Search

Abstract Mass spectra, which are agglomerations of ionized fragments from targeted molecules, play a crucial role across various fields for the identification of molecular structures. A prevalent analysis method involves spectral library searches, where unknown spectra are cross-referenced with a database. The effectiveness of such search-based approaches, however, is restricted by the scope of the existing mass spectra database, underscoring the need to expand the database via mass spectra prediction. In this research, we propose the Motif-based Mass Spectrum prediction Network (MoMS-Net), a GNN-based architecture to predict the mass spectra pattern utilizing the structural motif information of the molecule. MoMS-Net considers both a molecule and its substructures as a graph form, which facilitates the incorporation of long-range dependencies while using less memory compared to the graph transformer model. We evaluated our model over various types of mass spectra and showed the validity and superiority over the conventional models.

Abstract The detection of somatic DNA variants in tumor samples with low tumor purity or sequencing depth remains a daunting challenge despite numerous attempts to address this problem. In this study, we constructed a substantially extended set of actual positive variants originating from a wide range of tumor purities and sequencing depths, as well as actual negative variants derived from sequencer-specific sequencing errors. A deep learning model named AIVariant, trained on this extended dataset, outperforms previously reported methods when tested under various tumor purities and sequencing depths, especially low tumor purity and sequencing depth.

BackgroundAlthough coronary computed tomography angiography (CCTA) is currently utilized as the frontline test to accurately diagnose coronary artery disease (CAD) in clinical practice, there are still debates regarding its use as a screening tool for the asymptomatic population. Using deep learning (DL), we sought to develop a prediction model for significant coronary artery stenosis on CCTA and identify the individuals who would benefit from undergoing CCTA among apparently healthy asymptomatic adults.MethodsWe retrospectively reviewed 11,180 individuals who underwent CCTA as part of routine health check-ups between 2012 and 2019. The main outcome was the presence of coronary artery stenosis of ≥70% on CCTA. We developed a prediction model using machine learning (ML), including DL. Its performance was compared with pretest probabilities, including the pooled cohort equation (PCE), CAD consortium, and updated Diamond-Forrester (UDF) scores.ResultsIn the cohort of 11,180 apparently healthy asymptomatic individuals (mean age 56.1 years; men 69.8%), 516 (4.6%) presented with significant coronary artery stenosis on CCTA. Among the ML methods employed, a neural network with multi-task learning (19 selected features), one of the DL methods, was selected due to its superior performance, with an area under the curve (AUC) of 0.782 and a high diagnostic accuracy of 71.6%. Our DL-based model demonstrated a better prediction than the PCE (AUC, 0.719), CAD consortium score (AUC, 0.696), and UDF score (AUC, 0.705). Age, sex, HbA1c, and HDL cholesterol were highly ranked features. Personal education and monthly income levels were also included as important features of the model.ConclusionWe successfully developed the neural network with multi-task learning for the detection of CCTA-derived stenosis of ≥70% in asymptomatic populations. Our findings suggest that this model may provide more precise indications for the use of CCTA as a screening tool to identify individuals at a higher risk, even in asymptomatic populations, in clinical practice.

Purpose: To develop and evaluate the performance of a polygenic risk score (PRS) constructed in a Korean male population to predict clinically significant prostate cancer (csPCa). Materials and Methods: Total 2,702 PCa samples and 7,485 controls were used to discover csPCa susceptible single nucleotide polymorphisms (SNPs). Males with biopsy-proven or post-radical prostatectomy Gleason score 7 or higher were included for analysis. After genotype imputation for quality control, logistic regression models were applied to test association and calculate effect size. Extracted candidate SNPs were further tested to compare predictive performance according to number of SNPs included in the PRS. The best-fit model was validated in an independent cohort of 311 cases and 822 controls. Results: Of the 83 candidate SNPs with significant PCa association reported in previous literature, rs72725879 located in PRNCR1 showed the highest significance for PCa risk (odds ratio, 0.597; 95% confidence interval [CI], 0.555–0.641; p=4.3×10-45). Thirty-two SNPs within 26 distinct loci were further selected for PRS construction. Best performance was found with the top 29 SNPs, with AUC found to be 0.700 (95% CI, 0.667–0.734). Males with very-high PRS (above the 95th percentile) had a 4.92-fold increased risk for csPCa. Conclusions: Ethnic-specific PRS was developed and validated in Korean males to predict csPCa susceptibility using the largest csPCa sample size in Asia. PRS can be a potential biomarker to predict individual risk. Future multi-ethnic trials are required to further validate our results.

Backpropagation has been regarded as the most favorable algorithm for training artificial neural networks. However, it has been criticized for its biological implausibility because its learning mechanism contradicts the human brain. Although backpropagation has achieved super-human performance in various machine learning applications, it often shows limited performance in specific tasks. We collectively referred to such tasks as machine-challenging tasks (MCTs) and aimed to investigate methods to enhance machine learning for MCTs. Specifically, we start with a natural question: Can a learning mechanism that mimics the human brain lead to the improvement of MCT performances? We hypothesized that a learning mechanism replicating the human brain is effective for tasks where machine intelligence is difficult. Multiple experiments corresponding to specific types of MCTs where machine intelligence has room to improve performance were performed using predictive coding, a more biologically plausible learning algorithm than backpropagation. This study regarded incremental learning, long-tailed, and few-shot recognition as representative MCTs. With extensive experiments, we examined the effectiveness of predictive coding that robustly outperformed backpropagation-trained networks for the MCTs. We demonstrated that predictive coding-based incremental learning alleviates the effect of catastrophic forgetting. Next, predictive coding-based learning mitigates the classification bias in long-tailed recognition. Finally, we verified that the network trained with predictive coding could correctly predict corresponding targets with few samples. We analyzed the experimental result by drawing analogies between the properties of predictive coding networks and those of the human brain and discussing the potential of predictive coding networks in general machine learning.

While prime editing is a promising technology, PE2 systems often have low efficiency. Here the authors fuse a Rad51 DNA-binding domain to create hyPE2 with improved editing efficiency.

Despite recent developments in deep learning and their success in computer vision, model efficiency is increasingly becoming a vital factor for their deployment in various real-world applications. To provide a more effective form of computational capabilities, bio-inspired spiking neural networks (SNNs) have attracted considerable interest in recent years. SNNs are known as the third-generation of neural networks, which mimic how information is transmitted and processed in the human brain. SNNs enable sparse yet efficient information transmission through spike trains, leading to exceptional computational and energy efficiency. Nevertheless, critical challenges in SNNs to date are two-fold: (a) latency: the number of time steps required to achieve competitive results and (b) synaptic operations: the total number of spikes generated during inference. Many researchers have attempted to address these challenges, but their applications have been mainly limited to image classification. In this work, we present a threshold voltage balancing method for object detection in SNNs, which utilizes Bayesian optimization to find optimal threshold voltages in SNNs. We specifically design Bayesian optimization to consider important characteristics of SNNs such as latency and number of synaptic operations. Furthermore, we introduce two-phase threshold voltages to provide faster and more accurate object detection while providing high energy efficiency. According to experimental results, the proposed methods achieve the state-of-the-art object detection accuracy in SNNs, and converge 2x and 1.85x faster than conventional methods on PASCAL VOC and MS COCO, respectively. Moreover, the total number of synaptic operations is reduced by 40.33% and 45.31% on PASCAL VOC and MS COCO, respectively.

Deep neural networks (DNNs) have achieved impressive results in several image classification tasks. However, these architectures are unstable for adversarial examples (AEs) such as inputs crafted by a hardly perceptible perturbation with the intent of causing neural networks to make errors. AEs must be considered to prevent accidents in areas such as unmanned car driving using visual object detection in Internet of Things (IoT) networks. Gaussian noise with label smoothing or logit squeezing can be used to increase the robustness against AEs in the training of DNNs. However, from a model interpretability aspect, Gaussian noise with label smoothing does not increase the adversarial robustness of the model. To resolve this problem, we tackle the AE instead of measuring the accuracy of the model against AEs. Considering that a robust model shows a small curvature of the loss surface, we propose a metric to measure the strength of the AEs and the robustness of the model. Furthermore, we introduce a method to verify the existence of the obfuscated gradients of the model based on the black-box attack sanity check method. The proposed method enables us to identify a gradient masking problem wherein the model does not provide useful gradients and exploits false defenses. We evaluate our technique against representative adversarially trained models using the CIFAR10, CIFAR100, SVHN, and Restricted ImageNet datasets. Our results show that the performance of some false defense models decreases by up to 32% compared to the previous evaluation metrics. Moreover, our metric reveals that traditional metrics used to measure the robustness of the model may produce false results.

As industries become automated and connectivity technologies advance, a wide range of systems continues to generate massive amounts of data. Many approaches have been proposed to extract principal indicators from the vast sea of data to represent the entire system state. Detecting anomalies using these indicators on time prevent potential accidents and economic losses. Anomaly detection in multivariate time series data poses a particular challenge because it requires simultaneous consideration of temporal dependencies and relationships between variables. Recent deep learning-based works have made impressive progress in this field. They are highly capable of learning representations of the large-scaled sequences in an unsupervised manner and identifying anomalies from the data. However, most of them are highly specific to the individual use case and thus require domain knowledge for appropriate deployment. This review provides a background on anomaly detection in time-series data and reviews the latest applications in the real world. Also, we comparatively analyze state-of-the-art deep-anomaly-detection models for time series with several benchmark datasets. Finally, we offer guidelines for appropriate model selection and training strategy for deep learning-based time series anomaly detection.

Bridging the exponentially growing gap between the numbers of unlabeled and labeled protein sequences, several studies adopted semi-supervised learning for protein sequence modeling. In these studies, models were pre-trained with a substantial amount of unlabeled data, and the representations were transferred to various downstream tasks. Most pre-training methods solely rely on language modeling and often exhibit limited performance. In this paper, we introduce a novel pre-training scheme called PLUS, which stands for Protein sequence representations Learned Using Structural information. PLUS consists of masked language modeling and a complementary protein-specific pre-training task, namely same-family prediction. PLUS can be used to pre-train various model architectures. In this work, we use PLUS to pre-train a bidirectional recurrent neural network and refer to the resulting model as PLUS-RNN. Our experiment results demonstrate that PLUS-RNN outperforms other models of similar size solely pre-trained with the language modeling in six out of seven widely used protein biology tasks. Furthermore, we present the results from our qualitative interpretation analyses to illustrate the strengths of PLUS-RNN. PLUS provides a novel way to exploit evolutionary relationships among unlabeled proteins and is broadly applicable across a variety of protein biology tasks. We expect that the gap between the numbers of unlabeled and labeled proteins will continue to grow exponentially, and the proposed pre-training method will play a larger role. All the data and codes used in this study are available at https://github.com/mswzeus/PLUS.

Nucleic acid sequence classification is a fundamental task in the field of bioinformatics. Due to the increasing amount of unlabeled nucleotide sequences, fast and accurate classification of them on a large scale has become crucial. In this work, we developed NASCUP, a new classification method that captures statistical structures of nucleotide sequences by compact context-tree models and universal probability from information theory. A comprehensive experimental study involving nine public databases for functional non-coding RNA, microbial taxonomy and coding/non-coding RNA classification demonstrates the advantages of NASCUP over widely-used alternatives in efficiency, accuracy, and scalability across all datasets considered. NASCUP achieved BLAST-like classification accuracy consistently for several large-scale databases in orders-of-magnitude reduced runtime, and was applied to other bioinformatics tasks such as outlier detection and synthetic sequence generation.

There exist relations, which vary with time or by an event, between high dimensional elements in most real-world datasets. A dynamic graph or network has been used as one of the remarkable approaches to represent and analyze them. In spite of the advantages of representing data in the form of graphs, it is difficult to apply representation (deep) learning to graphs. Recently, AlphaFold by DeepMind has shown remarkable results in applying deep learning to graphs. This research is part of the current effort to extend the input domain of deep learning to arbitrarily graphs and their dynamics of variations. In this paper, we propose a method to predict the evolution of graphs by learning spatio-temporal features called dynamics. The method involves two main processes: extracting spatial features from static graphs obtained at different times and learning temporal features from the time-varying connection structure. Instead of predicting the overall changes of a highly complex graph, we detect the dynamic anomaly by predicting the affinity score with respect to a node (e.g., a hub as an important factor) of a dynamics graph. This facilitates the learning dynamics of graphs having sparsity of connections by alleviating the curse of dimensions using the fact that most graphs of real-world problems are scale-free. To justify our approach, we apply our method to real-world problems such as computer networks and public transportation. Experimental results show that our approach is competitive with other existing methods.

Abstract Background Quantitative structure-activity relationship (QSAR) is a computational modeling method for revealing relationships between structural properties of chemical compounds and biological activities. QSAR modeling is essential for drug discovery, but it has many constraints. Ensemble-based machine learning approaches have been used to overcome constraints and obtain reliable predictions. Ensemble learning builds a set of diversified models and combines them. However, the most prevalent approach random forest and other ensemble approaches in QSAR prediction limit their model diversity to a single subject. Results The proposed ensemble method consistently outperformed thirteen individual models on 19 bioassay datasets and demonstrated superiority over other ensemble approaches that are limited to a single subject. The comprehensive ensemble method is publicly available at http://data.snu.ac.kr/QSAR/. Conclusions We propose a comprehensive ensemble method that builds multi-subject diversified models and combines them through second-level meta-learning. In addition, we propose an end-to-end neural network-based individual classifier that can automatically extract sequential features from a simplified molecular-input line-entry system (SMILES). The proposed individual models did not show impressive results as a single model, but it was considered the most important predictor when combined, according to the interpretation of the meta-learning.

Deep neural networks are widely used and exhibit excellent performance in many areas. However, they are vulnerable to adversarial attacks that compromise networks at inference time by applying elaborately designed perturbations to input data. Although several defense methods have been proposed to address specific attacks, other types of attacks can circumvent these defense mechanisms. Therefore, we propose Purifying Variational AutoEncoder (PuVAE), a method to purify adversarial examples. The proposed method eliminates an adversarial perturbation by projecting an adversarial example on the manifold of each class and determining the closest projection as a purified sample. We experimentally illustrate the robustness of PuVAE against various attack methods without any prior knowledge about the attacks. In our experiments, the proposed method exhibits performances that are competitive with state-of-the-art defense methods, and the inference time is approximately 130 times faster than that of Defense-GAN which is a state-of-the art purifier method.

Cardiovascular disease is the leading cause of death in the world. It is vital to prevent it by rapid diagnosis and appropriate management through periodic blood pressure (BP) measurement. Recently, many studies have been conducted on methods to measure BP without a cuff. One of the most common methods of predicting BP without a cuff is to use the correlation between pulse wave velocity (PWV) and BP. Studies that predict BP through PWV have two problems to overcome: 1) Additional efforts are required to extract PWV features manually from various biomedical signals, such as electrocardiogram (ECG) and photoplethysmogram (PPG); and 2) in predicting BP using biomedical signals from other people, individual periodic calibration is required because the correlation between PWV and BP differs from person to person. In this study, we proposed a cuffless BP prediction method based on a deep convolutional neural network (CNN) that can overcome the problems mentioned above. The proposed CNN method 1) can use raw signals for training without PWV feature extraction; and 2) automatically learns the characteristics of biomedical signals from other people to predict BP accurately without calibration. We propose two schemes: extraction through multiple dilated convolution, and concentration through strided convolution with a large kernel, to process sequential ECG and PPG signals through CNN. BP prediction performance was the best when both ECG and PPG signals were used together. To this end, we conducted extensive experiments on the different settings of the proposed method and constructed an effective learning model. The proposed method achieved excellent performance in predicting both systolic blood pressure and diastolic blood pressure over other known approaches. We also verified that the performance of our method fulfills international standard protocols, AAMI, and BHS.

Sleep staging is an important part of clinical neurology. However, it is still performed manually by technical experts and is labor-intensive and time-consuming. To overcome these obstacles in the manual sleep staging process, a large number of machine learning-based classifiers with hand-engineered features have been proposed. Additionally, combinations of a deep neural network (DNN) have been recently highlighted as the state-of-the-art classifiers in view of their effectiveness for automatic sleep staging. In spite of the existence of a large number of these types of classifiers, to-this-date, no prior DNN-based approach has attempted sleep-stage classification using pediatric electroencephalographic (EEG) signals. In this paper, we propose a novel end-to-end classifier based on a multi-domain hybrid neural network (HNN-multi) approach consisting of a convolutional neural network and bidirectional long short-term memory for automatic sleep staging with pediatric scalp EEG recordings. To find effective temporal, spatial, and domain-specific conditions, we investigated noticeable changes in the classification performance corresponding to: 1) the length of input signals; 2) the number of channels; and 3) the types of input signals in the time and frequency domains. Our HNN-based classifier yielded the best performance metrics using 30-s time series in combination with an instantaneous frequency using a 19-channel, three-stage classification, with overall accuracy, F1 score, and Cohen's Kappa, equal to 92.21%, 0.90, and 0.88, respectively. We suggest that an effective combination of temporal and spatial time-domain clues with time-varying frequency domain information plays a pivotal role in pediatric, automatic sleep staging. Sufficiently reasonable performance of our HNN-based approach coping with the highly complicated pediatric EEG signatures hopefully sheds light on the clinical feasibility of the DNN-based automatic sleep staging for pediatric neurology.

The aim of this study was to evaluate changes in the skin surface microbiome in patients with atopic dermatitis during treatment. The effect of narrowband ultraviolet B phototherapy was also studied to determine the influence of exposure to ultraviolet. A total of 18 patients with atopic dermatitis were included in the study. Patients were divided into 2 groups based on treatment: 1 group treated with narrowband ultraviolet B phototherapy and topical corticosteroid, and the other group treated with topical corticosteroid only. Skin swabs and high-throughput sequencing of 16S ribosomal RNA bacterial genes were performed at 3 time-points. The microbial diversity of lesional skin increased greatly after treatment. The proportion of Staphylococcus aureus showed a significant positive correlation with eczema severity. In conclusion, a drastic increase in microbial diversity and decrease in S. aureus proportion were observed with eczema treatment. Narrowband ultraviolet B treatment did not exert additive effects on eczema improvement; however, it appeared to reduce the recurrence of eczema.

Abstract Background The conventional scores of the neuropsychological batteries are not fully optimized for diagnosing dementia despite their variety and abundance of information. To achieve low-cost high-accuracy diagnose performance for dementia using a neuropsychological battery, a novel framework is proposed using the response profiles of 2666 cognitively normal elderly individuals and 435 dementia patients who have participated in the Korean Longitudinal Study on Cognitive Aging and Dementia (KLOSCAD). Methods The key idea of the proposed framework is to propose a cost-effective and precise two-stage classification procedure that employed Mini Mental Status Examination (MMSE) as a screening test and the KLOSCAD Neuropsychological Assessment Battery as a diagnostic test using deep learning. In addition, an evaluation procedure of redundant variables is introduced to prevent performance degradation. A missing data imputation method is also presented to increase the robustness by recovering information loss. The proposed deep neural networks (DNNs) architecture for the classification is validated through rigorous evaluation in comparison with various classifiers. Results The k-nearest-neighbor imputation has been induced according to the proposed framework, and the proposed DNNs for two stage classification show the best accuracy compared to the other classifiers. Also, 49 redundant variables were removed, which improved diagnostic performance and suggested the potential of simplifying the assessment. Using this two-stage framework, we could get 8.06% higher diagnostic accuracy of dementia than MMSE alone and 64.13% less cost than KLOSCAD-N alone. Conclusion The proposed framework could be applied to general dementia early detection programs to improve robustness, preciseness, and cost-effectiveness.

Heat shock proteins (HSPs) play a pivotal role as molecular chaperones against unfavorable conditions. Although HSPs are of great importance, their computational identification remains a significant challenge. Previous studies have two major limitations. First, they relied heavily on amino acid composition features, which inevitably limited their prediction performance. Second, their prediction performance was overestimated because of the independent two-stage evaluations and train-test data redundancy. To overcome these limitations, we introduce two novel deep learning algorithms: (1) time-efficient DeepHSP and (2) high-performance DeeperHSP. We propose a convolutional neural network (CNN)-based DeepHSP that classifies both non-HSPs and six HSP families simultaneously. It outperforms state-of-the-art algorithms, despite taking 14-15 times less time for both training and inference. We further improve the performance of DeepHSP by taking advantage of protein transfer learning. While DeepHSP is trained on raw protein sequences, DeeperHSP is trained on top of pre-trained protein representations. Therefore, DeeperHSP remarkably outperforms state-of-the-art algorithms increasing F1 scores in both cross-validation and independent test experiments by 20% and 10%, respectively. We envision that the proposed algorithms can provide a proteome-wide prediction of HSPs and help in various downstream analyses for pathology and clinical research.

Abstract Background DNA damage causes aging, cancer, and other serious diseases. The comet assay can detect multiple types of DNA lesions with high sensitivity, and it has been widely applied. Although comet assay platforms have improved the limited throughput and reproducibility of traditional assays in recent times, analyzing large quantities of comet data often requires a tremendous human effort. To overcome this challenge, we proposed HiComet, a computational tool that can rapidly recognize and characterize a large number of comets, using little user intervention. Results We tested HiComet with real data from 35 high-throughput comet assay experiments, with over 700 comets in total. The proposed method provided unprecedented levels of performance as an automated comet recognition tool in terms of robustness (measured by precision and recall) and throughput. Conclusions HiComet is an automated tool for high-throughput comet-assay analysis and could significantly facilitate characterization of individual comets by accelerating its most rate-limiting step. An online implementation of HiComet is freely available at https://github.com/taehoonlee/HiComet/.

With the recent success of deep learning, the amount of data and computation continues to grow daily. Hence a distributed deep learning system that shares the training workload has been researched extensively. Although a scale-out distributed environment using commodity servers is widely used, not only is there a limit due to synchronous operation and communication traffic but also combining deep neural network (DNN) training with existing clusters often demands additional hardware and migration between different cluster frameworks or libraries, which is highly inefficient. Therefore, we propose TensorLightning which integrates the widely used data pipeline of Apache Spark with powerful deep learning libraries, Caffe and TensorFlow. TensorLightning embraces a brand-new parameter aggregation algorithm and parallel asynchronous parameter managing schemes to relieve communication discrepancies and overhead. We redesign the elastic averaging stochastic gradient descent algorithm with pruned and sparse form parameters. Our approach provides the fast and flexible DNN training with high accessibility. We evaluated our proposed framework with convolutional neural network and recurrent neural network models; the framework reduces network traffic by 67% with faster convergence.

Today’s data centers have various computing and storage devices for processing a myriad of data, and they generally consume a considerable amount of electrical energy. This paper proposes a smart grid-inspired methodology to observe and profile the power consumption of a data center. Based on this technique, our paper provides information that is useful for moderating the peak power consumption of the data centers. Our power measurement platform consists of several devices named CloudSockets, and each CloudSocket unit can measure the power consumption of multiple computing nodes and periodically transmit measurement data wirelessly to the coordinator unit. This data can be used to analyze the relationship between the workload and the power consumption of the data center. We tested our methodology through the application of various algorithms with a 32-node distributed system that runs Apache Spark for large-scale data analytics. An analysis of our experimental results reveals how and where the peak power of each node in the grid overlaps, providing opportunities for informed coordination of the computing components for peak power reduction.

In various disciplines, hierarchical clustering (HC) has been an effective tool for data analysis due to its ability to summarize hierarchical structures of data in an intuitive and interpretable manner. A run of HC requires multiple iterations, each of which needs to compute and update the pairwise distances between all intermediate clusters. This makes the exact algorithm for HC inevitably suffer from quadratic time and space complexities. To address large-scale data, various approximate/parallel algorithms have been proposed to reduce the computational cost of HC. However, such algorithms still rely on conventional linkage methods (such as single, centroid, average, complete, or Ward's) for defining pairwise distances, mostly focusing on the approximation/parallelization of linkage computations. Given that the choice of linkage profoundly affects not only the quality but also the efficiency of HC, we propose a new linkage method named NC-link and design an exact algorithm for NC-link-based HC. To guarantee the exactness, the proposed algorithm maintains the quadratic nature in time complexity but exhibits only linear space complexity, thereby allowing us to address million-object data on a personal computer. To underpin the extensibility of our approach, we showthat the algorithmic nature of NC-link enables single instruction multiple data (SIMD) parallelization and subquadratic-time approximation of HC. To verify our proposal, we thoroughly tested it with a number of large-scale real and synthetic data sets. In terms of efficiency, NC-link allowed us to perform HC substantially more space efficiently or faster than conventional methods: compared with average and complete linkages, using NC-link incurred only 0.7%-1.75% of the memory usage, and the NC-link-based implementation delivered speedups of approximately 3.5 times over the centroid and Ward's linkages. With regard to clustering quality, the proposed method was able to retrieve hierarchical structures from input data as faithfully as in the popular average and centroid linkage methods. We anticipate that the existing approximation/parallel algorithms will be able to benefit from adopting NC-link as their linkage method for obtaining better clustering results and reduced time and space demands.

Robust classification becomes challenging when each class consists of multiple subclasses. Examples include multi-font optical character recognition and automated protein function prediction. In correlation-based nearest-neighbor classification, the maximin correlation approach (MCA) provides the worst-case optimal solution by minimizing the maximum misclassification risk through an iterative procedure. Despite the optimality, the original MCA has drawbacks that have limited its wide applicability in practice. That is, the MCA tends to be sensitive to outliers, cannot effectively handle nonlinearities in datasets, and suffers from having high computational complexity. To address these limitations, we propose an improved solution, named regularized MCA (R-MCA). We first reformulate MCA as a quadratically constrained linear programming (QCLP) problem, incorporate regularization by introducing slack variables in the primal problem of the QCLP, and derive the corresponding Lagrangian dual. The dual formulation enables us to apply the kernel trick to R-MCA, so that it can better handle nonlinearities. Our experimental results demonstrate that the regularization and kernelization make the proposed R-MCA more robust and accurate for various classification tasks than the original MCA. Furthermore, when the data size or dimensionality grows, R-MCA runs substantially faster by solving either the primal or dual (whichever has a smaller variable dimension) of the QCLP.

Electrocardiogram (ECG) signals from mobile sensors are expected to increase the availability of authentication in the emerging wearable device industry. However, mobile sensors provide a relatively lower quality signal than the conventional medical devices. This paper proposes a practical authentication procedure for ECG signals that collected via one-chip-solution mobile sensors. We designed a cascading bandpass filter for noise cancellation and suggest eight fiducial features. For classification-based authentication, we use the radial basis function kernel-based support vector machine showing the best performance among nine classifiers through experimental comparisons. In spite of noisy ECG signals in mobile sensors, we achieved 4.61% of the equal error rate (EER) on a single heartbeat, and 1.87% of EER on 15 s testing time on 175 subjects, which is a reasonable result and supports the usability of low-cost ECGs for biometric authentication.

Purpose: The purpose of this article is to compare the predictive power of two models trained with computed tomography (CT)-based radiological features and both CT-based radiological and clinical features for pathologic femoral fractures in patients with lung cancer using machine learning algorithms. Methods: Between January 2010 and December 2014, 315 lung cancer patients with metastasis to the femur were included. Among them, 84 patients who underwent CT scan and were followed up for more than 3 months were enrolled. We examined clinical and radiological risk factors affecting pathologic fracture through logistic regression. Predictive analysis was performed using five different supervised learning algorithms. The power of predictive model trained with CT-based radiological features was compared to those trained with both CT-based radiological and clinical features. Results: In multivariate logistic regression, female sex (odds ratio = 0.25, p = 0.0126), osteolysis (odds ratio = 7.62, p = 0.0239), and absence of radiation therapy (odds ratio = 10.25, p = 0.0258) significantly increased the risk of pathologic fracture in proximal femur. The predictive model trained with both CT-based radiological and clinical features showed the highest area under the receiver operating characteristic curve (0.80 ± 0.14, p < 0.0001) through gradient boosting algorithm. Conclusion: We believe that machine learning algorithms may be useful in the prediction of pathologic femoral fracture, which are multifactorial problem.

We consider the correction of errors from nucleotide sequences produced by next-generation targeted amplicon sequencing. The next-generation sequencing (NGS) platforms can provide a great deal of sequencing data thanks to their high throughput, but the associated error rates often tend to be high. Denoising in high-throughput sequencing has thus become a crucial process for boosting the reliability of downstream analyses. Our methodology, named DUDE-Seq, is derived from a general setting of reconstructing finite-valued source data corrupted by a discrete memoryless channel and effectively corrects substitution and homopolymer indel errors, the two major types of sequencing errors in most high-throughput targeted amplicon sequencing platforms. Our experimental studies with real and simulated datasets suggest that the proposed DUDE-Seq not only outperforms existing alternatives in terms of error-correction capability and time efficiency, but also boosts the reliability of downstream analyses. Further, the flexibility of DUDE-Seq enables its robust application to different sequencing platforms and analysis pipelines by simple updates of the noise model. DUDE-Seq is available at http://data.snu.ac.kr/pub/dude-seq.

We developed the Korean Prostate Cancer Risk Calculator for High-Grade Prostate Cancer (KPCRC-HG) that predicts the probability of prostate cancer (PC) of Gleason score 7 or higher at the initial prostate biopsy in a Korean cohort (http://acl.snu.ac.kr/PCRC/RISC/). In addition, KPCRC-HG was validated and compared with internet-based Western risk calculators in a validation cohort.Using a logistic regression model, KPCRC-HG was developed based on the data from 602 previously unscreened Korean men who underwent initial prostate biopsies. Using 2,313 cases in a validation cohort, KPCRC-HG was compared with the European Randomized Study of Screening for PC Risk Calculator for high-grade cancer (ERSPCRC-HG) and the Prostate Cancer Prevention Trial Risk Calculator 2.0 for high-grade cancer (PCPTRC-HG). The predictive accuracy was assessed using the area under the receiver operating characteristic curve (AUC) and calibration plots.PC was detected in 172 (28.6%) men, 120 (19.9%) of whom had PC of Gleason score 7 or higher. Independent predictors included prostate-specific antigen levels, digital rectal examination findings, transrectal ultrasound findings, and prostate volume. The AUC of the KPCRC-HG (0.84) was higher than that of the PCPTRC-HG (0.79, p

After publication of the original article [1], it has been found that the author affiliations have been accidentally left out in the PDF. The full affiliations can be found in this correction:

Active surveillance (AS) is a promising option for patients with low-risk prostate cancer (PCa), however current criteria could not select the patients correctly, many patients who fulfilled recent AS criteria experienced pathological Gleason score upgrade (PGU) after radical prostatectomy (RP). In this study, we aimed to develop an accurate model for predicting PGU among low-risk PCa patients by using exome genotyping.We genotyped 242,221 single nucleotide polymorphisms (SNP)s on a custom HumanExome BeadChip v1.0 (Illuminam Inc.) in blood DNA from 257 low risk PCa patients (PSA

The assessment of information transfer in the global economic network helps to understand the current environment and the outlook of an economy. Most approaches on global networks extract information transfer based mainly on a single variable. This paper establishes an entirely new bioinformatics-inspired approach to integrating information transfer derived from multiple variables and develops an international economic network accordingly. In the proposed methodology, we first construct the transfer entropies (TEs) between various intra- and inter-country pairs of economic time series variables, test their significances, and then use a weighted sum approach to aggregate information captured in each TE. Through a simulation study, the new method is shown to deliver better information integration compared to existing integration methods in that it can be applied even when intra-country variables are correlated. Empirical investigation with the real world data reveals that Western countries are more influential in the global economic network and that Japan has become less influential following the Asian currency crisis.