Read Books Online and Download eBooks, EPub, PDF, Mobi, Kindle, Text Full Free.
Advanced Interpretable Machine Learning Methods For Clinical Ngs Big Data Of Complex Hereditary Diseases 2nd Edition
Download Advanced Interpretable Machine Learning Methods For Clinical Ngs Big Data Of Complex Hereditary Diseases 2nd Edition full books in PDF, epub, and Kindle. Read online Advanced Interpretable Machine Learning Methods For Clinical Ngs Big Data Of Complex Hereditary Diseases 2nd Edition ebook anywhere anytime directly on your device. Fast Download speed and no annoying ads. We cannot guarantee that every ebooks is available!
Book Synopsis Advanced Interpretable Machine Learning Methods for Clinical NGS Big Data of Complex Hereditary Diseases, 2nd Edition by : Yudong Cai
Download or read book Advanced Interpretable Machine Learning Methods for Clinical NGS Big Data of Complex Hereditary Diseases, 2nd Edition written by Yudong Cai and published by Frontiers Media SA. This book was released on 2021-07-01 with total page 219 pages. Available in PDF, EPUB and Kindle. Book excerpt: Publisher’s note: This is a 2nd edition due to an article retraction
Book Synopsis Advanced interpretable machine learning methods for clinical NGS big data of complex hereditary diseases – volume II by : Yudong Cai
Download or read book Advanced interpretable machine learning methods for clinical NGS big data of complex hereditary diseases – volume II written by Yudong Cai and published by Frontiers Media SA. This book was released on 2023-02-13 with total page 194 pages. Available in PDF, EPUB and Kindle. Book excerpt:
Book Synopsis Advanced Interpretable Machine Learning Methods for Clinical NGS Big Data of Complex Hereditary Diseases by : Yudong Cai
Download or read book Advanced Interpretable Machine Learning Methods for Clinical NGS Big Data of Complex Hereditary Diseases written by Yudong Cai and published by . This book was released on 2020 with total page 234 pages. Available in PDF, EPUB and Kindle. Book excerpt: This eBook is a collection of articles from a Frontiers Research Topic. Frontiers Research Topics are very popular trademarks of the Frontiers Journals Series: they are collections of at least ten articles, all centered on a particular subject. With their unique mix of varied contributions from Original Research to Review Articles, Frontiers Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author by contacting the Frontiers Editorial Office: frontiersin.org/about/contact.
Book Synopsis Big Data in Omics and Imaging by : Momiao Xiong
Download or read book Big Data in Omics and Imaging written by Momiao Xiong and published by CRC Press. This book was released on 2017-12-01 with total page 668 pages. Available in PDF, EPUB and Kindle. Book excerpt: Big Data in Omics and Imaging: Association Analysis addresses the recent development of association analysis and machine learning for both population and family genomic data in sequencing era. It is unique in that it presents both hypothesis testing and a data mining approach to holistically dissecting the genetic structure of complex traits and to designing efficient strategies for precision medicine. The general frameworks for association analysis and machine learning, developed in the text, can be applied to genomic, epigenomic and imaging data. FEATURES Bridges the gap between the traditional statistical methods and computational tools for small genetic and epigenetic data analysis and the modern advanced statistical methods for big data Provides tools for high dimensional data reduction Discusses searching algorithms for model and variable selection including randomization algorithms, Proximal methods and matrix subset selection Provides real-world examples and case studies Will have an accompanying website with R code The book is designed for graduate students and researchers in genomics, bioinformatics, and data science. It represents the paradigm shift of genetic studies of complex diseases– from shallow to deep genomic analysis, from low-dimensional to high dimensional, multivariate to functional data analysis with next-generation sequencing (NGS) data, and from homogeneous populations to heterogeneous population and pedigree data analysis. Topics covered are: advanced matrix theory, convex optimization algorithms, generalized low rank models, functional data analysis techniques, deep learning principle and machine learning methods for modern association, interaction, pathway and network analysis of rare and common variants, biomarker identification, disease risk and drug response prediction.
Book Synopsis Clinical Applications for Next-Generation Sequencing by : Urszula Demkow
Download or read book Clinical Applications for Next-Generation Sequencing written by Urszula Demkow and published by Academic Press. This book was released on 2015-09-10 with total page 336 pages. Available in PDF, EPUB and Kindle. Book excerpt: Clinical Applications for Next Generation Sequencing provides readers with an outstanding postgraduate resource to learn about the translational use of NGS in clinical environments. Rooted in both medical genetics and clinical medicine, the book fills the gap between state-of-the-art technology and evidence-based practice, providing an educational opportunity for users to advance patient care by transferring NGS to the needs of real-world patients. The book builds an interface between genetic laboratory staff and clinical health workers to not only improve communication, but also strengthen cooperation. Users will find valuable tactics they can use to build a systematic framework for understanding the role of NGS testing in both common and rare diseases and conditions, from prenatal care, like chromosomal abnormalities, up to advanced age problems like dementia. Fills the gap between state-of-the-art technology and evidence-based practice Provides an educational opportunity which advances patient care through the transfer of NGS to real-world patient assessment Promotes a practical tool that clinicians can apply directly to patient care Includes a systematic framework for understanding the role of NGS testing in many common and rare diseases Presents evidence regarding the important role of NGS in current diagnostic strategies
Book Synopsis Machine Learning Advanced Dynamic Omics Data Analysis for Precision Medicine by : Tao Zeng
Download or read book Machine Learning Advanced Dynamic Omics Data Analysis for Precision Medicine written by Tao Zeng and published by . This book was released on 2020 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: Precision medicine is being developed as a preventative, diagnostic and treatment tool to combat complex human diseases in a personalized manner. By utilizing high-throughput technologies, dynamic 'omics data including genetics, epi-genetics and even meta-genomics has produced temporal-spatial big biological datasets which can be associated with individual genotypes underlying pathogen progressive phenotypes. It is therefore necessary to investigate how to integrate these multi-scale 'omics datasets to distinguish the novel individual-specific disease causes from conventional cohort-common disease causes. Currently, machine learning plays an important role in biological and biomedical research, especially in the analysis of big 'omics data. However, in contrast to traditional big social data, 'omics datasets are currently always "small-sample-high-dimension", which causes overwhelming application problems and also introduces new challenges: (1) Big 'omics datasets can be extremely unbalanced, due to the difficulty of obtaining enough positive samples of such rare mutations or rare diseases; (2) A large number of machine learning models are "black box," which is enough to apply in social applications. However, in biological or biomedical fields, knowledge of the molecular mechanisms underlying any disease or biological study is necessary to deepen our understanding; (3) The genotype-phenotype association is a "white clue" captured in conventional big data studies. But identification of "causality" rather than association would be more helpful for physicians or biologists, as this can be used to determine an experimental target as the subject of future research. Therefore, to simultaneously improve the phenotype discrimination and genotype interpretability for complex diseases, it is necessary: To design and implement new machine learning technologies to integrate prior-knowledge with new 'omics datasets to provide transferable learning methods by combining multiple sources of data; To develop new network-based theories and methods to balance the trade-off between accuracy and interpretability of machine learning in biomedical and biological domains; To enhance the causality inference on "small-sample high dimension" data to capture the personalized causal relationship.
Book Synopsis Handbook of Machine Learning Applications for Genomics by : Sanjiban Sekhar Roy
Download or read book Handbook of Machine Learning Applications for Genomics written by Sanjiban Sekhar Roy and published by Springer Nature. This book was released on 2022-06-23 with total page 222 pages. Available in PDF, EPUB and Kindle. Book excerpt: Currently, machine learning is playing a pivotal role in the progress of genomics. The applications of machine learning are helping all to understand the emerging trends and the future scope of genomics. This book provides comprehensive coverage of machine learning applications such as DNN, CNN, and RNN, for predicting the sequence of DNA and RNA binding proteins, expression of the gene, and splicing control. In addition, the book addresses the effect of multiomics data analysis of cancers using tensor decomposition, machine learning techniques for protein engineering, CNN applications on genomics, challenges of long noncoding RNAs in human disease diagnosis, and how machine learning can be used as a tool to shape the future of medicine. More importantly, it gives a comparative analysis and validates the outcomes of machine learning methods on genomic data to the functional laboratory tests or by formal clinical assessment. The topics of this book will cater interest to academicians, practitioners working in the field of functional genomics, and machine learning. Also, this book shall guide comprehensively the graduate, postgraduates, and Ph.D. scholars working in these fields.
Book Synopsis Big Data Analytics in Genomics by : Ka-Chun Wong
Download or read book Big Data Analytics in Genomics written by Ka-Chun Wong and published by Springer. This book was released on 2016-10-24 with total page 426 pages. Available in PDF, EPUB and Kindle. Book excerpt: This contributed volume explores the emerging intersection between big data analytics and genomics. Recent sequencing technologies have enabled high-throughput sequencing data generation for genomics resulting in several international projects which have led to massive genomic data accumulation at an unprecedented pace. To reveal novel genomic insights from this data within a reasonable time frame, traditional data analysis methods may not be sufficient or scalable, forcing the need for big data analytics to be developed for genomics. The computational methods addressed in the book are intended to tackle crucial biological questions using big data, and are appropriate for either newcomers or veterans in the field.This volume offers thirteen peer-reviewed contributions, written by international leading experts from different regions, representing Argentina, Brazil, China, France, Germany, Hong Kong, India, Japan, Spain, and the USA. In particular, the book surveys three main areas: statistical analytics, computational analytics, and cancer genome analytics. Sample topics covered include: statistical methods for integrative analysis of genomic data, computation methods for protein function prediction, and perspectives on machine learning techniques in big data mining of cancer. Self-contained and suitable for graduate students, this book is also designed for bioinformaticians, computational biologists, and researchers in communities ranging from genomics, big data, molecular genetics, data mining, biostatistics, biomedical science, cancer research, medical research, and biology to machine learning and computer science. Readers will find this volume to be an essential read for appreciating the role of big data in genomics, making this an invaluable resource for stimulating further research on the topic.
Book Synopsis Big Data in Omics and Imaging by : Momiao Xiong
Download or read book Big Data in Omics and Imaging written by Momiao Xiong and published by CRC Press. This book was released on 2018-06-14 with total page 400 pages. Available in PDF, EPUB and Kindle. Book excerpt: Big Data in Omics and Imaging: Integrated Analysis and Causal Inference addresses the recent development of integrated genomic, epigenomic and imaging data analysis and causal inference in big data era. Despite significant progress in dissecting the genetic architecture of complex diseases by genome-wide association studies (GWAS), genome-wide expression studies (GWES), and epigenome-wide association studies (EWAS), the overall contribution of the new identified genetic variants is small and a large fraction of genetic variants is still hidden. Understanding the etiology and causal chain of mechanism underlying complex diseases remains elusive. It is time to bring big data, machine learning and causal revolution to developing a new generation of genetic analysis for shifting the current paradigm of genetic analysis from shallow association analysis to deep causal inference and from genetic analysis alone to integrated omics and imaging data analysis for unraveling the mechanism of complex diseases. FEATURES Provides a natural extension and companion volume to Big Data in Omic and Imaging: Association Analysis, but can be read independently. Introduce causal inference theory to genomic, epigenomic and imaging data analysis Develop novel statistics for genome-wide causation studies and epigenome-wide causation studies. Bridge the gap between the traditional association analysis and modern causation analysis Use combinatorial optimization methods and various causal models as a general framework for inferring multilevel omic and image causal networks Present statistical methods and computational algorithms for searching causal paths from genetic variant to disease Develop causal machine learning methods integrating causal inference and machine learning Develop statistics for testing significant difference in directed edge, path, and graphs, and for assessing causal relationships between two networks The book is designed for graduate students and researchers in genomics, epigenomics, medical image, bioinformatics, and data science. Topics covered are: mathematical formulation of causal inference, information geometry for causal inference, topology group and Haar measure, additive noise models, distance correlation, multivariate causal inference and causal networks, dynamic causal networks, multivariate and functional structural equation models, mixed structural equation models, causal inference with confounders, integer programming, deep learning and differential equations for wearable computing, genetic analysis of function-valued traits, RNA-seq data analysis, causal networks for genetic methylation analysis, gene expression and methylation deconvolution, cell –specific causal networks, deep learning for image segmentation and image analysis, imaging and genomic data analysis, integrated multilevel causal genomic, epigenomic and imaging data analysis.
Book Synopsis Patterns in Big Data Bioinformatics by : Mateusz Garbulowski
Download or read book Patterns in Big Data Bioinformatics written by Mateusz Garbulowski and published by . This book was released on 2021 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt:
Book Synopsis Multivariate Statistical Machine Learning Methods for Genomic Prediction by : Osval Antonio Montesinos López
Download or read book Multivariate Statistical Machine Learning Methods for Genomic Prediction written by Osval Antonio Montesinos López and published by Springer Nature. This book was released on 2022-02-14 with total page 707 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book is open access under a CC BY 4.0 license This open access book brings together the latest genome base prediction models currently being used by statisticians, breeders and data scientists. It provides an accessible way to understand the theory behind each statistical learning tool, the required pre-processing, the basics of model building, how to train statistical learning methods, the basic R scripts needed to implement each statistical learning tool, and the output of each tool. To do so, for each tool the book provides background theory, some elements of the R statistical software for its implementation, the conceptual underpinnings, and at least two illustrative examples with data from real-world genomic selection experiments. Lastly, worked-out examples help readers check their own comprehension.The book will greatly appeal to readers in plant (and animal) breeding, geneticists and statisticians, as it provides in a very accessible way the necessary theory, the appropriate R code, and illustrative examples for a complete understanding of each statistical learning tool. In addition, it weighs the advantages and disadvantages of each tool.
Book Synopsis Biologically Interpretable Machine Learning Methods to Understand Gene Regulation for Disease Phenotypes by : Ting Jin
Download or read book Biologically Interpretable Machine Learning Methods to Understand Gene Regulation for Disease Phenotypes written by Ting Jin and published by . This book was released on 2023 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: Gene expression and regulation is a key molecular mechanism driving the development of human diseases, particularly at the cell type level, but it remains elusive. For example in many brain diseases, such as Alzheimer's disease (AD), understanding how cell-type gene expression and regulation change across multiple stages of AD progression is still challenging. Moreover, interindividual variability of gene expression and regulation is a known characteristic of the human brain and brain diseases. However, it is still unclear how interindividual variability affects personalized gene regulation in brain diseases including AD, thereby contributing to their heterogeneity. Recent technological advances have enabled the detection of gene regulation activities through multi-omics (i.e., genomics, transcriptomics, epigenomics, proteomics). In particular, emerging single-cell sequencing technologies (e.g., scRNA-seq, scATAC-seq) allow us to study functional genomics and gene regulation at the cell-type level. Moreover, these multi-omics data of populations (e.g., human individuals) provide a unique opportunity to study the underlying regulatory mechanisms occurring in brain disease progression and clinical phenotypes. For instance, PsychAD is a large project generating single-cell multi-omics data including many neuronal and glial cell types, aiming to understand the molecular mechanisms of neuropsychiatric symptoms of multiple brain diseases (e.g., AD, SCZ, ASD, Bipolar) from over 1,000 individuals. However, analyzing and integrating large-scale multi-omics data at the population level, as well as understanding the mechanisms of gene regulation, also remains a challenge. Machine learning is a powerful and emerging tool to decode the unique complexities and heterogeneity of human diseases. For instance, Beebe-Wang, Nicosia, et al. developed MD-AD, a multi-task neural network model to predict various disease phenotypes in AD patients using RNA-seq. Additionally, with advancements in graph neural networks, which possess enhanced capabilities to represent sophisticated gene network structures like gene regulation networks that control gene expression. Efforts have also been made to capture the gene regulation heterogeneity of brain diseases. For instance, Kim SY has applied graph convolutional networks to offer personalized diagnostic insights through population graphs that correspond with disease progression. However, many existing machine learning methods are often limited to constructing accurate models for disease phenotype prediction and frequently lack biological interpretability or personalized insights, especially in gene regulation. Therefore, to address these challenges, my Ph.D. works have developed three machine-learning methods designed to decode the gene regulation mechanisms of human diseases. First, in this dissertation, I will present scGRNom, a computational pipeline that integrates multi-omic data to construct cell-type gene regulatory networks (GRNs) linking non-coding regulatory elements. Next, I will introduce i-BrainMap an interpretable knowledge-guided graph neural network model to prioritize personalized cell type disease genes, regulatory linkages, and modules. Thirdly, I introduce ECMaker, a semi-restricted Boltzmann machine (semi-RBM) method for identifying gene networks to predict diseases and clinical phenotypes. Overall, all our interpretable machine learning models improve phenotype prediction, prioritize key genes and networks associated with disease phenotypes, and are further aimed at enhancing our understanding of gene regulatory mechanisms driving disease progression and clinical phenotypes.
Book Synopsis Interpretable Machine Learning Methods for Regulatory and Disease Genomics by : Peyton Greis Greenside
Download or read book Interpretable Machine Learning Methods for Regulatory and Disease Genomics written by Peyton Greis Greenside and published by . This book was released on 2018 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt: It is an incredible feat of nature that the same genome contains the code to every cell in each living organism. From this same genome, each unique cell type gains a different program of gene expression that enables the development and function of an organism throughout its lifespan. The non-coding genome - the ~98 of the genome that does not code directly for proteins - serves an important role in generating the diverse programs of gene expression turned on in each unique cell state. A complex network of proteins bind specific regulatory elements in the non-coding genome to regulate the expression of nearby genes. While basic principles of gene regulation are understood, the regulatory code of which factors bind together at which genomic elements to turn on which genes remains to be revealed. Further, we do not understand how disruptions in gene regulation, such as from mutations that fall in non-coding regions, ultimately lead to disease or other changes in cell state. In this work we present several methods developed and applied to learn the regulatory code or the rules that govern non-coding regions of the genome and how they regulate nearby genes. We first formulate the problem as one of learning pairs of sequence motifs and expressed regulator proteins that jointly predict the state of the cell, such as the cell type specific gene expression or chromatin accessibility. Using pre-engineered sequence features and known expression, we use a paired-feature boosting approach to build an interpretable model of how the non-coding genome contributes to cell state. We also demonstrate a novel improvement to this method that takes into account similarities between closely related cell types by using a hierarchy imposed on all of the predicted cell states. We apply this method to discover validated regulators of tadpole tail regeneration and to predict protein-ligand binding interactions. Recognizing the need for improved sequence features and stronger predictive performance, we then move to a deep learning modeling framework to predict epigenomic phenotypes such as chromatin accessibility from just underlying DNA sequence. We use deep learning models, specifically multi-task convolutional neural networks, to learn a featurization of sequences over several kilobases long and their mapping to a functional phenotype. We develop novel architectures that encode principles of genomics in models typically designed for computer vision, such as incorporating reverse complementation and the 3D structure of the genome. We also develop methods to interpret traditionally ``black box" neural networks by 1) assigning importance scores to each input sequence to the model, 2) summarizing non-redundant patterns learned by the model that are predictive in each cell type, and 3) discovering interactions learned by the model that provide indications as to how different non-coding sequence features depend on each other. We apply these methods in the system of hematopoiesis to interpret chromatin dynamics across differentiation of blood cell types, to understand immune stimulation, and to interpret immune disease-associated variants that fall in non-coding regions. We demonstrate strong performance of our boosting and deep learning models and demonstrate improved performance of these machine learning frameworks when taking into account existing knowledge about the biological system being modeled. We benchmark our interpretation methods using gold standard systems and existing experimental data where available. We confirm existing knowledge surrounding essential factors in hematopoiesis, and also generate novel hypotheses surrounding how factors interact to regulate differentiation. Ultimately our work provides a set of tools for researchers to probe and understand the non-coding genome and its role in controlling gene expression as well as a set of novel insights surrounding how hematopoiesis is controlled on many scales from global quantification of regulatory sequence to interpretation of individual variants.
Book Synopsis Developing Machine Learning and Statistical Methods for the Analysis of Genetics and Genomics by : Jiajin Li
Download or read book Developing Machine Learning and Statistical Methods for the Analysis of Genetics and Genomics written by Jiajin Li and published by . This book was released on 2021 with total page 154 pages. Available in PDF, EPUB and Kindle. Book excerpt: With the development of next-generation sequencing technologies, we can detect numerous genetic variants associated with many diseases or complex traits over the past decades. Genome-wide association studies (GWAS) have been one of the most effective methods to identify those variants. It discovers disease-associated variants by comparing the genetic information between controls and cases. This approach is simple and effective and has been used by many studies. Before performing GWAS, we need to detect the genetic variants of the sample population. A subset of these variants, however, may have poor sequencing quality due to limitations in NGS or variant callers. In genetic studies that analyze a large number of sequenced individuals, it is critical to detect and remove those variants with poor quality as they may cause spurious findings. Here, I will present ForestQC, an efficient statistical tool for performing quality control on variants identified from NGS data by combining a traditional filtering approach and a machine learning approach, which outperforms widely used methods by considerably improving the quality of variants to be included in the analysis. Once this association is identified, the next step is to understand the genetic mechanism of rare variants on how the variants influence diseases, especially whether or how they regulate gene expression as they may affect diseases through gene regulation. However, it is challenging to identify the regulatory effects of rare variants because it often requires large sample sizes and the existing statistical approaches are not optimized for it. To improve statistical power, I will introduce a new approach, LRT-q, based on a likelihood ratio test that combines effects of multiple rare variants in a nonlinear manner and has higher power than previous approaches. I apply LRT-q to the GTEx dataset and find many novel biological insights. Recent studies have shown that omics data can be used for automatic disease diagnosis with machine learning algorithms. I will introduce an accurate and automated machine learning pipeline for the diagnosis of atopic dermatitis (AD) based on transcriptome and microbiota data. I will demonstrate that this classifier can accurately differentiate subjects with AD and healthy individuals. It also identifies a set of genes and microorganisms that are predictive for AD. I will show that they are directly or indirectly associated with AD.
Book Synopsis Clinical DNA Variant Interpretation by : Conxi Lázaro
Download or read book Clinical DNA Variant Interpretation written by Conxi Lázaro and published by Elsevier. This book was released on 2021-03-02 with total page 436 pages. Available in PDF, EPUB and Kindle. Book excerpt: We live in a very exciting time in the field of human genetics; NGS technology is generating enormous amounts of data for classifying genetic variants. However, defining the role of these variants in human health and disease can be difficult, especially when a variant's mechanism of action or the phenotype associated with a genetic mutation are not well defined. Work in multidisciplinary teams and development of multifactorial algorithms, including artificial intelligence and machine learning approaches, are integral to streamlining variant classification. Clinical DNA Variant Interpretation: Theory and Practice, a new volume in the Translational and Applied Genomics series, brings more than thirty international experts together to compile variant interpretation best practices and approaches in a single volume, covering foundational aspects, modes of analysis, technology, disease and disorder specific case studies, and clinical integration. This book provides a deep theoretical background, as well as applied case studies and methodology, enabling researchers, clinicians, and healthcare providers to effectively classify DNA variants associated with disease and patient phenotypes. Practical chapters discuss genomic variant interpretation, terminology and nomenclature; international consensus guidelines; population allele frequency; functional evidence transcripts for RNA, proteins, and enzymes; somatic mutations and somatic profiling; CNV interpretation; quantitative modeling; machine learning approaches; genomic data sharing; genetic testing in clinical practice; and holistic case-level interpretation. Biomedical specialties of relevance include internal medicine, medical genetics, oncology, psychiatry, neurology, and immunology, and those driving implementation of precision medicine and personalized treatments.
Book Synopsis Statistical Analysis of Next Generation Sequencing Data by : Somnath Datta
Download or read book Statistical Analysis of Next Generation Sequencing Data written by Somnath Datta and published by Springer. This book was released on 2016-09-17 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: Next Generation Sequencing (NGS) is the latest high throughput technology to revolutionize genomic research. NGS generates massive genomic datasets that play a key role in the big data phenomenon that surrounds us today. To extract signals from high-dimensional NGS data and make valid statistical inferences and predictions, novel data analytic and statistical techniques are needed. This book contains 20 chapters written by prominent statisticians working with NGS data. The topics range from basic preprocessing and analysis with NGS data to more complex genomic applications such as copy number variation and isoform expression detection. Research statisticians who want to learn about this growing and exciting area will find this book useful. In addition, many chapters from this book could be included in graduate-level classes in statistical bioinformatics for training future biostatisticians who will be expected to deal with genomic data in basic biomedical research, genomic clinical trials and personalized medicine. About the editors: Somnath Datta is Professor and Vice Chair of Bioinformatics and Biostatistics at the University of Louisville. He is Fellow of the American Statistical Association, Fellow of the Institute of Mathematical Statistics and Elected Member of the International Statistical Institute. He has contributed to numerous research areas in Statistics, Biostatistics and Bioinformatics. Dan Nettleton is Professor and Laurence H. Baker Endowed Chair of Biological Statistics in the Department of Statistics at Iowa State University. He is Fellow of the American Statistical Association and has published research on a variety of topics in statistics, biology and bioinformatics.
Book Synopsis Interpretable Machine Learning for Scientific Discovery in Regulatory Genomics by : Avanti Shrikumar
Download or read book Interpretable Machine Learning for Scientific Discovery in Regulatory Genomics written by Avanti Shrikumar and published by . This book was released on 2020 with total page pages. Available in PDF, EPUB and Kindle. Book excerpt: All cells in our body have approximately the same DNA sequence, yet different cell-types have distinct behavior due to differential expression of genes. This cell-type specific control of gene expression is governed by regulatory proteins that bind to DNA. Over 90% of disease-associated mutations do not disrupt the DNA sequences of genes, but rather disrupt functions involved in the regulation of gene expression. Unfortunately, conventional computational models can fail to distinguish between mutations that are benign and mutations that are likely to affect regulatory activity. Machine learning poses a solution to this dilemma: by training complex models, including deep learning models, to predict regulatory activity from DNA sequence, we implicitly force the models to learn which sequence features are relevant for regulation. However, our difficulty in interpreting and trusting these models limits our ability to extract novel scientific insights from them. In this thesis, I will present techniques I have developed to address some of these limitations. I will begin by discussing DeepLIFT, a fast algorithm for calculating example-specific importance scores to explain the predictions of a deep learning model, as well as GkmExplain, an algorithm for efficiently computing importance scores for gapped k-mer support vector machines. I will then describe TF-MoDISco, an algorithm that leverages importance scores produced by an algorithm such as DeepLIFT or GkmExplain to discover recurring patterns learned by the model. Next, I discuss two projects on leveraging domain-specific knowledge to improve the performance and interpretability of deep learning models trained on regulatory genomic data. The first project, on reverse-complement parameter sharing, introduces architectures that can account for symmetries inherent in the double-stranded nature of regulatory DNA. The second project, on separable fully-connected layers, introduces a novel parameterization to exploit the fact that positional patterns in DNA binding sites are often shared across different regulatory proteins. Finally, I will discuss three projects centered on improving the reliability of predictions derived from these models. The first project deals with the situation where a deep learning model trained on regulatory genomic data is leveraged to identify pairs of proteins that have non-additive interaction effects; we demonstrate that looking at change in the model's prediction loss, rather than simply looking at the change in the predictions, is a far more robust indicator of whether the model's learned interaction effect is likely to be an artifact. The second project presents a state-of-the-art algorithm for improving the model predictions under a type of data distribution shift known as ``label shift'', where the class proportions in the held-out testing set differ from the class proportions that the model was trained on (this can occur, for example, if a model that is trained to predict diseases given symptoms is deployed in a situation where the prevalence of the disease is far higher than in the data distribution it was trained on). The third project explores the scenario where a model can abstain from making predictions on a subset of examples that it is uncertain of, in order to improve user trust in the predictions on remaining examples; in the project, we devise a novel and flexible strategy for choosing which examples to abstain on when the goal is to optimize metrics other than simple prediction accuracy, such as the area under the ROC curve or the sensitivity at a target specificity level (such metrics are commonly used in genomics and medicine). Taken together, I hope these methods help pave the way for successful application of advanced machine learning techniques to derive novel scientific insights from regulatory genomic data.
