Recognizing names in biomedical texts: a machine learning approach

MOTIVATION: With an overwhelming amount of textual information in molecular biology and biomedicine, there is a need for effective and efficient literature mining and knowledge discovery that can help biologists to gather and make use of the knowledge encoded in text documents. In order to make organized and structured information available, automatically recognizing biomedical entity names becomes critical and is important for information retrieval, information extraction and automated knowledge acquisition. RESULTS: In this paper, we present a named entity recognition system in the biomedical domain, called PowerBioNE. In order to deal with the special phenomena of naming conventions in the biomedical domain, we propose various evidential features: (1) word formation pattern; (2) morphological pattern, such as prefix and suffix; (3) part-of-speech; (4) head noun trigger; (5) special verb trigger and (6) name alias feature. All the features are integrated effectively and efficiently through a hidden Markov model (HMM) and a HMM-based named entity recognizer. In addition, a k-Nearest Neighbor (k-NN) algorithm is proposed to resolve the data sparseness problem in our system. Finally, we present a pattern-based post-processing to automatically extract rules from the training data to deal with the cascaded entity name phenomenon. From our best knowledge, PowerBioNE is the first system which deals with the cascaded entity name phenomenon. Evaluation shows that our system achieves the F-measure of 66.6 and 62.2 on the 23 classes of GENIA V3.0 and V1.1, respectively. In particular, our system achieves the F-measure of 75.8 on the "protein" class of GENIA V3.0. For comparison, our system outperforms the best published result by 7.8 on GENIA V1.1, without help of any dictionaries. It also shows that our HMM and the k-NN algorithm outperform other models, such as back-off HMM, linear interpolated HMM, support vector machines, C4.5, C4.5 rules and RIPPER, by effectively capturing the local context dependency and resolving the data sparseness problem. Moreover, evaluation on GENIA V3.0 shows that the post-processing for the cascaded entity name phenomenon improves the F-measure by 3.9. Finally, error analysis shows that about half of the errors are caused by the strict annotation scheme and the annotation inconsistency in the GENIA corpus. This suggests that our system achieves an acceptable F-measure of 83.6 on the 23 classes of GENIA V3.0 and in particular 86.2 on the "protein" class, without help of any dictionaries. We think that a F-measure of 90 on the 23 classes of GENIA V3.0 and in particular 92 on the "protein" class, can be achieved through refining of the annotation scheme in the GENIA corpus, such as flexible annotation scheme and annotation consistency, and inclusion of a reasonable biomedical dictionary. AVAILABILITY: A demo system is available at http://textmining.i2r.a-star.edu.sg/NLS/demo.htm. Technology license is available upon the bilateral agreement.     

Extraction of knowledge on protein-protein interaction by association rule discovery

MOTIVATION: Protein-protein interactions are systematically examined using the yeast two-hybrid method. Consequently, a lot of protein-protein interaction data are currently being accumulated. Nevertheless, general information or knowledge on protein-protein interactions is poorly extracted from these data. Thus we have been trying to extract the knowledge from the protein-protein interaction data using data mining. RESULTS: A data mining method is proposed to discover association rules related to protein-protein interactions. To evaluate the detected rules by the method, a new scoring measure of the rules is introduced. The method allowed us to detect popular interaction rules such as "An SH3 domain binds to a proline-rich region." These results indicate that the method may detect novel knowledge on protein-protein interactions.     

Resource Construction and Evaluation for Indirect Opinion Mining of Drug Reviews

Opinion mining is a well-known problem in natural language processing that has attracted increasing attention in recent years. Existing approaches are mainly limited to the identification of direct opinions and are mostly dedicated to explicit opinions. However, in some domains such as medical, the opinions about an entity are not usually expressed by opinion words directly, but they are expressed indirectly by describing the effect of that entity on other ones. Therefore, ignoring indirect opinions can lead to the loss of valuable information and noticeable decline in overall accuracy of opinion mining systems. In this paper, we first introduce the task of indirect opinion mining. Then, we present a novel approach to construct a knowledge base of indirect opinions, called OpinionKB, which aims to be a resource for automatically classifying people’s opinions about drugs. Using our approach, we have extracted 896 quadruples of indirect opinions at a precision of 88.08 percent. Furthermore, experiments on drug reviews demonstrate that our approach can achieve 85.25 percent precision in polarity detection task, and outperforms the state-of-the-art opinion mining methods. We also build a corpus of indirect opinions about drugs, which can be used as a basis for supervised indirect opinion mining. The proposed approach for corpus construction achieves the precision of 88.42 percent.     

Automated extraction of information on protein-protein interactions from the biological literature

MOTIVATION: To understand biological process, we must clarify how proteins interact with each other. However, since information about protein-protein interactions still exists primarily in the scientific literature, it is not accessible in a computer-readable format. Efficient processing of large amounts of interactions therefore needs an intelligent information extraction method. Our aim is to develop an efficient method for extracting information on protein-protein interaction from scientific literature. RESULTS: We present a method for extracting information on protein-protein interactions from the scientific literature. This method, which employs only a protein name dictionary, surface clues on word patterns and simple part-of-speech rules, achieved high recall and precision rates for yeast (recall = 86.8% and precision = 94.3%) and Escherichia coli (recall = 82.5% and precision = 93.5%). The result of extraction suggests that our method should be applicable to any species for which a protein name dictionary is constructed. AVAILABILITY: The program is available on request from the authors.     

Development of a high-throughput yeast two-hybrid screening system to study protein-protein interactions in plants

We have developed a high-throughput yeast two-hybrid screening system (HTP-YTH) that incorporates yeast gap-repair cloning, multiple positive ( ADE2, HIS3, lacZ) and negative ( URA3-based) selection schemes to reduce the incidence of negative and false positive clones, and automation of laboratory procedures to increase throughput. This HTP-YTH system has been applied to the study of protein-protein interactions that are involved in rice defense signal transduction pathways. More than 100 genes involved in plant defense responses were selected from DuPont's rice expressed sequence tag (EST) databases as baits for HTP-YTH screening. Results from YTH screening of eight of these rice genes are presented in this paper. Not only have we identified known protein-protein interactions, but we have also discovered novel interactions, which may ultimately reveal the regulatory network of host defense signal transduction pathways. We have demonstrated that our HTP-YTH method can be used to map protein-protein interaction networks and signal transduction pathways in any system. In combination with other approaches, such efficient YTH screens can help us systemically to study the functions of known and unknown genes in the genomics era.     

Application of automatic mutation-gene pair extraction to diseases

To have a better understanding of the mechanisms of disease development, knowledge of mutations and the genes on which the mutations occur is of crucial importance. Information on disease-related mutations can be accessed through public databases or biomedical literature sources. However, information retrieval from such resources can be problematic because of two reasons: manually created databases are usually incomplete and not up to date, and reading through a vast amount of publicly available biomedical documents is very time-consuming. In this paper, we describe an automated system, MuGeX (Mutation Gene eXtractor), that automatically extracts mutation-gene pairs from Medline abstracts for a disease query. Our system is tested on a corpus that consists of 231 Medline abstracts. While recall for mutation detection alone is 85.9%, precision is 95.9%. For extraction of mutation-gene pairs, we focus on Alzheimer's disease. The recall for mutation-gene pair identification is estimated at 91.3%, and precision is estimated at 88.9%. With automatic extraction techniques, MuGeX overcomes the problems of information retrieval from public resources and reduces the time required to access relevant information, while preserving the accuracy of retrieved information.     

Estimating gene regulatory networks and protein-protein interactions of Saccharomyces cerevisiae from multiple genome-wide data

MOTIVATION: Biological processes in cells are properly performed by gene regulations, signal transductions and interactions between proteins. To understand such molecular networks, we propose a statistical method to estimate gene regulatory networks and protein-protein interaction networks simultaneously from DNA microarray data, protein-protein interaction data and other genome-wide data. RESULTS: We unify Bayesian networks and Markov networks for estimating gene regulatory networks and protein-protein interaction networks according to the reliability of each biological information source. Through the simultaneous construction of gene regulatory networks and protein-protein interaction networks of Saccharomyces cerevisiae cell cycle, we predict the role of several genes whose functions are currently unknown. By using our probabilistic model, we can detect false positives of high-throughput data, such as yeast two-hybrid data. In a genome-wide experiment, we find possible gene regulatory relationships and protein-protein interactions between large protein complexes that underlie complex regulatory mechanisms of biological processes.     

Extraction of regulatory gene/protein networks from Medline

MOTIVATION: We have previously developed a rule-based approach for extracting information on the regulation of gene expression in yeast. The biomedical literature, however, contains information on several other equally important regulatory mechanisms, in particular phosphorylation, which we now expanded for our rule-based system also to extract. RESULTS: This paper presents new results for extraction of relational information from biomedical text. We have improved our system, STRING-IE, to capture both new types of linguistic constructs as well as new types of biological information [i.e. (de-)phosphorylation]. The precision remains stable with a slight increase in recall. From almost one million PubMed abstracts related to four model organisms, we manage to extract regulatory networks and binary phosphorylations comprising 3,319 relation chunks. The accuracy is 83-90% and 86-95% for gene expression and (de-)phosphorylation relations, respectively. To achieve this, we made use of an organism-specific resource of gene/protein names considerably larger than those used in most other biology related information extraction approaches. These names were included in the lexicon when retraining the part-of-speech (POS) tagger on the GENIA corpus. For the domain in question, an accuracy of 96.4% was attained on POS tags. It should be noted that the rules were developed for yeast and successfully applied to both abstracts and full-text articles related to other organisms with comparable accuracy. AVAILABILITY: The revised GENIA corpus, the POS tagger, the extraction rules and the full sets of extracted relations are available from http://www.bork.embl.de/Docu/STRING-IE     

Mining Dense Overlapping Subgraphs in weighted protein-protein interaction networks

Many methods have been proposed for mining protein complexes from a protein-protein interaction network; however, most of them focus on unweighted networks and cannot find overlapping protein complexes. Since one protein may serve different roles within different functional groups, mining overlapping protein complexes in a weighted protein-protein interaction network has attracted more and more attention recently. In this paper, we propose an effective method, called MDOS (Mining Dense Overlapping Subgraphs), for mining dense overlapping protein complexes (subgraphs) in a weighted protein-protein interaction network. The proposed method can integrate the information about known complexes into a weighted protein-protein interaction network to improve the mining results. The experiment results show that our method mines more known complexes and has higher sensitivity and accuracy than the CODENSE and MCL methods.     

What Evidence Is There for the Homology of Protein-Protein Interactions?

The notion that sequence homology implies functional similarity underlies much of computational biology. In the case of protein-protein interactions, an interaction can be inferred between two proteins on the basis that sequence-similar proteins have been observed to interact. The use of transferred interactions is common, but the legitimacy of such inferred interactions is not clear. Here we investigate transferred interactions and whether data incompleteness explains the lack of evidence found for them. Using definitions of homology associated with functional annotation transfer, we estimate that conservation rates of interactions are low even after taking interactome incompleteness into account. For example, at a blastp -value threshold of , we estimate the conservation rate to be about between S. cerevisiae and H. sapiens. Our method also produces estimates of interactome sizes (which are similar to those previously proposed). Using our estimates of interaction conservation we estimate the rate at which protein-protein interactions are lost across species. To our knowledge, this is the first such study based on large-scale data. Previous work has suggested that interactions transferred within species are more reliable than interactions transferred across species. By controlling for factors that are specific to within-species interaction prediction, we propose that the transfer of interactions within species might be less reliable than transfers between species. Protein-protein interactions appear to be very rarely conserved unless very high sequence similarity is observed. Consequently, inferred interactions should be used with care.     

Characterizing the Google Books Corpus: Strong Limits to Inferences of Socio-Cultural and Linguistic Evolution

It is tempting to treat frequency trends from the Google Books data sets as indicators of the “true” popularity of various words and phrases. Doing so allows us to draw quantitatively strong conclusions about the evolution of cultural perception of a given topic, such as time or gender. However, the Google Books corpus suffers from a number of limitations which make it an obscure mask of cultural popularity. A primary issue is that the corpus is in effect a library, containing one of each book. A single, prolific author is thereby able to noticeably insert new phrases into the Google Books lexicon, whether the author is widely read or not. With this understood, the Google Books corpus remains an important data set to be considered more lexicon-like than text-like. Here, we show that a distinct problematic feature arises from the inclusion of scientific texts, which have become an increasingly substantive portion of the corpus throughout the 1900s. The result is a surge of phrases typical to academic articles but less common in general, such as references to time in the form of citations. We use information theoretic methods to highlight these dynamics by examining and comparing major contributions via a divergence measure of English data sets between decades in the period 1800–2000. We find that only the English Fiction data set from the second version of the corpus is not heavily affected by professional texts. Overall, our findings call into question the vast majority of existing claims drawn from the Google Books corpus, and point to the need to fully characterize the dynamics of the corpus before using these data sets to draw broad conclusions about cultural and linguistic evolution.     

Computational Prediction of Protein–Protein Interaction Networks: Algo-rithms and Resources

Protein interactions play an important role in the discovery of protein functions and pathways in biological processes. This is especially true in case of the diseases caused by the loss of specific protein-protein interactions in the organism. The accuracy of experimental results in finding protein-protein interactions, however, is rather dubious and high throughput experimental results have shown both high false positive beside false negative information for protein interaction. Computational methods have attracted tremendous attention among biologists because of the ability to predict protein-protein interactions and validate the obtained experimental results. In this study, we have reviewed several computational methods for protein-protein interaction prediction as well as describing major databases, which store both predicted and detected protein-protein interactions, and the tools used for analyzing protein interaction networks and improving protein-protein interaction reliability.     

Generic Information Can Retrieve Known Biological Associations: Implications for Biomedical Knowledge Discovery

Motivation

Weighted semantic networks built from text-mined literature can be used to retrieve known protein-protein or gene-disease associations, and have been shown to anticipate associations years before they are explicitly stated in the literature. Our text-mining system recognizes over 640,000 biomedical concepts: some are specific (i.e., names of genes or proteins) others generic (e.g., ‘Homo sapiens’). Generic concepts may play important roles in automated information retrieval, extraction, and inference but may also result in concept overload and confound retrieval and reasoning with low-relevance or even spurious links. Here, we attempted to optimize the retrieval performance for protein-protein interactions (PPI) by filtering generic concepts (node filtering) or links to generic concepts (edge filtering) from a weighted semantic network. First, we defined metrics based on network properties that quantify the specificity of concepts. Then using these metrics, we systematically filtered generic information from the network while monitoring retrieval performance of known protein-protein interactions. We also systematically filtered specific information from the network (inverse filtering), and assessed the retrieval performance of networks composed of generic information alone.

Results

Filtering generic or specific information induced a two-phase response in retrieval performance: initially the effects of filtering were minimal but beyond a critical threshold network performance suddenly drops. Contrary to expectations, networks composed exclusively of generic information demonstrated retrieval performance comparable to unfiltered networks that also contain specific concepts. Furthermore, an analysis using individual generic concepts demonstrated that they can effectively support the retrieval of known protein-protein interactions. For instance the concept “binding” is indicative for PPI retrieval and the concept “mutation abnormality” is indicative for gene-disease associations.

Conclusion

Generic concepts are important for information retrieval and cannot be removed from semantic networks without negative impact on retrieval performance.     

Protein-protein interactions: principles, techniques, and their potential role in new drug development

A vast network of genes is inter-linked through protein-protein interactions and is critical component of almost every biological process under physiological conditions. Any disruption of the biologically essential network leads to pathological conditions resulting into related diseases. Therefore, proper understanding of biological functions warrants a comprehensive knowledge of protein-protein interactions and the molecular mechanisms that govern such processes. The importance of protein-protein interaction process is highlighted by the fact that a number of powerful techniques/methods have been developed to understand how such interactions take place under various physiological and pathological conditions. Many of the key protein-protein interactions are known to participate in disease-associated signaling pathways, and represent novel targets for therapeutic intervention. Thus, controlling protein-protein interactions offers a rich dividend for the discovery of new drug targets. Availability of various tools to study and the knowledge of human genome have put us in a unique position to understand highly complex biological network, and the mechanisms involved therein. In this review article, we have summarized protein-protein interaction networks, techniques/methods of their binding/kinetic parameters, and the role of these interactions in the development of potential tools for drug designing.     

Protein microarrays, biosensors, and cell-based methods for secretome-wide extracellular protein-protein interaction mapping

Approximately one quarter of all human genes encode proteins that function in the extracellular space or serve to bridge the extracellular and intracellular environments. Physical associations between these secretome proteins serve to regulate a wide range of biological activities and consequently represent important therapeutic targets. Moreover, some extracellular proteins are targeted by pathogens to allow host access or immune evasion. Despite the importance of extracellular protein-protein interactions, our knowledge in this area has remained sparse. Weak affinities and low abundance have often hindered efforts to identify these interactions using traditional methods such as biochemical purification and cDNA library expression cloning. Moreover, current large-scale protein-protein interaction mapping techniques largely under represent extracellular protein-protein interactions. This review highlights emerging biosensor and protein microarray technology, along with more traditional cell-based techniques, that are compatible with secretome-wide screens for extracellular protein-protein interaction discovery. A combination of these approaches will serve to rapidly expand our knowledge of the extracellular protein-protein interactome.     

蛋白质相互作用数据库

随着“蛋白质组学”的蓬勃发展和人类对生物大分子功能机制的知识积累,涌现出海量的蛋白质相互作用数据。随之,研究者开发了300多个蛋白质相互作用数据库,用于存储、展示和数据的重利用。蛋白质相互作用数据库是系统生物学、分子生物学和临床药物研究的宝贵资源。本文将数据库分为3类：（1）综合蛋白质相互作用数据库;（2）特定物种的蛋白质相互作用数据库;（3）生物学通路数据库。重点介绍常用的蛋白质相互作用数据库,包括BioGRID、STRING、IntAct、MINT、DIP、IMEx、HPRD、Reactome和KEGG等。     

Access to Awareness for Faces during Continuous Flash Suppression Is Not Modulated by Affective Knowledge

It is a controversially debated topic whether stimuli can be analyzed up to the semantic level when they are suppressed from visual awareness during continuous flash suppression (CFS). Here, we investigated whether affective knowledge, i.e., affective biographical information about faces, influences the time it takes for initially invisible faces with neutral expressions to overcome suppression and break into consciousness. To test this, we used negative, positive, and neutral famous faces as well as initially unfamiliar faces, which were associated with negative, positive or neutral biographical information. Affective knowledge influenced ratings of facial expressions, corroborating recent evidence and indicating the success of our affective learning paradigm. Furthermore, we replicated shorter suppression durations for upright than for inverted faces, demonstrating the suitability of our CFS paradigm. However, affective biographical information did not modulate suppression durations for newly learned faces, and even though suppression durations for famous faces were influenced by affective knowledge, these effects did not differ between upright and inverted faces, indicating that they might have been due to low-level visual differences. Thus, we did not obtain unequivocal evidence for genuine influences of affective biographical information on access to visual awareness for faces during CFS.     

A computational tool for identifying minimotifs in protein-protein interactions and improving the accuracy of minimotif predictions

Protein-protein interactions are important to understanding cell functions; however, our theoretical understanding is limited. There is a general discontinuity between the well-accepted physical and chemical forces that drive protein-protein interactions and the large collections of identified protein-protein interactions in various databases. Minimotifs are short functional peptide sequences that provide a basis to bridge this gap in knowledge. However, there is no systematic way to study minimotifs in the context of protein-protein interactions or vice versa. Here we have engineered a set of algorithms that can be used to identify minimotifs in known protein-protein interactions and implemented this for use by scientists in Minimotif Miner. By globally testing these algorithms on verified data and on 100 individual proteins as test cases, we demonstrate the utility of these new computation tools. This tool also can be used to reduce false-positive predictions in the discovery of novel minimotifs. The statistical significance of these algorithms is demonstrated by an ROC analysis (P = 0.001).