RNA-Seq is revolutionizing the way transcript abundances are measured. A key challenge in transcript quantification from RNA-Seq data is the handling of reads that map to multiple genes or isoforms. This issue is particularly important for quantification with de novo transcriptome assemblies in the absence of sequenced genomes, as it is difficult to determine which transcripts are isoforms of the same gene. A second significant issue is the design of RNA-Seq experiments, in terms of the number of reads, read length, and whether reads come from one or both ends of cDNA fragments. We present RSEM, an user-friendly software package for quantifying gene and isoform abundances from single-end or paired-end RNA-Seq data. RSEM outputs abundance estimates, 95% credibility intervals, and visualization files and can also simulate RNA-Seq data. In contrast to other existing tools, the software does not require a reference genome. Thus, in combination with a de novo transcriptome assembler, RSEM enables accurate transcript quantification for species without sequenced genomes. On simulated and real data sets, RSEM has superior or comparable performance to quantification methods that rely on a reference genome. Taking advantage of RSEM's ability to effectively use ambiguously-mapping reads, we show that accurate gene-level abundance estimates are best obtained with large numbers of short single-end reads. On the other hand, estimates of the relative frequencies of isoforms within single genes may be improved through the use of paired-end reads, depending on the number of possible splice forms for each gene. RSEM is an accurate and user-friendly software tool for quantifying transcript abundances from RNA-Seq data. As it does not rely on the existence of a reference genome, it is particularly useful for quantification with de novo transcriptome assemblies. In addition, RSEM has enabled valuable guidance for cost-efficient design of quantification experiments with RNA-Seq, which is currently relatively expensive.

/pdf/rsem-accurate-transcript-quantification-from-rna-seq-data-14sfzcg8a9.pdf

RSEM: accurate transcript quantification from RNA-Seq data with or without a reference genome

THE DESIGN AND ANALYSIS OF EXPERIMENTS. By Oscar Kempthorne. New York, John Wiley and Sons, Inc., 1952. 631 pp. $8.50. This book by a teacher of statistics (as well as a consultant for \"experimenters\") is a comprehensive study of the philosophical background for the statistical design of experiment. It is necessary to have some facility with algebraic notation and manipulation to be able to use the volume intelligently. The problems are presented from the theoretical point of view, without such practical examples as would be helpful for those not acquainted with mathematics. The mathematical justification for the techniques is given. As a somewhat advanced treatment of the design and analysis of experiments, this volume will be interesting and helpful for many who approach statistics theoretically as well as practically. With emphasis on the \"why,\" and with description given broadly, the author relates the subject matter to the general theory of statistics and to the general problem of experimental inference. MARGARET J. ROBERTSON

The Design and Analysis of Experiments

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Recent advances in high-throughput cDNA sequencing (RNA-seq) can reveal new genes and splice variants and quantify expression genome-wide in a single assay. The volume and complexity of data from RNA-seq experiments necessitate scalable, fast and mathematically principled analysis software. TopHat and Cufflinks are free, open-source software tools for gene discovery and comprehensive expression analysis of high-throughput mRNA sequencing (RNA-seq) data. Together, they allow biologists to identify new genes and new splice variants of known ones, as well as compare gene and transcript expression under two or more conditions. This protocol describes in detail how to use TopHat and Cufflinks to perform such analyses. It also covers several accessory tools and utilities that aid in managing data, including CummeRbund, a tool for visualizing RNA-seq analysis results. Although the procedure assumes basic informatics skills, these tools assume little to no background with RNA-seq analysis and are meant for novices and experts alike. The protocol begins with raw sequencing reads and produces a transcriptome assembly, lists of differentially expressed and regulated genes and transcripts, and publication-quality visualizations of analysis results. The protocol's execution time depends on the volume of transcriptome sequencing data and available computing resources but takes less than 1 d of computer time for typical experiments and ∼1 h of hands-on time.

/pdf/differential-gene-and-transcript-expression-analysis-of-rna-3x9xt7iq01.pdf

Differential gene and transcript expression analysis of RNA-seq experiments with TopHat and Cufflinks

The modern science of networks has brought significant advances to our understanding of complex systems. One of the most relevant features of graphs representing real systems is community structure, or clustering, i. e. the organization of vertices in clusters, with many edges joining vertices of the same cluster and comparatively few edges joining vertices of different clusters. Such clusters, or communities, can be considered as fairly independent compartments of a graph, playing a similar role like, e. g., the tissues or the organs in the human body. Detecting communities is of great importance in sociology, biology and computer science, disciplines where systems are often represented as graphs. This problem is very hard and not yet satisfactorily solved, despite the huge effort of a large interdisciplinary community of scientists working on it over the past few years. We will attempt a thorough exposition of the topic, from the definition of the main elements of the problem, to the presentation of most methods developed, with a special focus on techniques designed by statistical physicists, from the discussion of crucial issues like the significance of clustering and how methods should be tested and compared against each other, to the description of applications to real networks.

/pdf/community-detection-in-graphs-34rogm3r6p.pdf

Community detection in graphs

In research and application, social networks are increasingly extracted from relationships inferred by name collocations in text-based documents. Despite the fact that names represent real entities, names are not unique identifiers and it is often unclear when two name observations correspond to the same underlying entity. One confounder stems from ambiguity, in which the same name correctly references multiple entities. Prior name disambiguation methods measured similarity between two names as a function of their respective documents. In this paper, we propose an alternative similarity metric based on the probability of walking from one ambiguous name to another in a random walk of the social network constructed from all documents. We experimentally validate our model on actor-actor relationships derived from the Internet Movie Database. Using a global similarity threshold, we demonstrate random walks achieve a significant increase in disambiguation capability in comparison to prior models.

/pdf/a-network-analysis-model-for-disambiguation-of-names-in-2lsf5ot9lo.pdf

A Network Analysis Model for Disambiguation of Names in Lists

@inbook{Boyd-Graber:Mimno:Newman-2014, Publisher = {CRC Press}, Address = {Boca Raton, Florida}, Title = {Care and Feeding of Topic Models: Problems, Diagnostics, and Improvements}, Url = {docs/2014_book_chapter_care_and_feeding.pdf}, Series = {CRC Handbooks of Modern Statistical Methods}, Booktitle = {Handbook of Mixed Membership Models and Their Applications}, Author = {Jordan Boyd-Graber and David Mimno and David Newman}, Year = {2014}, Editor = {Edoardo M. Airoldi and David Blei and Elena A. Erosheva and Stephen E. Fienberg}, }

/pdf/care-and-feeding-of-topic-models-problems-diagnostics-and-444ybsuhdu.pdf

Care and Feeding of Topic Models: Problems, Diagnostics, and Improvements

We examine the role of granular privacy controls on dynamic content-sharing activities and disclosure patterns of Facebook users based on the exogenous policy change in December 2009. Using a unique panel data set, we first conduct regression discontinuity analyses to verify a discontinuous jump in context generation activities and disclosure patterns around the time of the policy change. We next estimate unobserved effects models to assess the short-run and long-run effects of the change. Results show that Facebook users, on average, increase use of wall posts and decrease use of private messages after the introduction of granular privacy controls. Also, users’ disclosure patterns change to reflect the increased openness in content sharing. These effects are realized immediately and over time. More importantly, we show that user-specific factors play crucial roles in shaping users’ varying reactions to the policy change. While more privacy sensitive users (those who do not reveal their gender and/or thos...

Assessing the Impact of Granular Privacy Controls on Content Sharing and Disclosure on Facebook

We consider the statistical analysis of a collection of unipartite graphs, i.e., multiple matrices of relations among objects of a single type. Such data arise, for example, in biological settings, collections of author-recipient email, and social networks. In many applications, clustering the objects of study or situating them in a low dimensional space (e.g., a simplex) is only one of the goals of the analysis. Begin able to estimate relational structures among the clusters themselves is often times as important. For example, in biological applications we are interested in estimating how stable protein complexes (i.e., clusters of proteins) interact. To support such integrated data analyses, we develop the family of “stochastic block models of mixed membership”. Our models combine features of mixed-membership models (Erosheva & Fienberg, 2005) and block models for relational data (Holland et al., 1983) in a hierarchical Bayesian framework. We develop a novel “nested” variational inference scheme, which is necessary to successfully perform fast approximate posterior inference in our models of relational data. We present evidence to support our claims, using both synthetic data and biological case study.

Stochastic Block Models of Mixed Membership

Stochastic gradient descent procedures have gained popularity for parameter estimation from large data sets. However, their statistical properties are not well understood, in theory. And in practice, avoiding numerical instability requires careful tuning of key parameters. Here, we introduce implicit stochastic gradient descent procedures, which involve parameter updates that are implicitly defined. Intuitively, implicit updates shrink standard stochastic gradient descent updates. The amount of shrinkage depends on the observed Fisher information matrix, which does not need to be explicitly computed; thus, implicit procedures increase stability without increasing the computational burden. Our theoretical analysis provides the first full characterization of the asymptotic behavior of both standard and implicit stochastic gradient descent-based estimators, including finite-sample error bounds. Importantly, analytical expressions for the variances of these stochastic gradient-based estimators reveal their exact loss of efficiency. We also develop new algorithms to compute implicit stochastic gradient descent-based estimators for generalized linear models, Cox proportional hazards, M-estimators, in practice, and perform extensive experiments. Our results suggest that implicit stochastic gradient descent procedures are poised to become a workhorse for approximate inference from large data sets.

/pdf/asymptotic-and-finite-sample-properties-of-estimators-based-3jsgw8y629.pdf

Edoardo M. Airoldi

Papers

A Network Analysis Model for Disambiguation of Names in Lists

Care and Feeding of Topic Models: Problems, Diagnostics, and Improvements

Assessing the Impact of Granular Privacy Controls on Content Sharing and Disclosure on Facebook

Stochastic Block Models of Mixed Membership

Asymptotic and finite-sample properties of estimators based on stochastic gradients