BACKGROUND: Recent developments in the domain of biomedical knowledge bases (KBs) open up new ways to exploit biomedical knowledge that is available in the form of KBs. Significant work has been done in the direction of biomedical KB creation and KB completion, specifically, those having gene-disease associations and other related entities. However, the use of such biomedical KBs in combination with patients' temporal clinical data still largely remains unexplored, but has the potential to immensely benefit medical diagnostic decision support systems. RESULTS: We propose two new algorithms, LOADDx and SCADDx, to combine a patient's gene expression data with gene-disease association and other related information available in the form of a KB, to assist personalized disease diagnosis. We have tested both of the algorithms on two KBs and on four real-world gene expression datasets of respiratory viral infection caused by Influenza-like viruses of 19 subtypes. We also compare the performance of proposed algorithms with that of five existing state-of-the-art machine learning algorithms (k-NN, Random Forest, XGBoost, Linear SVM, and SVM with RBF Kernel) using two validation approaches: LOOCV and a single internal validation set. Both SCADDx and LOADDx outperform the existing algorithms when evaluated with both validation approaches. SCADDx is able to detect infections with up to 100% accuracy in the cases of Datasets 2 and 3. Overall, SCADDx and LOADDx are able to detect an infection within 72 h of infection with 91.38% and 92.66% average accuracy respectively considering all four datasets, whereas XGBoost, which performed best among the existing machine learning algorithms, can detect the infection with only 86.43% accuracy on an average. CONCLUSIONS: We demonstrate how our novel idea of using the most and least differentially expressed genes in combination with a KB can enable identification of the diseases that a patient is most likely to have at a particular time, from a KB with thousands of diseases. Moreover, the proposed algorithms can provide a short ranked list of the most likely diseases for each patient along with their most affected genes, and other entities linked with them in the KB, which can support health care professionals in their decision-making.

Artificial intelligence (AI) systems utilizing deep neural networks and machine learning (ML) algorithms are widely used for solving critical problems in bioinformatics, biomedical informatics and precision medicine. However, complex ML models that are often perceived as opaque and black-box methods make it difficult to understand the reasoning behind their decisions. This lack of transparency can be a challenge for both end-users and decision-makers, as well as AI developers. In sensitive areas such as healthcare, explainability and accountability are not only desirable properties but also legally required for AI systems that can have a significant impact on human lives. Fairness is another growing concern, as algorithmic decisions should not show bias or discrimination towards certain groups or individuals based on sensitive attributes. Explainable AI (XAI) aims to overcome the opaqueness of black-box models and to provide transparency in how AI systems make decisions. Interpretable ML models can explain how they make predictions and identify factors that influence their outcomes. However, the majority of the state-of-the-art interpretable ML methods are domain-agnostic and have evolved from fields such as computer vision, automated reasoning or statistics, making direct application to bioinformatics problems challenging without customization and domain adaptation. In this paper, we discuss the importance of explainability and algorithmic transparency in the context of bioinformatics. We provide an overview of model-specific and model-agnostic interpretable ML methods and tools and outline their potential limitations. We discuss how existing interpretable ML methods can be customized and fit to bioinformatics research problems. Further, through case studies in bioimaging, cancer genomics and text mining, we demonstrate how XAI methods can improve transparency and decision fairness. Our review aims at providing valuable insights and serving as a starting point for researchers wanting to enhance explainability and decision transparency while solving bioinformatics problems. GitHub: https://github.com/rezacsedu/XAI-for-bioinformatics.

The study of genetic variants (GVs) can help find correlating population groups and to identify cohorts that are predisposed to common diseases and explain differences in disease susceptibility and how patients react to drugs. Machine learning techniques are increasingly being applied to identify interacting GVs to understand their complex phenotypic traits. Since the performance of a learning algorithm not only depends on the size and nature of the data but also on the quality of underlying representation, deep neural networks (DNNs) can learn non-linear mappings that allow transforming GVs data into more clustering and classification friendly representations than manual feature selection. In this paper, we propose convolutional embedded networks (CEN) in which we combine two DNN architectures called convolutional embedded clustering (CEC) and convolutional autoencoder (CAE) classifier for clustering individuals and predicting geographic ethnicity based on GVs, respectively. We employed CAE-based representation learning to 95 million GVs from the '1000 genomes' (covering 2,504 individuals from 26 ethnic origins) and 'Simons genome diversity' (covering 279 individuals from 130 ethnic origins) projects. Quantitative and qualitative analyses with a focus on accuracy and scalability show that our approach outperforms state-of-the-art approaches such as VariantSpark and ADMIXTURE. In particular, CEC can cluster targeted population groups in 22 hours with an adjusted rand index (ARI) of 0.915, the normalized mutual information (NMI) of 0.92, and the clustering accuracy (ACC) of 89 percent. Contrarily, the CAE classifier can predict the geographic ethnicity of unknown samples with an F1 and Mathews correlation coefficient (MCC) score of 0.9004 and 0.8245, respectively. Further, to provide interpretations of the predictions, we identify significant biomarkers using gradient boosted trees (GBT) and SHapley Additive exPlanations (SHAP). Overall, our approach is transparent and faster than the baseline methods, and scalable for 5 to 100 percent of the full human genome.

Clustering is central to many data-driven bioinformatics research and serves a powerful computational method. In particular, clustering helps at analyzing unstructured and high-dimensional data in the form of sequences, expressions, texts and images. Further, clustering is used to gain insights into biological processes in the genomics level, e.g. clustering of gene expressions provides insights on the natural structure inherent in the data, understanding gene functions, cellular processes, subtypes of cells and understanding gene regulations. Subsequently, clustering approaches, including hierarchical, centroid-based, distribution-based, density-based and self-organizing maps, have long been studied and used in classical machine learning settings. In contrast, deep learning (DL)-based representation and feature learning for clustering have not been reviewed and employed extensively. Since the quality of clustering is not only dependent on the distribution of data points but also on the learned representation, deep neural networks can be effective means to transform mappings from a high-dimensional data space into a lower-dimensional feature space, leading to improved clustering results. In this paper, we review state-of-the-art DL-based approaches for cluster analysis that are based on representation learning, which we hope to be useful, particularly for bioinformatics research. Further, we explore in detail the training procedures of DL-based clustering algorithms, point out different clustering quality metrics and evaluate several DL-based approaches on three bioinformatics use cases, including bioimaging, cancer genomics and biomedical text mining. We believe this review and the evaluation results will provide valuable insights and serve a starting point for researchers wanting to apply DL-based unsupervised methods to solve emerging bioinformatics research problems.

In this paper1, we proposed an explainable deep neural networks (DNN)-based method for automatic detection of COVID-19 symptoms from chest radiography (CXR) images, which we call ‘DeepCOVIDExplainer’. We used 15,959 CXR images of 15,854 patients, covering normal, pneumonia, and COVID-19 cases. CXR images are first comprehensively preprocessed and augmented before classifying with a neural ensemble method, followed by highlighting class-discriminating regions using gradient-guided class activation maps (Grad-CAM ++) and layer-wise relevance propagation (LRP). Further, we provide human-interpretable explanations for the diagnosis. Evaluation results show that our approach can identify COVID-19 cases with a positive predictive value (PPV) of 91.6%, 92.45%, and 96.12%, respectively for normal, pneumonia, and COVID-19 cases, respectively, outperforming recent approaches.1Read longer version of this paper: https://arxiv.org/pdf/2004.04582.pdf

MOTIVATION: Searching for precise terms and terminological definitions in the biomedical data space is problematic, as researchers find overlapping, closely related and even equivalent concepts in a single or multiple ontologies. Search engines that retrieve ontological resources often suggest an extensive list of search results for a given input term, which leads to the tedious task of selecting the best-fit ontological resource (class or property) for the input term and reduces user confidence in the retrieval engines. A systematic evaluation of these search engines is necessary to understand their strengths and weaknesses in different search requirements. RESULT: We have implemented seven comparable Information Retrieval ranking algorithms to search through ontologies and compared them against four search engines for ontologies. Free-text queries have been performed, the outcomes have been judged by experts and the ranking algorithms and search engines have been evaluated against the expert-based ground truth (GT). In addition, we propose a probabilistic GT that is developed automatically to provide deeper insights and confidence to the expert-based GT as well as evaluating a broader range of search queries. CONCLUSION: The main outcome of this work is the identification of key search factors for biomedical ontologies together with search requirements and a set of recommendations that will help biomedical experts and ontology engineers to select the best-suited retrieval mechanism in their search scenarios. We expect that this evaluation will allow researchers and practitioners to apply the current search techniques more reliably and that it will help them to select the right solution for their daily work. AVAILABILITY: The source code (of seven ranking algorithms), ground truths and experimental results are available at https://github.com/danielapoliveira/bioont-search-benchmark.

BACKGROUND: Determining the association between tumor sample and the gene is demanding because it requires a high cost for conducting genetic experiments. Thus, the discovered association between tumor sample and gene further requires clinical verification and validation. This entire mechanism is time-consuming and expensive. Due to this issue, predicting the association between tumor samples and genes remain a challenge in biomedicine. RESULTS: Here we present, a computational model based on a heat diffusion algorithm which can predict the association between tumor samples and genes. We proposed a 2-layered graph. In the first layer, we constructed a graph of tumor samples and genes where these two types of nodes are connected by "hasGene" relationship. In the second layer, the gene nodes are connected by "interaction" relationship. We applied the heat diffusion algorithms in nine different variants of genetic interaction networks extracted from STRING and BioGRID database. The heat diffusion algorithm predicted the links between tumor samples and genes with mean AUC-ROC score of 0.84. This score is obtained by using weighted genetic interactions of fusion or co-occurrence channels from the STRING database. For the unweighted genetic interaction from the BioGRID database, the algorithms predict the links with an AUC-ROC score of 0.74. CONCLUSIONS: We demonstrate that the gene-gene interaction scores could improve the predictive power of the heat diffusion model to predict the links between tumor samples and genes. We showed the efficient runtime of the heat diffusion algorithm in various genetic interaction network. We statistically validated our prediction quality of the links between tumor samples and genes.

The research shared on a digital social media has enabled us to measure the impact of academic entities beyond the conventional bibliometric community. We explored a diffusion-based metrics to measure the influence of academic entities in social media using 2-layered graph where the first layer is the graph between academic and social media entities and a second layer is the graph between social media entities. We employed the heat diffusion algorithms to measure the social impact of academic entities and evaluate them by (i) predicting links between academic entities and social media and (ii) suggesting memes for the academic entities. Our analysis on predicting links between scientist and social media entities showed the AUC-ROC score of 0.73 and the AUC-PR score of 0.30. Similarly, predicting links between scientific publications and social media entities showed the AUC-ROC score of 0.80 and the AUC-PR score of 0.19. Our approach also provides decent social media entities (memes) suggestion for scientific publications.

A mishap in anti-cancer drug distribution is critical in breast cancer patients due to poor prediction model to identify the treatment regime in ER+ve and ER-ve (Estrogen Receptor (ER)) patients. The traditional method for the prediction depends on the change in expression across the normal-disease pair. However, it certainly misses the multidimensional aspect and underlying cause of relapse, such as various mutations, drug dosage side effects, methylation, etc. In this paper, we have developed a multi-layer neural network model to classify multidimensional genomics data into their similar annotation group. Further, we used this multi-layer cancer genomics perceptron for annotating differentially expressed genes (DEGs) to predict relapse based on ER status in breast cancer. This approach provides multivariate identification of genes, not just by differential expression, but, cause-effect of disease status due to drug overdosage and genomics-driven drug balancing method. The multi-layered neural network model, where each layer defines the relationship of similar databases with multidimensional knowledge. We illustrate that the use of multilayer knowledge graph with gene expression data for training the deep convolution neural network stratify the patient relapse and drug dosage along with underlying molecular properties.

Data workflow systems (DWFSs) enable bioinformatics researchers to combine components for data access and data analytics, and to share the final data analytics approach with their collaborators. Increasingly, such systems have to cope with large-scale data, such as full genomes (about 200 GB each), public fact repositories (about 100 TB of data) and 3D imaging data at even larger scales. As moving the data becomes cumbersome, the DWFS needs to embed its processes into a cloud infrastructure, where the data are already hosted. As the standardized public data play an increasingly important role, the DWFS needs to comply with Semantic Web technologies. This advancement to DWFS would reduce overhead costs and accelerate the progress in bioinformatics research based on large-scale data and public resources, as researchers would require less specialized IT knowledge for the implementation. Furthermore, the high data growth rates in bioinformatics research drive the demand for parallel and distributed computing, which then imposes a need for scalability and high-throughput capabilities onto the DWFS. As a result, requirements for data sharing and access to public knowledge bases suggest that compliance of the DWFS with Semantic Web standards is necessary. In this article, we will analyze the existing DWFS with regard to their capabilities toward public open data use as well as large-scale computational and human interface requirements. We untangle the parameters for selecting a preferable solution for bioinformatics research with particular consideration to using cloud services and Semantic Web technologies. Our analysis leads to research guidelines and recommendations toward the development of future DWFS for the bioinformatics research community.

The database, semantic web, and linked data communities have proposed solutions that federate queries over multiple data sources using a single data model. Nowadays, the data retrieval requirements originating from versatile and broad domains like healthcare and life sciences (HCLS) are changing this conventional trend - of federating query over a single data model - primarily due to the simultaneous use of different data models (CSV, JSON, RDB, RDF, XML, etc.) in a real-life scenario. It's now impractical to assume that the variety (graph, key-value, stream, text, table, tree, etc.) of high volume data residing in specialised storage engines will first be converted to a common data model, stored in a general-purpose data storage engine, and finally be queried over the Web. Nevertheless, in this era where genomics datasets are growing from petascale to exascale, it is now important to exploit such vast domain resources in their native data models. The key approach is to query the vast data resources from their native data models and specialised storage engines. In this paper, we propose a Web-based query federation mechanism - called PolyWeb - that unifies query answering over multiple native data models (CSV, RDB, and RDF). We demonstrate PolyWeb on a cancer genomics use-case where it is often the case that a description of biological and chemical entities (e.g., gene, disease, drug, pathways) span across multiple data models. In order to assess the benefits and limitations of evaluating queries over native data models, we evaluate PolyWeb with state-of-the-art query federation engine in terms of result completeness, source selection, and overall query execution time.

Phenotypes have gained increased notoriety in the clinical and biological domain owing to their application in numerous areas such as the discovery of disease genes and drug targets, phylogenetics and pharmacogenomics. Phenotypes, defined as observable characteristics of organisms, can be seen as one of the bridges that lead to a translation of experimental findings into clinical applications and thereby support 'bench to bedside' efforts. However, to build this translational bridge, a common and universal understanding of phenotypes is required that goes beyond domain-specific definitions. To achieve this ambitious goal, a digital revolution is ongoing that enables the encoding of data in computer-readable formats and the data storage in specialized repositories, ready for integration, enabling translational research. While phenome research is an ongoing endeavor, the true potential hidden in the currently available data still needs to be unlocked, offering exciting opportunities for the forthcoming years. Here, we provide insights into the state-of-the-art in digital phenotyping, by means of representing, acquiring and analyzing phenotype data. In addition, we provide visions of this field for future research work that could enable better applications of phenotype data.

Semantic web technologies offer an approach to data integration and sharing, even for resources developed independently or broadly distributed across the web. This approach is particularly suitable for scientific domains that profit from large amounts of data that reside in the public domain and that have to be exploited in combination. Translational medicine is such a domain, which in addition has to integrate private data from the clinical domain with proprietary data from the pharmaceutical domain. In this survey, we present the results of our analysis of translational medicine solutions that follow a semantic web approach. We assessed these solutions in terms of their target medical use case; the resources covered to achieve their objectives; and their use of existing semantic web resources for the purposes of data sharing, data interoperability and knowledge discovery. The semantic web technologies seem to fulfill their role in facilitating the integration and exploration of data from disparate sources, but it is also clear that simply using them is not enough. It is fundamental to reuse resources, to define mappings between resources, to share data and knowledge. All these aspects allow the instantiation of translational medicine at the semantic web-scale, thus resulting in a network of solutions that can share resources for a faster transfer of new scientific results into the clinical practice. The envisioned network of translational medicine solutions is on its way, but it still requires resolving the challenges of sharing protected data and of integrating semantic-driven technologies into the clinical practice.

BACKGROUND: The third edition of the BioNLP Shared Task was held with the grand theme "knowledge base construction (KB)". The Genia Event (GE) task was re-designed and implemented in light of this theme. For its final report, the participating systems were evaluated from a perspective of annotation. To further explore the grand theme, we extended the evaluation from a perspective of KB construction. Also, the Gene Regulation Ontology (GRO) task was newly introduced in the third edition. The final evaluation of the participating systems resulted in relatively low performance. The reason was attributed to the large size and complex semantic representation of the ontology. To investigate potential benefits of resource exchange between the presumably similar tasks, we measured the overlap between the datasets of the two tasks, and tested whether the dataset for one task can be used to enhance performance on the other. RESULTS: We report an extended evaluation on all the participating systems in the GE task, incoporating a KB perspective. For the evaluation, the final submission of each participant was converted to RDF statements, and evaluated using 8 queries that were formulated in SPARQL. The results suggest that the evaluation may be concluded differently between the two different perspectives, annotation vs. KB. We also provide a comparison of the GE and GRO tasks by converting their datasets into each other's format. More than 90% of the GE data could be converted into the GRO task format, while only half of the GRO data could be mapped to the GE task format. The imbalance in conversion indicates that the GRO is a comprehensive extension of the GE task ontology. We further used the converted GRO data as additional training data for the GE task, which helped improve GE task participant system performance. However, the converted GE data did not help GRO task participants, due to overfitting and the ontology gap.

OBJECTIVE: To create a multilingual gold-standard corpus for biomedical concept recognition. MATERIALS AND METHODS: We selected text units from different parallel corpora (Medline abstract titles, drug labels, biomedical patent claims) in English, French, German, Spanish, and Dutch. Three annotators per language independently annotated the biomedical concepts, based on a subset of the Unified Medical Language System and covering a wide range of semantic groups. To reduce the annotation workload, automatically generated preannotations were provided. Individual annotations were automatically harmonized and then adjudicated, and cross-language consistency checks were carried out to arrive at the final annotations. RESULTS: The number of final annotations was 5530. Inter-annotator agreement scores indicate good agreement (median F-score 0.79), and are similar to those between individual annotators and the gold standard. The automatically generated harmonized annotation set for each language performed equally well as the best annotator for that language. DISCUSSION: The use of automatic preannotations, harmonized annotations, and parallel corpora helped to keep the manual annotation efforts manageable. The inter-annotator agreement scores provide a reference standard for gauging the performance of automatic annotation techniques. CONCLUSION: To our knowledge, this is the first gold-standard corpus for biomedical concept recognition in languages other than English. Other distinguishing features are the wide variety of semantic groups that are being covered, and the diversity of text genres that were annotated.

Networks of molecular interactions explain complex biological processes, and all known information on molecular events is contained in a number of public repositories including the scientific literature. Metabolic and signalling pathways are often viewed separately, even though both types are composed of interactions involving proteins and other chemical entities. It is necessary to be able to combine data from all available resources to judge the functionality, complexity and completeness of any given network overall, but especially the full integration of relevant information from the scientific literature is still an ongoing and complex task. Currently, the text-mining research community is steadily moving towards processing the full body of the scientific literature by making use of rich linguistic features such as full text parsing, to extract biological interactions. The next step will be to combine these with information from scientific databases to support hypothesis generation for the discovery of new knowledge and the extension of biological networks. The generation of comprehensive networks requires technologies such as entity grounding, coordination resolution and co-reference resolution, which are not fully solved and are required to further improve the quality of results. Here, we analyse the state of the art for the extraction of network information from the scientific literature and the evaluation of extraction methods against reference corpora, discuss challenges involved and identify directions for future research.

MOTIVATION: Drug repositioning is the discovery of new indications for compounds that have already been approved and used in a clinical setting. Recently, some computational approaches have been suggested to unveil new opportunities in a systematic fashion, by taking into consideration gene expression signatures or chemical features for instance. We present here a novel method based on knowledge integration using semantic technologies, to capture the functional role of approved chemical compounds. RESULTS: In order to computationally generate repositioning hypotheses, we used the Web Ontology Language to formally define the semantics of over 20 000 terms with axioms to correctly denote various modes of action (MoA). Based on an integration of public data, we have automatically assigned over a thousand of approved drugs into these MoA categories. The resulting new resource is called the Functional Therapeutic Chemical Classification System and was further evaluated against the content of the traditional Anatomical Therapeutic Chemical Classification System. We illustrate how the new classification can be used to generate drug repurposing hypotheses, using Alzheimers disease as a use-case. AVAILABILITY: https://www.ebi.ac.uk/chembl/ftc; https://github.com/loopasam/ftc. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

We present a method which exploits automatically generated scientific discourse annotations to create a content model for the summarisation of scientific articles.Full papers are first automatically annotated using the CoreSC scheme, which captures 11 contentbased concepts such as Hypothesis, Result, Conclusion etc at the sentence level.A content model which follows the sequence of CoreSC categories observed in abstracts is used to provide the skeleton of the summary, making a distinction between dependent and independent categories.Summary creation is also guided by the distribution of CoreSC categories found in the full articles, in order to adequately represent the article content.Finally, we demonstrate the usefulness of the summaries by evaluating them in a complex question answering task.Results are very encouraging as summaries of papers from automatically obtained CoreSCs enable experts to answer 66% of complex content-related questions designed on the basis of paper abstracts.The questions were answered with a precision of 75%, where the upper bound for human summaries (abstracts) was 95%.

Abstract Summary: Brain is a Java software library facilitating the manipulation and creation of ontologies and knowledge bases represented with the Web Ontology Language (OWL). Availability and implementation: The Java source code and the library are freely available at https://github.com/loopasam/Brain and on the Maven Central repository (GroupId: uk.ac.ebi.brain). The documentation is available at https://github.com/loopasam/Brain/wiki. Contact: [email protected] Supplementary information: Supplementary data are available at Bioinformatics online.

MOTIVATION: The recognition of named entities (NER) is an elementary task in biomedical text mining. A number of NER solutions have been proposed in recent years, taking advantage of available annotated corpora, terminological resources and machine-learning techniques. Currently, the best performing solutions combine the outputs from selected annotation solutions measured against a single corpus. However, little effort has been spent on a systematic analysis of methods harmonizing the annotation results and measuring against a combination of Gold Standard Corpora (GSCs). RESULTS: We present Totum, a machine learning solution that harmonizes gene/protein annotations provided by heterogeneous NER solutions. It has been optimized and measured against a combination of manually curated GSCs. The performed experiments show that our approach improves the F-measure of state-of-the-art solutions by up to 10% (achieving ≈70%) in exact alignment and 22% (achieving ≈82%) in nested alignment. We demonstrate that our solution delivers reliable annotation results across the GSCs and it is an important contribution towards a homogeneous annotation of MEDLINE abstracts. AVAILABILITY AND IMPLEMENTATION: Totum is implemented in Java and its resources are available at http://bioinformatics.ua.pt/totum

MOTIVATION: Scholarly biomedical publications report on the findings of a research investigation. Scientists use a well-established discourse structure to relate their work to the state of the art, express their own motivation and hypotheses and report on their methods, results and conclusions. In previous work, we have proposed ways to explicitly annotate the structure of scientific investigations in scholarly publications. Here we present the means to facilitate automatic access to the scientific discourse of articles by automating the recognition of 11 categories at the sentence level, which we call Core Scientific Concepts (CoreSCs). These include: Hypothesis, Motivation, Goal, Object, Background, Method, Experiment, Model, Observation, Result and Conclusion. CoreSCs provide the structure and context to all statements and relations within an article and their automatic recognition can greatly facilitate biomedical information extraction by characterizing the different types of facts, hypotheses and evidence available in a scientific publication. RESULTS: We have trained and compared machine learning classifiers (support vector machines and conditional random fields) on a corpus of 265 full articles in biochemistry and chemistry to automatically recognize CoreSCs. We have evaluated our automatic classifications against a manually annotated gold standard, and have achieved promising accuracies with 'Experiment', 'Background' and 'Model' being the categories with the highest F1-scores (76%, 62% and 53%, respectively). We have analysed the task of CoreSC annotation both from a sentence classification as well as sequence labelling perspective and we present a detailed feature evaluation. The most discriminative features are local sentence features such as unigrams, bigrams and grammatical dependencies while features encoding the document structure, such as section headings, also play an important role for some of the categories. We discuss the usefulness of automatically generated CoreSCs in two biomedical applications as well as work in progress. AVAILABILITY: A web-based tool for the automatic annotation of articles with CoreSCs and corresponding documentation is available online at http://www.sapientaproject.com/software http://www.sapientaproject.com also contains detailed information pertaining to CoreSC annotation and links to annotation guidelines as well as a corpus of manually annotated articles, which served as our training data. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Ontologies are essential in biomedical research due to their ability to semantically integrate content from different scientific databases and resources. Their application improves capabilities for querying and mining biological knowledge. An increasing number of ontologies is being developed for this purpose, and considerable effort is invested into formally defining them in order to represent their semantics explicitly. However, current biomedical ontologies do not facilitate data integration and interoperability yet, since reasoning over these ontologies is very complex and cannot be performed efficiently or is even impossible. We propose the use of less expressive subsets of ontology representation languages to enable efficient reasoning and achieve the goal of genuine interoperability between ontologies. RESULTS: We present and evaluate EL Vira, a framework that transforms OWL ontologies into the OWL EL subset, thereby enabling the use of tractable reasoning. We illustrate which OWL constructs and inferences are kept and lost following the conversion and demonstrate the performance gain of reasoning indicated by the significant reduction of processing time. We applied EL Vira to the open biomedical ontologies and provide a repository of ontologies resulting from this conversion. EL Vira creates a common layer of ontological interoperability that, for the first time, enables the creation of software solutions that can employ biomedical ontologies to perform inferences and answer complex queries to support scientific analyses. AVAILABILITY AND IMPLEMENTATION: The EL Vira software is available from http://el-vira.googlecode.com and converted OBO ontologies and their mappings are available from http://bioonto.gen.cam.ac.uk/el-ont.

BACKGROUND: Due to the rapidly expanding body of biomedical literature, biologists require increasingly sophisticated and efficient systems to help them to search for relevant information. Such systems should account for the multiple written variants used to represent biomedical concepts, and allow the user to search for specific pieces of knowledge (or events) involving these concepts, e.g., protein-protein interactions. Such functionality requires access to detailed information about words used in the biomedical literature. Existing databases and ontologies often have a specific focus and are oriented towards human use. Consequently, biological knowledge is dispersed amongst many resources, which often do not attempt to account for the large and frequently changing set of variants that appear in the literature. Additionally, such resources typically do not provide information about how terms relate to each other in texts to describe events. RESULTS: This article provides an overview of the design, construction and evaluation of a large-scale lexical and conceptual resource for the biomedical domain, the BioLexicon. The resource can be exploited by text mining tools at several levels, e.g., part-of-speech tagging, recognition of biomedical entities, and the extraction of events in which they are involved. As such, the BioLexicon must account for real usage of words in biomedical texts. In particular, the BioLexicon gathers together different types of terms from several existing data resources into a single, unified repository, and augments them with new term variants automatically extracted from biomedical literature. Extraction of events is facilitated through the inclusion of biologically pertinent verbs (around which events are typically organized) together with information about typical patterns of grammatical and semantic behaviour, which are acquired from domain-specific texts. In order to foster interoperability, the BioLexicon is modelled using the Lexical Markup Framework, an ISO standard. CONCLUSIONS: The BioLexicon contains over 2.2 M lexical entries and over 1.8 M terminological variants, as well as over 3.3 M semantic relations, including over 2 M synonymy relations. Its exploitation can benefit both application developers and users. We demonstrate some such benefits by describing integration of the resource into a number of different tools, and evaluating improvements in performance that this can bring.

MOTIVATION: Phenotypic information is important for the analysis of the molecular mechanisms underlying disease. A formal ontological representation of phenotypic information can help to identify, interpret and infer phenotypic traits based on experimental findings. The methods that are currently used to represent data and information about phenotypes fail to make the semantics of the phenotypic trait explicit and do not interoperate with ontologies of anatomy and other domains. Therefore, valuable resources for the analysis of phenotype studies remain unconnected and inaccessible to automated analysis and reasoning. RESULTS: We provide a framework to formalize phenotypic descriptions and make their semantics explicit. Based on this formalization, we provide the means to integrate phenotypic descriptions with ontologies of other domains, in particular anatomy and physiology. We demonstrate how our framework leads to the capability to represent disease phenotypes, perform powerful queries that were not possible before and infer additional knowledge. AVAILABILITY: http://bioonto.de/pmwiki.php/Main/PheneOntology.

MOTIVATION: The automatic analysis of scientific literature can support authors in writing their manuscripts. IMPLEMENTATION: PaperMaker is a novel IT solution that receives a scientific manuscript via a Web interface, automatically analyses the publication, evaluates consistency parameters and interactively delivers feedback to the author. It analyses the proper use of acronyms and their definitions, and the use of specialized terminology. It provides Gene Ontology (GO) and Medline Subject Headings (MeSH) categorization of text passages, the retrieval of relevant publications from public scientific literature repositories, and the identification of missing or unused references. RESULT: The author receives a summary of findings, the manuscript in its corrected form and a digital abstract containing the GO and MeSH annotations in the NLM/PubMed format. AVAILABILITY: http://www.ebi.ac.uk/Rebholz-srv/PaperMaker.

BACKGROUND: most biomedical ontologies are represented in the OBO Flatfile Format, which is an easy-to-use graph-based ontology language. The semantics of the OBO Flatfile Format 1.2 enforces a strict predetermined interpretation of relationship statements between classes. It does not allow flexible specifications that provide better approximations of the intuitive understanding of the considered relations. If relations cannot be accurately expressed then ontologies built upon them may contain false assertions and hence lead to false inferences. Ontologies in the OBO Foundry must formalize the semantics of relations according to the OBO Relationship Ontology (RO). Therefore, being able to accurately express the intended meaning of relations is of crucial importance. Since the Web Ontology Language (OWL) is an expressive language with a formal semantics, it is suitable to de ne the meaning of relations accurately. RESULTS: we developed a method to provide definition patterns for relations between classes using OWL and describe a novel implementation of the RO based on this method. We implemented our extension in software that converts ontologies in the OBO Flatfile Format to OWL, and also provide a prototype to extract relational patterns from OWL ontologies using automated reasoning. The conversion software is freely available at http://bioonto.de/obo2owl, and can be accessed via a web interface. CONCLUSIONS: explicitly defining relations permits their use in reasoning software and leads to a more flexible and powerful way of representing biomedical ontologies. Using the extended langua0067e and semantics avoids several mistakes commonly made in formalizing biomedical ontologies, and can be used to automatically detect inconsistencies. The use of our method enables the use of graph-based ontologies in OWL, and makes complex OWL ontologies accessible in a graph-based form. Thereby, our method provides the means to gradually move the representation of biomedical ontologies into formal knowledge representation languages that incorporates an explicit semantics. Our method facilitates the use of OWL-based software in the back-end while ontology curators may continue to develop ontologies with an OBO-style front-end.

[Abstract Not Available]

MOTIVATION: Controlled vocabularies such as the Medical Subject Headings (MeSH) thesaurus and the Gene Ontology (GO) provide an efficient way of accessing and organizing biomedical information by reducing the ambiguity inherent to free-text data. Different methods of automating the assignment of MeSH concepts have been proposed to replace manual annotation, but they are either limited to a small subset of MeSH or have only been compared with a limited number of other systems. RESULTS: We compare the performance of six MeSH classification systems [MetaMap, EAGL, a language and a vector space model-based approach, a K-Nearest Neighbor (KNN) approach and MTI] in terms of reproducing and complementing manual MeSH annotations. A KNN system clearly outperforms the other published approaches and scales well with large amounts of text using the full MeSH thesaurus. Our measurements demonstrate to what extent manual MeSH annotations can be reproduced and how they can be complemented by automatic annotations. We also show that a statistically significant improvement can be obtained in information retrieval (IR) when the text of a user's query is automatically annotated with MeSH concepts, compared to using the original textual query alone. CONCLUSIONS: The annotation of biomedical texts using controlled vocabularies such as MeSH can be automated to improve text-only IR. Furthermore, the automatic MeSH annotation system we propose is highly scalable and it generates improvements in IR comparable with those observed for manual annotations.

Abstract Contact: [email protected]; [email protected] As developers and primary users of MTI and MetaMap, Névéol et al. made a number of interesting comments on our recent publication in Bioinformatics. However, some of the results and conclusions found in the reply seem premature and lack proper clarification.

This paper is intended to explore how to use terminological resources for ontology engineering. Nowadays there are several biomedical ontologies describing overlapping domains, but there is not a clear correspondence between the concepts that are supposed to be equivalent or just similar. These resources are quite precious but their integration and further development are expensive. Terminologies may support the ontological development in several stages of the lifecycle of the ontology; e.g. ontology integration. In this paper we investigate the use of terminological resources during the ontology lifecycle. We claim that the proper creation and use of a shared thesaurus is a cornerstone for the successful application of the Semantic Web technology within life sciences. Moreover, we have applied our approach to a real scenario, the Health-e-Child (HeC) project, and we have evaluated the impact of filtering and re-organizing several resources. As a result, we have created a reference thesaurus for this project, named HeCTh.

BACKGROUND: A protein annotation database, such as the Universal Protein Resource knowledge base (UniProtKb), is a valuable resource for the validation and interpretation of predicted 3D structure patterns in proteins. Existing studies have focussed on point mutation extraction methods from biomedical literature which can be used to support the time consuming work of manual database curation. However, these methods were limited to point mutation extraction and do not extract features for the annotation of proteins at the residue level. RESULTS: This work introduces a system that identifies protein residues in MEDLINE abstracts and annotates them with features extracted from the context written in the surrounding text. MEDLINE abstract texts have been processed to identify protein mentions in combination with taxonomic species and protein residues (F1-measure 0.52). The identified protein-species-residue triplets have been validated and benchmarked against reference data resources (UniProtKb, average F1-measure of 0.54). Then, contextual features were extracted through shallow and deep parsing and the features have been classified into predefined categories (F1-measure ranges from 0.15 to 0.67). Furthermore, the feature sets have been aligned with annotation types in UniProtKb to assess the relevance of the annotations for ongoing curation projects. Altogether, the annotations have been assessed automatically and manually against reference data resources. CONCLUSION: This work proposes a solution for the automatic extraction of functional annotation for protein residues from biomedical articles. The presented approach is an extension to other existing systems in that a wider range of residue entities are considered and that features of residues are extracted as annotations.

Biomedical researchers have to efficiently explore the scientific literature, keeping the focus on their research. This goal can only be achieved if the available means for accessing the literature meet the researchers' retrieval needs and if they understand how the tools filter the perpetually increasing number of documents. We have examined existing web-based services for information retrieval in order to give users guidance to improve their everyday practice of literature analysis. We propose two dimensions along which the services may be categorized: categories of input and output formats; and categories of behavioural usage. The categorization would be helpful for biologists to understand the differences in the input and output formats and the tasks they fulfil in information-retrieval activities. Also, they may inspire future bioinformaticians to further innovative development in this field.

UNLABELLED: Search engines running on MEDLINE abstracts have been widely used by biologists to find publications that are related to their research. The existing search engines such as PubMed, however, have limitations when applied for the task of seeking textual evidence of relations between given concepts. The limitations are mainly due to the problem that the search engines do not effectively deal with multi-term queries which may imply semantic relations between the terms. To address this problem, we present MedEvi, a novel search engine that imposes positional restriction on occurrences matching multi-term queries, based on the observation that terms with semantic relations which are explicitly stated in text are not found too far from each other. MedEvi further identifies additional keywords of biological and statistical significance from local context of matching occurrences in order to help users reformulate their queries for better results. AVAILABILITY: http://www.ebi.ac.uk/tc-test/textmining/medevi/

MOTIVATION: Text-mining (TM) solutions are developing into efficient services to researchers in the biomedical research community. Such solutions have to scale with the growing number and size of resources (e.g. available controlled vocabularies), with the amount of literature to be processed (e.g. about 17 million documents in PubMed) and with the demands of the user community (e.g. different methods for fact extraction). These demands motivated the development of a server-based solution for literature analysis. Whatizit is a suite of modules that analyse text for contained information, e.g. any scientific publication or Medline abstracts. Special modules identify terms and then link them to the corresponding entries in bioinformatics databases such as UniProtKb/Swiss-Prot data entries and gene ontology concepts. Other modules identify a set of selected annotation types like the set produced by the EBIMed analysis pipeline for proteins. In the case of Medline abstracts, Whatizit offers access to EBI's in-house installation via PMID or term query. For large quantities of the user's own text, the server can be operated in a streaming mode (http://www.ebi.ac.uk/webservices/whatizit).

BACKGROUND: Functional annotation of proteins remains a challenging task. Currently the scientific literature serves as the main source for yet uncurated functional annotations, but curation work is slow and expensive. Automatic techniques that support this work are still lacking reliability. We developed a method to identify conserved protein interaction graphs and to predict missing protein functions from orthologs in these graphs. To enhance the precision of the results, we furthermore implemented a procedure that validates all predictions based on findings reported in the literature. RESULTS: Using this procedure, more than 80% of the GO annotations for proteins with highly conserved orthologs that are available in UniProtKb/Swiss-Prot could be verified automatically. For a subset of proteins we predicted new GO annotations that were not available in UniProtKb/Swiss-Prot. All predictions were correct (100% precision) according to the verifications from a trained curator. CONCLUSION: Our method of integrating CCSs and literature mining is thus a highly reliable approach to predict GO annotations for weakly characterized proteins with orthologs.

BACKGROUND: In recent years, the recognition of semantic types from the biomedical scientific literature has been focused on named entities like protein and gene names (PGNs) and gene ontology terms (GO terms). Other semantic types like diseases have not received the same level of attention. Different solutions have been proposed to identify disease named entities in the scientific literature. While matching the terminology with language patterns suffers from low recall (e.g., Whatizit) other solutions make use of morpho-syntactic features to better cover the full scope of terminological variability (e.g., MetaMap). Currently, MetaMap that is provided from the National Library of Medicine (NLM) is the state of the art solution for the annotation of concepts from UMLS (Unified Medical Language System) in the literature. Nonetheless, its performance has not yet been assessed on an annotated corpus. In addition, little effort has been invested so far to generate an annotated dataset that links disease entities in text to disease entries in a database, thesaurus or ontology and that could serve as a gold standard to benchmark text mining solutions. RESULTS: As part of our research work, we have taken a corpus that has been delivered in the past for the identification of associations of genes to diseases based on the UMLS Metathesaurus and we have reprocessed and re-annotated the corpus. We have gathered annotations for disease entities from two curators, analyzed their disagreement (0.51 in the kappa-statistic) and composed a single annotated corpus for public use. Thereafter, three solutions for disease named entity recognition including MetaMap have been applied to the corpus to automatically annotate it with UMLS Metathesaurus concepts. The resulting annotations have been benchmarked to compare their performance. CONCLUSIONS: The annotated corpus is publicly available at ftp://ftp.ebi.ac.uk/pub/software/textmining/corpora/diseases and can serve as a benchmark to other systems. In addition, we found that dictionary look-up already provides competitive results indicating that the use of disease terminology is highly standardized throughout the terminologies and the literature. MetaMap generates precise results at the expense of insufficient recall while our statistical method obtains better recall at a lower precision rate. Even better results in terms of precision are achieved by combining at least two of the three methods leading, but this approach again lowers recall. Altogether, our analysis gives a better understanding of the complexity of disease annotations in the literature. MetaMap and the dictionary based approach are available through the Whatizit web service infrastructure (Rebholz-Schuhmann D, Arregui M, Gaudan S, Kirsch H, Jimeno A: Text processing through Web services: Calling Whatizit. Bioinformatics 2008, 24:296-298).

BACKGROUND: Many bioinformatics applications rely on controlled vocabularies or ontologies to consistently interpret and seamlessly integrate information scattered across public resources. Experimental data sets from metabolomics studies need to be integrated with one another, but also with data produced by other types of omics studies in the spirit of systems biology, hence the pressing need for vocabularies and ontologies in metabolomics. However, it is time-consuming and non trivial to construct these resources manually. RESULTS: We describe a methodology for rapid development of controlled vocabularies, a study originally motivated by the needs for vocabularies describing metabolomics technologies. We present case studies involving two controlled vocabularies (for nuclear magnetic resonance spectroscopy and gas chromatography) whose development is currently underway as part of the Metabolomics Standards Initiative. The initial vocabularies were compiled manually, providing a total of 243 and 152 terms. A total of 5,699 and 2,612 new terms were acquired automatically from the literature. The analysis of the results showed that full-text articles (especially the Materials and Methods sections) are the major source of technology-specific terms as opposed to paper abstracts. CONCLUSIONS: We suggest a text mining method for efficient corpus-based term acquisition as a way of rapidly expanding a set of controlled vocabularies with the terms used in the scientific literature. We adopted an integrative approach, combining relatively generic software and data resources for time- and cost-effective development of a text mining tool for expansion of controlled vocabularies across various domains, as a practical alternative to both manual term collection and tailor-made named entity recognition methods.

UNLABELLED: To allow efficient and systematic retrieval of statements from Medline we have developed EBIMed, a service that combines document retrieval with co-occurrence-based analysis of Medline abstracts. Upon keyword query, EBIMed retrieves the abstracts from EMBL-EBI's installation of Medline and filters for sentences that contain biomedical terminology maintained in public bioinformatics resources. The extracted sentences and terminology are used to generate an overview table on proteins, Gene Ontology (GO) annotations, drugs and species used in the same biological context. All terms in retrieved abstracts and extracted sentences are linked to their entries in biomedical databases. We assessed the quality of the identification of terms and relations in the retrieved sentences. More than 90% of the protein names found indeed represented a protein. According to the analysis of four protein-protein pairs from the Wnt pathway we estimated that 37% of the statements containing such a pair mentioned a meaningful interaction and clarified the interaction of Dkk with LRP. We conclude that EBIMed improves access to information where proteins and drugs are involved in the same biological process, e.g. statements with GO annotations of proteins, protein-protein interactions and effects of drugs on proteins. AVAILABILITY: Available at http://www.ebi.ac.uk/Rebholz-srv/ebimed

BACKGROUND: The SYMBIOmatics Specific Support Action (SSA) is "an information gathering and dissemination activity" that seeks "to identify synergies between the bioinformatics and the medical informatics" domain to improve collaborative progress between both domains (ref. to http://www.symbiomatics.org). As part of the project experts in both research fields will be identified and approached through a survey. To provide input to the survey, the scientific literature was analysed to extract topics relevant to both medical informatics and bioinformatics. RESULTS: This paper presents results of a systematic analysis of the scientific literature from medical informatics research and bioinformatics research. In the analysis pairs of words (bigrams) from the leading bioinformatics and medical informatics journals have been used as indication of existing and emerging technologies and topics over the period 2000-2005 ("recent") and 1990-1990 ("past"). We identified emerging topics that were equally important to bioinformatics and medical informatics in recent years such as microarray experiments, ontologies, open source, text mining and support vector machines. Emerging topics that evolved only in bioinformatics were system biology, protein interaction networks and statistical methods for microarray analyses, whereas emerging topics in medical informatics were grid technology and tissue microarrays. CONCLUSION: We conclude that although both fields have their own specific domains of interest, they share common technological developments that tend to be initiated by new developments in biotechnology and computer science.

This paper reports on an analysis of the bioinformatics and medical informatics literature with the objective to identify upcoming trends that are shared among both research fields to derive benefits from potential collaborative initiatives for their future. Our results present the main characteristics of the two fields and show that these domains are still relatively separated.

MOTIVATION: Biological literature contains many abbreviations with one particular sense in each document. However, most abbreviations do not have a unique sense across the literature. Furthermore, many documents do not contain the long forms of the abbreviations. Resolving an abbreviation in a document consists of retrieving its sense in use. Abbreviation resolution improves accuracy of document retrieval engines and of information extraction systems. RESULTS: We combine an automatic analysis of Medline abstracts and linguistic methods to build a dictionary of abbreviation/sense pairs. The dictionary is used for the resolution of abbreviations occurring with their long forms. Ambiguous global abbreviations are resolved using support vector machines that have been trained on the context of each instance of the abbreviation/sense pairs, previously extracted for the dictionary set-up. The system disambiguates abbreviations with a precision of 98.9% for a recall of 98.2% (98.5% accuracy). This performance is superior in comparison with previously reported research work. AVAILABILITY: The abbreviation resolution module is available at http://www.ebi.ac.uk/Rebholz/software.html.

Modern tomography technologies like CT or MRI produce high-quality scans of the human anatomy. While conventional computer-aided image analysis falls back upon editing tomograms layer by layer, virtual environments offer enhanced visualization, image analysis and manipulation of the three-dimensional data sets. In this paper, the application of multimodal, user-oriented human–computer interaction is presented, facilitating and accelerating work with the tomographical data of individual patients. Hand gesture recognition is a major component of the interface, completed by speech understanding and further units like a 6-DOF mouse or acoustic feedback. Three-dimensional image segmentation, virtual bronchoscopy and virtual angioscopy are typical examples that illustrate the benefits of virtual environments for the realm of medicine.