PubMed Health⌕ Search

Biomedical subjects

Andrey Rzhetsky

Publications and source records attributed to Andrey Rzhetsky.

18 recordsLinked to original sources
PubMed2006

Self-correcting maps of molecular pathways.

Reliable and comprehensive maps of molecular pathways are indispensable for guiding complex biomedical experiments. Such maps are typically assembled from myriads of disparate research reports and are replete with inconsistencies due to variations in experimental conditions and/or errors. It is often an intractable task to manually verify internal consistency over a large collection of experimental statements. To automate large-scale reconciliation efforts, we propose a random-arcs-and-nodes model where both nodes (tissue-specific states of biological molecules) and arcs (interactions between them) are represented with random variables. We show how to obtain a non-contradictory model of a molecular network by computing the joint distribution for arc and node variables, and then apply our methodology to a realistic network, generating a set of experimentally testable hypotheses. This network, derived from an automated analysis of over 3,000 full-text research articles, includes genes that have been hypothetically linked to four neurological disorders: Alzheimer's disease, autism, bipolar disorder, and schizophrenia. We estimated that approximately 10% of the published molecular interactions are logically incompatible. Our approach can be directly applied to an array of diverse problems including those encountered in molecular biology, ecology, economics, politics, and sociology.

Bayes Theorem↗
PubMed2006

Imitating manual curation of text-mined facts in biomedicine.

Text-mining algorithms make mistakes in extracting facts from natural-language texts. In biomedical applications, which rely on use of text-mined data, it is critical to assess the quality (the probability that the message is correctly extracted) of individual facts--to resolve data conflicts and inconsistencies. Using a large set of almost 100,000 manually produced evaluations (most facts were independently reviewed more than once, producing independent evaluations), we implemented and tested a collection of algorithms that mimic human evaluation of facts provided by an automated information-extraction system. The performance of our best automated classifiers closely approached that of our human evaluators (ROC score close to 0.95). Our hypothesis is that, were we to use a larger number of human experts to evaluate any given sentence, we could implement an artificial-intelligence curator that would perform the classification job at least as accurately as an average individual human evaluator. We illustrated our analysis by visualizing the predicted accuracy of the text-mined relations involving the term cocaine.

Abstracting and Indexing↗
PubMed2006

New directions in biomedical text annotation: definitions, guidelines and corpus construction.

BACKGROUND: While biomedical text mining is emerging as an important research area, practical results have proven difficult to achieve. We believe that an important first step towards more accurate text-mining lies in the ability to identify and characterize text that satisfies various types of information needs. We report here the results of our inquiry into properties of scientific text that have sufficient generality to transcend the confines of a narrow subject area, while supporting practical mining of text for factual information. Our ultimate goal is to annotate a significant corpus of biomedical text and train machine learning methods to automatically categorize such text along certain dimensions that we have defined. RESULTS: We have identified five qualitative dimensions that we believe characterize a broad range of scientific sentences, and are therefore useful for supporting a general approach to text-mining: focus, polarity, certainty, evidence, and directionality. We define these dimensions and describe the guidelines we have developed for annotating text with regard to them. To examine the effectiveness of the guidelines, twelve annotators independently annotated the same set of 101 sentences that were randomly selected from current biomedical periodicals. Analysis of these annotations shows 70-80% inter-annotator agreement, suggesting that our guidelines indeed present a well-defined, executable and reproducible task. CONCLUSION: We present our guidelines defining a text annotation task, along with annotation results from multiple independently produced annotations, demonstrating the feasibility of the task. The annotation of a very large corpus of documents along these guidelines is currently ongoing. These annotations form the basis for the categorization of text along multiple dimensions, to support viable text mining for experimental results, methodology statements, and other forms of information. We are currently developing machine learning methods, to be trained and tested on the annotated corpus, that would allow for the automatic categorization of biomedical text along the general dimensions that we have presented. The guidelines in full detail, along with annotated examples, are publicly available.

Computational Biology↗
PubMed2006

Microparadigms: chains of collective reasoning in publications about molecular interactions.

We analyzed a very large set of molecular interactions that had been derived automatically from biological texts. We found that published statements, regardless of their verity, tend to interfere with interpretation of the subsequent experiments and, therefore, can act as scientific "microparadigms," similar to dominant scientific theories [Kuhn, T. S. (1996) The Structure of Scientific Revolutions (Univ. Chicago Press, Chicago)]. Using statistical tools, we measured the strength of the influence of a single published statement on subsequent interpretations. We call these measured values the momentums of the published statements and treat separately the majority and minority of conflicting statements about the same molecular event. Our results indicate that, when building biological models based on published experimental data, we may have to treat the data as highly dependent-ordered sequences of statements (i.e., chains of collective reasoning) rather than unordered and independent experimental observations. Furthermore, our computations indicate that our data set can be interpreted in two very different ways (two "alternative universes"): one is an "optimists' universe" with a very low incidence of false results (<5%), and another is a "pessimists' universe" with an extraordinarily high rate of false results (>90%). Our computations deem highly unlikely any milder intermediate explanation between these two extremes.

Computer Simulation↗
PubMed2004

Listening to viral tongues: comparing viral trees using a stochastic context-free grammar.

We suggest a probabilistic method for comparing the topological features of large phylogenetic trees. Using this method, we demonstrate that a stochastic grammar can generate three influenza-subtype (A H1, A H3, and B) hemagglutinin trees used in an earlier study, with statistically similar parameters. The proposed methodology is applicable to a broad class of problems that require comparison of the topological properties of various dendrograms.

Orthomyxoviridae↗
PubMed2004

Molecular triangulation: bridging linkage and molecular-network information for identifying candidate genes in Alzheimer's disease.

A major challenge in human genetics is identifying the molecular basis of common heritable disorders. In contrast to rare single-gene diseases, multifactorial disorders are thought to arise from the combined effect of multiple gene variants, such that any single variant may have only a modest effect on disease susceptibility. We present a method to identify genes that may harbor a significant proportion of the genetic variation that predisposes individuals to a given multifactorial disorder. First, we perform an automated literature analysis that predicts physical interactions (edges) among candidate disease genes (seed nodes, selected on the basis of prior information) and other molecular entities. We derive models of molecular networks from this analysis and map the seed nodes to them. We then compute the graph-theoretic distance (the minimum number of edges that must be traversed) between the seed nodes and all other nodes in the network. We assume that nodes that are found in close proximity to multiple seed nodes are the best disease-related candidate genes. To evaluate this approach, we selected four seed genes, each with a proven role in Alzheimer's disease (AD). The method performed well in predicting additional network nodes that match AD gene candidates identified manually by an expert. We also show that the method prioritizes among the seed nodes themselves, rejecting false-positive seeds that are derived from (noisy) whole-genome genetic-linkage scans. We propose that this strategy will provide a valuable means to bridge genetic and genomic knowledge in the search for genetic determinants of multifactorial disorders.

Algorithms↗
PubMed2004

The genomic sequence of the accidental pathogen Legionella pneumophila.

We present the genomic sequence of Legionella pneumophila, the bacterial agent of Legionnaires' disease, a potentially fatal pneumonia acquired from aerosolized contaminated fresh water. The genome includes a 45-kilobase pair element that can exist in chromosomal and episomal forms, selective expansions of important gene families, genes for unexpected metabolic pathways, and previously unknown candidate virulence determinants. We highlight the genes that may account for Legionella's ability to survive in protozoa, mammalian macrophages, and inhospitable environmental niches and that may define new therapeutic targets.

DNA, Bacterial↗
PubMed2004

Probabilistic inference of molecular networks from noisy data sources.

Information on molecular networks, such as networks of interacting proteins, comes from diverse sources that contain remarkable differences in distribution and quantity of errors. Here, we introduce a probabilistic model useful for predicting protein interactions from heterogeneous data sources. The model describes stochastic generation of protein-protein interaction networks with real-world properties, as well as generation of two heterogeneous sources of protein-interaction information: research results automatically extracted from the literature and yeast two-hybrid experiments. Based on the domain composition of proteins, we use the model to predict protein interactions for pairs of proteins for which no experimental data are available. We further explore the prediction limits, given experimental data that cover only part of the underlying protein networks. This approach can be extended naturally to include other types of biological data sources.

Algorithms↗
PubMed2004

GeneWays: a system for extracting, analyzing, visualizing, and integrating molecular pathway data.

The immense growth in the volume of research literature and experimental data in the field of molecular biology calls for efficient automatic methods to capture and store information. In recent years, several groups have worked on specific problems in this area, such as automated selection of articles pertinent to molecular biology, or automated extraction of information using natural-language processing, information visualization, and generation of specialized knowledge bases for molecular biology. GeneWays is an integrated system that combines several such subtasks. It analyzes interactions between molecular substances, drawing on multiple sources of information to infer a consensus view of molecular networks. GeneWays is designed as an open platform, allowing researchers to query, review, and critique stored information.

Artificial Intelligence↗
PubMed2003

Learning to predict protein-protein interactions from protein sequences.

In order to understand the molecular machinery of the cell, we need to know about the multitude of protein-protein interactions that allow the cell to function. High-throughput technologies provide some data about these interactions, but so far that data is fairly noisy. Therefore, computational techniques for predicting protein-protein interactions could be of significant value. One approach to predicting interactions in silico is to produce from first principles a detailed model of a candidate interaction. We take an alternative approach, employing a relatively simple model that learns dynamically from a large collection of data. In this work, we describe an attraction-repulsion model, in which the interaction between a pair of proteins is represented as the sum of attractive and repulsive forces associated with small, domain- or motif-sized features along the length of each protein. The model is discriminative, learning simultaneously from known interactions and from pairs of proteins that are known (or suspected) not to interact. The model is efficient to compute and scales well to very large collections of data. In a cross-validated comparison using known yeast interactions, the attraction-repulsion method performs better than several competing techniques.

Algorithms↗
PubMed2003

Identification of the Anopheles gambiae ATP-binding cassette transporter superfamily genes.

The Anopheles gambiae genome sequence has been analyzed to find ATP-binding cassette protein genes based on deduced protein similarity to known family members. A nonredundant collection of 44 putative genes was identified including five genes not detected by the original Anopheles genome project machine annotation. These genes encode at least one member of all the human and Drosophila melanogaster ATP-binding protein subgroups. Like D. melanogaster, A. gambiae has subgroup ABCH genes encoding proteins different from the ABC proteins found in other complex organisms. The largest Anopheles subgroup is the ABCC genes which includes one member that can potentially encode ten different isoforms of the protein by differential splicing. As with Drosophila, the second largest Anopheles group is the ABCG subgroup with 12 genes compared to 15 genes in D. melanogaster, but only 5 genes in the human genome. In contrast, fewer ABCA and ABCB genes were identified in the mosquito genome than in the human or Drosophila genomes. Gene duplication is very evident in the Anopheles ABC genes with two groups of four genes, one group with three genes and three groups with two head to tail duplicated genes. These characteristics argue that the A. gambiae is actively using gene duplication as a mechanism to drive genetic variation in this important gene group.

ATP-Binding Cassette Transporters↗
PubMed2002

Immunity-related genes and gene families in Anopheles gambiae.

We have identified 242 Anopheles gambiae genes from 18 gene families implicated in innate immunity and have detected marked diversification relative to Drosophila melanogaster. Immune-related gene families involved in recognition, signal modulation, and effector systems show a marked deficit of orthologs and excessive gene expansions, possibly reflecting selection pressures from different pathogens encountered in these insects' very different life-styles. In contrast, the multifunctional Toll signal transduction pathway is substantially conserved, presumably because of counterselection for developmental stability. Representative expression profiles confirm that sequence diversification is accompanied by specific responses to different immune challenges. Alternative RNA splicing may also contribute to expansion of the immune repertoire.

Alternative Splicing↗
PubMed2002

Two biomedical sublanguages: a description based on the theories of Zellig Harris.

Natural language processing (NLP) systems have been developed to provide access to the tremendous body of data and knowledge that is available in the biomedical domain in the form of natural language text. These NLP systems are valuable because they can encode and amass the information in the text so that it can be used by other automated processes to improve patient care and our understanding of disease processes and treatments. Zellig Harris proposed a theory of sublanguage that laid the foundation for natural language processing in specialized domains. He hypothesized that the informational content and structure form a specialized language that can be delineated in the form of a sublanguage grammar. The grammar can then be used by a language processor to capture and encode the salient information and relations in text. In this paper, we briefly summarize his language and sublanguage theories. In addition, we summarize our prior research, which is associated with the sublanguage grammars we developed for two different biomedical domains. These grammars illustrate how Harris' theories provide a basis for the development of language processing systems in the biomedical domain. The two domains and their associated sublanguages discussed are: the clinical domain, where the text consists of patient reports, and the biomolecular domain, where the text consists of complete journal articles.

Abstracting and Indexing↗
PubMed2002

Of truth and pathways: chasing bits of information through myriads of articles.

Knowledge on interactions between molecules in living cells is indispensable for theoretical analysis and practical applications in modern genomics and molecular biology. Building such networks relies on the assumption that the correct molecular interactions are known or can be identified by reading a few research articles. However, this assumption does not necessarily hold, as truth is rather an emerging property based on many potentially conflicting facts. This paper explores the processes of knowledge generation and publishing in the molecular biology literature using modelling and analysis of real molecular interaction data. The data analysed in this article were automatically extracted from 50000 research articles in molecular biology using a computer system called GeneWays containing a natural language processing module. The paper indicates that truthfulness of statements is associated in the minds of scientists with the relative importance (connectedness) of substances under study, revealing a potential selection bias in the reporting of research results. Aiming at understanding the statistical properties of the life cycle of biological facts reported in research articles, we formulate a stochastic model describing generation and propagation of knowledge about molecular interactions through scientific publications. We hope that in the future such a model can be useful for automatically producing consensus views of molecular interaction data.

Algorithms↗
PubMed2002

Towards the prediction of complete protein--protein interaction networks.

We present a statistical method for the prediction of protein--protein interactions within an organism. This approach is based on the treatment of proteins as collections of conserved domains, where each domain is responsible for a specific interaction with another domain. By characterizing the frequency with which specific domain--domain interactions occur within known interactions, our model can assign a probability to an arbitrary interaction between any two proteins with defined domains. Domain interaction data is complemented with information on the topology of a network and is incorporated into the model by assigning greater probabilities to networks displaying more biologically realistic topologies. We use Markov chain Monte Carlo techniques for the prediction of posterior probabilities of interaction between a set of proteins; allowing its application to large data sets. In this work we attempt to predict interactions in a set of 40 human proteins, known to form a connected network, and discuss methods for future improvement.

Markov Chains↗
PubMed2002

Automatic extraction of gene and protein synonyms from MEDLINE and journal articles.

Genes and proteins are often associated with multiple names, and more names are added as new functional or structural information is discovered. Because authors often alternate between these synonyms, information retrieval and extraction benefits from identifying these synonymous names. We have developed a method to extract automatically synonymous gene and protein names from MEDLINE and journal articles. We first identified patterns authors use to list synonymous gene and protein names. We developed SGPE (for synonym extraction of gene and protein names), a software program that recognizes the patterns and extracts from MEDLINE abstracts and full-text journal articles candidate synonymous terms. SGPE then applies a sequence of filters that automatically screen out those terms that are not gene and protein names. We evaluated our method to have an overall precision of 71% on both MEDLINE and journal articles, and 90% precision on the more suitable full-text articles alone

Electronic Data Processing↗
PubMedDate not supplied

Automatically identifying gene/protein terms in MEDLINE abstracts.

MOTIVATION: Natural language processing (NLP) techniques are used to extract information automatically from computer-readable literature. In biology, the identification of terms corresponding to biological substances (e.g., genes and proteins) is a necessary step that precedes the application of other NLP systems that extract biological information (e.g., protein-protein interactions, gene regulation events, and biochemical pathways). We have developed GPmarkup (for "gene/protein-full name mark up"), a software system that automatically identifies gene/protein terms (i.e., symbols or full names) in MEDLINE abstracts. As a part of marking up process, we also generated automatically a knowledge source of paired gene/protein symbols and full names (e.g., LARD for lymphocyte associated receptor of death) from MEDLINE. We found that many of the pairs in our knowledge source do not appear in the current GenBank database. Therefore our methods may also be used for automatic lexicon generation. RESULTS: GPmarkup has 73% recall and 93% precision in identifying and marking up gene/protein terms in MEDLINE abstracts. AVAILABILITY: A random sample of gene/protein symbols and full names and a sample set of marked up abstracts can be viewed at http://www.cpmc.columbia.edu/homepages/yuh9001/GPmarkup/. Contact. hy52@columbia.edu. Voice: 212-939-7028; fax: 212-666-0140.

Abstracting and Indexing↗