Single-cell RNA-seq (scRNAseq) analyses performed at the cellular level aim to understand the cellular landscape of tissue sections, offer insights into rare cell-types, and identify marker genes for annotating distinct cell types. ScRNAseq analyses are widely applied to cancer research to understand tumor heterogeneity, disease progression, and resistance to therapy. Single-cell data processing is a challenging task due to its high-dimensionality, sparsity, and having imbalanced class(cell-type) distributions. An accurate cell-type identification is highly dependent on preprocessing and quality control steps. To address these issues, generative models have been widely used in recent years. Techniques frequently used include Variational Autoencoders (VAE), Generative Adversarial Networks (GANs), Gaussian-based methods, and, more recently, Flow-based (FB) generative models. We developed a Masked Affine Autoregressive transform-embedded FB (MAF-FB) model. Then, to improve MAF-FB further, we incorporated a mixture of experts (MOE) of attention mechanisms on top of it, resulting in our proposed MOE-FB model. We conducted a comparative analysis of fundamental generative models, aiming to serve as a preliminary guidance for developing novel automated scRNAseq data analysis systems. We performed a large-scale analysis by combiningfour datasets derived from pancreatic tissue sections and for further generalizability assessments, we employed Peripheral Blood Mononuclear Cells (PBMC68K and PBMC3K) and Human Cell Atlas Bone Marrow (HCA-BM10K) datasets. We utilized VAE, GAN, Gaussian Copula, and Automated Cell-Type-informed Introspective Variational Autoencoder (ACTIVA), and compared them against our two novel FB models, MAF-FB and MOE-FB for ScRnaseq synthesis. To evaluate the performances of generative models, we used various discrepancy metrics and performed automated cell-type classification tasks. We also identified differentially expressed genes for each cell type, and inferred cell-cell interactions based on ligand-receptor bindings across distinct cell-type pairs. Among the generative models, FB models, especially MOE-FB, consistently outperformed others across all experimental setups in both discrepancy metrics with comparison to the baseline test set and cell-type classification tasks (with an F1-score of 0.90 precision of 0.89 and recall of 0.92 for the integrated pancreatic datasets). MOE-FB produced biologically more relevant synthetic data, and ligand-receptor-based cell-cell interactions inferred from the synthetic cells closely resemble the original data, achieving an RMSE of 0.65 against the corresponding pancreatic test set. These findings highlight the potential and promising use of FB models, especially MOE-FB, in scRNAseq analyses.

The Biological sequence data are increasing rapidly, so there is a vital need of effective method for gene detection. Predicting of splice site is an important part of gene finding. Therefore, attempts to improve the prediction accuracy of the computational methods for splice sites detection continue. In this paper we propose a hybrid algorithm for splice sites prediction by combining AdaBoost classifier with a novel nucleotide encoding method, namely FDDM. Our encoding method provides frequency difference between the true sites and false sites (FD) along with distance measure (DM). The proposed method produces an improvement in comparison with the result of current methods such as MM1-SVM, Reduced MM1-SVM, SVM-B, LVMM, DM-SVM, DM2-AdaBoost and MSC+Pos(+APR)-SVM, when applied to the HS3D dataset with repeated 10-fold cross validation. In addition, for demonstrating the stability of the method, we also applied it to NN269 dataset. The obtained results indicate that the new method is practicable and efficient.

Biomedical signals (BSs), which give information about the normal condition and also the inherent irregularities of our body, are expected to have non-stationary character due to the time-varying behavior of physiological systems. The Fourier transform and the short time Fourier transform are the widely used frequency and time-frequency analysis methods for extracting information from BSs with fixed frequency and time-frequency resolution respectively. However, in order to derive relevant information from non-stationary BSs, an appropriate analysis method which exhibits adjustable time-frequency resolution is needed. The wavelet transform (WT) can be used as a mathematical microscope in which the time-frequency resolution can be adjusted according to the different parts of the signal. The discrete wavelet transform (DWT) is a fast and discretized implementation for classical WT. Due to the aliasing, lack of directionality and shift-variance disadvantages, the DWT exhibits limited performance in the process of BSs. In literature, an improved version of the DWT, which is named as Dual Tree Complex Wavelet Transform (DTCWT), is employed in the analysis of BSs with great success. In this study, considering the improvements in embedded system technology and the needs for wavelet based real-time feature extraction or de-noising systems in portable medical devices, the DTCWT is implemented as a sub-system in field programmable gate arrays. In proposed hardware architecture, for every data input-channel, DTCWT is implemented by using only one adder and one multiplier. Additionally, considering the multi-channel outputs of biomedical data acquisition systems, this architecture is designed with the capability of running in parallel for N channels.

In this study, we propose a novel method for medical data classification, it is the integration of new heuristic algorithm that get inspired the black hole phenomenon called as Black Hole Algorithm (BHA) and decision tree (C4.5). To evaluate the effectiveness of our proposed method, it is implemented on 2 microarray dataset and 5 different medical data sets obtained from UCI machine learning databases. The results of BHA + C4.5 implementation are compared to seven well-known benchmark classification methods (support vector machine under the kernel of Radial Basis Function, Classification And Regression Tree (CART), C4.5 decision tree, C5.0 decision tree, Linear Discriminant Analysis (LDA), Self-Organizing Map and Naive Bayes). Repeated five-fold cross-validation method is used to justify the performance of classifiers. Two criteria are used for model evaluation. They are Matthews' Correlation Coefficient (MCC) and Accuracy. Experimental results show that our proposed method outperforms the other classification methods in MCC index and have higher accuracy after SVM and LDA classifiers.

Transcranial Doppler (TCD) is a widely used, non-invasive, rapid and reproducible monitoring method for observing the condition of middle cerebral artery. Micro embolic signals, which appear in various clinical scenarios such as; carotid stenosis, aortic arch plaques, atrial fibrillation, myocardial infarction, patent foramen ovale and valvular stenosis, can be detected by the analysis of TCD signals. Discrete wavelet transform based methods were frequently used in literature for micro embolic signal detection. However, in all the previously used complex/non-complex discrete wavelet transform based methods, low Q-factor wavelets were employed for feature extraction. Low Q-factor wavelets have been successfully used for processing piecewise smooth signals but for the embolic signals, a discrete wavelet transform with better frequency resolution is needed. Therefore in this study, a novel Directional Dual Tree Rational Dilation Wavelet Transform (DDT-RADWT), in which the Q-factor of the analysis and synthesis filters can be adjusted due to the properties of signal of interest, is used as the feature extractor. DDT-RADWT is applied to a dataset consisting of 130 micro embolic signals and 130 non-embolic signals (65 artifacts and 65 Doppler speckles) and the obtained coefficients are used as features. In the proposed method, in order to utilize from the different frequency characteristics of micro embolic, artifact and Doppler speckle signals, the DDT-RADWT is applied with high Q-factor filters. The extracted coefficients are given to k-NN and SVM classifiers with the aim of discriminating two classes of micro embolic signals and non-embolic signals. The results show that higher general accuracy and micro embolic signal detection accuracies are obtained with high Q-factor wavelet analysis.

In order to achieve informative gene from thousands of candidate genes contributing to the symptom of cancer, two novel gene selection approaches for classification of multiclass microarray datasets are proposed. In the first, method we use k-means clustering to remove redundancy, and then apply Random Forest (RF) to rank each gene in every cluster to remove irrelevance. The top scored genes from each cluster is gathered and a new feature subset (filtered genes) is generated. At the last stage filtered genes is used as input to eight benchmark classification methods. In the second approach we develop a novel method utilizing Particle Swarm Optimization combined with BoostedC5.0 decision tree as the classifier. We apply filtered genes that achieved by first proposed method as input to PSO+BoostedC5.0 classifier and compare the performance of it with 8 classifiers. Experimental results show that by using clustering technique and RF ranking we can give a true pattern which select a smaller number of feature subset and obtain better classification accuracy. Also by applying this method on ten microarray datasets and using filtered genes as input for 9 classifiers we showed that proposed PSO+BoostedC5.0 simplifies features effectively and obtains higher classification accuracy compared to the other classification methods.

MOTIVATION: Gene network inference (GNI) algorithms enable the researchers to explore the interactions among the genes and gene products by revealing these interactions. The principal process of the GNI algorithms is to obtain the association scores among genes. Although there are several association estimators used in different applications, there is no commonly accepted estimator as the best one for the GNI applications. In this study, 27 different interaction estimators were reviewed and 14 most promising ones among them were evaluated by using three popular GNI algorithms with two synthetic and two real biological datasets belonging to Escherichia coli bacteria and Saccharomyces cerevisiae yeast. Influences of the Copula Transform (CT) pre-processing operation on the performance of the interaction estimators are also observed. This study is expected to assist many researchers while studying with GNI applications. RESULTS: B-spline, Pearson-based Gaussian and Spearman-based Gaussian association score estimators outperform the others for all datasets in terms of the performance and runtime. In addition to this, it is observed that, when the CT operation is used, inference performances of the estimators mostly increase, especially for two synthetic datasets. Detailed evaluations and discussions are given in the experimental results. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Gene Network Inference (GNI) algorithms enable searching the interactions among the several cell molecules. Many application fields such as computational biology and pharmacology utilize the GNI algorithms to illustrate the interaction networks of the cell molecules. Association score estimation is the most crucial step of the GNI applications. B-spline is a popular approach, which efficiently estimates the interaction scores between the variable (gene) pairs. In this study inference performance of the B-spline estimator according to the selected spline order is examined. In addition to evaluating B-spline performance according to the spline order, influences of using a frequently used pre-processing operation Copula Transform on the performance of B-spline is also examined. Conservative Causal Core network (C3NET) GNI algorithm is used in the experiments. At the overall analysis, B-spline estimator with the spline order 2 gave the best inference performance among the selected spline orders from 1 to 10.

Recent years have seen the rapid development of microsensor technology, system on chip design, wireless technology and ubiquitous computing. When assembled into a complex microsystem the technologies become powerful tools in medical diagnostics, environmental monitoring and personal connectivity. In this paper we describe the demonstration of a silicon chip that has all the attributes required of a microsystem for use in these applications. The design methodology we have employed is a variant of the system on chip approach whereby many intellectual property blocks are integrated at a high level in the design flow. Our intellectual property blocks include the analogue sensor instrumentation for temperature and pH, a data multiplexing and conversion module, a digital platform based around an 8-bit microcontroller, data encoding for spread-spectrum wireless transmission and a RF section requiring very few off-chip components. The chip has been fully evaluated and tested by connection to external sensors. Each block has well defined interfaces so that they can be easily reused in future designs targeted to different applications

Some of the most important challenges in health-care technologies have been identified to be development of noninvasive systems and miniaturization. In developing the core technologies, progress is required in pushing the limits of miniaturization, minimizing the costs and power consumption of microsystems components, developing mobile/wireless communication infrastructures and computing technologies that are reliable. The implementation of such miniaturized systems has become feasible by the advent of system-on-chip technology, which enables us to integrate most of the components of a system on to a single chip. One of the most important tasks in such a system is to convey information reliably on a multiple-access-based environment. When considering the design of telecommunication system for such a network, the receiver is the key performance critical block. The paper describes the application environment, the choice of the communication protocol, the implementation of the transmitter and receiver circuitry, and research work carried out on studying the impact of input data characteristics and internal data path complexity on area and power performance of the receiver. We provide results using a test data recorded from a pH sensor. The results demonstrate satisfying functionality, area, and power constraints even when a degree of programmability is incorporated in the system.

Mobile video processing as defined in standards like MPEG-4 and H.263 contains a number of timeconsuming computations that cannot be efficiently executed on current hardware architectures. The authors recently introduced a reconfigurable SoC platform that permits a low-power, high-throughput and flexible implementation of the motion estimation and DCT algorithms. The computations are done using domainspecific reconfigurable arrays that have demonstrated up to 75% reduction in power consumption when compared to generic FPGA architecture, which makes them suitable for portable devices. This paper presents and compares different configurations of the arrays to efficiently implementing DCT and motion estimation algorithms. A number of algorithms are mapped into the various reconfigurable fabrics demonstrating the flexibility of the new reconfigurable SoC architecture and its ability to support a number of implementations having different performance characteristics.

A higher-radix algebra for full-addition of two numbers is described and realised by combining multivalued logic min, max, literal and cyclic operators in terms disjoint terms. The latter operator is designed by using a current-mode threshold circuit while the other operator is realised by only voltage-mode switching circuits. The threshold circuit employed allows for much higher radices compared to architectures employing voltage-mode binary logic switching circuits as well as better mismatch properties compared to previous threshold circuits. Due to disjoint terms involved, multi-valued logic min and max operators can be replaced with ordinary transmission operation and addition, respectively. Resultant a single-digit, radix-8 full-adder and its 3-bit counterpart voltage-mode circuits are realised and compared. The algorithm is also exploited for a multi-digit case and its HSPICE simulation results are presented.

Asymptomatic circulating emboli can be detected by Doppler ultrasound. Embolic Doppler ultrasound signals are short duration transient like signals. The wavelet transform is an ideal method for analysis and detection of such signals by optimizing time-frequency resolution. We propose a detection system based on the discrete wavelet transform (DWT) and study some parameters, which might be useful for describing embolic signals (ES). We used a fast DWT algorithm based on the Daubechies eighth-order wavelet filters with eight scales. In order to evaluate feasibility of the DWT of ES, two independent data sets, each comprising of short segments containing an ES (N = 100), artifact (N = 100) or Doppler speckle (DS) (N = 100), were used. After applying the DWT to the data, several parameters were evaluated. The threshold values used for both data sets were optimized using the first data set. While the DWT coefficients resulting from artifacts dominantly appear at the higher scales (five, six, seven, and eight), the DWT coefficients at the lower scales (one, two, three, and four) are mainly dominated by ES and DS. The DWT is able to filter out most of the artifacts inherently during the transform process. For the first data set, 98 out of 100 ES were detected as ES. For the second data set, 95 out of 100 ES were detected as ES when the same threshold values were used. The algorithm was also tested with a third data set comprising 202 normal ES; 198 signals were detected as ES.

Communication systems targeting miniaturized sensor microsystem networks are characterized by their restricted power and area constraints. When considering the design of telecommunication system for such a network, the receiver is the key performance critical block. This paper describes research work carried out on studying the impact of input data characteristics and resolution and internal data path complexity on area and power performance of the receiver. We have constructed a number of transmitter/receiver architectures and analyzed their power/area. We demonstrate that up to 59% and 11% savings in area and power respectively could be achieved by optimizing input data size and internal register width for a particular application while maintaining signal quality.

Almost any system for the detection of asymptomatic circulating emboli by Doppler ultrasound employs the fast Fourier Transform (FFT). However, the FFT is not ideally suited to study short-lived embolic signals. The wavelet transform (WT) is an optimized way of analyzing short-lived signals and performs better than the FFT in some respects. We propose a detection method based on the discrete wavelet transform (DWT) and study some parameters, which might be useful for describing embolic signals. We used 2 independent data sets, comprising 100 low intensity embolic signals, 100 various type of artifacts and 100 Doppler speckle. After applying the DWT to the data, several parameters were evaluated. The threshold values used for both data sets were optimized using the first data set. 98 out of 100 embolic signals were detected as embolic signals for the first data set. 95 out of 100 embolic signals were detected for the second data set when the same threshold values were used.

Compensatory fuzzy neural networks (CFNN) without normalization, which can be trained with a backpropagation learning algorithm, is proposed as a pattern recognition technique for intelligent detection of Doppler ultrasound waveforms of abnormal neonatal cerebral hemodynamics. Doppler ultrasound signals were recorded from the anterior cerebral arteries of 40 normal full-term babies and 14 mature babies with intracranial pathology. The features of normal and abnormal groups as inputs to pattern recognition algorithms were extracted from the maximum velocity waveforms by using principal component analysis. The proposed technique is compared with the CFNN with normalization and other pattern recognition techniques applied to Doppler ultrasound signals from various arteries. The results show that the proposed method is superior to the others, and can be a powerful technique to be used in analyzing Doppler ultrasound signals from various arteries.

Most Doppler ultrasound systems employ quadrature demodulation techniques at the detection stage. The information concerning flow direction encoded in the phase relationship between in-phase and quadrature phase channels is not obvious at this stage. A method based on the utilization of complex wavelets and negative scales has been described. It eliminates the intermediate processing stages by mapping directional information in the scale domain.