MCFF-MTDDI: multi-channel feature fusion for multi-typed drug-drug interaction prediction.

Adverse drug-drug interactions (DDIs) have become an increasingly serious problem in the medical and health system. Recently, the effective application of deep learning and biomedical knowledge graphs (KGs) have improved the DDI prediction performance of computational models. However, the problems of feature redundancy and KG noise also arise, bringing new challenges for researchers. To overcome these challenges, we proposed a Multi-Channel Feature Fusion model for multi-typed DDI prediction (MCFF-MTDDI). Specifically, we first extracted drug chemical structure features, drug pairs' extra label features, and KG features of drugs. Then, these different features were effectively fused by a multi-channel feature fusion module. Finally, multi-typed DDIs were predicted through the fully connected neural network. To our knowledge, we are the first to integrate the extra label information into KG-based multi-typed DDI prediction; besides, we innovatively proposed a novel KG feature learning method and a State Encoder to obtain target drug pairs' KG-based features which contained more abundant and more key drug-related KG information with less noise; furthermore, a Gated Recurrent Unit-based multi-channel feature fusion module was proposed in an innovative way to yield more comprehensive feature information about drug pairs, effectively alleviating the problem of feature redundancy. We experimented with four datasets in the multi-class and the multi-label prediction tasks to comprehensively evaluate the performance of MCFF-MTDDI for predicting interactions of known-known drugs, known-new drugs and new-new drugs. In addition, we further conducted ablation studies and case studies. All the results fully demonstrated the effectiveness of MCFF-MTDDI.

Learning multi-scale heterogenous network topologies and various pairwise attributes for drug-disease association prediction.

MOTIVATION: Identifying new therapeutic effects for the approved drugs is beneficial for effectively reducing the drug development cost and time. Most of the recent computational methods concentrate on exploiting multiple kinds of information about drugs and disease to predict the candidate associations between drugs and diseases. However, the drug and disease nodes have neighboring topologies with multiple scales, and the previous methods did not fully exploit and deeply integrate these topologies. RESULTS: We present a prediction method, multi-scale topology learning for drug-disease (MTRD), to integrate and learn multi-scale neighboring topologies and the attributes of a pair of drug and disease nodes. First, for multiple kinds of drug similarities, multiple drug-disease heterogenous networks are constructed respectively to integrate the similarities and associations related to drugs and diseases. Moreover, each heterogenous network has its specific topology structure, which is helpful for learning the corresponding specific topology representation. We formulate the topology embeddings for each drug node and disease node by random walking on each heterogeneous network, and the embeddings cover the neighboring topologies with different scopes. Because the multi-scale topology embeddings have context relationships, we construct Bi-directional long short-term memory-based module to encode these embeddings and their relationships and learn the neighboring topology representation. We also design the attention mechanisms at feature level and at scale level to obtain the more informative pairwise features and topology embeddings. A module based on multi-layer convolutional networks is constructed to learn the representative attributes of the drug-disease node pair according to their related similarity and association information. Comprehensive experimental results indicate that MTRD achieves the superior performance than several state-of-the-art methods for predicting drug-disease associations. MTRD also retrieves more actual drug-disease associations in the top-ranked candidates of the prediction result. Case studies on five drugs further demonstrate MTRD's ability in discovering the potential candidate diseases for the interested drugs.

Error detection using a multi-channel hybrid network with a low-resolution detector in patient-specific quality assurance.

PURPOSE: This study aimed to develop a hybrid multi-channel network to detect multileaf collimator (MLC) positional errors using dose difference (DD) maps and gamma maps generated from low-resolution detectors in patient-specific quality assurance (QA) for Intensity Modulated Radiation Therapy (IMRT). METHODS: A total of 68 plans with 358 beams of IMRT were included in this study. The MLC leaf positions of all control points in the original IMRT plans were modified to simulate four types of errors: shift error, opening error, closing error, and random error. These modified plans were imported into the treatment planning system (TPS) to calculate the predicted dose, while the PTW seven29 phantom was utilized to obtain the measured dose distributions. Based on the measured and predicted dose, DD maps and gamma maps, both with and without errors, were generated, resulting in a dataset with 3222 samples. The network's performance was evaluated using various metrics, including accuracy, sensitivity, specificity, precision, F1-score, ROC curves, and normalized confusion matrix. Besides, other baseline methods, such as single-channel hybrid network, ResNet-18, and Swin-Transformer, were also evaluated as a comparison. RESULTS: The experimental results showed that the multi-channel hybrid network outperformed other methods, demonstrating higher average precision, accuracy, sensitivity, specificity, and F1-scores, with values of 0.87, 0.89, 0.85, 0.97, and 0.85, respectively. The multi-channel hybrid network also achieved higher AUC values in the random errors (0.964) and the error-free (0.946) categories. Although the average accuracy of the multi-channel hybrid network was only marginally better than that of ResNet-18 and Swin Transformer, it significantly outperformed them regarding precision in the error-free category. CONCLUSION: The proposed multi-channel hybrid network exhibits a high level of accuracy in identifying MLC errors using low-resolution detectors. The method offers an effective and reliable solution for promoting quality and safety of IMRT QA.

A High-Performance System for Weak ECG Real-Time Detection.

Wearable devices have been widely used for the home monitoring of physical activities and healthcare conditions, among which ambulatory electrocardiogram (ECG) stands out for the diagnostic cardiovascular information it contains. Continuous and unobtrusive sensing often requires the integration of wearable sensors to existing devices such as watches, armband, headphones, etc.; nonetheless, it is difficult to detect high-quality ECG due to the nature of low signal amplitude at these areas. In this paper, a high-performance system with multi-channel signal superposition for weak ECG real-time detection is proposed. Firstly, theoretical analysis and simulation is performed to demonstrate the effectiveness of this system design. The detection system, including electrode array, acquisition board, and the application (APP), is then developed and the electrical characteristics are measured. A common mode rejection ratio (CMRR) of up to 100 dB and input inferred voltage noise below 1 µV are realized. Finally, the technique is implemented in form of ear-worn and armband devices, achieving an SNR over 20 dB. Results are also compared with the simultaneous recording of standard lead I ECG. The correlation between the heart rates derived from experimental and standard signals is higher than 0.99, showing the feasibility of the proposed technique.

Adaptive Weighted Error-Correction Method Based on the Error Distribution Characteristics of Multi-Channel Alignment.

As process nodes of advanced integrated circuits continue to decrease below 10 nm, the requirement for overlay accuracy is becoming stricter. The alignment sensor measures the position of the alignment mark relative to the wafer; thus, sub-nanometer alignment position accuracy is vital. The Phase Grating Alignment (PGA) method is widely used due to its high precision and stability. However, the alignment error caused by the mark asymmetry is the key obstacle preventing PGA technology from achieving sub-nanometer alignment accuracy. This error can be corrected using many methods, such as process verification and multi-channel weighted methods based on multi-diffraction, multi-wavelength and multi-polarization state alignment sensors. However, the mark asymmetry is unpredictable, complex and difficult to obtain in advance. In this case, the fixed-weight method cannot effectively reduce the alignment error. Therefore, an adaptive weighted method based on the error distribution characteristic of a multi-channel is proposed. Firstly, the simulation result proves that the error distribution characteristic of the multi-alignment result has a strong correlation with the mark asymmetry. Secondly, a concrete method of constructing weight values based on error distribution is described. We assume that the relationship between the weight value of each channel and the deviations of all channels' results is second-order linear. Finally, without other prior process correction in the simulation experiment, the residual error's Root Mean Square (RMS) of fixed weighted method is 14.0 nm, while the RMS of the adaptive weighted method is 0.01 nm, when dealing with five typical types of mark asymmetry. The adaptive weighted method exhibits a more stable error correction effect under unpredictable and complicated mark asymmetry.

High-Performance Four-Channel Tactile Sensor for Measuring the Magnitude and Orientation of Forces.

Flexible sensors have gained popularity in recent years. This study proposes a novel structure of a resistive four-channel tactile sensor capable of distinguishing the magnitude and direction of normal forces acting on its sensing surface. The sensor uses EcoflexTM00-30 as the substrate and EGaIn alloy as the conductive filler, featuring four mutually perpendicular and curved channels to enhance the sensor's dynamic responsiveness. Experiments and simulations show that the sensor has a large dynamic range (31.25-100 mΩ), high precision (deviation of repeated pressing below 0.1%), linearity (R2 above 0.97), fast response/recovery time (0.2 s/0.15 s), and robust stability (with fluctuations below 0.9%). This work uses an underactuated robotic hand equipped with a four-channel tactile sensor to grasp various objects. The sensor data collected effectively predicts the shapes of the objects grasped. Furthermore, the four-channel tactile sensor proposed in this work may be employed in smart wearables, medical diagnostics, and other industries.

Pulse Compression Shape-Based ADC/DAC Chain Synchronization Measurement Algorithm with Sub-Sampling Resolution.

In this article, we address the problem of synchronizing multiple analog-to-digital converter (ADC) and digital-to-analog converter (DAC) chains in a multi-channel system, which is constrained by the sampling frequency and inconsistencies among the components during system integration. To evaluate and compensate for the synchronization differences, we propose a pulse compression shape-based algorithm to measure the entire delay parameter of the ADC/DAC chain, which achieves sub-sampling resolution by mapping the shape of the discrete pulse compression peak to the signal propagation delay. Moreover, owing to the matched filtering in the pulse compression process, the algorithm exhibits good noise performance and is suitable for wireless scenarios. Experiments verified that the algorithm can achieve precise measurements with sub-sampling resolution in scenarios where the signal-to-noise ratio (SNR) is greater than -10 dB.

Phase Noise Compensation Algorithm for Space-Borne Azimuth Multi-Channel SAR.

Azimuth multi-channel synthetic aperture radar (SAR) has always been an important technical means to achieve high-resolution wide-swath (HRWS) SAR imaging. However, in the space-borne azimuth multi-channel SAR system, random phase noise will be produced during the operation of each channel receiver. The phase noise of each channel is superimposed on the SAR echo signal of the corresponding channel, which will cause the phase imbalance between the channels and lead to the generation of false targets. In view of the above problems, this paper proposes a random phase noise compensation method for space-borne azimuth multi-channel SAR. This method performs feature decomposition by calculating the covariance matrix of the echo signal and converts the random phase noise estimation into the optimal solution of the cost function. Considering that the phase noise in the receiver has frequency-dependent and time-varying characteristics, this method calculates the phase noise estimation value corresponding to each range-frequency point in the range direction and obtains the phase noise estimation value by expectation in the azimuth direction. The proposed random phase noise compensation method can suppress false targets well and make the radar present a well-focused SAR image. Finally, the usefulness of the suggested method is verified by simulation experiments.

A Novel Approach to Evaluating Crosstalk for Near-Infrared Spectrometers.

Multi-channel and multi-parameter near-infrared spectroscopy (NIRS) has gradually become a new research direction and hot spot due to its ability to provide real-time, continuous, comprehensive indicators of multiple parameters. However, multi-channel and multi-parameter detection may lead to crosstalk between signals. There is still a lack of benchmarks for the evaluation of the reliability, sensitivity, stability and response consistency of the NIRS instruments. In this study, a set of test methods (a human blood model test, ink drop test, multi-channel crosstalk test and multi-parameter crosstalk test) for analyzing crosstalk and verifying the reliability of NIRS was conducted to test experimental verification on a multi-channel (8-channel), multi-parameter (4-parameter) NIRS instrument independently developed by our team. Results show that these tests can be used to analyze the signal crosstalk and verify the reliability, sensitivity, stability and response consistency of the NIRS instrument. This study contributes to the establishment of benchmarks for the NIRS instrument crosstalk and reliability testing. These novel tests have the potential to become the benchmark for NIRS instrument reliability testing.

Application of Multi-Channel Synchronized Dynamic Strain Gauges in Monitoring the Neutral Axis Position and Prestress Loss of Box Girder Bridges.

The aim of this paper was to explore the application of multi-channel synchronized dynamic strain gauges in monitoring the neutral axis (N.A.) position of prestressed concrete box girders. The N.A. position has recently been proposed as an indicator for monitoring the health of bridge structures. Laboratory experiments were conducted on a prestressed T-beam under different prestress level conditions to investigate the correlation between the prestress magnitude and the N.A. position. In the development of the multi-channel synchronized dynamic strain gauges, edge computing was employed to significantly reduce the amount of data transmitted from the sensor nodes on-site. In edge computing, only the dynamic strain response caused by the maximum vehicle load in each minute is transmitted. This approach greatly enhances the monitoring efficiency and enables the realization of on-site non-computer-based monitoring systems. The laboratory test results of the prestressed T-beam showed that the N.A. position tends to move slightly downward as the prestress force increases. In other words, when the prestress force decreases due to loss, the N.A. position exhibits a slight upward movement. This study selected a newly constructed prestressed box girder as the subject for on-site measurement of the N.A. position using multi-channel synchronized dynamic strain gauges shortly after the prestress was applied. The on-site monitoring data indeed revealed a gradual upward movement of the N.A. position. This phenomenon confirmed that soon after the completion of prestressed concrete bridges, there is a gradual loss of prestress due to the significant shrinkage and creep effects of the early-age concrete. The on-site monitoring result aligned with the findings from the laboratory experiments, where the N.A. position was observed to move upward as the prestress decreased.

Hammerstein-Wiener Motion Artifact Correction for Functional Near-Infrared Spectroscopy: A Novel Inertial Measurement Unit-Based Technique.

Participant movement is a major source of artifacts in functional near-infrared spectroscopy (fNIRS) experiments. Mitigating the impact of motion artifacts (MAs) is crucial to estimate brain activity robustly. Here, we suggest and evaluate a novel application of the nonlinear Hammerstein-Wiener model to estimate and mitigate MAs in fNIRS signals from direct-movement recordings through IMU sensors mounted on the participant's head (head-IMU) and the fNIRS probe (probe-IMU). To this end, we analyzed the hemodynamic responses of single-channel oxyhemoglobin (HbO) and deoxyhemoglobin (HbR) signals from 17 participants who performed a hand tapping task with different levels of concurrent head movement. Additionally, the tapping task was performed without head movements to estimate the ground-truth brain activation. We compared the performance of our novel approach with the probe-IMU and head-IMU to eight established methods (PCA, tPCA, spline, spline Savitzky-Golay, wavelet, CBSI, RLOESS, and WCBSI) on four quality metrics: SNR, △AUC, RMSE, and R. Our proposed nonlinear Hammerstein-Wiener method achieved the best SNR increase (p < 0.001) among all methods. Visual inspection revealed that our approach mitigated MA contaminations that other techniques could not remove effectively. MA correction quality was comparable with head- and probe-IMUs.

Sensor-Integrated Chairs for Lower Body Strength and Endurance Assessment.

This paper describes an automated method and device to conduct the Chair Stand Tests of the Fullerton Functional Test Battery. The Fullerton Functional Test is a suite of physical tests designed to assess the physical fitness of older adults. The Chair Stand Tests, which include the Five Times Sit-to-Stand Test (5xSST) and the 30 Second Sit-to-Stand Test (30CST), are the standard for measuring lower-body strength in older adults. However, these tests are performed manually, which can be labor-intensive and prone to error. We developed a sensor-integrated chair that automatically captures the dynamic weight and distribution on the chair. The collected time series weight-sensor data is automatically uploaded for immediate determination of the sit-to-stand timing and counts, as well as providing a record for future comparison of lower-body strength progression. The automatic test administration can provide significant labor savings for medical personnel and deliver much more accurate data. Data from 10 patients showed good agreement between the manually collected and sensor-collected 30CST data (M = 0.5, SD = 1.58, 95% CI = 1.13). Additional data processing will be able to yield measurements of fatigue and balance and evaluate the mechanisms of failed standing attempts.

[Precise measurement of human heart rate based on multi-channel radar data fusion].

To achieve non-contact measurement of human heart rate and improve its accuracy, this paper proposes a method for measuring human heart rate based on multi-channel radar data fusion. The radar data were firstly extracted by human body position identification, phase extraction and unwinding, phase difference, band-pass filtering optimized by power spectrum entropy, and fast independent component analysis for each channel data. After overlaying and fusing the four-channel data, the heartbeat signal was separated using frost-optimized variational modal decomposition. Finally, a chirp Z-transform was introduced for heart rate estimation. After validation with 40 sets of data, the average root mean square error of the proposed method was 2.35 beats per minute, with an average error rate of 2.39%, a Pearson correlation coefficient of 0.97, a confidence interval of [-4.78, 4.78] beats per minute, and a consistency error of -0.04. The experimental results show that the proposed measurement method performs well in terms of accuracy, correlation, and consistency, enabling precise measurement of human heart rate.

RegiSTORM: channel registration for multi-color stochastic optical reconstruction microscopy.

BACKGROUND: Stochastic optical reconstruction microscopy (STORM), a super-resolution microscopy technique based on single-molecule localizations, has become popular to characterize sub-diffraction limit targets. However, due to lengthy image acquisition, STORM recordings are prone to sample drift. Existing cross-correlation or fiducial marker-based algorithms allow correcting the drift within each channel, but misalignment between channels remains due to interchannel drift accumulating during sequential channel acquisition. This is a major drawback in multi-color STORM, a technique of utmost importance for the characterization of various biological interactions. RESULTS: We developed RegiSTORM, a software for reducing channel misalignment by accurately registering STORM channels utilizing fiducial markers in the sample. RegiSTORM identifies fiducials from the STORM localization data based on their non-blinking nature and uses them as landmarks for channel registration. We first demonstrated accurate registration on recordings of fiducials only, as evidenced by significantly reduced target registration error with all the tested channel combinations. Next, we validated the performance in a more practically relevant setup on cells multi-stained for tubulin. Finally, we showed that RegiSTORM successfully registers two-color STORM recordings of cargo-loaded lipid nanoparticles without fiducials, demonstrating the broader applicability of this software. CONCLUSIONS: The developed RegiSTORM software was demonstrated to be able to accurately register multiple STORM channels and is freely available as open-source (MIT license) at https://github.com/oystein676/RegiSTORM.git and https://doi.org/10.5281/zenodo.5509861 (archived), and runs as a standalone executable (Windows) or via Python (Mac OS, Linux).

Metabolic cues impact non-oscillatory intergeniculate leaflet and ventral lateral geniculate nucleus: standard versus high-fat diet comparative study.

The intergeniculate leaflet and ventral lateral geniculate nucleus (IGL/VLG) are subcortical structures involved in entrainment of the brain's circadian system to photic and non-photic (e.g. metabolic and arousal) cues. Both receive information about environmental light from photoreceptors, exhibit infra-slow oscillations (ISO) in vivo, and connect to the master circadian clock. Although current evidence demonstrates that the IGL/VLG communicate metabolic information and are crucial for entrainment of circadian rhythms to time-restricted feeding, their sensitivity to food intake-related peptides has not been investigated yet. We examined the effect of metabolically relevant peptides on the spontaneous activity of IGL/VLG neurons. Using ex vivo and in vivo electrophysiological recordings as well as in situ hybridisation, we tested potential sensitivity of the IGL/VLG to anorexigenic and orexigenic peptides, such as cholecystokinin, glucagon-like peptide 1, oxyntomodulin, peptide YY, orexin A and ghrelin. We explored neuronal responses to these drugs during day and night, and in standard vs. high-fat diet conditions. We found that IGL/VLG neurons responded to all the substances tested, except peptide YY. Moreover, more neurons responded to anorexigenic drugs at night, while a high-fat diet affected the IGL/VLG sensitivity to orexigenic peptides. Interestingly, ISO neurons responded to light and orexin A, but did not respond to the other food intake-related peptides. In contrast, non-ISO cells were activated by metabolic peptides, with only some being responsive to light. Our results show for the first time that peptides involved in the body's energy homeostasis stimulate the thalamus and suggest functional separation of the IGL/VLG cells. KEY POINTS: The intergeniculate leaflet and ventral lateral geniculate nucleus (IGL/VLG) of the rodent thalamus process various signals and participate in circadian entrainment. In both structures, cells exhibiting infra-slow oscillatory activity as well as non-rhythmically firing neurons being observed. Here, we reveal that only one of these two groups of cells responds to anorexigenic (cholecystokinin, glucagon-like peptide 1 and oxyntomodulin) and orexigenic (ghrelin and orexin A) peptides. Neuronal responses vary depending on the time of day (day vs. night) and on the diet (standard vs. high-fat diet). Additionally, we visualised receptors to the tested peptides in the IGL/VLG using in situ hybridisation. Our results suggest that two electrophysiologically different subpopulations of IGL/VLG neurons are involved in two separate functions: one related to the body's energy homeostasis and one associated with the subcortical visual system.

Effects of radiofrequency channel numbers on B1+ mapping using the Bloch-Siegert shift method.

PURPOSE: This paper aims to investigate the impact of the channel numbers on the performance of B1+ mapping, by using the Bloch-Siegert shift (BSS) method. B1+ mapping plays a crucial role in various brain imaging protocols. THEORY AND METHODS: We simulated the radiofrequency field of the human head model in six groups of multi-channel receive coil with a range of different channel numbers. MR signals were synthesized according to the standard BSS sequence, with quantified Gaussian added. Next, we combined the signals of each channel to reconstruct the B1+ map by weighted averaging and maximum likelihood estimation strategies and evaluate the bias by relative standard deviation of each coil. RESULTS: The simulation results revealed that the accuracy of B1+ maps improved with the increasing of channel numbers, meanwhile the per channel efficiency of B1+maps accuracy gradually decrease. Both trends slowed down when the channel numbers reached 12 or above. CONCLUSION: Our finding suggests that increasing the channel numbers can improve the accuracy of B1+map. However, a diminishing efficiency of per channel accuracy improvement was overserved, indicating that the relationship between quality of B1+ map and the channel numbers is nonlinear. Based on these findings, our study provides a reference for determining channel numbers to achieve a balance of coil selection and manufacturing cost. It also provides a theoretical basis for evaluating other B1+ mapping techniques.

Chiroptical Nanocellulose Bio-Labels for Independent Multi-Channel Optical Encryption.

Advanced multiplexing optical labels with multiple information channels provide a powerful strategy for large-capacity and high-security information encryption. However, current optical labels face challenges of difficulty to realize independent multi-channel encryption, cumbersome design, and environmental pollution. Herein, multiplexing chiroptical bio-labels integrating with multiple optical elements, including structural color, photoluminescence (PL), circular polarized light activity, humidity-responsible color, and micro/nano physical patterns, are constructed in complex design based on host-guest self-assembly of cellulose nanocrystals and bio-gold nanoclusters. The thin nanocellulose labels exhibit tunable circular polarized structural color crossover the entire visible wavelength and circularly polarized PL with the highest-recorded dissymmetry factor up to 1.05 due to the well-ordered chiral organization of templated gold nanoclusters. Most importantly, these elements can independently encode customized anti-counterfeiting information to achieve five independent channels of high-level anti-counterfeiting, which are rarely achieved in traditional materials and design counterparts. Considering the exceptional seamless integration of five independent encryption channels and the recyclable features of labels, the bio-labels have great potential for the next generation anti-counterfeiting materials technology.

Multiple slot modules for high field magnetic resonance imaging array coils.

PURPOSE: Mitigating coupling effects between coil elements represents a continuing challenge. Here, we present a 16-bowtie slot volume coil arranged in eight independent dual-slot modules without the use of any decoupling circuits. METHODS: Two electrically short "bowtie" slot antennas were used to form a "module." A bowtie configuration was chosen because electromagnetic modeling results show that bowtie slots exhibit improved B 1 + P in $$ \frac{B_1^{+}}{\sqrt{P_{in}}} $$ efficiency when compared to thin rectangular slots. An eight-module volume coil was evaluated through electromagnetic modeling, bench tests, and MRI experiments at 4.7 T. RESULTS: Bench tests indicate that worst-case coupling between modules did not exceed -14.5 dB. MR images demonstrate well-localized patterns about single excited modules confirming the low coupling between modules. Homogeneous MR images were acquired from a synthesized quadrature birdcage transmit mode. MRI experiments show that the RF power requirements for the proposed coil are 9.2 times more than a birdcage coil. Whereas from simulations performed to assess the proposed coil losses, the total power dissipated in the phantom was 1.1 times more for the birdcage. Simulation results at 7 T reveal an equivalent B1 + homogeneity when compared with an eight-dipole coil. CONCLUSION: Although exhibiting higher RF power requirements, as a transmit coil when the power availability is not a restriction, the inherently low coupling between electrically short slots should enable the use of many slot elements around the imaging volume. The slot module described in this paper should be useful in the design of multi-channel transmit coils.

Development of a dual-electrospray ionization source with in-line absorbance-based voltage control.

Emitter tip arrays for electrospray ionization have been used for a variety of MS sample introduction purposes, including detection of multiple sample eluent streams and improved accuracy through parallel infusion of an internal standard. User control is typically required for targeted application of high voltage to specific channels to maximize analyte signal and minimize other background signals. In this communication, an automated approach to applying electrospray voltage only when a detectable analyte is present is described. An in-line absorbance detector is used to identify the presence of an analyte in the fluidic path between the sample introduction valve and the mass spectrometer. A Raspberry Pi-controlled system is then used to apply high voltage to a downstream emitter tip at the MS inlet following a delay volume between the detectors. Demonstration of this technique on two parallel sample channels is reported, including a pulsed voltage application to maximize signal when analytes elute on each channel simultaneously.

Toward drug-miRNA resistance association prediction by positional encoding graph neural network and multi-channel neural network.

Drug discovery is a costly and time-consuming process, and most drugs exert therapeutic efficacy by targeting specific proteins. However, there are a large number of proteins that are not targeted by any drug. Recently, miRNA-based therapeutics are becoming increasingly important, since miRNA can regulate the expressions of specific genes and affect a variety of human diseases. Therefore, it is of great significance to study the associations between miRNAs and drugs to enable drug discovery and disease treatment. In this work, we propose a novel method named DMR-PEG, which facilitates drug-miRNA resistance association (DMRA) prediction by leveraging positional encoding graph neural network with layer attention (LAPEG) and multi-channel neural network (MNN). LAPEG considers both the potential information in the miRNA-drug resistance heterogeneous network and the specific characteristics of entities (i.e., drugs and miRNAs) to learn favorable representations of drugs and miRNAs. And MNN models various sophisticated relations and synthesizes the predictions from different perspectives effectively. In the comprehensive experiments, DMR-PEG achieves the area under the precision-recall curve (AUPR) score of 0.2793 and the area under the receiver-operating characteristic curve (AUC) score of 0.9475, which outperforms the most state-of-the-art methods. Further experimental results show that our proposed method has good robustness and stability. The ablation study demonstrates each component in DMR-PEG is essential for drug-miRNA drug resistance association prediction. And real-world case study presents that DMR-PEG is promising for DMRA inference.