Search

ObjectiveTo investigate whether alternative statistical approaches can improve daily aberration detection using syndromic surveillance in England.IntroductionSyndromic surveillance involves monitoring big health datasets to provide early warning of threats to public health. Public health authorities use statistical detection algorithms to interrogate these datasets for aberrations that are indicative of emerging threats. The algorithm currently in use at Public Health England (PHE) for syndromic surveillance is the ‘rising activity, multi-level mixed effects, indicator emphasis’ (RAMMIE) method (Morbey et al, 2015), which fits a mixed model to counts of syndromes on a daily basis. This research checks whether the RAMMIE method works across a range of public health scenarios and how it compares to alternative methods.MethodsFor this purpose, we compare RAMMIE to the improved quasi-Poisson regression-based approach (Noufaily et al, 2013), currently implemented at PHE for weekly infectious disease laboratory surveillance, and to the Early Aberration Reporting System (EARS) method (Rossi et al, 1999), which is used for syndromic surveillance aberration detection in many other countries. We model syndromic datasets, capturing real data aspects such as long-term trends, seasonality, public holidays, and day-of-the-week effects, with or without added outbreaks. Then, we compute the sensitivity and specificity to compare how well each of the algorithms detects synthetic outbreaks to provide recommendations for the most suitable statistical methods to use during different public health scenarios.ResultsPreliminary results suggest all methods provide high sensitivity and specificity, with the (Noufaily et al, 2013) approach having the highest sensitivity and specificity. We showed that for syndromes with long-term increasing trends, RAMMIE required modificaiton to prevent excess false alarms. Also, our study suggests further work is needed to fully account for public holidays and day-of-the-week effects.ConclusionsOur study will provide recommendations for which algorithm is most effective for PHE's syndromic surveillance for a range of different syndromes. Furthermore our work to generate standardised synthetic syndromic datasets and a range of outbreaks can be used for future evaluations in England and elsewhere.ReferencesNoufaily, A., Enki, D. G., Farrington, C. P., Garthwaite, P., Andrews, N. and Charlett, A. (2013). An Improved Algorithm for Outbreak Detection in Multiple Surveillance Systems. Statistics in Medicine, 32(7), 1206-1222.Morbey, R. A., Elliot, A. J., Charlett, A., Verlander, A. Q, Andrews, N. and Smith, G. (2013). The application of a novel ‘rising activity, multi-level mixed effects, indicator emphasis’ (RAMMIE) method for syndromic surveillance in England, Bioinformatics, 31(22), 3660-3665.Rossi, G, Lampugnani, L, Marchi, M. (1999), An approximate CUSUM procedure for surveillance of health events. Statistics in Medicine, 18, 2111–2122

Motivation Automatic biomedical named entity recognition (BioNER) is a key task in biomedical information extraction. For some time, state-of-the-art BioNER has been dominated by machine learning methods, particularly conditional random fields (CRFs), with a recent focus on deep learning. However, recent work has suggested that the high performance of CRFs for BioNER may not generalize to corpora other than the one it was trained on. In our analysis, we find that a popular deep learning-based approach to BioNER, known as bidirectional long short-term memory network-conditional random field (BiLSTM-CRF), is correspondingly poor at generalizing. To address this, we evaluate three modifications of BiLSTM-CRF for BioNER to improve generalization: improved regularization via variational dropout, transfer learning and multi-task learning. Results We measure the effect that each strategy has when training/testing on the same corpus (‘in-corpus’ performance) and when training on one corpus and evaluating on another (‘out-of-corpus’ performance), our measure of the model’s ability to generalize. We found that variational dropout improves out-of-corpus performance by an average of 4.62%, transfer learning by 6.48% and multi-task learning by 8.42%. The maximal increase we identified combines multi-task learning and variational dropout, which boosts out-of-corpus performance by 10.75%. Furthermore, we make available a new open-source tool, called Saber that implements our best BioNER models. Availability and implementation Source code for our biomedical IE tool is available at https://github.com/BaderLab/saber. Corpora and other resources used in this study are available at https://github.com/BaderLab/Towards-reliable-BioNER. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation: Many researchers with domain expertise are unable to easily apply machine learning to their bioinformatics data due to a lack of machine learning and/or coding expertise. Methods that have been proposed thus far to automate machine learning mostly require programming experience as well as expert knowledge to tune and apply the algorithms correctly. Here, we study a method of automating biomedical data science using a web-based platform that uses AI to recommend model choices and conduct experiments. We have two goals in mind: first, to make it easy to construct sophisticated models of biomedical processes; and second, to provide a fully automated AI agent that can choose and conduct promising experiments for the user, based on the user's experiments as well as prior knowledge. To validate this framework, we experiment with hundreds of classification problems, comparing to state-of-the-art, automated approaches. Finally, we use this tool to develop predictive models of septic shock in critical care patients. Results: We find that matrix factorization-based recommendation systems outperform meta-learning methods for automating machine learning. This result mirrors the results of earlier recommender systems research in other domains. The proposed AI is competitive with state-of-the-art automated machine learning methods in terms of choosing optimal algorithm configurations for datasets. In our application to prediction of septic shock, the AI-driven analysis produces a competent machine learning model (AUROC 0.85 +/- 0.02) that performs on par with state-of-the-art deep learning results for this task, with much less computational effort., Comment: 17 pages, 8 figures. this version fixes link to pennai in abstract

Motivation Analysis toolkits for shotgun metagenomic data achieve strain-level characterization of complex microbial communities by capturing intra-species gene content variation. Yet, these tools are hampered by the extent of reference genomes that are far from covering all microbial variability, as many species are still not sequenced or have only few strains available. Binning co-abundant genes obtained from de novo assembly is a powerful reference-free technique to discover and reconstitute gene repertoire of microbial species. While current methods accurately identify species core parts, they miss many accessory genes or split them into small gene groups that remain unassociated to core clusters. Results We introduce MSPminer, a computationally efficient software tool that reconstitutes Metagenomic Species Pan-genomes (MSPs) by binning co-abundant genes across metagenomic samples. MSPminer relies on a new robust measure of proportionality coupled with an empirical classifier to group and distinguish not only species core genes but accessory genes also. Applied to a large scale metagenomic dataset, MSPminer successfully delineates in a few hours the gene repertoires of 1661 microbial species with similar specificity and higher sensitivity than existing tools. The taxonomic annotation of MSPs reveals microorganisms hitherto unknown and brings coherence in the nomenclature of the species of the human gut microbiota. The provided MSPs can be readily used for taxonomic profiling and biomarkers discovery in human gut metagenomic samples. In addition, MSPminer can be applied on gene count tables from other ecosystems to perform similar analyses. Availability and implementation The binary is freely available for non-commercial users at www.enterome.com/downloads. Supplementary information Supplementary data are available at Bioinformatics online.

Graph embedding learning that aims to automatically learn low-dimensional node representations, has drawn increasing attention in recent years. To date, most recent graph embedding methods are evaluated on social and information networks and are not comprehensively studied on biomedical networks under systematic experiments and analyses. On the other hand, for a variety of biomedical network analysis tasks, traditional techniques such as matrix factorization (which can be seen as a type of graph embedding methods) have shown promising results, and hence there is a need to systematically evaluate the more recent graph embedding methods (e.g. random walk-based and neural network-based) in terms of their usability and potential to further the state-of-the-art. We select 11 representative graph embedding methods and conduct a systematic comparison on 3 important biomedical link prediction tasks: drug-disease association (DDA) prediction, drug-drug interaction (DDI) prediction, protein-protein interaction (PPI) prediction; and 2 node classification tasks: medical term semantic type classification, protein function prediction. Our experimental results demonstrate that the recent graph embedding methods achieve promising results and deserve more attention in the future biomedical graph analysis. Compared with three state-of-the-art methods for DDAs, DDIs and protein function predictions, the recent graph embedding methods achieve competitive performance without using any biological features and the learned embeddings can be treated as complementary representations for the biological features. By summarizing the experimental results, we provide general guidelines for properly selecting graph embedding methods and setting their hyper-parameters for different biomedical tasks., Comment: Published in Bioinformatics

Motivation: Detecting drug-drug interaction (DDI) has become a vital part of public health safety. Therefore, using text mining techniques to extract DDIs from biomedical literature has received great attentions. However, this research is still at an early stage and its performance has much room to improve. Results: In this article, we present a syntax convolutional neural network (SCNN) based DDI extraction method. In this method, a novel word embedding, syntax word embedding, is proposed to employ the syntactic information of a sentence. Then the position and part of speech features are introduced to extend the embedding of each word. Later, auto-encoder is introduced to encode the traditional bag-of-words feature (sparse 0–1 vector) as the dense real value vector. Finally, a combination of embedding-based convolutional features and traditional features are fed to the softmax classifier to extract DDIs from biomedical literature. Experimental results on the DDIExtraction 2013 corpus show that SCNN obtains a better performance (an F-score of 0.686) than other state-of-the-art methods. Availability and Implementation: The source code is available for academic use at http://202.118.75.18:8080/DDI/SCNN-DDI.zip. Contact: yangzh@dlut.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online.

Motivation: Developing targeted therapeutics and identifying biomarkers relies on large amounts of research participant data. Beyond human DNA, scientists now investigate the DNA of micro-organisms inhabiting the human body. Recent work shows that an individual’s collection of microbial DNA consistently identifies that person and could be used to link a real-world identity to a sensitive attribute in a research dataset. Unfortunately, the current suite of DNA-specific privacy-preserving analysis tools does not meet the requirements for microbiome sequencing studies. Results: To address privacy concerns around microbiome sequencing, we implement metagenomic analyses using secure computation. Our implementation allows comparative analysis over combined data without revealing the feature counts for any individual sample. We focus on three analyses and perform an evaluation on datasets currently used by the microbiome research community. We use our implementation to simulate sharing data between four policy-domains. Additionally, we describe an application of our implementation for patients to combine data that allows drug developers to query against and compensate patients for the analysis. Availability and implementation: The software is freely available for download at: http://cbcb.umd.edu/∼hcorrada/projects/secureseq.html Supplementary information: Supplementary data are available at Bioinformatics online. Contact: hcorrada@umiacs.umd.edu

Motivation: RNA binding proteins (RBPs) play important roles in post-transcriptional control of gene expression, including splicing, transport, polyadenylation and RNA stability. To model protein–RNA interactions by considering all available sources of information, it is necessary to integrate the rapidly growing RBP experimental data with the latest genome annotation, gene function, RNA sequence and structure. Such integration is possible by matrix factorization, where current approaches have an undesired tendency to identify only a small number of the strongest patterns with overlapping features. Because protein–RNA interactions are orchestrated by multiple factors, methods that identify discriminative patterns of varying strengths are needed. Results: We have developed an integrative orthogonality-regularized nonnegative matrix factorization (iONMF) to integrate multiple data sources and discover non-overlapping, class-specific RNA binding patterns of varying strengths. The orthogonality constraint halves the effective size of the factor model and outperforms other NMF models in predicting RBP interaction sites on RNA. We have integrated the largest data compendium to date, which includes 31 CLIP experiments on 19 RBPs involved in splicing (such as hnRNPs, U2AF2, ELAVL1, TDP-43 and FUS) and processing of 3’UTR (Ago, IGF2BP). We show that the integration of multiple data sources improves the predictive accuracy of retrieval of RNA binding sites. In our study the key predictive factors of protein–RNA interactions were the position of RNA structure and sequence motifs, RBP co-binding and gene region type. We report on a number of protein-specific patterns, many of which are consistent with experimentally determined properties of RBPs. Availability and implementation: The iONMF implementation and example datasets are available at https://github.com/mstrazar/ionmf. Contact: tomaz.curk@fri.uni-lj.si Supplementary information: Supplementary data are available at Bioinformatics online.

Summary: heatmaply is an R package for easily creating interactive cluster heatmaps that can be shared online as a stand-alone HTML file. Interactivity includes a tooltip display of values when hovering over cells, as well as the ability to zoom in to specific sections of the figure from the data matrix, the side dendrograms, or annotated labels. Thanks to the synergistic relationship between heatmaply and other R packages, the user is empowered by a refined control over the statistical and visual aspects of the heatmap layout. Availability and implementation: The heatmaply package is available under the GPL-2 Open Source license. It comes with a detailed vignette, and is freely available from: http://cran.r-project.org/package=heatmaply. Supplementary information: Supplementary data are available at Bioinformatics online., Comment: 3 pages

MOTIVATION: Psychiatric disorders have a great impact on morbidity and mortality. Genotype-phenotype resources for psychiatric diseases are key to enable the translation of research findings to a better care of patients. PsyGeNET is a knowledge resource on psychiatric diseases and their genes, developed by text mining and curated by domain experts. RESULTS: We present psygenet2r, an R package that contains a variety of functions for leveraging PsyGeNET database and facilitating its analysis and interpretation. The package offers different types of queries to the database along with variety of analysis and visualization tools, including the study of the anatomical structures in which the genes are expressed and gaining insight of gene's molecular function. Psygenet2r is especially suited for network medicine analysis of psychiatric disorders. AVAILABILITY AND IMPLEMENTATION: The package is implemented in R and is available under MIT license from Bioconductor (http://bioconductor.org/packages/release/bioc/html/psygenet2r.html). This work was supported by ISCIII-FEDER [PI13/00082, CP10/00524, CPII16/00026], MICINN [MTM2015-68140-R], IMI-JU under grants agreements no. 115191 (Open PHACTS), no. 115372 (EMIF), no. 115735 (iPiE), resources of which are composed of financial contribution from the EU-FP7 [FP7/2007–2013] and EFPIA companies in kind contribution, and the EU H2020 Programme 2014–2020 under grant agreements no. 634143 (MedBioinformatics) and no. 676559 (Elixir-Excelerate). The Research Programme on Biomedical Informatics (GRIB) is a member of ELIXIR-ES and the Spanish National Bioinformatics Institute (INB), PRB2-ISCIII and is supported by grant PT13/0001/0023, of the PE I + D+i 2013-2016, funded by ISCIII and FEDER. A.G.S. acknowledges financial support from the Spanish Ministry of Economy and Competitiveness, through the ‘María de Maeztu’ Programme for Units of Excellence in R&D [MDM-2014-0370].

Summary We introduce matter, an R package for direct interactions with larger-than-memory datasets, stored in an arbitrary number of files of any size. matter is primarily designed for datasets in new and rapidly evolving file formats, which may lack extensive software support. matter enables a wide variety of data exploration and manipulation steps and is extensible to many bioinformatics applications. It supports reproducible research by minimizing the need of converting and storing data in multiple formats. We illustrate the performance of matter in conjunction with the Bioconductor package Cardinal for analysis of high-resolution, high-throughput mass spectrometry imaging experiments. Availability and implementation The package, vignettes and examples of applications in several areas of bioinformatics are available open-source at www.bioconductor.org under the Artistic-2.0 license.

Summary FQC is software that facilitates quality control of FASTQ files by carrying out a QC protocol using FastQC, parsing results, and aggregating quality metrics into an interactive dashboard designed to richly summarize individual sequencing runs. The dashboard groups samples in dropdowns for navigation among the data sets, utilizes human-readable configuration files to manipulate the pages and tabs, and is extensible with CSV data. Availability and implementation FQC is implemented in Python 3 and Javascript, and is maintained under an MIT license. Documentation and source code is available at: https://github.com/pnnl/fqc.

Timely identification of Mycobacterium tuberculosis (MTB) resistance to existing drugs is vital to decrease mortality and prevent the amplification of existing antibiotic resistance. Machine learning methods have been widely applied for timely predicting resistance of MTB given a specific drug and identifying resistance markers. However, they have been not validated on a large cohort of MTB samples from multi-centers across the world in terms of resistance prediction and resistance marker identification. Several machine learning classifiers and linear dimension reduction techniques were developed and compared for a cohort of 13 402 isolates collected from 16 countries across 6 continents and tested 11 drugs. Results Compared to conventional molecular diagnostic test, area under curve of the best machine learning classifier increased for all drugs especially by 23.11%, 15.22% and 10.14% for pyrazinamide, ciprofloxacin and ofloxacin, respectively (P Availability and implementation The source code can be found at http://www.robots.ox.ac.uk/ davidc/code.php Supplementary information Supplementary data are available at Bioinformatics online.

Motivation Prognostic models are widely used in clinical decision-making, such as risk stratification and tailoring treatment strategies, with the aim to improve patient outcomes while reducing overall healthcare costs. While prognostic models have been adopted into clinical use, benchmarking their performance has been difficult due to lack of open clinical datasets. The recent DREAM 9.5 Prostate Cancer Challenge carried out an extensive benchmarking of prognostic models for metastatic Castration-Resistant Prostate Cancer (mCRPC), based on multiple cohorts of open clinical trial data. Results We make available an open-source implementation of the top-performing model, ePCR, along with an extended toolbox for its further re-use and development, and demonstrate how to best apply the implemented model to real-world data cohorts of advanced prostate cancer patients. Availability and implementation The open-source R-package ePCR and its reference documentation are available at the Central R Archive Network (CRAN): https://CRAN.R-project.org/package=ePCR. R-vignette provides step-by-step examples for the ePCR usage. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation Information extraction by mining the scientific literature is key to uncovering relations between biomedical entities. Most existing approaches based on natural language processing extract relations from single sentence-level co-mentions, ignoring co-occurrence statistics over the whole corpus. Existing approaches counting entity co-occurrences ignore the textual context of each co-occurrence. Results We propose a novel corpus-wide co-occurrence scoring approach to relation extraction that takes the textual context of each co-mention into account. Our method, called CoCoScore, scores the certainty of stating an association for each sentence that co-mentions two entities. CoCoScore is trained using distant supervision based on a gold-standard set of associations between entities of interest. Instead of requiring a manually annotated training corpus, co-mentions are labeled as positives/negatives according to their presence/absence in the gold standard. We show that CoCoScore outperforms previous approaches in identifying human disease–gene and tissue–gene associations as well as in identifying physical and functional protein–protein associations in different species. CoCoScore is a versatile text mining tool to uncover pairwise associations via co-occurrence mining, within and beyond biomedical applications. Availability and implementation CoCoScore is available at: https://github.com/JungeAlexander/cocoscore. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation Figures and captions convey essential information in biomedical documents. As such, there is a growing interest in mining published biomedical figures and in utilizing their respective captions as a source of knowledge. Notably, an essential step underlying such mining is the extraction of figures and captions from publications. While several PDF parsing tools that extract information from such documents are publicly available, they attempt to identify images by analyzing the PDF encoding and structure and the complex graphical objects embedded within. As such, they often incorrectly identify figures and captions in scientific publications, whose structure is often non-trivial. The extraction of figures, captions and figure-caption pairs from biomedical publications is thus neither well-studied nor yet well-addressed. Results We introduce a new and effective system for figure and caption extraction, PDFigCapX. Unlike existing methods, we first separate between text and graphical contents, and then utilize layout information to effectively detect and extract figures and captions. We generate files containing the figures and their associated captions and provide those as output to the end-user. We test our system both over a public dataset of computer science documents previously used by others, and over two newly collected sets of publications focusing on the biomedical domain. Our experiments and results comparing PDFigCapX to other state-of-the-art systems show a significant improvement in performance, and demonstrate the effectiveness and robustness of our approach. Availability and implementation Our system is publicly available for use at: https://www.eecis.udel.edu/~compbio/PDFigCapX. The two new datasets are available at: https://www.eecis.udel.edu/~compbio/PDFigCapX/Downloads

Summary Although the publication rate of the biomedical literature has been growing steadily during the last decades, the accessibility of pertinent research publications for biologist and medical practitioners remains a challenge. This article describes Thalia, which is a semantic search engine that can recognize eight different types of concepts occurring in biomedical abstracts. Thalia is available via a web-based interface or a RESTful API. A key aspect of our search engine is that it is updated from PubMed on a daily basis. We describe here the main building blocks of our tool as well as an evaluation of the retrieval capabilities of Thalia in the context of a precision medicine dataset. Availability and implementation Thalia is available at http://nactem.ac.uk/Thalia_BI/. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation:Computational biologists face many challenges related to data size, and they need to manage complicated analyses often including multiple stages and multiple tools, all of which must be deployed to modern infrastructures. To address these challenges and maintain reproducibility of results, researchers need (i) a reliable way to run processing stages in any computational environment, (ii) a well-defined way to orchestrate those processing stages, and (iii) a data management layer that tracks data as it moves through the processing pipeline.Results:Pachyderm is an open-source workflow system and data management framework that fulfills these needs by creating a data pipelining and data versioning layer on top of projects from the container ecosystem, having Kubernetes as the backbone for container orchestration. We adapted Pachyderm and demonstrated its attractive properties in bioinformatics. A Helm Chart was created so that researchers can use Pachyderm in multiple scenarios. The Pachyderm File System was extended to support block storage. A wrapper for initiating Pachyderm on cloud-agnostic virtual infrastructures was created. The benefits of Pachyderm are illustrated via a large metabolomics workflow, demonstrating that Pachyderm enables efficient and sustainable data science workflows while maintaining reproducibility and scalability.Availability:Pachyderm is available from https://github.com/pachyderm/pachyderm. The Pachyderm Helm Chart is available from https://github.com/kubernetes/charts/tree/master/stable/pachyderm. Pachyderm is available out-of-the-box from the PhenoMeNal VRE (https://github.com/phnmnl/KubeNow-plugin) and general Kubernetes environments instantiated via KubeNow. The code of the workflow used for the analysis is available on GitHub (https://github.com/pharmbio/LC-MS-Pachyderm).Contact:jon.novella@farmbio.uu.se

Recent hurricane events have caused unprecedented amounts of damage and severely threatened our public safety and economy. The most observable (and severe) impact of these hurricanes is the loss of electric power in many regions, which causes the breakdown of many public services. Understanding the power outages and how they evolve during a hurricane provide insights on how to reduce outages in the future, and how to improve the robustness of the underlying critical infrastructure systems. In this paper, we propose a novel segmentation with explanations framework to help experts understand such datasets. Our method, CUT-n-REVEAL, first finds a segmentation of the outage sequences to capture pattern changes in the sequences. We then propose a novel explanation optimization problem to find an intuitive explanation of the segmentation, that highlights the culprit of the change. Via extensive experiments, we show that our method performs consistently in multiple datasets with ground truth. We further study real county-level power outage data from several recent hurricanes (Matthew, Harvey, Irma) and show that CUT-n-REVEAL recovers important, nontrivial and actionable patterns for domain experts.

Microblogging websites, like Twitter and Weibo, are used by billions of people to create and spread information. This activity depends on various factors such as the friendship links between users, their topic interests and social influence between them. Making sense of these behaviors is very important for fully understanding and utilizing these platforms. Most prior work on modeling social-media either ignores the effect of social influence, or considers its effect only on link formation or post generation. In contrast, in this paper we propose POLIM, which jointly models the effect of influence on both link and post generation, leveraging weak supervision. We also give POLIM-FIT, an efficient parallel inference algorithm for POLIM which scales to large datasets. In our experiments on a large tweets corpus, we detect meaningful topical communities, celebrities, as well as the influence strengths patterns among them. Further, we find that there are significant portions of posts and links that are caused by influence, and this portion increases when the data focuses on a specific event. We also show that differentiating and identifying these influenced content benefits other quantitative downstream tasks as well, like predicting future tweets and link formation.

Motivation One goal of synthetic biology is to make new enzymes to generate new products, but identifying the starting enzymes for further investigation is often elusive and relies on expert knowledge, intensive literature searching and trial and error. Results We present Transform Molecules in Enzyme Reactions, an online computational tool that transforms query substrate molecules into products using enzyme reactions. The most similar native enzyme reactions for each transformation are found, highlighting those that may be of most interest for enzyme design and directed evolution approaches. Availability and implementation https://www.ebi.ac.uk/thornton-srv/transform-miner

Motivation Recognition of biomedical entities from scientific text is a critical component of natural language processing and automated information extraction platforms. Modern named entity recognition approaches rely heavily on supervised machine learning techniques, which are critically dependent on annotated training corpora. These approaches have been shown to perform well when trained and tested on the same source. However, in such scenario, the performance and evaluation of these models may be optimistic, as such models may not necessarily generalize to independent corpora, resulting in potential non-optimal entity recognition for large-scale tagging of widely diverse articles in databases such as PubMed. Results Here we aggregated published corpora for the recognition of biomolecular entities (such as genes, RNA, proteins, variants, drugs and metabolites), identified entity class overlap and performed leave-corpus-out cross validation strategy to test the efficiency of existing models. We demonstrate that accuracies of models trained on individual corpora decrease substantially for recognition of the same biomolecular entity classes in independent corpora. This behavior is possibly due to limited generalizability of entity-class-related features captured by individual corpora (model ‘overtraining’) which we investigated further at the orthographic level, as well as potential annotation standard differences. We show that the combined use of multi-source training corpora results in overall more generalizable models for named entity recognition, while achieving comparable individual performance. By performing learning-curve-based power analysis we further identified that performance is often not limited by the quantity of the annotated data. Availability and implementation Compiled primary and secondary sources of the aggregated corpora are available on: https://github.com/dterg/biomedical_corpora/wiki and https://bitbucket.org/iAnalytica/bioner. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation: Predictive tools that model protein–ligand binding on demand are needed to promote ligand research in an innovative drug-design environment. However, it takes considerable time and effort to develop predictive tools that can be applied to individual ligands. An automated production pipeline that can rapidly and efficiently develop user-friendly protein–ligand binding predictive tools would be useful. Results: We developed a system for automatically generating protein–ligand binding predictions. Implementation of this system in a pipeline of Semantic Web technique-based web tools will allow users to specify a ligand and receive the tool within 0.5–1 day. We demonstrated high prediction accuracy for three machine learning algorithms and eight ligands. Availability and implementation: The source code and web application are freely available for download at http://utprot.net. They are implemented in Python and supported on Linux. Contact: shimizu@bi.a.u-tokyo.ac.jp Supplementary information: Supplementary data are available at Bioinformatics online.

Motivation: Most data analysis tools for high-throughput screening (HTS) seek to uncover interesting hits for further analysis. They typically assume a low hit rate per plate. Hit rates can be dramatically higher in secondary screening, RNAi screening and in drug sensitivity testing using biologically active drugs. In particular, drug sensitivity testing on primary cells is often based on dose–response experiments, which pose a more stringent requirement for data quality and for intra- and inter-plate variation. Here, we compared common plate normalization and noise-reduction methods, including the B-score and the Loess a local polynomial fit method under high hit-rate scenarios of drug sensitivity testing. We generated simulated 384-well plate HTS datasets, each with 71 plates having a range of 20 (5%) to 160 (42%) hits per plate, with controls placed either at the edge of the plates or in a scattered configuration. Results: We identified 20% (77/384) as the critical hit-rate after which the normalizations started to perform poorly. Results from real drug testing experiments supported this estimation. In particular, the B-score resulted in incorrect normalization of high hit-rate plates, leading to poor data quality, which could be attributed to its dependency on the median polish algorithm. We conclude that a combination of a scattered layout of controls per plate and normalization using a polynomial least squares fit method, such as Loess helps to reduce column, row and edge effects in HTS experiments with high hit-rates and is optimal for generating accurate dose–response curves. Contact: john.mpindi@helsinki.fi Availability and implementation, Supplementary information: R code and Supplementary data are available at Bioinformatics online.

Summary: Medical Subject Headings (MeSH®) is a controlled vocabulary for indexing and searching biomedical literature. MeSH terms and subheadings are organized in a hierarchical structure and are used to indicate the topics of an article. Biologists can use either MeSH terms as queries or the MeSH interface provided in PubMed® for searching PubMed abstracts. However, these are rarely used, and there is no convenient way to link standardized MeSH terms to user queries. Here, we introduce a web interface which allows users to enter queries to find MeSH terms closely related to the queries. Our method relies on co-occurrence of text words and MeSH terms to find keywords that are related to each MeSH term. A query is then matched with the keywords for MeSH terms, and candidate MeSH terms are ranked based on their relatedness to the query. The experimental results show that our method achieves the best performance among several term extraction approaches in terms of topic coherence. Moreover, the interface can be effectively used to find full names of abbreviations and to disambiguate user queries. Availability and Implementation: https://www.ncbi.nlm.nih.gov/IRET/MESHABLE/ Contact: sun.kim@nih.gov Supplementary information: Supplementary data are available at Bioinformatics online.

Summary: FILTUS is a stand-alone tool for working with annotated variant files, e.g. when searching for variants causing Mendelian disease. Very flexible in terms of input file formats, FILTUS offers efficient filtering and a range of downstream utilities, including statistical analysis of gene sharing patterns, detection of de novo mutations in trios, quality control plots and autozygosity mapping. The autozygosity mapping is based on a hidden Markov model and enables accurate detection of autozygous regions directly from exome-scale variant files. Availability and implementation: FILTUS is written in Python and runs on Windows, Mac and Linux. Binaries and source code are freely available at http://folk.uio.no/magnusv/filtus.html and on GitHub: https://github.com/magnusdv/filtus. Automatic installation is available via PyPI (e.g. pip install filtus). Contact: magnusdv@medisin.uio.no Supplementary information: Supplementary data are available at Bioinformatics online.

Author(s): Hinrichs, Angie S; Raney, Brian J; Speir, Matthew L; Rhead, Brooke; Casper, Jonathan; Karolchik, Donna; Kuhn, Robert M; Rosenbloom, Kate R; Zweig, Ann S; Haussler, David; Kent, W James | Abstract: UnlabelledTwo new tools on the UCSC Genome Browser web site provide improved ways of combining information from multiple datasets, optionally including the user's own custom track data and/or data from track hubs. The Data Integrator combines columns from multiple data tracks, showing all items from the first track along with overlapping items from the other tracks. The Variant Annotation Integrator is tailored to adding functional annotations to variant calls; it offers a more restricted set of underlying data tracks but adds predictions of each variant's consequences for any overlapping or nearby gene transcript. When available, it optionally adds additional annotations including effect prediction scores from dbNSFP for missense mutations, ENCODE regulatory summary tracks and conservation scores.Availability and implementationThe web tools are freely available at http://genome.ucsc.edu/ and the underlying database is available for download at http://hgdownload.cse.ucsc.edu/ The software (written in C and Javascript) is available from https://genome-store.ucsc.edu/ and is freely available for academic and non-profit usage; commercial users must obtain a license.Contactangie@soe.ucsc.eduSupplementary informationSupplementary data are available at Bioinformatics online.

Motivation This work uses the Random Forest (RF) classification algorithm to predict if a gene is over-expressed, under-expressed or has no change in expression with age in the brain. RFs have high predictive power, and RF models can be interpreted using a feature (variable) importance measure. However, current feature importance measures evaluate a feature as a whole (all feature values). We show that, for a popular type of biological data (Gene Ontology-based), usually only one value of a feature is particularly important for classification and the interpretation of the RF model. Hence, we propose a new algorithm for identifying the most important and most informative feature values in an RF model. Results The new feature importance measure identified highly relevant Gene Ontology terms for the aforementioned gene classification task, producing a feature ranking that is much more informative to biologists than an alternative, state-of-the-art feature importance measure. Availability and implementation The dataset and source codes used in this paper are available as ‘Supplementary Material’ and the description of the data can be found at: https://fabiofabris.github.io/bioinfo2018/web/. Supplementary information Supplementary data are available at Bioinformatics online.

SummaryWith the rapid accumulation of sequencing data from genomic and metagenomic studies, there is an acute need for better tools that facilitate their analyses against biological functions. To this end, we developed MetQy, an open–source R package designed for query–based analysis of functional units in [meta]genomes and/or sets of genes using the The Kyoto Encyclopedia of Genes and Genomes (KEGG) database. Furthermore, MetQy contains visualization and analysis tools and facilitates KEGG’s flat file manipulation. Thus, MetQy enables better understanding of metabolic capabilities of known genomes or user–specified [meta]genomes by using the available information and can help guide studies in microbial ecology, metabolic engineering and synthetic biology.Availability and ImplementationThe MetQy R package is freely available and can be downloaded from our group’s website (http://osslab.lifesci.warwick.ac.uk) or GitHub (https://github.com/OSS-Lab/MetQy).ContactO.Soyer@warwick.ac.uk

Motivation Adverse drug reactions (ADRs) are one of the main causes of death and a major financial burden on the world’s economy. Due to the limitations of the animal model, computational prediction of serious and rare ADRs is invaluable. However, current state-of-the-art computational methods do not yield significantly better predictions of rare ADRs than random guessing. Results We present a novel method, based on the theory of ‘compressed sensing’ (CS), which can accurately predict serious side-effects of candidate and market drugs. Not only is our method able to infer new chemical-ADR associations using existing noisy, biased and incomplete databases, but our data also demonstrate that the accuracy of CS in predicting a serious ADR for a candidate drug increases with increasing knowledge of other ADRs associated with the drug. In practice, this means that as the candidate drug moves up the different stages of clinical trials, the prediction accuracy of our method will increase accordingly. Availability and implementation The program is available at https://github.com/poleksic/side-effects. Supplementary information Supplementary data are available at Bioinformatics online.

Motivation The increasing amount of peer-reviewed manuscripts requires the development of specific mining tools to facilitate the visual exploration of evidence linking diseases and proteins. Results We developed TIN-X, the Target Importance and Novelty eXplorer, to visualize the association between proteins and diseases, based on text mining data processed from scientific literature. In the current implementation, TIN-X supports exploration of data for G-protein coupled receptors, kinases, ion channels, and nuclear receptors. TIN-X supports browsing and navigating across proteins and diseases based on ontology classes, and displays a scatter plot with two proposed new bibliometric statistics: Importance and Novelty. Availability and Implementation http://www.newdrugtargets.org

Summary Second use of clinical data commonly involves annotating biomedical text with terminologies and ontologies. The National Center for Biomedical Ontology Annotator is a frequently used annotation service, originally designed for biomedical data, but not very suitable for clinical text annotation. In order to add new functionalities to the NCBO Annotator without hosting or modifying the original Web service, we have designed a proxy architecture that enables seamless extensions by pre-processing of the input text and parameters, and post processing of the annotations. We have then implemented enhanced functionalities for annotating and indexing free text such as: scoring, detection of context (negation, experiencer, temporality), new output formats and coarse-grained concept recognition (with UMLS Semantic Groups). In this paper, we present the NCBO Annotator+, a Web service which incorporates these new functionalities as well as a small set of evaluation results for concept recognition and clinical context detection on two standard evaluation tasks (Clef eHealth 2017, SemEval 2014). Availability and implementation The Annotator+ has been successfully integrated into the SIFR BioPortal platform—an implementation of NCBO BioPortal for French biomedical terminologies and ontologies—to annotate English text. A Web user interface is available for testing and ontology selection (http://bioportal.lirmm.fr/ncbo_annotatorplus); however the Annotator+ is meant to be used through the Web service application programming interface (http://services.bioportal.lirmm.fr/ncbo_annotatorplus). The code is openly available, and we also provide a Docker packaging to enable easy local deployment to process sensitive (e.g. clinical) data in-house (https://github.com/sifrproject). Contact andon.tchechmedjiev@lirmm.fr Supplementary information Supplementary data are available at Bioinformatics online.

Motivation: In neuroscience, as in many other scientific domains, the primary form of knowledge dissemination is through published articles. One challenge for modern neuroinformatics is finding methods to make the knowledge from the tremendous backlog of publications accessible for search, analysis and the integration of such data into computational models. A key example of this is metascale brain connectivity, where results are not reported in a normalized repository. Instead, these experimental results are published in natural language, scattered among individual scientific publications. This lack of normalization and centralization hinders the large-scale integration of brain connectivity results. In this article, we present text-mining models to extract and aggregate brain connectivity results from 13.2 million PubMed abstracts and 630 216 full-text publications related to neuroscience. The brain regions are identified with three different named entity recognizers (NERs) and then normalized against two atlases: the Allen Brain Atlas (ABA) and the atlas from the Brain Architecture Management System (BAMS). We then use three different extractors to assess inter-region connectivity. Results: NERs and connectivity extractors are evaluated against a manually annotated corpus. The complete in litero extraction models are also evaluated against in vivo connectivity data from ABA with an estimated precision of 78%. The resulting database contains over 4 million brain region mentions and over 100 000 (ABA) and 122 000 (BAMS) potential brain region connections. This database drastically accelerates connectivity literature review, by providing a centralized repository of connectivity data to neuroscientists. Availability and implementation: The resulting models are publicly available at github.com/BlueBrain/bluima. Contact: renaud.richardet@epfl.ch Supplementary information: Supplementary data are available at Bioinformatics online.

Motivation To understand the molecular mechanisms involved in cancer development, significant efforts are being invested in cancer research. This has resulted in millions of scientific articles. An efficient and thorough review of the existing literature is crucially important to drive new research. This time-demanding task can be supported by emerging computational approaches based on text mining which offer a great opportunity to organize and retrieve the desired information efficiently from sizable databases. One way to organize existing knowledge on cancer is to utilize the widely accepted framework of the Hallmarks of Cancer. These hallmarks refer to the alterations in cell behaviour that characterize the cancer cell. Results We created an extensive Hallmarks of Cancer taxonomy and developed automatic text mining methodology and a tool (CHAT) capable of retrieving and organizing millions of cancer-related references from PubMed into the taxonomy. The efficiency and accuracy of the tool was evaluated intrinsically as well as extrinsically by case studies. The correlations identified by the tool show that it offers a great potential to organize and correctly classify cancer-related literature. Furthermore, the tool can be useful, for example, in identifying hallmarks associated with extrinsic factors, biomarkers and therapeutics targets. Availability and implementation CHAT can be accessed at: http://chat.lionproject.net. The corpus of hallmark-annotated PubMed abstracts and the software are available at: http://chat.lionproject.net/about Contact simon.baker@cl.cam.ac.uk Supplementary information Supplementary data are available at Bioinformatics online.

Motivation We recently published MS2LDA, a method for the decomposition of sets of molecular fragment data derived from large metabolomics experiments. To make the method more widely available to the community, here we present ms2lda.org, a web application that allows users to upload their data, run MS2LDA analyses and explore the results through interactive visualizations. Results Ms2lda.org takes tandem mass spectrometry data in many standard formats and allows the user to infer the sets of fragment and neutral loss features that co-occur together (Mass2Motifs). As an alternative workflow, the user can also decompose a data set onto predefined Mass2Motifs. This is accomplished through the web interface or programmatically from our web service. Availability and implementation The website can be found at http://ms2lda.org, while the source code is available at https://github.com/sdrogers/ms2ldaviz under the MIT license. Contact simon.rogers@glasgow.ac.uk Supplementary information Supplementary data are available at Bioinformatics online.

This repository contains labeled, weighted networks of chemical-gene, gene-gene, gene-disease, and chemical-disease relationships based on single sentences in PubMed abstracts. All raw dependency paths are provided in addition to the labeled relationships. PART I: Connects dependency paths to labels, or "themes". Each record contains a dependency path followed by its score for each theme, and indicators of whether or not the path is part of the flagship path set for each theme (meaning that it was manually reviewed and determined to reflect that theme). The themes themselves are listed below and are in our paper (reference below). PART II: Connects sentences to dependency paths. It consists of sentences and associated metadata, entity pairs found in the sentences, and dependency paths connecting those entity pairs. Each record contains the following information: PubMed ID Sentence number (0 = title) First entity name, formatted First entity name, location (characters from start of abstract) Second entity name, formatted Second entity name, location First entity name, raw string Second entity name, raw string First entity name, database ID(s) Second entity name, database ID(s) First entity type (Chemical, Gene, Disease) Second entity type (Chemical, Gene, Disease) Dependency path Sentence, tokenized The "with-themes.txt" files only contain dependency paths with corresponding theme assignments from Part I. The plain ".txt" files contain all dependency paths. This release contains the annotated network for the September 15, 2017 version of PubTator . The version discussed in our paper, below, is an older one - from April 30, 2016. If you're interested in that network, it can be found in Version 1 of this repository. We will be releasing updated networks periodically, as the PubTator community continues to release new versions of named entity annotations for Medline each month or so. ------------------------------------------------------------------------------------ REFERENCES Percha B, Altman RBA (2017) A global network of biomedical relationships derived from text. (Submitted to Bioinformatics ; currently in revision.) Percha B, Altman RBA (2015) Learning the structure of biomedical relationships from unstructured text. PLoS Computational Biology, 11(7): e1004216. This project depends on named entity annotations from the PubTator project: https://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/PubTator/ Reference: Wei CH et. al., PubTator: a Web-based text mining tool for assisting Biocuration, Nucleic acids research, 2013, 41 (W1): W518-W522. doi: 10.1093/nar/gkt44 Dependency parsing was provided by the Stanford CoreNLP toolkit: https://stanfordnlp.github.io/CoreNLP/index.html Reference: Manning, Christopher D., Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David McClosky. 2014. The Stanford CoreNLP Natural Language Processing Toolkit In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 55-60. ------------------------------------------------------------------------------------ THEMES chemical-gene (A+) agonism, activation (A-) antagonism, blocking (B) binding, ligand (esp. receptors) (E+) increases expression/production (E-) decreases expression/production (E) affects expression/production (neutral) (N) inhibits gene-chemical (O) transport, channels (K) metabolism, pharmacokinetics (Z) enzyme activity chemical-disease (T) treatment/therapy (including investigatory) (C) inhibits cell growth (esp. cancers) (Sa) side effect/adverse event (Pr) prevents, suppresses (Pa) alleviates, reduces (J) role in disease pathogenesis disease-chemical (Mp) biomarkers (of disease progression) gene-disease (U) causal mutations (Ud) mutations affecting disease course (D) drug targets (J) role in pathogenesis (Te) possible therapeutic effect (Y) polymorphisms alter risk (G) promotes progression disease-gene (Md) biomarkers (diagnostic) (X) overexpression in disease (L) improper regulation linked to disease gene-gene (B) binding, ligand (esp. receptors) (W) enhances response (V+) activates, stimulates (E+) increases expression/production (E) affects expression/production (neutral) (I) signaling pathway (H) same protein or complex (Rg) regulation (Q) production by cell population

Summary: Modelling biological associations or dependencies using linear regression is often complicated when the analyzed data-sets are high-dimensional and less observations than variables are available (n p). For genomic data-sets penalized regression methods have been applied settling this issue. Recently proposed regression models utilize prior knowledge on dependencies, e.g. in the form of graphs, arguing that this information will lead to more reliable estimates for regression coefficients. However, none of the proposed models for multivariate genomic response variables have been implemented as a computationally efficient, freely available library. In this paper we propose netReg, a package for graph-penalized regression models that use large networks and thousands of variables. netReg incorporates a priori generated biological graph information into linear models yielding sparse or smooth solutions for regression coefficients. Availability and implementation: netReg is implemented as both R-package and Cþþ commandline tool. The main computations are done in Cþþ, where we use Armadillo for fast matrix calculations and Dlib for optimization. The R package is freely available on Bioconductor https://bioconductor.org/ packages/netReg. The command line tool can be installed using the conda channel Bioconda. Installation details, issue reports, development versions, documentation and tutorials for the R and Cþþ versions and the R package vignette can be found on GitHub https://dirmeier.github.io/netReg/. The GitHub page also contains code for benchmarking and example datasets used in this paper., Bioinformatics, 34 (5), ISSN:1367-4803, ISSN:1460-2059

Epigenetic research focuses on understanding non-inheritable factors influencing gene regulation and covers various cellular mechanisms such as DNA methylation, histone modification, miRNA function and transcription factor binding sites. Recent advances in high-throughput profiling technologies allow for systematically collecting data on each of these mechanisms in large-scale experiments. These efforts are fostered and concerted by international collaborations, such as the International Human Epigenome Consortium (IHEC) and its members. As a result of these collaborations, researchers can exploit massive amounts of publicly available epigenomic data on dozens of cell types, cell lines and tissues. Access to these data is streamlined by existing data portals and, in principle, allows for answering important biomedical questions. However, working with such data requires a suitable computational infrastructure not accessible ubiquitously. This creates a serious bottleneck in research and, as a result, data from these costly experiments are currently underused. To address this issue, we developed a new web resource, the DeepBlue Epigenomic Data Server to provide access to more than 40,000 experimental files from four major epigenome projects: ENCODE, ROADMAP, BLUEPRINT, the German Epigenome Program DEEP, the Canadian CEEHRC, and the Japanese CREST. A common challenge with this resources is that researchers are typically interested in a small fraction of the available epigenomic data to answer specific biomedical questions. Using a typical data repository to solve this task would require the user to download several files amounting to gigabytes of data that subsequently need to be filtered locally. In addition, it is often important to perform memory- and cpu-intensive operations to transform or aggregate these data, while the necessary computational resources are not accessible to every user. Therefore, the DeepBlue Data Server offers features beyond those of a centralized epigenomic data repository. It has a comprehensive programmatic interface (API) to enable users to perform complex data operations, such as searching, selecting, filtering, summarizing, and downloading of epigenomic data of interest. These operations can be combined into custom workflows, thus offering nearly the same degree of flexibility as a local programming environment. Here, we present DeepBlueR, a new R/Bioconductor package that enables users to engage with the DeepBlue server in a seamless fashion from within the R environment. DeepBlueR mirrors all DeepBlue data operations as R commands and provides additional features for compressing, downloading and transforming aggregated epigenomic data into suitable R data structures. A mechanism for local caching guarantees that complex scripts can be executed without the need to download previously requested data from the server.

myGenomeBrowser is a web-based environment that provides biologists with a way to build, query and share their genome browsers. This tool, that builds on JBrowse, is designed to give users more autonomy while simplifying and minimizing intervention from system administrators. We have extended genome browser basic features to allow users to query, analyze and share their data. Availability and implementation: myGenomeBrowser is freely available at https://bbric-pipelines.toulouse.inra.fr/myGenomeBrowser and includes tutorial screencasts. Source code and installation instructions can be found at https://framagit.org/BBRIC/myGenomeBrowser. myGenomeBrowser is open-source and mainly implemented in Perl, JavaScript, Apache and Docker.

Motivation: Methods for computational drug target identification use information from diverse information sources to predict or prioritize drug targets for known drugs. One set of resources that has been relatively neglected for drug repurposing is animal model phenotype. Results: We investigate the use of mouse model phenotypes for drug target identification. To achieve this goal, we first integrate mouse model phenotypes and drug effects, and then systematically compare the phenotypic similarity between mouse models and drug effect profiles. We find a high similarity between phenotypes resulting from loss-of-function mutations and drug effects resulting from the inhibition of a protein through a drug action, and demonstrate how this approach can be used to suggest candidate drug targets. Availability and implementation: Analysis code and supplementary data files are available on the project Web site at https://drugeffects.googlecode.com. Contact: leechuck@leechuck.de or roh25@aber.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online.

Summary When sequencing several libraries simultaneously, the selection of compatible combinations of indexes is critical for ensuring that the sequencer will be able to decipher the short, sample-specific barcodes added to each fragment. However, researchers have few tools to help them choose optimal indexes. Here, we present checkMyIndex, an online R/Shiny application that facilitates the selection of the right indexes as a function of the experimental constraints. Availability and implementation checkMyIndex is available free of charge at https://checkmyindex.pasteur.fr as an online, web-based R/Shiny application. The source code is available on GitHub at https://github.com/PF2-pasteur-fr/checkMyIndex.

Motivation In a scenario where populations A, B1 and B2 (subpopulations of B) exist, pronounced differences between A and B may mask subtle differences between B1 and B2. Results Here we present iterClust, an iterative clustering framework, which can separate more pronounced differences (e.g. A and B) in starting iterations, followed by relatively subtle differences (e.g. B1 and B2), providing a comprehensive clustering trajectory. Availability and implementation iterClust is implemented as a Bioconductor R package. Supplementary information Supplementary data are available at Bioinformatics online.

Summary: Cytoscape.js is an open-source JavaScript-based graph library. Its most common use case is as a visualization software component, so it can be used to render interactive graphs in a web browser. It also can be used in a headless manner, useful for graph operations on a server, such as Node.js. Availability and implementation: Cytoscape.js is implemented in JavaScript. Documentation, downloads and source code are available at http://js.cytoscape.org. Contact: gary.bader@utoronto.ca

Summary: dendextend is an R package for creating and comparing visually appealing tree diagrams. dendextend provides utility functions for manipulating dendrogram objects (their color, shape and content) as well as several advanced methods for comparing trees to one another (both statistically and visually). As such, dendextend offers a flexible framework for enhancing R's rich ecosystem of packages for performing hierarchical clustering of items. Availability and implementation: The dendextend R package (including detailed introductory vignettes) is available under the GPL-2 Open Source license and is freely available to download from CRAN at: (http://cran.r-project.org/package=dendextend) Contact: Tal.Galili@math.tau.ac.il

Summary: Precision-recall (PR) and receiver operating characteristic (ROC) curves are valuable measures of classifier performance. Here, we present the R-package PRROC, which allows for computing and visualizing both PR and ROC curves. In contrast to available R-packages, PRROC allows for computing PR and ROC curves and areas under these curves for soft-labeled data using a continuous interpolation between the points of PR curves. In addition, PRROC provides a generic plot function for generating publication-quality graphics of PR and ROC curves. Availability and implementation: PRROC is available from CRAN and is licensed under GPL 3. Contact: grau@informatik.uni-halle.de

Motivation: Anatomical entities ranging from subcellular structures to organ systems are central to biomedical science, and mentions of these entities are essential to understanding the scientific literature. Despite extensive efforts to automatically analyze various aspects of biomedical text, there have been only few studies focusing on anatomical entities, and no dedicated methods for learning to automatically recognize anatomical entity mentions in free-form text have been introduced. Results: We present AnatomyTagger, a machine learning-based system for anatomical entity mention recognition. The system incorporates a broad array of approaches proposed to benefit tagging, including the use of Unified Medical Language System (UMLS)- and Open Biomedical Ontologies (OBO)-based lexical resources, word representations induced from unlabeled text, statistical truecasing and non-local features. We train and evaluate the system on a newly introduced corpus that substantially extends on previously available resources, and apply the resulting tagger to automatically annotate the entire open access scientific domain literature. The resulting analyses have been applied to extend services provided by the Europe PubMed Central literature database. Availability and implementation: All tools and resources introduced in this work are available from http://nactem.ac.uk/anatomytagger. Contact: sophia.ananiadou@manchester.ac.uk Supplementary Information: Supplementary data are available at Bioinformatics online.

Motivation: Despite the central role of diseases in biomedical research, there have been much fewer attempts to automatically determine which diseases are mentioned in a text—the task of disease name normalization (DNorm)—compared with other normalization tasks in biomedical text mining research. Methods: In this article we introduce the first machine learning approach for DNorm, using the NCBI disease corpus and the MEDIC vocabulary, which combines MeSH® and OMIM. Our method is a high-performing and mathematically principled framework for learning similarities between mentions and concept names directly from training data. The technique is based on pairwise learning to rank, which has not previously been applied to the normalization task but has proven successful in large optimization problems for information retrieval. Results: We compare our method with several techniques based on lexical normalization and matching, MetaMap and Lucene. Our algorithm achieves 0.782 micro-averaged F-measure and 0.809 macro-averaged F-measure, an increase over the highest performing baseline method of 0.121 and 0.098, respectively. Availability: The source code for DNorm is available at http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/DNorm, along with a web-based demonstration and links to the NCBI disease corpus. Results on PubMed abstracts are available in PubTator: http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/PubTator Contact: zhiyong.lu@nih.gov