A knowledge model for analysis and simulation of regulatory

  networks

Rzhetsky, Andrey; Koike, Takafumi; Kalachikov, Sergey; Gomez, Shawn M.; Krauthammer, Michael; Kaplan, Sabina H.; Kra, Pauline; Russo, James J.; Friedman, Carol

doi:10.1093/bioinformatics/16.12.1120

Cited by 64 publications

(30 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, AVAD automatically classified co-localize and synergize as interaction verbs, both of which do not appear in the detailed knowledge model for interaction verbs constructed for the GeneWays system [16]. Our analysis showed that AVAD proposes a large number of verbs that humans did not include in the knowledge base and that most of these verbs should in fact be included in the knowledge base.…”

Section: Resultsmentioning

confidence: 95%

“…In addition to the validation, database management and visualization components, its text analysis component includes algorithms for the detection and disambiguation of genes and proteins in text and for the detection of relationships that match patterns known to the system. Currently, the patterns that represent the system's understanding of biological relationships are encoded as part of GeneWays detailed knowledge model, which was built by hand by consulting experts in the domain of pathway analysis [16]. These patterns are then represented as rules in a semantic grammar and a parser adapted to the biological domain [17], extracts new instances of gene and protein relationships as new texts arrive.…”

Section: Comparison With a Manually Built List Of Activation Verbsmentioning

confidence: 99%

See 1 more Smart Citation

Learning anchor verbs for biological interaction patterns from published text articles

Hatzivassiloglou

Weng

2002

International Journal of Medical Informatics

View full text Add to dashboard Cite

Much of knowledge modeling in the molecular biology domain involves interactions between proteins, genes, various forms of RNA, small molecules, etc. Interactions between these substances are typically extracted and codified manually, increasing the cost and time for modeling and substantially limiting the coverage of the resulting knowledge base. In this paper, we describe an automatic system that learns from text interaction verbs; these verbs can then form the core of automatically retrieved patterns which model classes of biological interactions. We investigate text features relating verbs with genes and proteins, and apply statistical tests and a logistic regression statistical model to determine whether a given verb belongs to the class of interaction verbs. Our system, AVAD, achieves over 87% precision and 82% recall when tested on an 11 million word corpus of journal articles. In addition, we compare the automatically obtained results with a manually constructed database of interaction verbs and show that the automatic approach can significantly enrich the manual list by detecting rarer interaction verbs that were omitted from the database. #

show abstract

Section: Resultsmentioning

confidence: 95%

Section: Comparison With a Manually Built List Of Activation Verbsmentioning

confidence: 99%

Learning anchor verbs for biological interaction patterns from published text articles

Hatzivassiloglou

Weng

2002

International Journal of Medical Informatics

View full text Add to dashboard Cite

show abstract

“…processing (NLP) techniques can help to extract useful semantics from scientific papers [6], [7], [8], even the best NLP methods still do not perform well in terms of precision and recall of scientific papers [9], [10].…”

Section: Using Semantics For More Accurate Searchingmentioning

confidence: 99%

EKOSS: A Knowledge-User Centered Approach to Knowledge Sharing, Discovery, and Integration on the Semantic Web

Kraines

Guo

Kemper

et al. 2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The scientific enterprise depends on the effective transfer of knowledge from creator to user. Recently the rate of scientific knowledge production is overwhelming the ability for researchers to process it. Semantic web technologies may help to handle this vast amount of scientific knowledge. However, automatic computerized techniques that extract semantics from natural language text for use in matching with the requests of knowledge seekers achieve only mediocre results. Clearly, semantic descriptions of expert knowledge that are constructed by the knowledge creators themselves will be more accurate. We report an approach and software implementation of a knowledge sharing platform based on semantic web technologies, called EKOSS for expert knowledge ontology-based semantic search, that helps knowledge creators construct semantic descriptions of their knowledge. The EKOSS system enables knowledge creators to construct computer-interpretable semantically rich statements describing their knowledge with minimal effort and without any knowledge of semantic web technologies.

show abstract

“…Although many protein and nucleotide databases still use mainly human readable text as annotation, different approaches have been developed to structure this knowledge. These were as straightforward as defining specific keywords or as complicated as setting up an ontology for different aspects of protein function [Rzhetsky et al, 2000]; probably, the most widely used of the latter approaches is from the Gene Ontology project [Consortium, 2008].…”

Section: Introductionmentioning

confidence: 99%

Searching in Protein State Space

Seipel

Schultz

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The increasing complexity of protein interaction networks makes their manual analysis infeasible. Signal transduction processes pose a specific challenge, as each protein can perform different functions, depending on its state. Here, we present a PROLOG and XML based system which explores the protein state space. Starting with state based information about the function of single proteins, the system searches for all biologically reasonable states that can be reached from the starting point. As facts of general molecular biology have been integrated, novel reasonable states, not encoded in the starting set, can be reached. Furthermore, the influence of modifications like mutations or the addition of further proteins can be explored. Thus, the system could direct experiments and allow to predict their outcome.

show abstract

A knowledge model for analysis and simulation of regulatory networks

Cited by 64 publications

References 14 publications

Learning anchor verbs for biological interaction patterns from published text articles

Learning anchor verbs for biological interaction patterns from published text articles

EKOSS: A Knowledge-User Centered Approach to Knowledge Sharing, Discovery, and Integration on the Semantic Web

Searching in Protein State Space

Contact Info

Product

Resources

About