Download or read book Scalable Kernel Methods and Algorithms for General Sequence Analysis written by Pavel Kuksa and published by . This book was released on 2011 with total page 114 pages. Available in PDF, EPUB and Kindle. Book excerpt: Analysis of large-scale sequential data has become an important task in machine learning and pattern recognition, inspired in part by numerous scientific and technological applications such as the document and text classification or the analysis of biological sequences. However, current computational methods for sequence comparison still lack accuracy and scalability necessary for reliable analysis of large datasets. To this end, we develop a new framework (efficient algorithms and methods) that solve sequence matching, comparison, classification, and pattern extraction problems in linear time, with increased accuracy, improving over the prior art. In particular, we propose novel ways of modeling sequences under complex transformations (such as multiple insertions, deletions, mutations) and present a new family of similarity measures (kernels), the spatial string kernels (SSK). SSKs can be computed very efficiently and perform better than the best available methods on a variety of distinct classification tasks. We also present new algorithms for approximate (e.g., with mismatches) string comparison that improve currently known time complexity bounds for such tasks and show order-of-magnitude running time improvements. We then propose novel linear time algorithms for representative pattern extraction in sequence data sets that exploit developed computational framework. In an extensive set of experiments on many challenging classification problems, such as detecting homology (evolutionary similarity) of remotely related proteins, categorizing texts, and performing classification of music samples, our algorithms and similarity measures display state-of-the-art classification performance and run significantly faster than existing methods.

Download or read book Efficient Large Scale Machine Learning Algorithms for Genomic Sequences written by Daniel Quang and published by . This book was released on 2017 with total page 114 pages. Available in PDF, EPUB and Kindle. Book excerpt: High-throughput sequencing (HTS) has led to many breakthroughs in basic and translational biology research. With this technology, researchers can interrogate whole genomes at single-nucleotide resolution. The large volume of data generated by HTS experiments necessitates the development of novel algorithms that can efficiently process these data. At the advent of HTS, several rudimentary methods were proposed. Often, these methods applied compromising strategies such as discarding a majority of the data or reducing the complexity of the models. This thesis focuses on the development of machine learning methods for efficiently capturing complex patterns from high volumes of HTS data.First, we focus on on de novo motif discovery, a popular sequence analysis method that predates HTS. Given multiple input sequences, the goal of motif discovery is to identify one or more candidate motifs, which are biopolymer sequence patterns that are conjectured to have biological significance. In the context of transcription factor (TF) binding, motifs may represent the sequence binding preference of proteins. Traditional motif discovery algorithms do not scale well with the number of input sequences, which can make motif discovery intractable for the volume of data generated by HTS experiments. One common solution is to only perform motif discovery on a small fraction of the sequences. Scalable algorithms that simplify the motif models are popular alternatives. Our approach is a stochastic method that is scalable and retains the modeling power of past methods.Second, we leverage deep learning methods to annotate the pathogenicity of genetic variants. Deep learning is a class of machine learning algorithms concerned with deep neural networks (DNNs). DNNs use a cascade of layers of nonlinear processing units for feature extraction and transformation. Each layer uses the output from the previous layer as its input. Similar to our novel motif discovery algorithm, artificial neural networks can be efficiently trained in a stochastic manner. Using a large labeled dataset comprised of tens of millions of pathogenic and benign genetic variants, we trained a deep neural network to discriminate between the two categories. Previous methods either focused only on variants lying in protein coding regions, which cover less than 2% of the human genome, or applied simpler models such as linear support vector machines, which can not usually capture non-linear patterns like deep neural networks can.Finally, we discuss convolutional (CNN) and recurrent (RNN) neural networks, variations of DNNs that are especially well-suited for studying sequential data. Specifically, we stacked a bidirectional recurrent layer on top of a convolutional layer to form a hybrid model. The model accepts raw DNA sequences as inputs and predicts chromatin markers, including histone modifications, open chromatin, and transcription factor binding. In this specific application, the convolutional kernels are analogous to motifs, hence the model learning is essentially also performing motif discovery. Compared to a pure convolutional model, the hybrid model requires fewer free parameters to achieve superior performance. We conjecture that the recurrent layer allows our model spatial and orientation dependencies among motifs better than a pure convolutional model can. With some modifications to this framework, the model can accept cell type-specific features, such as gene expression and open chromatin DNase I cleavage, to accurately predict transcription factor binding across cell types. We submitted our model to the ENCODE-DREAM in vivo Transcription Factor Binding Site Prediction Challenge, where it was among the top performing models. We implemented several novel heuristics, which significantly reduced the training time and the computational overhead. These heuristics were instrumental to meet the Challenge deadlines and to make the method more accessible for the research community.HTS has already transformed the landscape of basic and translational research, proving itself as a mainstay of modern biological research. As more data are generated and new assays are developed, there will be an increasing need for computational methods to integrate the data to yield new biological insights. We have only begun to scratch the surface of discovering what is possible from both an experimental and a computational perspective. Thus, further development of versatile and efficient statistical models is crucial to maintaining the momentum for new biological discoveries.

Download or read book Kernel Methods for Pattern Analysis written by John Shawe-Taylor and published by Cambridge University Press. This book was released on 2004-06-28 with total page 520 pages. Available in PDF, EPUB and Kindle. Book excerpt: Publisher Description

Download or read book Scalable Kernel Methods and Their Use in Black box Optimization written by David Mikael Eriksson and published by . This book was released on 2018 with total page 264 pages. Available in PDF, EPUB and Kindle. Book excerpt: This dissertation uses structured linear algebra to scale kernel regression methods based on Gaussian processes (GPs) and radial basis function (RBF) interpolation to large, high-dimensional datasets. While kernel methods provide a general, principled framework for approximating functions from scattered data, they are often seen as impractical for large data sets as the standard approach to model fitting scales cubically with the number of data points. We introduce RBFs in Section 1.3 and GPs in Section 1.4. Chapter 2 develops novel O(n) approaches for GP regression with n points using fast approximate matrix vector multiplications (MVMs). Kernel learning with GPs require solving linear systems and computing the log determinant of an n x n kernel matrix. We use iterative methods relying on the fast MVMs to solve the linear systems and leverage stochastic approximations based on Chebyshev and Lanczos to approximate the log determinant. We find that Lanczos is generally highly efficient and accurate and superior to Chebyshev for kernel learning. We consider a large variety of experiments to demonstrate the generality of this approach. Chapter 3 extends the ideas from Chapter 3 to fitting a GP to both function values and derivatives. This requires linear solves and log determinants with an n(d+1) x n(d+1) kernel matrix in d dimensions, leading to O(n^3 d^3) computations for standard methods. We extend the previous methods and introduce a pivoted Cholesky preconditioner that cuts the iterations to convergence by several orders of magnitude. Our approaches, together with dimensionality reduction, lets us scale Bayesian optimization with derivatives to high-dimensional problems and large evaluation budgets. We introduce surrogate optimization in Section 1.5. Surrogate optimization is a key application of GPs and RBFs, where they are used to model a computationally-expensive black-box function based on previous evaluations. Chapter 4 introduces a global optimization algorithm for computationally expensive black-box function based on RBFs. Given an upper bound on the semi-norm of the objective function in a reproducing kernel Hilbert space associated with the RBF, we prove that our algorithm is globally convergent even though it may not sample densely. We discuss expected convergence rates and illustrate the performance of the method via experiments on a set of test problems. Chapter 5 describes Plumbing for Optimization with Asynchronous Parallelism (POAP) and the Python Surrogate Optimization Toolbox (pySOT). POAP is an event-driven framework for building and combining asynchronous optimization strategies, designed for global optimization of computationally expensive black-box functions where concurrent function evaluations are appealing. pySOT is a collection of synchronous and asynchronous surrogate optimization strategies, implemented in the POAP framework. The pySOT framework includes a variety of surrogate models, experimental designs, optimization strategies, test problems, and serves as a useful platform to compare methods. We use pySOT, to make an extensive comparison between synchronous and asynchronous parallel surrogate optimization methods, and find that asynchrony is never worse than synchrony on several challenging multimodal test p...

Download or read book Kernel Methods in Bioengineering Signal and Image Processing written by Gustavo Camps-Valls and published by IGI Global. This book was released on 2007-01-01 with total page 431 pages. Available in PDF, EPUB and Kindle. Book excerpt: "This book presents an extensive introduction to the field of kernel methods and real world applications. The book is organized in four parts: the first is an introductory chapter providing a framework of kernel methods; the others address Bioegineering, Signal Processing and Communications and Image Processing"--Provided by publisher.

Download or read book Scalable Pattern Recognition Algorithms written by Pradipta Maji and published by Springer Science & Business Media. This book was released on 2014-03-19 with total page 316 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book addresses the need for a unified framework describing how soft computing and machine learning techniques can be judiciously formulated and used in building efficient pattern recognition models. The text reviews both established and cutting-edge research, providing a careful balance of theory, algorithms, and applications, with a particular emphasis given to applications in computational biology and bioinformatics. Features: integrates different soft computing and machine learning methodologies with pattern recognition tasks; discusses in detail the integration of different techniques for handling uncertainties in decision-making and efficiently mining large biological datasets; presents a particular emphasis on real-life applications, such as microarray expression datasets and magnetic resonance images; includes numerous examples and experimental results to support the theoretical concepts described; concludes each chapter with directions for future research and a comprehensive bibliography.

Download or read book Scalable Information Systems written by Peter Mueller and published by Springer. This book was released on 2009-11-16 with total page 332 pages. Available in PDF, EPUB and Kindle. Book excerpt: In view of the incessant growth of data and knowledge and the continued diversifi- tion of information dissemination on a global scale, scalability has become a ma- stream research area in computer science and information systems. The ICST INFO- SCALE conference is one of the premier forums for presenting new and exciting research related to all aspects of scalability, including system architecture, resource management, data management, networking, and performance. As the fourth conf- ence in the series, INFOSCALE 2009 was held in Hong Kong on June 10 and 11, 2009. The articles presented in this volume focus on a wide range of scalability issues and new approaches to tackle problems arising from the ever-growing size and c- plexity of information of all kind. More than 60 manuscripts were submitted, and the Program Committee selected 22 papers for presentation at the conference. Each s- mission was reviewed by three members of the Technical Program Committee.

Download or read book Efficient Kernel Methods for Large Scale Classification written by S. Asharaf and published by . This book was released on 2011 with total page 111 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Kernel Methods in Computational Biology written by Bernhard Schölkopf and published by MIT Press. This book was released on 2004 with total page 428 pages. Available in PDF, EPUB and Kindle. Book excerpt: A detailed overview of current research in kernel methods and their application to computational biology.

Download or read book Scalable Algorithms for Data and Network Analysis written by Shang-Hua Teng and published by . This book was released on 2016-05-04 with total page 292 pages. Available in PDF, EPUB and Kindle. Book excerpt: In the age of Big Data, efficient algorithms are in high demand. It is also essential that efficient algorithms should be scalable. This book surveys a family of algorithmic techniques for the design of scalable algorithms. These techniques include local network exploration, advanced sampling, sparsification, and geometric partitioning.

Download or read book Scalable Parallel Algorithms for Genome Analysis written by Evangelos Georganas and published by . This book was released on 2016 with total page 129 pages. Available in PDF, EPUB and Kindle. Book excerpt: A critical problem for computational genomics is the problem of de novo genome assembly: the development of robust scalable methods for transforming short randomly sampled "shotgun" sequences, namely reads, into the contiguous and accurate reconstruction of complex genomes. These reads are significantly shorter (e.g. hundreds of bases long) than the size of chromosomes and also include errors. While advanced methods exist for assembling the small and haploid genomes of prokaryotes, the genomes of eukaryotes are more complex. Moreover, de novo assembly has been unable to keep pace with the flood of data, due to the dramatic increases in genome sequencer capabilities, combined with the computational requirements and the algorithmic complexity of assembling large scale genomes and metagenomes. In this dissertation, we address this challenge head on by developing parallel algorithms for de novo genome assembly with the ambition to scale to massive concurrencies. Our work is based on the Meraculous assembler, a state-of-the-art de novo assembler for short reads developed at JGI. Meraculous identifies non-erroneous overlapping substrings of length k (k-mers) with high quality extensions and uniquely assembles genome regions into uncontested sequences called contigs by constructing and traversing a de Bruijn graph of k-mers, a special graph that is used to represent overlaps among k-mers. The original reads are subsequently aligned onto the contigs to obtain information regarding the relative orientation of the contigs. Contigs are then linked together to create scaffolds, sequences of contigs that may contain gaps among them. Finally gaps are filled using localized assemblies based on the original reads. First, we design efficient scalable algorithms for k-mer analysis and contig generation. K-mer analysis is characterized by intensive communication and I/O requirements and our parallel algorithms successfully reduce the memory requirements by 7×. Then, contig generation relies on efficient parallelization of the de Bruijn graph construction and traversal, which necessitates a distributed hash table and is a key component of most de novo assemblers. We present a novel algorithm that leverages one-sided communication capabilities of the UPC to facilitate the requisite fine-grained, irregular parallelism and the avoidance of data hazards. The sequence alignment is characterized by intensive I/O and large computation requirements. We introduce mer-Aligner, a highly parallel sequence aligner that employs parallelism in all of its components. Finally, this thesis details the parallelization of the scaffolding modules, enabling the first massively scalable, high quality, complete end-to-end de novo assembly pipeline. Experimental large-scale results using human and wheat genomes demonstrate efficient performance and scalability on thousands of cores. Compared to the original Meraculous code, which requires approximately 48 hours to assemble the human genome, our pipeline called HipMer computes the assembly in only 4 minutes using 23,040 cores of Edison - an overall speedup of approximately 720×. In the last part of the dissertation we tackle the problem of metagenome assembly. Metagenomics is currently the leading technology to study the uncultured microbial diversity. While accessing an unprecedented number of environmental samples that consist of thousands of individual microbial genomes is now possible, the bottleneck is becoming computational, since the sequencing cost improvements exceed that of Moore's Law. Metagenome assembly is further complicated by repeated sequences across genomes, polymorphisms within a species and variable frequency of the genomes within the sample. In our work we repurpose HipMer components for the problem of metagenome assembly and we design a versatile, high-performance metagenome assembly pipeline that outperforms state-of-the-art tools in both quality and performance.

Download or read book Advances in Kernel Methods written by Yves-Laurent Kom Samo and published by . This book was released on 2017 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Proceedings of the Fourth SIAM International Conference on Data Mining written by Michael W. Berry and published by SIAM. This book was released on 2004-01-01 with total page 556 pages. Available in PDF, EPUB and Kindle. Book excerpt: The Fourth SIAM International Conference on Data Mining continues the tradition of providing an open forum for the presentation and discussion of innovative algorithms as well as novel applications of data mining. This is reflected in the talks by the four keynote speakers who discuss data usability issues in systems for data mining in science and engineering, issues raised by new technologies that generate biological data, ways to find complex structured patterns in linked data, and advances in Bayesian inference techniques. This proceedings includes 61 research papers.

Download or read book Semi Supervised Learning written by Olivier Chapelle and published by MIT Press. This book was released on 2010-01-22 with total page 525 pages. Available in PDF, EPUB and Kindle. Book excerpt: A comprehensive review of an area of machine learning that deals with the use of unlabeled data in classification problems: state-of-the-art algorithms, a taxonomy of the field, applications, benchmark experiments, and directions for future research. In the field of machine learning, semi-supervised learning (SSL) occupies the middle ground, between supervised learning (in which all training examples are labeled) and unsupervised learning (in which no label data are given). Interest in SSL has increased in recent years, particularly because of application domains in which unlabeled data are plentiful, such as images, text, and bioinformatics. This first comprehensive overview of SSL presents state-of-the-art algorithms, a taxonomy of the field, selected applications, benchmark experiments, and perspectives on ongoing and future research.Semi-Supervised Learning first presents the key assumptions and ideas underlying the field: smoothness, cluster or low-density separation, manifold structure, and transduction. The core of the book is the presentation of SSL methods, organized according to algorithmic strategies. After an examination of generative models, the book describes algorithms that implement the low-density separation assumption, graph-based methods, and algorithms that perform two-step learning. The book then discusses SSL applications and offers guidelines for SSL practitioners by analyzing the results of extensive benchmark experiments. Finally, the book looks at interesting directions for SSL research. The book closes with a discussion of the relationship between semi-supervised learning and transduction.

Download or read book Algorithms in Bioinformatics written by Raffaele Giancarlo and published by Springer Science & Business Media. This book was released on 2007-08-22 with total page 443 pages. Available in PDF, EPUB and Kindle. Book excerpt: The refereed proceedings from the 7th International Workshop on Algorithms in Bioinformatics are provided in this volume. Papers address current issues in algorithms in bioinformatics, ranging from mathematical tools to experimental studies of approximation algorithms to significant computational analyses. Biological problems examined include genetic mapping, sequence alignment and analysis, phylogeny, comparative genomics, and protein structure.

Download or read book Foundation Architecture and Prototyping of Humanized AI written by Mark Chang and published by CRC Press. This book was released on 2023-08-08 with total page 385 pages. Available in PDF, EPUB and Kindle. Book excerpt: Humanized AI (HAI), emerging as the next of the AI waves, refers to artificial social beings that are very close to humans in various aspects, beings who are machine-race humans, not digital slaves. Foundation, Architecture, and Prototyping of HAI deploy a novel smalldata approach to vertically explore the spectrum of HAI. Different from the popular big-data philosophy that is based on the rigid notion that the connotation of each concept is fixed and the same to everyone, this book treats understanding as a process from simple to complex, and uses the similarity principle to effectively deal with novelties. Combining the efficiency of the Behaviorists’ goal-driven approach and the flexibility of a Constructivists’ approach, both the architecture of HAI and the philosophical discussions arising from it are elaborated upon. Advancing a unique approach to the concept of HAI, this book appeals to professors and students of both AI and philosophy, as well as industry professionals looking to stay at the forefront of developments within the field.

Download or read book Iterative Methods for Sparse Linear Systems written by Yousef Saad and published by SIAM. This book was released on 2003-04-01 with total page 537 pages. Available in PDF, EPUB and Kindle. Book excerpt: Mathematics of Computing -- General.