Search

In this paper, we propose an end-to-end approach to addressing QRS complex detection and measurement of Electrocardiograph (ECG) paper using convolutional neural networks (CNNs). Unlike conventional detection solutions that convert images to digital data, our method can directly detect QRS complex in images using Faster-RCNN, then the R-peak can be located and measured through a CNN. Validated by clinical ECG data in the St.-Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database and real ECG paper from Peking University People’s Hospital, the proposed method can achieve the recall of 98.32%, the precision of 99.01% in detecting and 0.012 mv of mean absolute error in measuring. Experimental results demonstrate the superior performance of our method over conventional solutions, which would pave the way to detect and measure ECG paper using CNNs.

Purpose: Earlier work showed that IVIM-NET orig, an unsupervised physics-informed deep neural network, was faster and more accurate than other state-of-the-art intravoxel-incoherent motion (IVIM) fitting approaches to diffusion-weighted imaging (DWI). This study presents a substantially improved version, IVIM-NET optim, and characterizes its superior performance in pancreatic cancer patients. Method: In simulations (signal-to-noise ratio [SNR] = 20), the accuracy, independence, and consistency of IVIM-NET were evaluated for combinations of hyperparameters (fit S0, constraints, network architecture, number of hidden layers, dropout, batch normalization, learning rate), by calculating the normalized root-mean-square error (NRMSE), Spearman’s ρ, and the coefficient of variation (CV NET), respectively. The best performing network, IVIM-NET optim was compared to least squares (LS) and a Bayesian approach at different SNRs. IVIM-NET optim’s performance was evaluated in an independent dataset of 23 patients with pancreatic ductal adenocarcinoma. Fourteen of the patients received no treatment between two repeated scan sessions and nine received chemoradiotherapy between the repeated sessions. Intersession within-subject standard deviations (wSD) and treatment-induced changes were assessed. Results: In simulations (SNR = 20), IVIM-NET optim outperformed IVIM-NET orig in accuracy (NRMSE(D) = 0.177 vs 0.196; NMRSE(f) = 0.220 vs 0.267; NMRSE(D*) = 0.386 vs 0.393), independence (ρ(D*, f) = 0.22 vs 0.74), and consistency (CV NET(D) = 0.013 vs 0.104; CV NET(f) = 0.020 vs 0.054; CV NET(D*) = 0.036 vs 0.110). IVIM-NET optim showed superior performance to the LS and Bayesian approaches at SNRs < 50. In vivo, IVIM-NET optim showed significantly less noisy parameter maps with lower wSD for D and f than the alternatives. In the treated cohort, IVIM-NET optim detected the most individual patients with significant parameter changes compared to day-to-day variations. Conclusion: IVIM-NET optim is recommended for accurate, informative, and consistent IVIM fitting to DWI data.

Maximum intensity projection (MIP) technology is a computer visualization method that projects three-dimensional spatial data on a visualization plane. According to the specific purposes, the specific lab thickness and direction can be selected. This technology can better show organs, such as blood vessels, arteries, veins, and bronchi and so forth, from different directions, which could bring more intuitive and comprehensive results for doctors in the diagnosis of related diseases. However, in this traditional projection technology, the details of the small projected target are not clearly visualized when the projected target is not much different from the surrounding environment, which could lead to missed diagnosis or misdiagnosis. Therefore, it is urgent to develop a new technology that can better and clearly display the angiogram. However, to the best of our knowledge, research in this area is scarce. To fill this gap in the literature, in the present study, we propose a new method based on the hybrid of convolutional neural network (CNN) and radial basis function neural network (RBFNN) to synthesize the projection image. We first adopted the U-net to obtain feature or enhanced images to be projected; subsequently, the RBF neural network performed further synthesis processing for these data; finally, the projection images were obtained. For experimental data, in order to increase the robustness of the proposed algorithm, the following three different types of datasets were adopted: the vascular projection of the brain, the bronchial projection of the lung parenchyma, and the vascular projection of the liver. In addition, radiologist evaluation and five classic metrics of image definition were implemented for effective analysis. Finally, compared to the traditional MIP technology and other structures, the use of a large number of different types of data and superior experimental results proved the versatility and robustness of the proposed method.

The prediction of poor ovarian response (POR) for stratified interference is a critical clinical issue that has received an increasing amount of recent concern. Anthropogenic diagnostic modes remain too simple for the handling of actual clinical complexity. Therefore, this study conducted extensive selection using models that were derived from a variety of machine learning algorithms, including random forest (RF), decision trees, eXtreme Gradient Boosting (XGBoost), support vector machine (SVM), and artificial neural networks (ANN) for the development of two models called the COS pre-launch model (CPLM) and the hCG pre-trigger model (HPTM) to assess POR based on different requirements. The results demonstrated that CPLM constructed using ANN achieved the highest AUC result of all the algorithms in COS pre-launch (AUC=0.859, C-index=0.87, good calibration), and HPTL constructed using random forest was found to be the most effective in hCG pre-trigger (AUC=0.903, C-index=0.90, good calibration). It is notable that CPLM and HPTM exhibited better performance than common clinical characteristics (0.895 [CPLM], and 0.903 [HPTM] in comparison to 0.824 [anti-Müllerian hormone (AMH)], and 0.799 [antral follicle count (AFC)]). Furthermore, variable importance figure elucidated the values of AMH, AFC, and E2 level and follicle number on hCG day, which provides important theoretical guidance and experimental data for further application. Generally, the CPLM and HPTM can offer effective POR prediction for patients who are receiving assisted reproduction technology (ART), and has great potential for guiding the clinical treatment of infertility.

Motivation Recent years have witnessed that the inter-residue contact/distance in proteins could be accurately predicted by deep neural networks, which significantly improve the accuracy of predicted protein structure models. In contrast, fewer studies have been done for the prediction of RNA inter-nucleotide 3D closeness. Results We proposed a new algorithm named RNAcontact for the prediction of RNA inter-nucleotide 3D closeness. RNAcontact was built based on the deep residual neural networks. The covariance information from multiple sequence alignments and the predicted secondary structure were used as the input features of the networks. Experiments show that RNAcontact achieves the respective precisions of 0.8 and 0.6 for the top L/10 and L (where L is the length of an RNA) predictions on an independent test set, significantly higher than other evolutionary coupling methods. Analysis shows that about 1/3 of the correctly predicted 3D closenesses are not base pairings of secondary structure, which are critical to the determination of RNA structure. In addition, we demonstrated that the predicted 3D closeness could be used as distance restraints to guide RNA structure folding by the 3dRNA package. More accurate models could be built by using the predicted 3D closeness than the models without using 3D closeness. Availability and implementation The webserver and a standalone package are available at: http://yanglab.nankai.edu.cn/RNAcontact/. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation Protein domains are subunits that can fold and function independently. Correct domain boundary assignment is thus a critical step toward accurate protein structure and function analyses. There is, however, no efficient algorithm available for accurate domain prediction from sequence. The problem is particularly challenging for proteins with discontinuous domains, which consist of domain segments that are separated along the sequence. Results We developed a new algorithm, FUpred, which predicts protein domain boundaries utilizing contact maps created by deep residual neural networks coupled with coevolutionary precision matrices. The core idea of the algorithm is to retrieve domain boundary locations by maximizing the number of intra-domain contacts, while minimizing the number of inter-domain contacts from the contact maps. FUpred was tested on a large-scale dataset consisting of 2549 proteins and generated correct single- and multi-domain classifications with a Matthew’s correlation coefficient of 0.799, which was 19.1% (or 5.3%) higher than the best machine learning (or threading)-based method. For proteins with discontinuous domains, the domain boundary detection and normalized domain overlapping scores of FUpred were 0.788 and 0.521, respectively, which were 17.3% and 23.8% higher than the best control method. The results demonstrate a new avenue to accurately detect domain composition from sequence alone, especially for discontinuous, multi-domain proteins. Availability and implementation https://zhanglab.ccmb.med.umich.edu/FUpred. Supplementary information Supplementary data are available at Bioinformatics online.

Significance: Early detection of oral cancer is vital for high-risk patients, and machine learning-based automatic classification is ideal for disease screening. However, current datasets collected from high-risk populations are unbalanced and often have detrimental effects on the performance of classification. Aim: To reduce the class bias caused by data imbalance. Approach: We collected 3851 polarized white light cheek mucosa images using our customized oral cancer screening device. We use weight balancing, data augmentation, undersampling, focal loss, and ensemble methods to improve the neural network performance of oral cancer image classification with the imbalanced multi-class datasets captured from high-risk populations during oral cancer screening in low-resource settings. Results: By applying both data-level and algorithm-level approaches to the deep learning training process, the performance of the minority classes, which were difficult to distinguish at the beginning, has been improved. The accuracy of “premalignancy” class is also increased, which is ideal for screening applications. Conclusions: Experimental results show that the class bias induced by imbalanced oral cancer image datasets could be reduced using both data- and algorithm-level methods. Our study may provide an important basis for helping understand the influence of unbalanced datasets on oral cancer deep learning classifiers and how to mitigate.

Background Word embeddings are dense numeric vectors used to represent language in neural networks. Until recently, there had been no publicly released embeddings trained on clinical data. Our work is the first to study the privacy implications of releasing these models. Objective This paper aims to demonstrate that traditional word embeddings created on clinical corpora that have been deidentified by removing personal health information (PHI) can nonetheless be exploited to reveal sensitive patient information. Methods We used embeddings created from 400,000 doctor-written consultation notes and experimented with 3 common word embedding methods to explore the privacy-preserving properties of each. Results We found that if publicly released embeddings are trained from a corpus anonymized by PHI removal, it is possible to reconstruct up to 68.5% (n=411/600) of the full names that remain in the deidentified corpus and associated sensitive information to specific patients in the corpus from which the embeddings were created. We also found that the distance between the word vector representation of a patient’s name and a diagnostic billing code is informative and differs significantly from the distance between the name and a code not billed for that patient. Conclusions Special care must be taken when sharing word embeddings created from clinical texts, as current approaches may compromise patient privacy. If PHI removal is used for anonymization before traditional word embeddings are trained, it is possible to attribute sensitive information to patients who have not been fully deidentified by the (necessarily imperfect) removal algorithms. A promising alternative (ie, anonymization by PHI replacement) may avoid these flaws. Our results are timely and critical, as an increasing number of researchers are pushing for publicly available health data.

Background The number of patients with neurological diseases is currently increasing annually, which presents tremendous challenges for both patients and doctors. With the advent of advanced information technology, digital medical care is gradually changing the medical ecology. Numerous people are exploring new ways to receive a consultation, track their diseases, and receive rehabilitation training in more convenient and efficient ways. In this paper, we explore the use of facial expression recognition via artificial intelligence to diagnose a typical neurological system disease, Parkinson disease (PD). Objective This study proposes methods to diagnose PD through facial expression recognition. Methods We collected videos of facial expressions of people with PD and matched controls. We used relative coordinates and positional jitter to extract facial expression features (facial expression amplitude and shaking of small facial muscle groups) from the key points returned by Face++. Algorithms from traditional machine learning and advanced deep learning were utilized to diagnose PD. Results The experimental results showed our models can achieve outstanding facial expression recognition ability for PD diagnosis. Applying a long short-term model neural network to the positions of the key features, precision and F1 values of 86% and 75%, respectively, can be reached. Further, utilizing a support vector machine algorithm for the facial expression amplitude features and shaking of the small facial muscle groups, an F1 value of 99% can be achieved. Conclusions This study contributes to the digital diagnosis of PD based on facial expression recognition. The disease diagnosis model was validated through our experiment. The results can help doctors understand the real-time dynamics of the disease and even conduct remote diagnosis.

The purpose of the present study was to reconstruct the energy spectrum of a poly-energetic neutron source using an algorithm developed based on an Adaptive Neuro-Fuzzy Inference System (ANFIS). ANFIS is a kind of artificial neural network based on the Takagi–Sugeno fuzzy inference system. The ANFIS algorithm uses the advantages of both fuzzy inference systems and artificial neural networks to improve the effectiveness of algorithms in various applications such as modeling, control and classification. The neutron pulse height distributions used as input data in the training procedure for the ANFIS algorithm were obtained from the simulations performed by MCNPX-ESUT computational code (MCNPX-Energy engineering of Sharif University of Technology). Taking into account the normalization condition of each energy spectrum, 4300 neutron energy spectra were generated randomly. (The value in each bin was generated randomly, and finally a normalization of each generated energy spectrum was performed). The randomly generated neutron energy spectra were considered as output data of the developed ANFIS computational code in the training step. To calculate the neutron energy spectrum using conventional methods, an inverse problem with an approximately singular response matrix (with the determinant of the matrix close to zero) should be solved. The solution of the inverse problem using the conventional methods unfold neutron energy spectrum with low accuracy. Application of the iterative algorithms in the solution of such a problem, or utilizing the intelligent algorithms (in which there is no need to solve the problem), is usually preferred for unfolding of the energy spectrum. Therefore, the main reason for development of intelligent algorithms like ANFIS for unfolding of neutron energy spectra is to avoid solving the inverse problem. In the present study, the unfolded neutron energy spectra of 252Cf and 241Am-9Be neutron sources using the developed computational code were found to have excellent agreement with the reference data. Also, the unfolded energy spectra of the neutron sources as obtained using ANFIS were more accurate than the results reported from calculations performed using artificial neural networks in previously published papers.

Motivation Almost all protein residue contact prediction methods rely on the availability of deep multiple sequence alignments (MSAs). However, many proteins from the poorly populated families do not have sufficient number of homologs in the conventional UniProt database. Here we aim to solve this issue by exploring the rich sequence data from the metagenome sequencing projects. Results Based on the improved MSA constructed from the metagenome sequence data, we developed MapPred, a new deep learning-based contact prediction method. MapPred consists of two component methods, DeepMSA and DeepMeta, both trained with the residual neural networks. DeepMSA was inspired by the recent method DeepCov, which was trained on 441 matrices of covariance features. By considering the symmetry of contact map, we reduced the number of matrices to 231, which makes the training more efficient in DeepMSA. Experiments show that DeepMSA outperforms DeepCov by 10–13% in precision. DeepMeta works by combining predicted contacts and other sequence profile features. Experiments on three benchmark datasets suggest that the contribution from the metagenome sequence data is significant with P-values less than 4.04E-17. MapPred is shown to be complementary and comparable the state-of-the-art methods. The success of MapPred is attributed to three factors: the deeper MSA from the metagenome sequence data, improved feature design in DeepMSA and optimized training by the residual neural networks. Availability and implementation http://yanglab.nankai.edu.cn/mappred/. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation Sequence analysis is arguably a foundation of modern biology. Classic approaches to sequence analysis are based on sequence alignment, which is limited when dealing with large-scale sequence data. A dozen of alignment-free approaches have been developed to provide computationally efficient alternatives to alignment-based approaches. However, existing methods define sequence similarity based on various heuristics and can only provide rough approximations to alignment distances. Results In this article, we developed a new approach, referred to as SENSE (SiamEse Neural network for Sequence Embedding), for efficient and accurate alignment-free sequence comparison. The basic idea is to use a deep neural network to learn an explicit embedding function based on a small training dataset to project sequences into an embedding space so that the mean square error between alignment distances and pairwise distances defined in the embedding space is minimized. To the best of our knowledge, this is the first attempt to use deep learning for alignment-free sequence analysis. A large-scale experiment was performed that demonstrated that our method significantly outperformed the state-of-the-art alignment-free methods in terms of both efficiency and accuracy. Availability and implementation Open-source software for the proposed method is developed and freely available at https://www.acsu.buffalo.edu/∼yijunsun/lab/SENSE.html. Supplementary information Supplementary data are available at Bioinformatics online.

Background Studies have shown that artificial intelligence achieves similar or better performance than dermatologists in specific dermoscopic image classification tasks. However, artificial intelligence is susceptible to the influence of confounding factors within images (eg, skin markings), which can lead to false diagnoses of cancerous skin lesions. Image segmentation can remove lesion-adjacent confounding factors but greatly change the image representation. Objective The aim of this study was to compare the performance of 2 image classification workflows where images were either segmented or left unprocessed before the subsequent training and evaluation of a binary skin lesion classifier. Methods Separate binary skin lesion classifiers (nevus vs melanoma) were trained and evaluated on segmented and unsegmented dermoscopic images. For a more informative result, separate classifiers were trained on 2 distinct training data sets (human against machine [HAM] and International Skin Imaging Collaboration [ISIC]). Each training run was repeated 5 times. The mean performance of the 5 runs was evaluated on a multi-source test set (n=688) consisting of a holdout and an external component. Results Our findings showed that when trained on HAM, the segmented classifiers showed a higher overall balanced accuracy (75.6% [SD 1.1%]) than the unsegmented classifiers (66.7% [SD 3.2%]), which was significant in 4 out of 5 runs (P Conclusions Image segmentation does not result in overall performance decrease but it causes the beneficial removal of lesion-adjacent confounding factors. Thus, it is a viable option to address the negative impact that confounding factors have on deep learning models in dermatology. However, the segmentation step might introduce new pitfalls, which require further investigations.

Automatic segmentation of bones in computed tomography (CT) images is used for instance in beam hardening correction algorithms where it improves the accuracy of resulting CT numbers. Of special interest are pelvic bones, which—because of their strong attenuation—affect the accuracy of brachytherapy in this region. This work evaluated the performance of the JJ2016 algorithm with the performance of MK2014v2 and JS2018 algorithms; all these algorithms were developed by authors. Visual comparison, and, in the latter case, also Dice similarity coefficients derived from the ground truth were used. It was found that the 3D-based JJ2016 performed better than the 2D-based MK2014v2, mainly because of the more accurate hole filling that benefitted from information in adjacent slices. The neural network-based JS2018 outperformed both traditional algorithms. It was, however, limited to the resolution of 1283 owing to the limited amount of memory in the graphical processing unit (GPU). Funding: VetenskapsradetSwedish Research Council [VR-NT 2016-05033]

Epileptic seizures are caused by a disturbance in the electrical activity of the brain and classified as many different types of epileptic seizures based on the characteristics of EEG and other parameters. Till now research has been conducted to classify EEG as seizure and non-seizures, but the classification of seizure types has not been explored. Thus, in this paper, we have proposed the 8-class classification problem in order to classify different seizure types using convolutional neural networks (CNN). This research study suggests a CNN based framework for classification of epileptic seizure types that include simple partial, complex partial, focal non-specific, generalized non-specific, absence, tonic, and tonic-clonic, and non-seizures. EEG time series was converted into spectrogram stacks and used as input for CNN. To the best of authors knowledge, ours is the very first study that classified the seizures types using the computational algorithm. The four CNN models, namely AlexNet, VGG16, VGG19, and basic CNN model was applied to study the performance of 8-class classification problem. The proposed study showed a classification accuracy of 84.06%, 79.71%, 76.81%, and 82.14% using AlexNet, VGG16, VGG19 and basic CNN models respectively. The experimental results suggest that the proposed framework could be helpful to the neurology community for recognition of seizures types.

Background As the need for sharing genomic data grows, privacy issues and concerns, such as the ethics surrounding data sharing and disclosure of personal information, are raised. Objective The main purpose of this study was to verify whether genomic data is sufficient to predict a patient's personal information. Methods RNA expression data and matched patient personal information were collected from 9538 patients in The Cancer Genome Atlas program. Five personal information variables (age, gender, race, cancer type, and cancer stage) were recorded for each patient. Four different machine learning algorithms (support vector machine, decision tree, random forest, and artificial neural network) were used to determine whether a patient's personal information could be accurately predicted from RNA expression data. Performance measurement of the prediction models was based on the accuracy and area under the receiver operating characteristic curve. We selected five cancer types (breast carcinoma, kidney renal clear cell carcinoma, head and neck squamous cell carcinoma, low-grade glioma, and lung adenocarcinoma) with large samples sizes to verify whether predictive accuracy would differ between them. We also validated the efficacy of our four machine learning models in analyzing normal samples from 593 cancer patients. Results In most samples, personal information with high genetic relevance, such as gender and cancer type, could be predicted from RNA expression data alone. The prediction accuracies for gender and cancer type, which were the best models, were 0.93-0.99 and 0.78-0.94, respectively. Other aspects of personal information, such as age, race, and cancer stage, were difficult to predict from RNA expression data, with accuracies ranging from 0.0026-0.29, 0.76-0.96, and 0.45-0.79, respectively. Among the tested machine learning methods, the highest predictive accuracy was obtained using the support vector machine algorithm (mean accuracy 0.77), while the lowest accuracy was obtained using the random forest method (mean accuracy 0.65). Gender and race were predicted more accurately than other variables in the samples. On average, the accuracy of cancer stage prediction ranged between 0.71-0.67, while the age prediction accuracy ranged between 0.18-0.23 for the five cancer types. Conclusions We attempted to predict patient information using RNA expression data. We found that some identifiers could be predicted, but most others could not. This study showed that personal information available from RNA expression data is limited and this information cannot be used to identify specific patients.

Objectives:High throughput pre-treatment imaging features may predict radiation treatment outcome and guide individualized treatment in radiotherapy (RT). Given relatively small patient sample (as compared with high dimensional imaging features), identifying potential prognostic imaging biomarkers is typically challenging. We aimed to develop robust machine learning methods for patient survival prediction using pre-treatment quantitative CT image features for a subgroup of head-and-neck cancer patients.Methods:Three neural network models, including back propagation (BP), Genetic Algorithm-Back Propagation (GA-BP), and Probabilistic Genetic Algorithm-Back Propagation (PGA-BP) neural networks were trained to simulate association between patient survival and radiomics data in radiotherapy. To evaluate the models, a subgroup of 59 head-and-neck patients with primary cancers in oral tongue area were utilized. Quantitative image features were extracted from planning CT images, a novel t-Distributed Stochastic Neighbor Embedding (t-SNE) method was used to remove irrelevant and redundant image features before fed into the network models. 80% patients were used to train the models, and remaining 20% were used for evaluation.Results:Of the three supervised machine-learning methods studied, PGA-BP yielded the best predictive performance. The reported actual patient survival interval of 30.5 ± 21.3 months, the predicted survival times were 47.3 ± 38.8, 38.5 ± 13.5 and 29.9 ± 15.3 months using the traditional PCA. Combining with the novel t-SNE dimensionality reduction algorithm, the predicted survival intervals are 35.8 ± 15.2, 32.3 ± 13.1 and 31.6 ± 15.8 months for the BP, GA-BP and PGA-BP neural network models, respectively.Conclusion:The work demonstrated that the proposed probabilistic genetic algorithm optimized neural network models, integrating with the t-SNE dimensionality reduction algorithm, achieved accurate prediction of patient survival.Advances in knowledge:The proposed PGA-BP neural network, integrating with an advanced dimensionality reduction algorithm (t-SNE), improved patient survival prediction accuracy using pre-treatment quantitative CT image features of head-and-neck cancer patients.

Sputum sounds are biological signals used to evaluate the condition of sputum deposition in a respiratory system. To improve the efficiency of intensive care unit (ICU) staff and achieve timely clearance of secretion in patients with mechanical ventilation, we propose a method consisting of feature extraction of sputum sound signals using the wavelet transform and classification of sputum existence using artificial neural network (ANN). Sputum sound signals were decomposed into the frequency subbands using the wavelet transform. A set of features was extracted from the subbands to represent the distribution of wavelet coefficients. An ANN system, trained using the Back Propagation (BP) algorithm, was implemented to recognize the existence of sputum sounds. The maximum precision rate of automatic recognition in texture of signals was as high as 84.53%. This study can be referred to as the optimization of performance and design in the automatic technology for sputum detection using sputum sound signals.

Motivation Creating large datasets for biomedical relation classification can be prohibitively expensive. While some datasets have been curated to extract protein-protein and drug-drug interactions (PPIs and DDIs) from text, we are also interested in other interactions including gene-disease and chemical-protein connections. Also, many biomedical researchers have begun to explore ternary relationships. Even when annotated data are available, many datasets used for relation classification are inherently biased. For example, issues such as sample selection bias typically prevent models from generalizing in the wild. To address the problem of cross-corpora generalization, we present a novel adversarial learning algorithm for unsupervised domain adaptation tasks where no labeled data are available in the target domain. Instead, our method takes advantage of unlabeled data to improve biased classifiers through learning domain-invariant features via an adversarial process. Finally, our method is built upon recent advances in neural network (NN) methods. Results We experiment by extracting PPIs and DDIs from text. In our experiments, we show domain invariant features can be learned in NNs such that classifiers trained for one interaction type (protein-protein) can be re-purposed to others (drug-drug). We also show that our method can adapt to different source and target pairs of PPI datasets. Compared to prior convolutional and recurrent NN-based relation classification methods without domain adaptation, we achieve improvements as high as 30% in F1-score. Likewise, we show improvements over state-of-the-art adversarial methods. Availability and implementation Experimental code is available at https://github.com/bionlproc/adversarial-relation-classification. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation Nucleosome positioning plays significant roles in proper genome packing and its accessibility to execute transcription regulation. Despite a multitude of nucleosome positioning resources available on line including experimental datasets of genome-wide nucleosome occupancy profiles and computational tools to the analysis on these data, the complex language of eukaryotic Nucleosome positioning remains incompletely understood. Results Here, we address this challenge using an approach based on a state-of-the-art machine learning method. We present a novel convolutional neural network (CNN) to understand nucleosome positioning. We combined Inception-like networks with a gating mechanism for the response of multiple patterns and long term association in DNA sequences. We developed the open-source package LeNup based on the CNN to predict nucleosome positioning in Homo sapiens, Caenorhabditis elegans, Drosophila melanogaster as well as Saccharomyces cerevisiae genomes. We trained LeNup on four benchmark datasets. LeNup achieved greater predictive accuracy than previously published methods. Availability and implementation LeNup is freely available as Python and Lua script source code under a BSD style license from https://github.com/biomedBit/LeNup. Supplementary information Supplementary data are available at Bioinformatics online.

Self-interacting proteins (SIPs) play a significant role in the execution of most important molecular processes in cells, such as signal transduction, gene expression regulation, immune response and enzyme activation. Although the traditional experimental methods can be used to generate SIPs data, it is very expensive and time-consuming based only on biological technique. Therefore, it is important and urgent to develop an efficient computational method for SIPs detection. In this study, we present a novel SIPs identification method based on machine learning technology by combing the Zernike Moments (ZMs) descriptor on Position Specific Scoring Matrix (PSSM) with Probabilistic Classification Vector Machines (PCVM) and Stacked Sparse Auto-Encoder (SSAE). More specifically, an efficient feature extraction technique called ZMs is firstly utilized to generate feature vectors on Position Specific Scoring Matrix (PSSM); Then, Deep neural network is employed for reducing the feature dimensions and noise; Finally, the Probabilistic Classification Vector Machine is used to execute the classification. The prediction performance of the proposed method is evaluated on S.erevisiae and Human SIPs datasets via cross-validation. The experimental results indicate that the proposed method can achieve good accuracies of 92.55% and 97.47%, respectively. To further evaluate the advantage of our scheme for SIPs prediction, we also compared the PCVM classifier with the Support Vector Machine (SVM) and other existing techniques on the same data sets. Comparison results reveal that the proposed strategy is outperforms other methods and could be a used tool for identifying SIPs.

Background COVID-19 is caused by the SARS-CoV-2 virus and has strikingly heterogeneous clinical manifestations, with most individuals contracting mild disease but a substantial minority experiencing fulminant cardiopulmonary symptoms or death. The clinical covariates and the laboratory tests performed on a patient provide robust statistics to guide clinical treatment. Deep learning approaches on a data set of this nature enable patient stratification and provide methods to guide clinical treatment. Objective Here, we report on the development and prospective validation of a state-of-the-art machine learning model to provide mortality prediction shortly after confirmation of SARS-CoV-2 infection in the Mayo Clinic patient population. Methods We retrospectively constructed one of the largest reported and most geographically diverse laboratory information system and electronic health record of COVID-19 data sets in the published literature, which included 11,807 patients residing in 41 states of the United States of America and treated at medical sites across 5 states in 3 time zones. Traditional machine learning models were evaluated independently as well as in a stacked learner approach by using AutoGluon, and various recurrent neural network architectures were considered. The traditional machine learning models were implemented using the AutoGluon-Tabular framework, whereas the recurrent neural networks utilized the TensorFlow Keras framework. We trained these models to operate solely using routine laboratory measurements and clinical covariates available within 72 hours of a patient’s first positive COVID-19 nucleic acid test result. Results The GRU-D recurrent neural network achieved peak cross-validation performance with 0.938 (SE 0.004) as the area under the receiver operating characteristic (AUROC) curve. This model retained strong performance by reducing the follow-up time to 12 hours (0.916 [SE 0.005] AUROC), and the leave-one-out feature importance analysis indicated that the most independently valuable features were age, Charlson comorbidity index, minimum oxygen saturation, fibrinogen level, and serum iron level. In the prospective testing cohort, this model provided an AUROC of 0.901 and a statistically significant difference in survival (P Conclusions Our deep learning approach using GRU-D provides an alert system to flag mortality for COVID-19–positive patients by using clinical covariates and laboratory values within a 72-hour window after the first positive nucleic acid test result.

Background Accurate solutions for the estimation of physical activity and energy expenditure at scale are needed for a range of medical and health research fields. Machine learning techniques show promise in research-grade accelerometers, and some evidence indicates that these techniques can be applied to more scalable commercial devices. Objective This study aims to test the validity and out-of-sample generalizability of algorithms for the prediction of energy expenditure in several wearables (ie, Fitbit Charge 2, ActiGraph GT3-x, SenseWear Armband Mini, and Polar H7) using two laboratory data sets comprising different activities. Methods Two laboratory studies (study 1: n=59, age 44.4 years, weight 75.7 kg; study 2: n=30, age=31.9 years, weight=70.6 kg), in which adult participants performed a sequential lab-based activity protocol consisting of resting, household, ambulatory, and nonambulatory tasks, were combined in this study. In both studies, accelerometer and physiological data were collected from the wearables alongside energy expenditure using indirect calorimetry. Three regression algorithms were used to predict metabolic equivalents (METs; ie, random forest, gradient boosting, and neural networks), and five classification algorithms (ie, k-nearest neighbor, support vector machine, random forest, gradient boosting, and neural networks) were used for physical activity intensity classification as sedentary, light, or moderate to vigorous. Algorithms were evaluated using leave-one-subject-out cross-validations and out-of-sample validations. Results The root mean square error (RMSE) was lowest for gradient boosting applied to SenseWear and Polar H7 data (0.91 METs), and in the classification task, gradient boost applied to SenseWear and Polar H7 was the most accurate (85.5%). Fitbit models achieved an RMSE of 1.36 METs and 78.2% accuracy for classification. Errors tended to increase in out-of-sample validations with the SenseWear neural network achieving RMSE values of 1.22 METs in the regression tasks and the SenseWear gradient boost and random forest achieving an accuracy of 80% in classification tasks. Conclusions Algorithms trained on combined data sets demonstrated high predictive accuracy, with a tendency for superior performance of random forests and gradient boosting for most but not all wearable devices. Predictions were poorer in the between-study validations, which creates uncertainty regarding the generalizability of the tested algorithms.

To develop a modified predictive model for severe COVID-19 in people infected with Sars-Cov-2. We developed the predictive model for severe patients of COVID-19 based on the clinical date from the Tumor Center of Union Hospital affiliated with Tongji Medical College, China. A total of 151 cases from Jan. 26 to Mar. 20, 2020, were included. Then we followed 5 steps to predict and evaluate the model: data preprocessing, data splitting, feature selection, model building, prevention of overfitting, and Evaluation, and combined with artificial neural network algorithms. We processed the results in the 5 steps. In feature selection, ALB showed a strong negative correlation (r = 0.771, P

In the context of epilepsy monitoring, electroencephalography (EEG) remains the modality of choice. Functional near-infrared spectroscopy (fNIRS) is a relatively innovative modality that cannot only characterize hemodynamic profiles of seizures but also allow for long-term recordings. We employ deep learning methods to investigate the benefits of integrating fNIRS measures for seizure detection. We designed a deep recurrent neural network with long short-term memory units and subsequently validated it using the CHBMIT scalp EEG database—a compendium of 896 h of surface EEG seizure recordings. After validating our network using EEG, fNIRS, and multimodal data comprising a corpus of 89 seizures from 40 refractory epileptic patients was used as model input to evaluate the integration of fNIRS measures. Following heuristic hyperparameter optimization, multimodal EEG-fNIRS data provide superior performance metrics (sensitivity and specificity of 89.7% and 95.5%, respectively) in a seizure detection task, with low generalization errors and loss. False detection rates are generally low, with 11.8% and 5.6% for EEG and multimodal data, respectively. Employing multimodal neuroimaging, particularly EEG-fNIRS, in epileptic patients, can enhance seizure detection performance. Furthermore, the neural network model proposed and characterized herein offers a promising framework for future multimodal investigations in seizure detection and prediction.

In the organosolv pulping of the oil palm fronds, the influence of the operational variables of the pulping reactor (viz. cooking temperature and time, ethanol and NaOH concentration) on the properties of the resulting pulp (yield and kappa number) and paper sheets (tensile index and tear index) was investigated using a wavelet neural network model. The experimental results with error less than 0.0965 (in terms of MSE) were produced, and were then compared with those obtained from the response surface methodology. Performance assessment indicated that the neural network model possessed superior predictive ability than the polynomial model, since a very close agreement between the experimental and the predicted values was obtained.

Motivation: Alternative splicing (AS) is a regulated process that directs the generation of different transcripts from single genes. A computational model that can accurately predict splicing patterns based on genomic features and cellular context is highly desirable, both in understanding this widespread phenomenon, and in exploring the effects of genetic variations on AS. Methods: Using a deep neural network, we developed a model inferred from mouse RNA-Seq data that can predict splicing patterns in individual tissues and differences in splicing patterns across tissues. Our architecture uses hidden variables that jointly represent features in genomic sequences and tissue types when making predictions. A graphics processing unit was used to greatly reduce the training time of our models with millions of parameters. Results: We show that the deep architecture surpasses the performance of the previous Bayesian method for predicting AS patterns. With the proper optimization procedure and selection of hyperparameters, we demonstrate that deep architectures can be beneficial, even with a moderately sparse dataset. An analysis of what the model has learned in terms of the genomic features is presented. Contact: frey@psi.toronto.edu Supplementary information: Supplementary data are available at Bioinformatics online.

Significance: The use of optofluidic time-stretch flow cytometry enables extreme-throughput cell imaging but suffers from the difficulties of capturing and processing a large amount of data. As significant amounts of continuous image data are generated, the images require identification with high speed. Aim: We present an intelligent cell phenotyping framework for high-throughput optofluidic time-stretch microscopy based on the XGBoost algorithm, which is able to classify obtained cell images rapidly and accurately. The applied image recognition consists of density-based spatial clustering of applications with noise outlier detection, histograms of oriented gradients combining gray histogram fused feature, and XGBoost classification. Approach: We tested the ability of this framework against other previously proposed or commonly used algorithms to phenotype two groups of cell images. We quantified their performances with measures of classification ability and computational complexity based on AUC and test runtime. The tested cell image datasets were acquired from high-throughput imaging of over 20,000 drug-treated and untreated cells with an optofluidic time-stretch microscope. Results: The framework we built beats other methods with an accuracy of over 97% and a classification frequency of 3000 cells/s. In addition, we determined the optimal structure of training sets according to model performances under different training set components. Conclusions: The proposed XGBoost-based framework acts as a promising solution to processing large flow image data. This work provides a foundation for future cell sorting and clinical practice of high-throughput imaging cytometers.

In the course of infecting their hosts, pathogenic bacteria secrete numerous effectors, namely, bacterial proteins that pervert host cell biology. Many Gram-negative bacteria, including context-dependent human pathogens, use a type IV secretion system (T4SS) to translocate effectors directly into the cytosol of host cells. Various type IV secreted effectors (T4SEs) have been experimentally validated to play crucial roles in virulence by manipulating host cell gene expression and other processes. Consequently, the identification of novel effector proteins is an important step in increasing our understanding of host-pathogen interactions and bacterial pathogenesis. Here, we train and compare six machine learning models, namely, Naive Bayes (NB), K-nearest neighbor (KNN), logistic regression (LR), random forest (RF), support vector machines (SVMs) and multilayer perceptron (MLP), for the identification of T4SEs using 10 types of selected features and 5-fold cross-validation. Our study shows that: (1) including different but complementary features generally enhance the predictive performance of T4SEs; (2) ensemble models, obtained by integrating individual single-feature models, exhibit a significantly improved predictive performance and (3) the 'majority voting strategy' led to a more stable and accurate classification performance when applied to predicting an ensemble learning model with distinct single features. We further developed a new method to effectively predict T4SEs, Bastion4 (Bacterial secretion effector predictor for T4SS), and we show our ensemble classifier clearly outperforms two recent prediction tools. In summary, we developed a state-of-the-art T4SE predictor by conducting a comprehensive performance evaluation of different machine learning algorithms along with a detailed analysis of single- and multi-feature selections.

Speech understanding in noisy environments is still one of the major challenges for cochlear implant (CI) users in everyday life. We evaluated a speech enhancement algorithm based on neural networks (NNSE) for improving speech intelligibility in noise for CI users. The algorithm decomposes the noisy speech signal into time-frequency units, extracts a set of auditory-inspired features and feeds them to the neural network to produce an estimation of which frequency channels contain more perceptually important information (higher signal-to-noise ratio, SNR). This estimate is used to attenuate noise-dominated and retain speech-dominated CI channels for electrical stimulation, as in traditional n-of-m CI coding strategies. The proposed algorithm was evaluated by measuring the speech-in-noise performance of 14 CI users using three types of background noise. Two NNSE algorithms were compared: a speaker-dependent algorithm, that was trained on the target speaker used for testing, and a speaker-independent algorithm, that was trained on different speakers. Significant improvements in the intelligibility of speech in stationary and fluctuating noises were found relative to the unprocessed condition for the speaker-dependent algorithm in all noise types and for the speaker-independent algorithm in 2 out of 3 noise types. The NNSE algorithms used noise-specific neural networks that generalized to novel segments of the same noise type and worked over a range of SNRs. The proposed algorithm has the potential to improve the intelligibility of speech in noise for CI users while meeting the requirements of low computational complexity and processing delay for application in CI devices., Highlights • An algorithm for improving speech understanding in noise for cochlear implant users is evaluated. • Significant improvements were found for stationary and non-stationary noise types. • It generalizes to a novel speaker and works over a range of signal-to-noise ratios. • The small algorithmic delay makes it suitable for real-time application.

This paper addresses the issues of neural network model development and maintenance in the context of a complex task taken from the papermaking industry. In particular, it describes a comparison study of early stopping techniques and model selection, both to optimise neural network models for generalisation performance. The results presented here show that early stopping via use of a Bayesian model evidence measure is a viable way of optimising performance while also making maximum use of all the data. In addition, they show that ten-fold cross-validation performs well as a model selector and as an estimator of prediction accuracy. These results are important in that they show how neural network models may be optimally trained and selected for highly complex industrial tasks where the data are noisy and limited in number.

Motivation: Recent large-scale chromatin states mapping efforts have revealed characteristic chromatin modification signatures for various types of functional DNA elements. Given the important influence of chromatin states on gene regulation and the rapid accumulation of genome-wide chromatin modification data, there is a pressing need for computational methods to analyze these data in order to identify functional DNA elements. However, existing computational tools do not exploit data transformation and feature extraction as a means to achieve a more accurate prediction. Results: We introduce a new computational framework for identifying functional DNA elements using chromatin signatures. The framework consists of a data transformation and a feature extraction step followed by a classification step using time-delay neural network. We implemented our framework in a software tool CSI-ANN (chromatin signature identification by artificial neural network). When applied to predict transcriptional enhancers in the ENCODE region, CSI-ANN achieved a 65.5% sensitivity and 66.3% positive predictive value, a 5.9% and 11.6% improvement, respectively, over the previously best approach. Availability and Implementation: CSI-ANN is implemented in Matlab. The source code is freely available at http://www.medicine.uiowa.edu/Labs/tan/CSIANNsoft.zip Contact: kai-tan@uiowa.edu Supplementary Information: Supplementary Materials are available at Bioinformatics online.

Motivation: In both genome-wide association studies (GWAS) and pathway analysis, the modest sample size relative to the number of genetic markers presents formidable computational, statistical and methodological challenges for accurately identifying markers/interactions and for building phenotype-predictive models. Results: We address these objectives via maximum entropy conditional probability modeling (MECPM), coupled with a novel model structure search. Unlike neural networks and support vector machines (SVMs), MECPM makes explicit and is determined by the interactions that confer phenotype-predictive power. Our method identifies both a marker subset and the multiple k-way interactions between these markers. Additional key aspects are: (i) evaluation of a select subset of up to five-way interactions while retaining relatively low complexity; (ii) flexible single nucleotide polymorphism (SNP) coding (dominant, recessive) within each interaction; (iii) no mathematical interaction form assumed; (iv) model structure and order selection based on the Bayesian Information Criterion, which fairly compares interactions at different orders and automatically sets the experiment-wide significance level; (v) MECPM directly yields a phenotype-predictive model. MECPM was compared with a panel of methods on datasets with up to 1000 SNPs and up to eight embedded penetrance function (i.e. ground-truth) interactions, including a five-way, involving less than 20 SNPs. MECPM achieved improved sensitivity and specificity for detecting both ground-truth markers and interactions, compared with previous methods. Availability: http://www.cbil.ece.vt.edu/ResearchOngoingSNP.htm Contact: djmiller@engr.psu.edu Supplementary information: Supplementary data are available at Bioinformatics online.