Conrad Plake

Inter-species normalization of gene mentions with GNAT

MOTIVATION Text mining in the biomedical domain aims at helping researchers to access information contained in scientific publications in a faster, easier and more complete way. One step towards this aim is the recognition of named entities and their subsequent normalization to database identifiers. Normalization helps to link objects of potential interest, such as genes, to detailed information not contained in a publication; it is also key for integrating different knowledge sources. From an information retrieval perspective, normalization facilitates indexing and querying. Gene mention normalization (GN) is particularly challenging given the high ambiguity of gene names: they refer to orthologous or entirely different genes, are named after phenotypes and other biomedical terms, or they resemble common English words. RESULTS We present the first publicly available system, GNAT, reported to handle inter-species GN. Our method uses extensive background knowledge on genes to resolve ambiguous names to EntrezGene identifiers. It performs comparably to single-species approaches proposed by us and others. On a benchmark set derived from BioCreative 1 and 2 data that contains genes from 13 species, GNAT achieves an F-measure of 81.4% (90.8% precision at 73.8% recall). For the single-species task, we report an F-measure of 85.4% on human genes. AVAILABILITY A web-frontend is available at http://cbioc.eas.asu.edu/gnat/. GNAT will also be available within the BioCreativeMetaService project, see http://bcms.bioinfo.cnio.es. SUPPLEMENTARY INFORMATION The test data set, lexica, and links toexternal data are available at http://cbioc.eas.asu.edu/gnat/

Facts from text: can text mining help to scale-up high-quality manual curation of gene products with ontologies?

The biomedical literature can be seen as a large integrated, but unstructured data repository. Extracting facts from literature and making them accessible is approached from two directions: manual curation efforts develop ontologies and vocabularies to annotate gene products based on statements in papers. Text mining aims to automatically identify entities and their relationships in text using information retrieval and natural language processing techniques. Manual curation is highly accurate but time consuming, and does not scale with the ever increasing growth of literature. Text mining as a high-throughput computational technique scales well, but is error-prone due to the complexity of natural language. How can both be married to combine scalability and accuracy? Here, we review the state-of-the-art text mining approaches that are relevant to annotation and discuss available online services analysing biomedical literature by means of text mining techniques, which could also be utilised by annotation projects. We then examine how far text mining has already been utilised in existing annotation projects and conclude how these techniques could be tightly integrated into the manual annotation process through novel authoring systems to scale-up high-quality manual curation.

Gene mention normalization and interaction extraction with context models and sentence motifs

Background:The goal of text mining is to make the information conveyed in scientific publications accessible to structured search and automatic analysis. Two important subtasks of text mining are entity mention normalization - to identify biomedical objects in text - and extraction of qualified relationships between those objects. We describe a method for identifying genes and relationships between proteins.Results:We present solutions to gene mention normalization and extraction of protein-protein interactions. For the first task, we identify genes by using background knowledge on each gene, namely annotations related to function, location, disease, and so on. Our approach currently achieves an f-measure of 86.4% on the BioCreative II gene normalization data. For the extraction of protein-protein interactions, we pursue an approach that builds on classical sequence analysis: motifs derived from multiple sequence alignments. The method achieves an f-measure of 24.4% (micro-average) in the BioCreative II interaction pair subtask.Conclusion:For gene mention normalization, our approach outperforms strategies that utilize only the matching of genes names against dictionaries, without invoking further knowledge on each gene. Motifs derived from alignments of sentences are successful at identifying protein interactions in text; the approach we present in this report is fully automated and performs similarly to systems that require human intervention at one or more stages.Availability:Our methods for gene, protein, and species identification, and extraction of protein-protein are available as part of the BioCreative Meta Services (BCMS), see http://bcms.bioinfo.cnio.es/.

The GNAT library for local and remote gene mention normalization

Summary: Identifying mentions of named entities, such as genes or diseases, and normalizing them to database identifiers have become an important step in many text and data mining pipelines. Despite this need, very few entity normalization systems are publicly available as source code or web services for biomedical text mining. Here we present the Gnat Java library for text retrieval, named entity recognition, and normalization of gene and protein mentions in biomedical text. The library can be used as a component to be integrated with other text-mining systems, as a framework to add user-specific extensions, and as an efficient stand-alone application for the identification of gene and protein names for data analysis. On the BioCreative III test data, the current version of Gnat achieves a Tap-20 score of 0.1987. Availability: The library and web services are implemented in Java and the sources are available from http://gnat.sourceforge.net. Contact: jorg.hakenberg@roche.com

Systematic feature evaluation for gene name recognition

In task 1A of the BioCreAtIvE evaluation, systems had to be devised that recognize words and phrases forming gene or protein names in natural language sentences. We approach this problem by building a word classification system based on a sliding window approach with a Support Vector Machine, combined with a pattern-based post-processing for the recognition of phrases. The performance of such a system crucially depends on the type of features chosen for consideration by the classification method, such as pre- or postfixes, character n-grams, patterns of capitalization, or classification of preceding or following words. We present a systematic approach to evaluate the performance of different feature sets based on recursive feature elimination, RFE. Based on a systematic reduction of the number of features used by the system, we can quantify the impact of different feature sets on the results of the word classification problem. This helps us to identify descriptive features, to learn about the structure of the problem, and to design systems that are faster and easier to understand. We observe that the SVM is robust to redundant features. RFE improves the performance by 0.7%, compared to using the complete set of attributes. Moreover, a performance that is only 2.3% below this maximum can be obtained using fewer than 5% of the features.

Large-scale De Novo Prediction of Physical Protein-Protein Association

Information about the physical association of proteins is extensively used for studying cellular processes and disease mechanisms. However, complete experimental mapping of the human interactome will remain prohibitively difficult in the near future. Here we present a map of predicted human protein interactions that distinguishes functional association from physical binding. Our network classifies more than 5 million protein pairs predicting 94,009 new interactions with high confidence. We experimentally tested a subset of these predictions using yeast two-hybrid analysis and affinity purification followed by quantitative mass spectrometry. Thus we identified 462 new protein-protein interactions and confirmed the predictive power of the network. These independent experiments address potential issues of circular reasoning and are a distinctive feature of this work. Analysis of the physical interactome unravels subnetworks mediating between different functional and physical subunits of the cell. Finally, we demonstrate the utility of the network for the analysis of molecular mechanisms of complex diseases by applying it to genome-wide association studies of neurodegenerative diseases. This analysis provides new evidence implying TOMM40 as a factor involved in Alzheimers disease. The network provides a high-quality resource for the analysis of genomic data sets and genetic association studies in particular. Our interactome is available via the hPRINT web server at: www.print-db.org.

GoGene: gene annotation in the fast lane

High-throughput screens such as microarrays and RNAi screens produce huge amounts of data. They typically result in hundreds of genes, which are often further explored and clustered via enriched GeneOntology terms. The strength of such analyses is that they build on high-quality manual annotations provided with the GeneOntology. However, the weakness is that annotations are restricted to process, function and location and that they do not cover all known genes in model organisms. GoGene addresses this weakness by complementing high-quality manual annotation with high-throughput text mining extracting co-occurrences of genes and ontology terms from literature. GoGene contains over 4 000 000 associations between genes and gene-related terms for 10 model organisms extracted from more than 18 000 000 PubMed entries. It does not cover only process, function and location of genes, but also biomedical categories such as diseases, compounds, techniques and mutations. By bringing it all together, GoGene provides the most recent and most complete facts about genes and can rank them according to novelty and importance. GoGene accepts keywords, gene lists, gene sequences and protein sequences as input and supports search for genes in PubMed, EntrezGene and via BLAST. Since all associations of genes to terms are supported by evidence in the literature, the results are transparent and can be verified by the user. GoGene is available at http://gopubmed.org/gogene.

Optimizing syntax patterns for discovering protein-protein interactions

We propose a method for automated extraction of protein-protein interactions from scientific text. Our system matches sentences against syntax patterns typically describing protein interactions. We define a set of 22 patterns, each a regular expression consisting of anchor positions and parameterizable constraints. This small set is then refined and optimized using a genetic algorithm on a training set. No heuristic definitions are necessary, and the final pattern set can be generated completely without manual curation. Our method can be applied to any syntax pattern-based protein-protein interaction system and thus complements related work on building comprehensive sets of such patterns. The application of different fitness-functions during evolution provides an easy way to tune the system either toward precision, recall, or f-measure. We evaluate our system on two samples, one derived from the BioCreAtIvE corpus, the other from references in the DIP. The automatic refinement of patterns adds up to 16% to the precision, and 5% to the recall of our system. We additionally study the impact of a proper protein name recognition, which could improve precision by about 17% and recall by 12%.

GoPubMed: Exploring PubMed with Ontological Background Knowledge

With the ever increasing size of scientific literature, finding relevant documents and answering questions has become even more of a challenge. Recently, ontologies—hierarchical, controlled vocabularies—have been introduced to annotate genomic data. They can also improve the question and answering and the selection of relevant documents in the literature search. Search engines such as GoPubMed.org use ontological background knowledge to give an overview over large query results and to answer questions. We review the problems and solutions underlying these next-generation intelligent search engines and give examples of the power of this new search paradigm.

Improved mutation tagging with gene identifiers applied to membrane protein stability prediction.

BackgroundThe automated retrieval and integration of information about protein point mutations in combination with structure, domain and interaction data from literature and databases promises to be a valuable approach to study structure-function relationships in biomedical data sets.ResultsWe developed a rule- and regular expression-based protein point mutation retrieval pipeline for PubMed abstracts, which shows an F-measure of 87% for the mutation retrieval task on a benchmark dataset. In order to link mutations to their proteins, we utilize a named entity recognition algorithm for the identification of gene names co-occurring in the abstract, and establish links based on sequence checks. Vice versa, we could show that gene recognition improved from 77% to 91% F-measure when considering mutation information given in the text. To demonstrate practical relevance, we utilize mutation information from text to evaluate a novel solvation energy based model for the prediction of stabilizing regions in membrane proteins. For five G protein-coupled receptors we identified 35 relevant single mutations and associated phenotypes, of which none had been annotated in the UniProt or PDB database. In 71% reported phenotypes were in compliance with the model predictions, supporting a relation between mutations and stability issues in membrane proteins.ConclusionWe present a reliable approach for the retrieval of protein mutations from PubMed abstracts for any set of genes or proteins of interest. We further demonstrate how amino acid substitution information from text can be utilized for protein structure stability studies on the basis of a novel energy model.