Tagging gene and protein names in biomedical text

MOTIVATION: The MEDLINE database of biomedical abstracts contains scientific knowledge about thousands of interacting genes and proteins. Automated text processing can aid in the comprehension and synthesis of this valuable information. The fundamental task of identifying gene and protein names is a necessary first step towards making full use of the information encoded in biomedical text. This remains a challenging task due to the irregularities and ambiguities in gene and protein nomenclature. We propose to approach the detection of gene and protein names in scientific abstracts as part-of-speech tagging, the most basic form of linguistic corpus annotation. RESULTS: We present a method for tagging gene and protein names in biomedical text using a combination of statistical and knowledge-based strategies. This method incorporates automatically generated rules from a transformation-based part-of-speech tagger, and manually generated rules from morphological clues, low frequency trigrams, indicator terms, suffixes and part-of-speech information. Results of an experiment on a test corpus of 56K MEDLINE documents demonstrate that our method to extract gene and protein names can be applied to large sets of MEDLINE abstracts, without the need for special conditions or human experts to predetermine relevant subsets. AVAILABILITY: The programs are available on request from the authors.     

Assignment of protein function and discovery of novel nucleolar proteins based on automatic analysis of MEDLINE

Attribution of the most probable functions to proteins identified by proteomics is a significant challenge that requires extensive literature analysis. We have developed a system for automated prediction of implicit and explicit biologically meaningful functions for a proteomics study of the nucleolus. This approach uses a set of vocabulary terms to map and integrate the information from the entire MEDLINE database. Based on a combination of cross-species sequence homology searches and the corresponding literature, our approach facilitated the direct association between sequence data and information from biological texts describing function. Comparison of our automated functional assignment to manual annotation demonstrated our method to be highly effective. To establish the sensitivity, we defined the functional subtleties within a family containing a highly conserved sequence. Clustering of the DEAD-box protein family of RNA helicases confirmed that these proteins shared similar morphology although functional subfamilies were accurately identified by our approach. We visualized the nucleolar proteome in terms of protein functions using multi-dimensional scaling, showing functional associations between nucleolar proteins that were not previously realized. Finally, by clustering the functional properties of the established nucleolar proteins, we predicted novel nucleolar proteins. Subsequently, nonproteomics studies confirmed the predictions of previously unidentified nucleolar proteins.     

Gene symbol disambiguation using knowledge-based profiles

MOTIVATION: The ambiguity of biomedical entities, particularly of gene symbols, is a big challenge for text-mining systems in the biomedical domain. Existing knowledge sources, such as Entrez Gene and the MEDLINE database, contain information concerning the characteristics of a particular gene that could be used to disambiguate gene symbols. RESULTS: For each gene, we create a profile with different types of information automatically extracted from related MEDLINE abstracts and readily available annotated knowledge sources. We apply the gene profiles to the disambiguation task via an information retrieval method, which ranks the similarity scores between the context where the ambiguous gene is mentioned, and candidate gene profiles. The gene profile with the highest similarity score is then chosen as the correct sense. We evaluated the method on three automatically generated testing sets of mouse, fly and yeast organisms, respectively. The method achieved the highest precision of 93.9% for the mouse, 77.8% for the fly and 89.5% for the yeast. AVAILABILITY: The testing data sets and disambiguation programs are available at http://www.dbmi.columbia.edu/~hux7002/gsd2006     

Literature mining and database annotation of protein phosphorylation using a rule-based system

MOTIVATION: A large volume of experimental data on protein phosphorylation is buried in the fast-growing PubMed literature. While of great value, such information is limited in databases owing to the laborious process of literature-based curation. Computational literature mining holds promise to facilitate database curation. RESULTS: A rule-based system, RLIMS-P (Rule-based LIterature Mining System for Protein Phosphorylation), was used to extract protein phosphorylation information from MEDLINE abstracts. An annotation-tagged literature corpus developed at PIR was used to evaluate the system for finding phosphorylation papers and extracting phosphorylation objects (kinases, substrates and sites) from abstracts. RLIMS-P achieved a precision and recall of 91.4 and 96.4% for paper retrieval, and of 97.9 and 88.0% for extraction of substrates and sites. Coupling the high recall for paper retrieval and high precision for information extraction, RLIMS-P facilitates literature mining and database annotation of protein phosphorylation.     

RelEx--relation extraction using dependency parse trees

MOTIVATION: The discovery of regulatory pathways, signal cascades, metabolic processes or disease models requires knowledge on individual relations like e.g. physical or regulatory interactions between genes and proteins. Most interactions mentioned in the free text of biomedical publications are not yet contained in structured databases. RESULTS: We developed RelEx, an approach for relation extraction from free text. It is based on natural language preprocessing producing dependency parse trees and applying a small number of simple rules to these trees. We applied RelEx on a comprehensive set of one million MEDLINE abstracts dealing with gene and protein relations and extracted approximately 150,000 relations with an estimated performance of both 80% precision and 80% recall. AVAILABILITY: The used natural language preprocessing tools are free for use for academic research. Test sets and relation term lists are available from our website (http://www.bio.ifi.lmu.de/publications/RelEx/).     

EPO-KB: a searchable knowledge base of biomarker to protein links

The knowledge base EPO-KB (Empirical Proteomic Ontology Knowledge Base) is based on an OWL ontology that represents current knowledge linking mass-to-charge (m/z) ratios to proteins on multiple platforms including Matrix Assisted Laser/Desorption Ionization (MALDI) and Surface Enhanced Laser/Desorption Ionization (SELDI)--Time of Flight (TOF). At present, it contains information on m/z ratio to protein links that were extracted from 120 published research papers. It has a web interface that allows researchers to query and retrieve putative proteins that correspond to a user-specified m/z ratio. EPO-KB also allows automated entry of additional m/z ratio to protein links and is expandable to the addition of gene to protein and protein to disease links. AVAILABILITY: http://www.dbmi.pitt.edu/EPO-KB     

BioContrasts: extracting and exploiting protein-protein contrastive relations from biomedical literature

MOTIVATION: Contrasts are useful conceptual vehicles for learning processes and exploratory research of the unknown. For example, contrastive information between proteins can reveal what similarities, divergences and relations there are of the two proteins, leading to invaluable insights for better understanding about the proteins. Such contrastive information are found to be reported in the biomedical literature. However, there have been no reported attempts in current biomedical text mining work that systematically extract and present such useful contrastive information from the literature for exploitation. RESULTS: Our BioContrasts system extracts protein-protein contrastive information from MEDLINE abstracts and presents the information to biologists in a web-application for exploitation. Contrastive information are identified in the text abstracts with contrastive negation patterns such as 'A but not B'. A total of 799 169 pairs of contrastive expressions were successfully extracted from 2.5 million MEDLINE abstracts. Using grounding of contrastive protein names to Swiss-Prot entries, we were able to produce 41 471 pieces of contrasts between Swiss-Prot protein entries. These contrastive pieces of information are then presented via a user-friendly interactive web portal that can be exploited for applications such as the refinement of biological pathways. AVAILABILITY: BioContrasts can be accessed at http://biocontrasts.i2r.a-star.edu.sg. It is also mirrored at http://biocontrasts.biopathway.org. SUPPLEMENTARY INFORMATION: Supplementary materials are available at Bioinformatics online.     

HYPROSP: a hybrid protein secondary structure prediction algorithm--a knowledge-based approach

We develop a knowledge-based approach (called PROSP) for protein secondary structure prediction. The knowledge base contains small peptide fragments together with their secondary structural information. A quantitative measure M, called match rate, is defined to measure the amount of structural information that a target protein can extract from the knowledge base. Our experimental results show that proteins with a higher match rate will likely be predicted more accurately based on PROSP. That is, there is roughly a monotone correlation between the prediction accuracy and the amount of structure matching with the knowledge base. To fully utilize the strength of our knowledge base, a hybrid prediction method is proposed as follows: if the match rate of a target protein is at least 80%, we use the extracted information to make the prediction; otherwise, we adopt a popular machine-learning approach. This comprises our hybrid protein structure prediction (HYPROSP) approach. We use the DSSP and EVA data as our datasets and PSIPRED as our underlying machine-learning algorithm. For target proteins with match rate at least 80%, the average Q₃ of PROSP is 3.96 and 7.2 better than that of PSIPRED on DSSP and EVA data, respectively.     

Genome-wide enzyme annotation with precision control: catalytic families (CatFam) databases

In this article, we present a new method termed CatFam (Catalytic Families) to automatically infer the functions of catalytic proteins, which account for 20-40% of all proteins in living organisms and play a critical role in a variety of biological processes. CatFam is a sequence-based method that generates sequence profiles to represent and infer protein catalytic functions. CatFam generates profiles through a stepwise procedure that carefully controls profile quality and employs nonenzymes as negative samples to establish profile-specific thresholds associated with a predefined nominal false-positive rate (FPR) of predictions. The adjustable FPR allows for fine precision control of each profile and enables the generation of profile databases that meet different needs: function annotation with high precision and hypothesis generation with moderate precision but better recall. Multiple tests of CatFam databases (generated with distinct nominal FPRs) against enzyme and nonenzyme datasets show that the method's predictions have consistently high precision and recall. For example, a 1% FPR database predicts protein catalytic functions for a dataset of enzymes and nonenzymes with 98.6% precision and 95.0% recall. Comparisons of CatFam databases against other established profile-based methods for the functional annotation of 13 bacterial genomes indicate that CatFam consistently achieves higher precision and (in most cases) higher recall, and that (on average) CatFam provides 21.9% additional catalytic functions not inferred by the other similarly reliable methods. These results strongly suggest that the proposed method provides a valuable contribution to the automated prediction of protein catalytic functions. The CatFam databases and the database search program are freely available at http://www.bhsai.org/downloads/catfam.tar.gz.     

PPI_SVM: Prediction of protein-protein interactions using machine learning,domain-domain affinities and frequency tables

Protein-protein interactions (PPI) control most of the biological processes in a living cell. In order to fully understand protein functions, a knowledge of protein-protein interactions is necessary. Prediction of PPI is challenging, especially when the three-dimensional structure of interacting partners is not known. Recently, a novel prediction method was proposed by exploiting physical interactions of constituent domains. We propose here a novel knowledge-based prediction method, namely PPI_SVM, which predicts interactions between two protein sequences by exploiting their domain information. We trained a two-class support vector machine on the benchmarking set of pairs of interacting proteins extracted from the Database of Interacting Proteins (DIP). The method considers all possible combinations of constituent domains between two protein sequences, unlike most of the existing approaches. Moreover, it deals with both single-domain proteins and multi domain proteins; therefore it can be applied to the whole proteome in high-throughput studies. Our machine learning classifier, following a brainstorming approach, achieves accuracy of 86%, with specificity of 95%, and sensitivity of 75%, which are better results than most previous methods that sacrifice recall values in order to boost the overall precision. Our method has on average better sensitivity combined with good selectivity on the benchmarking dataset. The PPI_SVM source code, train/test datasets and supplementary files are available freely in the public domain at: .     

MedScan,a natural language processing engine for MEDLINE abstracts

MOTIVATION: The importance of extracting biomedical information from scientific publications is well recognized. A number of information extraction systems for the biomedical domain have been reported, but none of them have become widely used in practical applications. Most proposals to date make rather simplistic assumptions about the syntactic aspect of natural language. There is an urgent need for a system that has broad coverage and performs well in real-text applications. RESULTS: We present a general biomedical domain-oriented NLP engine called MedScan that efficiently processes sentences from MEDLINE abstracts and produces a set of regularized logical structures representing the meaning of each sentence. The engine utilizes a specially developed context-free grammar and lexicon. Preliminary evaluation of the system's performance, accuracy, and coverage exhibited encouraging results. Further approaches for increasing the coverage and reducing parsing ambiguity of the engine, as well as its application for information extraction are discussed.     

Gene clustering by latent semantic indexing of MEDLINE abstracts

MOTIVATION: A major challenge in the interpretation of high-throughput genomic data is understanding the functional associations between genes. Previously, several approaches have been described to extract gene relationships from various biological databases using term-matching methods. However, more flexible automated methods are needed to identify functional relationships (both explicit and implicit) between genes from the biomedical literature. In this study, we explored the utility of Latent Semantic Indexing (LSI), a vector space model for information retrieval, to automatically identify conceptual gene relationships from titles and abstracts in MEDLINE citations. RESULTS: We found that LSI identified gene-to-gene and keyword-to-gene relationships with high average precision. In addition, LSI identified implicit gene relationships based on word usage patterns in the gene abstract documents. Finally, we demonstrate here that pairwise distances derived from the vector angles of gene abstract documents can be effectively used to functionally group genes by hierarchical clustering. Our results provide proof-of-principle that LSI is a robust automated method to elucidate both known (explicit) and unknown (implicit) gene relationships from the biomedical literature. These features make LSI particularly useful for the analysis of novel associations discovered in genomic experiments. AVAILABILITY: The 50-gene document collection used in this study can be interactively queried at http://shad.cs.utk.edu/sgo/sgo.html.     

Evaluation of features for catalytic residue prediction in novel folds

Structural genomics projects are determining the three-dimensional structure of proteins without full characterization of their function. A critical part of the annotation process involves appropriate knowledge representation and prediction of functionally important residue environments. We have developed a method to extract features from sequence, sequence alignments, three-dimensional structure, and structural environment conservation, and used support vector machines to annotate homologous and nonhomologous residue positions based on a specific training set of residue functions. In order to evaluate this pipeline for automated protein annotation, we applied it to the challenging problem of prediction of catalytic residues in enzymes. We also ranked the features based on their ability to discriminate catalytic from noncatalytic residues. When applying our method to a well-annotated set of protein structures, we found that top-ranked features were a measure of sequence conservation, a measure of structural conservation, a degree of uniqueness of a residue's structural environment, solvent accessibility, and residue hydrophobicity. We also found that features based on structural conservation were complementary to those based on sequence conservation and that they were capable of increasing predictor performance. Using a family nonredundant version of the ASTRAL 40 v1.65 data set, we estimated that the true catalytic residues were correctly predicted in 57.0% of the cases, with a precision of 18.5%. When testing on proteins containing novel folds not used in training, the best features were highly correlated with the training on families, thus validating the approach to nonhomologous catalytic residue prediction in general. We then applied the method to 2781 coordinate files from the structural genomics target pipeline and identified both highly ranked and highly clustered groups of predicted catalytic residues.     

An incremental approach to automated protein localisation

Background  

The subcellular localisation of proteins in intact living cells is an important means for gaining information about protein functions. Even dynamic processes can be captured, which can barely be predicted based on amino acid sequences. Besides increasing our knowledge about intracellular processes, this information facilitates the development of innovative therapies and new diagnostic methods. In order to perform such a localisation, the proteins under analysis are usually fused with a fluorescent protein. So, they can be observed by means of a fluorescence microscope and analysed. In recent years, several automated methods have been proposed for performing such analyses. Here, two different types of approaches can be distinguished: techniques which enable the recognition of a fixed set of protein locations and methods that identify new ones. To our knowledge, a combination of both approaches – i.e. a technique, which enables supervised learning using a known set of protein locations and is able to identify and incorporate new protein locations afterwards – has not been presented yet. Furthermore, associated problems, e.g. the recognition of cells to be analysed, have usually been neglected.     

Analysis of albumen gland proteins suggests survival strategies of developing embryos of Pomacea canaliculata

The albumen gland of Pomacea canaliculata secretes the perivitelline fluid (PVF) surrounding the developing embryo which gives its eggs a highly effective defence against environmental factors and predators. Although previous studies have determined the functions of some PVF proteins extracted from P. canaliculata eggs, knowledge of the protein composition of PVF is still limited. In this study we use LC-MS/MS to identify 87 proteins from the albumen gland of P. canaliculata, 53 of which (60.9%) were annotated using the KEGG database. These classified into five functional groups: metabolism (54.7%); genetic information processing (9.4%); environmental information processing (3.8%); cellular processes (11.3%); and organismal systems (20.8%). The analyses found 12 proteins related to innate immunity and three proteins linked to defence against predation, providing important information for studies on embryo survival strategies and the invasive capabilities of P. canaliculata.     

Pathway studio--the analysis and navigation of molecular networks

SUMMARY: PathwayAssist is a software application developed for navigation and analysis of biological pathways, gene regulation networks and protein interaction maps. It comes with the built-in natural language processing module MedScan and the comprehensive database describing more than 100 000 events of regulation, interaction and modification between proteins, cell processes and small molecules. AVAILABILITY: PathwayAssist is available for commercial licensing from Ariadne Genomics, Inc. The light version with limited functionality will be available for free for academic users at www.ariadnegenomics.com/downloads/.     

Textmining in support of knowledge discovery for vaccine development

Complete genome data of infectious microorganisms permit systematic computational sequence-based predictions and experimental testing of candidate vaccine epitopes. Both, predictions and the interpretation of experiments rely on existing information in the literature which is mostly manually extracted and curated. The growing amount of data and literature information has created a major bottleneck for the interpretation of results and maintenance of curated databases. The lack of suitable free-text information extraction, processing, and reporting tools prompted us to develop a knowledge discovery support system that enhances the understanding of immune response and vaccine development. The current prototype system, Gene expression/epitpopes/protein interaction (GEpi), focuses on molecular functions of HIV-infected T-cells and HIV epitope information, using textmining, and interrelation of biomolecular data from domain-specific databases with MEDLINE abstract-inferred information. Results showed that extraction and processing of molecular interaction, disease associations, and gene ontology-derived functional information generate intuitive knowledge reports that aid the interpretation of host-pathogen interaction. In contrast, epitope (word and sequence) information in MEDLINE abstracts is surprisingly sparse and often lacks necessary context information, such as HLA-restriction. Since the majority of epitope information is found in tables, figures, and legends of full-text articles, its extraction may not require sophisticated natural language processing techniques. Support of vaccine development through textmining requires therefore the timely development of domain-specific extraction rules for full-text articles, and a knowledge model for epitope-related information.     

Automated image analysis of protein localization in budding yeast

MOTIVATION: The yeast Saccharomyces cerevisiae is the first eukaryotic organism to have its genome completely sequenced. Since then, several large-scale analyses of the yeast genome have provided extensive functional annotations of individual genes and proteins. One fundamental property of a protein is its subcellular localization, which provides critical information about how this protein works in a cell. An important project therefore was the creation of the yeast GFP fusion localization database by the University of California, San Francisco, USA (UCSF). This database provides localization data for 75% of the proteins believed to be encoded by the yeast genome. These proteins were classified into 22 distinct subcellular location categories by visual examination. Based on our past success at building automated systems to classify subcellular location patterns in mammalian cells, we sought to create a similar system for yeast. RESULTS: We developed computational methods to automatically analyze the images created by the UCSF yeast GFP fusion localization project. The system was trained to recognize the same location categories that were used in that study. We applied the system to 2640 images, and the system gave the same label as the previous assignments to 2139 images (81%). When only the highest confidence assignments were considered, 94.7% agreement was observed. Visual examination of the proteins for which the two approaches disagree suggests that at least some of the automated assignments may be more accurate. The automated method provides an objective, quantitative and repeatable assignment of protein locations that can be applied to new collections of yeast images (e.g. for different strains or the same strain under different conditions). It is also important to note that this performance could be achieved without requiring colocalization with any marker proteins. AVAILABILITY: The original images analyzed in this article are available at http://yeastgfp.ucsf.edu, and source code and results are available at http://murphylab.web.cmu.edu/software.     

An integrated probabilistic model for functional prediction of proteins.

We develop an integrated probabilistic model to combine protein physical interactions, genetic interactions, highly correlated gene expression networks, protein complex data, and domain structures of individual proteins to predict protein functions. The model is an extension of our previous model for protein function prediction based on Markovian random field theory. The model is flexible in that other protein pairwise relationship information and features of individual proteins can be easily incorporated. Two features distinguish the integrated approach from other available methods for protein function prediction. One is that the integrated approach uses all available sources of information with different weights for different sources of data. It is a global approach that takes the whole network into consideration. The second feature is that the posterior probability that a protein has the function of interest is assigned. The posterior probability indicates how confident we are about assigning the function to the protein. We apply our integrated approach to predict functions of yeast proteins based upon MIPS protein function classifications and upon the interaction networks based on MIPS physical and genetic interactions, gene expression profiles, tandem affinity purification (TAP) protein complex data, and protein domain information. We study the recall and precision of the integrated approach using different sources of information by the leave-one-out approach. In contrast to using MIPS physical interactions only, the integrated approach combining all of the information increases the recall from 57% to 87% when the precision is set at 57%-an increase of 30%.