Alzheimer’s disease (AD) is an irreversible brain disease. In addition to the functional deterioration of memory and cognition, patients with severe conditions lose their self‐care ability. Patients exhibiting symptoms are often attributed to aging and thus lack proper medical care. If it can be diagnosed early, the doctor can provide adequate treatments to mitigate the symptoms. Magnetic resonance imaging (MRI) can reflect the characteristics of different human tissues and organs, and is a common tool implemented in clinical examinations. In this study, we tested learning‐based approaches to detect disease progression in AD patients using MRI. Specifically, each patient is categorized as one of the following four classes: cognitive normal, early mild cognitive impairment, late mild cognitive impairment, and AD. To extract 3D information in MRI, we proposed a 3D convolutional neural network structure based on ResNet3D‐18. We designed various multiclass classification frameworks. Moreover, we implemented ensemble classification combining these frameworks. Experiments demonstrated great potential for learning‐based approaches on the Alzheimer’s Disease Neuroimaging Initiative dataset. The ensemble approach performed the best with an accuracy of 0.950, which is competitive with neurologists in diagnosing AD progression in clinical practice. With precise detection, patients can understand their conditions early and seek proper treatments.

Total isotropic sensitivity (TIS) measurement is strongly required by the industry, but the procedure takes a long time. We explore a machine learning (ML) approach to speed up TIS test procedure. The experiments are conducted using 5G devices and frequency bands. The results show that our methodology can improve measurement efficiency by 35% to 65%, while still maintain high accuracy within 1 dB deviation from standard procedure. Disconnection is a critical issue during TIS measurement, so we design a calibration mechanism to reduce the risk of disconnection. Our approach can be applied widely to different system configurations. It supports not only 5G but also previous generations on different frequency bands.

BACKGROUND: A new emerged cancer treatment utilizes intrinsic immune surveillance mechanism that is silenced by those malicious cells. Hence, studies of tumor infiltrating lymphocyte populations (TILs) are key to the success of advanced treatments. In addition to laboratory methods such as immunohistochemistry and flow cytometry, in silico gene expression deconvolution methods are available for analyses of relative proportions of immune cell types. RESULTS: Herein, we used microarray data from the public domain to profile gene expression pattern of twenty-two immune cell types. Initially, outliers were detected based on the consistency of gene profiling clustering results and the original cell phenotype notation. Subsequently, we filtered out genes that are expressed in non-hematopoietic normal tissues and cancer cells. For every pair of immune cell types, we ran t-tests for each gene, and defined differentially expressed genes (DEGs) from this comparison. Equal numbers of DEGs were then collected as candidate lists and numbers of conditions and minimal values for building signature matrixes were calculated. Finally, we used v -Support Vector Regression to construct a deconvolution model. The performance of our system was finally evaluated using blood biopsies from 20 adults, in which 9 immune cell types were identified using flow cytometry. The present computations performed better than current state-of-the-art deconvolution methods. CONCLUSIONS: Finally, we implemented the proposed method into R and tested extensibility and usability on Windows, MacOS, and Linux operating systems. The method, MySort, is wrapped as the Galaxy platform pluggable tool and usage details are available at https://testtoolshed.g2.bx.psu.edu/view/moneycat/mysort/e3afe097e80a .

Pseudo-random number generators (PRNGs) play an important role in both areas of computer simulation and computer security. Currently, there appears to be a huge divide between the types of PRNGs used in these two areas. For PRNGs in computer security applications, the security concern is extremely important. For PRNGs in computer simulation applications, the properties of high-dimensional equi-distribution, efficiency, long period-length, and portability are important. In recent years, there have been many PRNGs proposed in the area of computer simulation satisfying these nice properties. However, most of them are linear generators, thus sharing the same weakness in predictability. The major aim of this article is to propose a general class of secure generators, called SAFE (secure and fast encryption) generators, by properly “mixing” two baseline generators with the aforementioned properties to obtain a secure generator that would inherit these nice properties. Specifically, we propose applying a general mutual-shuffling method to certain linear generators, such as the currently most popular MT19937 generator and large-order multiple recursive generators, as well as outputting certain nonlinear transformations of the generated variates to construct secure PRNGS.

This paper presents a budgetary learning algorithm for online multiclass classification. Based on the multiclass passive-aggressive learning with kernels, we introduce a dual perspective that gives rise to the proposed budgetary algorithm. Basically, the proposed algorithm limits the amount of data in use and fully exploits the available data on hand through optimization. The algorithm has both constant time and space complexities and thus can avoid the curse of kernelization. Experimental results with open datasets show that the proposed budgetary algorithm is competitive with state-of-the-art algorithms.

It has been a challenging task to build a genome-wide phylogenetic tree for a large group of species containing a large number of genes with long nucleotides sequences. The most popular method, called feature frequency profile (FFP- k ), finds the frequency distribution for all words of certain length k over the whole genome sequence using (overlapping) windows of the same length. For a satisfactory result, the recommended word length ( k ) ranges from 6 to 15 and it may not be a multiple of 3 (codon length). The total number of possible words needed for FFP- k can range from 4 6 =4096 to 4 15 . We propose a simple improvement over the popular FFP method using only a typical word length of 3. A new method, called Trinucleotide Usage Profile (TUP), is proposed based only on the (relative) frequency distribution using non-overlapping windows of length 3. The total number of possible words needed for TUP is 4 3 =64, which is much less than the total count for the recommended optimal “resolution” for FFP. To build a phylogenetic tree, we propose first representing each of the species by a TUP vector and then using an appropriate distance measure between pairs of the TUP vectors for the tree construction. In particular, we propose summarizing a DNA sequence by a matrix of three rows corresponding to three reading frames, recording the frequency distribution of the non-overlapping words of length 3 in each of the reading frame. We also provide a numerical measure for comparing trees constructed with various methods. Compared to the FFP method, our empirical study showed that the proposed TUP method is more capable of building phylogenetic trees with a stronger biological support. We further provide some justifications on this from the information theory viewpoint. Unlike the FFP method, the TUP method takes the advantage that the starting of the first reading frame is (usually) known. Without this information, the FFP method could only rely on the frequency distribution of overlapping words, which is the average (or mixture) of the frequency distributions of three possible reading frames. Consequently, we show (from the entropy viewpoint) that the FFP procedure could dilute important gene information and therefore provides less accurate classification.

Spectral matting is a useful technique for image matting problem. A crucial issue of spectral matting is to determine the number of matting components which has large impacts on the matting performance. In this paper, we propose an improved framework based on spectral matting in order to solve this limitation. Iterative K-means clustering with the assistance of the modularity measure is adopted to obtain the hard segmentation that can be used as the initial guess of soft matting components. The number of matting components can be determined automatically because the improved framework will search possible image components by iteratively dividing image subgraphs.

For the importance of communication between human and machine interface, it would be valuable to develop an implement which has the ability to recognize emotional states. In this paper, we proposed an approach which can deal with the daily dependence and personal dependence in the data of multiple subjects and samples. 30 features were extracted from the physiological signals of subject for three states of emotion. The physiological signals measured were: electrocardiogram (ECG), skin temperature (SKT) and galvanic skin response (GSR). After removing the daily dependence and personal dependence by the statistical technique of MANOVA, six machine learning methods including Bayesian network learning, naive Bayesian classification, SVM, decision tree of C4.5, Logistic model and K-nearest-neighbor (KNN) were implemented to differentiate the emotional states. The results showed that Logistic model gives the best classification accuracy and the statistical technique of MANOVA can significantly improve the performance of all six machine learning methods in emotion recognition system.

The performance of a maximum-period multiple recursive generator (MRG) depends on the choices of the recurrence order k, the prime modulus p, and the multipliers used. For a maximum-period MRG, a large-order k not only means a large period length (i.e., pk − 1) but, more importantly, also guarantees the equidistribution property in high dimensions (i.e., up to k dimensions), a desirable feature for a good random-number generator. As to generating efficiency, in addition to the multipliers, some special choices of the prime modulus p can significantly speed up the generation of pseudo-random numbers by replacing the expensive modulo operation with efficient logical operations. To construct efficient maximum-period MRGs of a large order, we consider the prime modulus p = 231 − 1 and, via extensive computer search, find two large values of k, 7,499 and 20,897, for which pk − 1 can be completely factorized. The successful search is achieved with the help of some results in number theory as well as some modern factorization methods. A general class of MRGs is introduced, which includes several existing classes of efficient generators. With the factorization results, we are able to identify via computer search within this class many portable and efficient maximum-period MRGs of order 7,499 or 20,897 with prime modulus 231 − 1 and multipliers of powers-of-two decomposition. These MRGs all pass the stringent TestU01 test suite empirically.

Nuclear genes encode most mitochondrial proteins, and their mutations cause diverse and debilitating clinical disorders. To date, 1,200 of these mitochondrial genes have been recorded, while no standardized catalog exists of the associated clinical phenotypes. Such a catalog would be useful to develop methods to analyze human phenotypic data, to determine genotype-phenotype relations among many genes and diseases, and to support the clinical diagnosis of mitochondrial disorders. Here we establish a clinical phenotype catalog of 174 mitochondrial disease genes and study associations of diseases and genes. Phenotypic features such as clinical signs and symptoms were manually annotated from full-text medical articles and classified based on the hierarchical MeSH ontology. This classification of phenotypic features of each gene allowed for the comparison of diseases between different genes. In turn, we were then able to measure the phenotypic associations of disease genes for which we calculated a quantitative value that is based on their shared phenotypic features. The results showed that genes sharing more similar phenotypes have a stronger tendency for functional interactions, proving the usefulness of phenotype similarity values in disease gene network analysis. We then constructed a functional network of mitochondrial genes and discovered a higher connectivity for non-disease than for disease genes, and a tendency of disease genes to interact with each other. Utilizing these differences, we propose 168 candidate genes that resemble the characteristic interaction patterns of mitochondrial disease genes. Through their network associations, the candidates are further prioritized for the study of specific disorders such as optic neuropathies and Parkinson disease. Most mitochondrial disease phenotypes involve several clinical categories including neurologic, metabolic, and gastrointestinal disorders, which might indicate the effects of gene defects within the mitochondrial system. The accompanying knowledgebase (http://www.mitophenome.org/) supports the study of clinical diseases and associated genes.

BACKGROUND: Multi-dimensional scaling (MDS) is aimed to represent high dimensional data in a low dimensional space with preservation of the similarities between data points. This reduction in dimensionality is crucial for analyzing and revealing the genuine structure hidden in the data. For noisy data, dimension reduction can effectively reduce the effect of noise on the embedded structure. For large data set, dimension reduction can effectively reduce information retrieval complexity. Thus, MDS techniques are used in many applications of data mining and gene network research. However, although there have been a number of studies that applied MDS techniques to genomics research, the number of analyzed data points was restricted by the high computational complexity of MDS. In general, a non-metric MDS method is faster than a metric MDS, but it does not preserve the true relationships. The computational complexity of most metric MDS methods is over O(N2), so that it is difficult to process a data set of a large number of genes N, such as in the case of whole genome microarray data. RESULTS: We developed a new rapid metric MDS method with a low computational complexity, making metric MDS applicable for large data sets. Computer simulation showed that the new method of split-and-combine MDS (SC-MDS) is fast, accurate and efficient. Our empirical studies using microarray data on the yeast cell cycle showed that the performance of K-means in the reduced dimensional space is similar to or slightly better than that of K-means in the original space, but about three times faster to obtain the clustering results. Our clustering results using SC-MDS are more stable than those in the original space. Hence, the proposed SC-MDS is useful for analyzing whole genome data. CONCLUSION: Our new method reduces the computational complexity from O(N3) to O(N) when the dimension of the feature space is far less than the number of genes N, and it successfully reconstructs the low dimensional representation as does the classical MDS. Its performance depends on the grouping method and the minimal number of the intersection points between groups. Feasible methods for grouping methods are suggested; each group must contain both neighboring and far apart data points. Our method can represent high dimensional large data set in a low dimensional space not only efficiently but also effectively.

MOTIVATION: Identifying transcription factor binding sites (TFBSs) is helpful for understanding the mechanism of transcriptional regulation. The abundance and the diversity of genomic data provide an excellent opportunity for identifying TFBSs. Developing methods to integrate various types of data has become a major trend in this pursuit. RESULTS: We develop a TFBS identification method, TFBSfinder, which utilizes several data sources, including DNA sequences, phylogenetic information, microarray data and ChIP-chip data. For a TF, TFBSfinder rigorously selects a set of reliable target genes and a set of non-target genes (as a background set) to find overrepresented and conserved motifs in target genes. A new metric for measuring the degree of conservation at a binding site across species and methods for clustering motifs and for inferring position weight matrices are proposed. For synthetic data and yeast cell cycle TFs, TFBSfinder identifies motifs that are highly similar to known consensuses. Moreover, TFBSfinder outperforms well-known methods. AVAILABILITY: http://cg1.iis.sinica.edu.tw/~TFBSfinder/.

We use an optimization technique to accurately locate a distorted grid structure in a microarray image. By assuming that spot centers deviate smoothly from a checkerboard grid structure, we show that the process of gridding spot centers can be formulated as a constrained optimization problem. The constraint is equal to the variations of the transform parameter. We demonstrate the accuracy of our algorithm on two sets of microarray images. One set consists of some images from the Stanford Microarray Database; we compare our centers with those annotated in the Database. The other set consists of oligonucleotide images, and we compare our results with those obtained by GenePix Pro 5.0. Our experiments were performed completely automatically.

An efficient new method, termed as the cross-reference weighted least square estimate (WLSE) [CRWLSE], is proposed to integrate the incomplete local smoothness information to improve the reconstruction of positron emission tomography (PET) images in the presence of accidental coincidence events and attenuation. The algebraic reconstruction technique (ART) is applied to this new estimate and the convergence is proved. This numerical technique is based on row operations. The computational complexity is only linear in the sizes of pixels and detector tubes. Hence, it is efficient in storage and computation for a large and sparse system. Moreover, the easy incorporation of range limits and spatially variant penalty will not deprive the efficiency. All this makes the new method practically applicable. An automatically data-driven selection method for this new estimate based on the generalized cross validation is also studied. The Monte Carlo studies demonstrate the advantages of this new method.