follow our previous concept, namely user-placement ushering (UPU), by use of the user's mobility. A mobile user can be relocated to an optimal, or at least a better place to boost the QoS for a particular application. Novel fast algorithms are devised here to usher (guide) the mobile user to an appropriate spot with sufficient QoS, which is nearby. We address the UPU problem to accommodate realistic complex indoor environments, where obstacles are present. Our simulation results have demonstrated that our new fast UPU algorithms are capable of finding new appropriate locations satisfying the required QoSs for different wireless network applications.

This paper proposes a novel approach to measure the object size using a regular digital camera. Nowadays, the remote object-size measurement is very crucial to many multimedia applications. Our proposed computer-aided automatic object-size measurement technique is based on a new depth-information extraction (range finding) scheme using a regular digital camera. The conventional range finders are often carried out using the passive method such as stereo cameras or the active method such as ultrasonic and infrared equipment. They either require the cumbersome set-up or deal with point targets only. The proposed approach requires only a digital camera with certain image processing techniques and relies on the basic principles of visible light. Experiments are conducted to evaluate the performance of our proposed new object-size measurement mechanism. The average error-percentage of this method is below 2%. It demonstrates the striking effectiveness of our proposed new method.

In this paper, a novel approach to locate the activation points of atrial fibrillation (AF) is proposed. This new method is built upon machine learning, where common parameters, such as dominant frequency, first harmonic frequency, etc., are adopted. Features are extracted from the original electrocardiography (ECG) and then clustering is performed to classify the ECG signals into two groups, namely activation and nonactivation points. The experimental results are compared with those from the state-of-the-art system, Topera, used in East Jefferson General Hospital nowadays.