Disease named entity recognition from biomedical literature using a novel convolutional neural network

Background

Automatic disease named entity recognition (DNER) is of utmost importance for development of more sophisticated BioNLP tools. However, most conventional CRF based DNER systems rely on well-designed features whose selection is labor intensive and time-consuming. Though most deep learning methods can solve NER problems with little feature engineering, they employ additional CRF layer to capture the correlation information between labels in neighborhoods which makes them much complicated.

Methods

In this paper, we propose a novel multiple label convolutional neural network (MCNN) based disease NER approach. In this approach, instead of the CRF layer, a multiple label strategy (MLS) first introduced by us, is employed. First, the character-level embedding, word-level embedding and lexicon feature embedding are concatenated. Then several convolutional layers are stacked over the concatenated embedding. Finally, MLS strategy is applied to the output layer to capture the correlation information between neighboring labels.

Results

As shown by the experimental results, MCNN can achieve the state-of-the-art performance on both NCBI and CDR corpora.

Conclusions

The proposed MCNN based disease NER method achieves the state-of-the-art performance with little feature engineering. And the experimental results show the MLS strategy’s effectiveness of capturing the correlation information between labels in the neighborhood.

     

Comparison of named entity recognition methodologies in biomedical documents

Background

Biomedical named entity recognition (Bio-NER) is a fundamental task in handling biomedical text terms, such as RNA, protein, cell type, cell line, and DNA. Bio-NER is one of the most elementary and core tasks in biomedical knowledge discovery from texts. The system described here is developed by using the BioNLP/NLPBA 2004 shared task. Experiments are conducted on a training and evaluation set provided by the task organizers.

Results

Our results show that, compared with a baseline having a 70.09% F1 score, the RNN Jordan- and Elman-type algorithms have F1 scores of approximately 60.53% and 58.80%, respectively. When we use CRF as a machine learning algorithm, CCA, GloVe, and Word2Vec have F1 scores of 72.73%, 72.74%, and 72.82%, respectively.

Conclusions

By using the word embedding constructed through the unsupervised learning, the time and cost required to construct the learning data can be saved.

     

Optimization of fecal sample preparation for untargeted LC-HRMS based metabolomics

Introduction

Collecting feces is easy. It offers direct outcome to endogenous and microbial metabolites.

Objectives

In a context of lack of consensus about fecal sample preparation, especially in animal species, we developed a robust protocol allowing untargeted LC-HRMS fingerprinting.

Methods

The conditions of extraction (quantity, preparation, solvents, dilutions) were investigated in bovine feces.

Results

A rapid and simple protocol involving feces extraction with methanol (1/3, M/V) followed by centrifugation and a step filtration (10 kDa) was developed.

Conclusion

The workflow generated repeatable and informative fingerprints for robust metabolome characterization.

     

Metabolites predict cardiovascular disease events in persons living with HIV: a pilot case–control study

Introduction

Persons living with HIV (PLWH) are at higher risk for cardiovascular disease (CVD) events than uninfected persons. Current risk-stratification methods to define PLWH at highest risk for CVD events are lacking.

Methods

Using tandem flow injection mass spectrometry, we quantified plasma levels of 60 metabolites in 24 matched pairs of PLWH [1:1 with and without known coronary artery disease (CAD)]. Metabolite levels were reduced to interpretable factors using principal components analysis.

Results

Factors derived from short-chain dicarboxylacylcarnitines (SCDA) (p?=?0.08) and glutamine/valine (p?=?0.003) were elevated in CAD cases compared to controls.

Conclusion

SCDAs and glutamine/valine may be valuable markers of cardiovascular risk among persons living with HIV in the future, pending validation in larger cohorts.

     

Biomedical event trigger detection by dependency-based word embedding

Background

In biomedical research, events revealing complex relations between entities play an important role. Biomedical event trigger identification has become a research hotspot since its important role in biomedical event extraction. Traditional machine learning methods, such as support vector machines (SVM) and maxent classifiers, which aim to manually design powerful features fed to the classifiers, depend on the understanding of the specific task and cannot generalize to the new domain or new examples.

Methods

In this paper, we propose an approach which utilizes neural network model based on dependency-based word embedding to automatically learn significant features from raw input for trigger classification. First, we employ Word2vecf, the modified version of Word2vec, to learn word embedding with rich semantic and functional information based on dependency relation tree. Then neural network architecture is used to learn more significant feature representation based on raw dependency-based word embedding. Meanwhile, we dynamically adjust the embedding while training for adapting to the trigger classification task. Finally, softmax classifier labels the examples by specific trigger class using the features learned by the model.

Results

The experimental results show that our approach achieves a micro-averaging F1 score of 78.27 and a macro-averaging F1 score of 76.94 % in significant trigger classes, and performs better than baseline methods. In addition, we can achieve the semantic distributed representation of every trigger word.

     

Estrogen Receptor-α Correlates with Higher Fungal Cell Number in Oral Paracoccidioidomycosis in Women

Background

Paracoccidioidomycosis is a neglected tropical fungal infection with great predilection for adult men, indicating the participation of female hormone estrogen in preventing paracoccidioidomycosis development in women. Estrogen has an immunologic effect leading to polarization toward the Th2 immune response, which favors the disease evolution.

Objectives

To evaluate estrogen and progesterone receptors in oral paracoccidioidomycosis lesions and to verify any association with tissue fungi counting in women and men.

Methods

Thirty-two cases of chronic oral paracoccidioidomycosis were included. Immunohistochemical analyses for anti-estrogen receptor-α, anti-progesterone receptor and anti-Paracoccidioides brasiliensis antibodies were performed. The differences between women and men and the relations among the immunomarkers for each gender were also evaluated.

Results

A significant positive correlation was observed between estrogen receptor-α and the amount of fungi in women. In addition, estrogen receptor-α was mildly expressed in the inflammatory cells of female patients, while progesterone receptor was expressed in both genders, with similar expression between women and men. Moreover, fungi counting revealed no differences between genders.

Conclusions

Estrogen receptor-α was expressed only in women and showed a positive correlation with the amount of fungi in oral paracoccidioidomycosis, while progesterone receptor was observed in both genders and exhibited no correlation with estrogen receptor-α or fungi counting.

     

Anchoring quartet-based phylogenetic distances and applications to species tree reconstruction

Background

Inferring species trees from gene trees using the coalescent-based summary methods has been the subject of much attention, yet new scalable and accurate methods are needed.

Results

We introduce DISTIQUE, a new statistically consistent summary method for inferring species trees from gene trees under the coalescent model. We generalize our results to arbitrary phylogenetic inference problems; we show that two arbitrarily chosen leaves, called anchors, can be used to estimate relative distances between all other pairs of leaves by inferring relevant quartet trees. This results in a family of distance-based tree inference methods, with running times ranging between quadratic to quartic in the number of leaves.

Conclusions

We show in simulated studies that DISTIQUE has comparable accuracy to leading coalescent-based summary methods and reduced running times.

     

Integrated analysis of microRNA-target interactions with clinical outcomes for cancers

Background

Clinical statement alone is not enough to predict the progression of disease. Instead, the gene expression profiles have been widely used to forecast clinical outcomes. Many genes related to survival have been identified, and recently miRNA expression signatures predicting patient survival have been also investigated for several cancers. However, miRNAs and their target genes associated with clinical outcomes have remained largely unexplored.

Methods

Here, we demonstrate a survival analysis based on the regulatory relationships of miRNAs and their target genes. The patient survivals for the two major cancers, ovarian cancer and glioblastoma multiforme (GBM), are investigated through the integrated analysis of miRNA-mRNA interaction pairs.

Results

We found that there is a larger survival difference between two patient groups with an inversely correlated expression profile of miRNA and mRNA. It supports the idea that signatures of miRNAs and their targets related to cancer progression can be detected via this approach.

Conclusions

This integrated analysis can help to discover coordinated expression signatures of miRNAs and their target mRNAs that can be employed for therapeutics in human cancers.

     

Investigation of the relationship between cell surface hydrophobicity and demulsifying capability of biodemulsifier-producing bacteria

Background

Cell surface hydrophobicity (CSH) is one of the key physicochemical features of biodemulsifier-producing bacteria that influence their demulsification capability maintenance in petroleum contaminated environments.

Methods

In present study, biodemulsifier-producing bacteria were isolated from petroleum contaminated environments using different isolation media and the correlation between their CSH and demulsifying ability was investigated. The demulsifying ability of isolates was measured through demulsification tests on water in kerosene emulsions. The microbial adhesion to the hydrocarbon (MATH) assay was used to denote their CSH.

Results

The evaluation of CSH showed that majority of biodemulsifier producing bacteria have high CSH which indicating a positive correlation between CSH and demulsifying capability.

Conclusions

According to these results it can be concluded that CSH can be used as an indicator for assessment of biodemulsifier-producing bacteria and screening of new isolates for their biodemulsifier production.

     

Removing the bottlenecks of cell culture metabolomics: fast normalization procedure,correlation of metabolites to cell number,and impact of the cell harvesting method

Introduction

Although cultured cells are nowadays regularly analyzed by metabolomics technologies, some issues in study setup and data processing are still not resolved to complete satisfaction: a suitable harvesting method for adherent cells, a fast and robust method for data normalization, and the proof that metabolite levels can be normalized to cell number.

Objectives

We intended to develop a fast method for normalization of cell culture metabolomics samples, to analyze how metabolite levels correlate with cell numbers, and to elucidate the impact of the kind of harvesting on measured metabolite profiles.

Methods

We cultured four different human cell lines and used them to develop a fluorescence-based method for DNA quantification. Further, we assessed the correlation between metabolite levels and cell numbers and focused on the impact of the harvesting method (scraping or trypsinization) on the metabolite profile.

Results

We developed a fast, sensitive and robust fluorescence-based method for DNA quantification showing excellent linear correlation between fluorescence intensities and cell numbers for all cell lines. Furthermore, 82–97 % of the measured intracellular metabolites displayed linear correlation between metabolite concentrations and cell numbers. We observed differences in amino acids, biogenic amines, and lipid levels between trypsinized and scraped cells.

Conclusion

We offer a fast, robust, and validated normalization method for cell culture metabolomics samples and demonstrate the eligibility of the normalization of metabolomics data to the cell number. We show a cell line and metabolite-specific impact of the harvesting method on metabolite concentrations.

     

WNT and NOTCH signaling pathways as activators for epidermal growth factor receptor in esophageal squamous cell carcinoma

Background

Esophageal squamous cell carcinoma (ESCC) is the most common histological type of esophageal cancer, with a poor prognosis. Deregulation of WNT and NOTCH signaling pathways is important in ESCC progression, which can be due to either malfunction of their components or crosstalk with other pathways. Therefore, identification of new crosstalk between such pathways may be effective to introduce new strategies for targeted therapy of cancer. A correlation study was performed to assess the probable interaction between growth factor receptors and WNT/NOTCH pathways via the epidermal growth factor receptor (EGFR) and Musashi1 (MSI1), respectively.

Methods

Levels of MSI1/EGFR mRNA expression in tumor tissues from 48 ESCC patients were compared to their corresponding normal tissues using real-time polymerase chain reaction.

Results

There was a significant correlation between EGFR and MSI1 expression (p?=?0.05). Moreover, there was a significant correlation between EGFR/MSI1 expression and grade of tumor differentiation (p?=?0.02).

Conclusion

This study confirms a direct correlation between MSI1 and EGFR and may support the important role of MSI1 in activation of EGFR through NOTCH/WNT pathways in ESCC.

     

Epidemic cycling in a multi-strain SIRS epidemic network model

Background

One common observation in infectious diseases caused by multi-strain pathogens is that both the incidence of all infections and the relative fraction of infection with each strain oscillate with time (i.e., so-called Epidemic cycling). Many different mechanisms have been proposed for the pervasive nature of epidemic cycling. Nevertheless, the two facts that people contact each other through a network rather than following a simple mass-action law and most infectious diseases involve multiple strains have not been considered together for their influence on the epidemic cycling.

Methods

To demonstrate how the structural contacts among people influences the dynamical patterns of multi-strain pathogens, we investigate a two strain epidemic model in a network where every individual randomly contacts with a fixed number of other individuals. The standard pair approximation is applied to describe the changing numbers of individuals in different infection states and contact pairs.

Results

We show that spatial correlation due to contact network and interactions between strains through both ecological interference and immune response interact to generate epidemic cycling. Compared to one strain epidemic model, the two strain model presented here can generate epidemic cycling within a much wider parameter range that covers many infectious diseases.

Conclusion

Our results suggest that co-circulation of multiple strains within a contact network provides an explanation for epidemic cycling.

     

A lost opportunity for science: journals promote data sharing in metabolomics but do not enforce it

Introduction

Data sharing is being increasingly required by journals and has been heralded as a solution to the ‘replication crisis’.

Objectives

(i) Review data sharing policies of journals publishing the most metabolomics papers associated with open data and (ii) compare these journals’ policies to those that publish the most metabolomics papers.

Methods

A PubMed search was used to identify metabolomics papers. Metabolomics data repositories were manually searched for linked publications.

Results

Journals that support data sharing are not necessarily those with the most papers associated to open metabolomics data.

Conclusion

Further efforts are required to improve data sharing in metabolomics.

     

Association between HMGB1 and asthma: a literature review

Background

Recently, some studies demonstrated that HMGB1, as proinflammatory mediator belonging to the alarmin family, has a key role in different acute and chronic immune disorders. Asthma is a complex disease characterised by recurrent and reversible airflow obstruction associated to airway hyper-responsiveness and airway inflammation.

Objective

This literature review aims to analyse advances on HMGB1 role, employment and potential diagnostic application in asthma.

Methods

We reviewed experimental studies that investigated the pathogenetic role of HMGB in bronchial airway hyper-responsiveness, inflammation and the correlation between HMGB1 level and asthma.

Results

A total of 19 studies assessing the association between HMGB1 and asthma were identified.

Conclusions

What emerged from this literature review was the confirmation of HMGB-1 involvement in diseases characterised by chronic inflammation, especially in pulmonary pathologies. Findings reported suggest a potential role of the alarmin in being a stadiation method and a marker of therapeutic efficacy; finally, inhibiting HMGB1 in humans in order to contrast inflammation should be the aim for future further studies.

     

DGCA: A comprehensive R package for Differential Gene Correlation Analysis

Background

Dissecting the regulatory relationships between genes is a critical step towards building accurate predictive models of biological systems. A powerful approach towards this end is to systematically study the differences in correlation between gene pairs in more than one distinct condition.

Results

In this study we develop an R package, DGCA (for Differential Gene Correlation Analysis), which offers a suite of tools for computing and analyzing differential correlations between gene pairs across multiple conditions. To minimize parametric assumptions, DGCA computes empirical p-values via permutation testing. To understand differential correlations at a systems level, DGCA performs higher-order analyses such as measuring the average difference in correlation and multiscale clustering analysis of differential correlation networks. Through a simulation study, we show that the straightforward z-score based method that DGCA employs significantly outperforms the existing alternative methods for calculating differential correlation. Application of DGCA to the TCGA RNA-seq data in breast cancer not only identifies key changes in the regulatory relationships between TP53 and PTEN and their target genes in the presence of inactivating mutations, but also reveals an immune-related differential correlation module that is specific to triple negative breast cancer (TNBC).

Conclusions

DGCA is an R package for systematically assessing the difference in gene-gene regulatory relationships under different conditions. This user-friendly, effective, and comprehensive software tool will greatly facilitate the application of differential correlation analysis in many biological studies and thus will help identification of novel signaling pathways, biomarkers, and targets in complex biological systems and diseases.

     

DTL reconciliation repair

Background

Maximum parsimony phylogenetic tree reconciliation is an important technique for reconstructing the evolutionary histories of hosts and parasites, genes and species, and other interdependent pairs. Since the problem of finding temporally feasible maximum parsimony reconciliations is NP-complete, current methods use either exact algorithms with exponential worst-case running time or heuristics that do not guarantee optimal solutions.

Results

We offer an efficient new approach that begins with a potentially infeasible maximum parsimony reconciliation and iteratively “repairs” it until it becomes temporally feasible.

Conclusions

In a non-trivial number of cases, this approach finds solutions that are better than those found by the widely-used Jane heuristic.

     

Inter-individual relationships in empathic traits and feedback-related fronto-central brain activity: an event-related potential study

Background

Neuroimaging studies continue to indicate the major role the anterior cingulate cortex (ACC) plays in processing empathic responses. Error-related negativity (ERN), an event-related potential (ERP) thought to arise from the ACC, has been found to correlate with scores for individual empathic personality. This study investigated the relationship between empathic personality traits and the amplitude of feedback-related negativity (FRN), an ERP sourced from the ACC and similar to the ERN, using a task involving feedback of monetary gains or losses.

Methods

Sixteen healthy participants answered an empathy trait questionnaire and performed a gambling task to elicit FRN. Because FRN amplitude is thought to be associated with attention, motivation, emotional state, and anxiety trait, we performed a partial correlation analysis between the empathic trait score and FRN amplitude while controlling for variables.

Results

In partial correlation analysis, FRN amplitude was significantly inversely correlated with scores for personal distress and marginally correlated with scores for empathic concern and with total average score.

Discussion

The study revealed for the first time an association between FRN and emotional empathic traits, after controlling for variables that can affect FRN amplitude. However, we also found a reversed directional correlation contrary to our expectations. This fronto-central brain activity may be associated with empathic properties via dopaminergic neuronal function. Future study using these electric potentials as experimental tools is expected to help elucidate the neurological mechanism of empathy.

     

Attributional and consequential LCA in the ILCD handbook

Purpose

This discussion article aims to highlight two problematic aspects in the International Reference Life Cycle Data System (ILCD) Handbook: its guidance to the choice between attributional and consequential modeling and to the choice between average and marginal data as input to the life cycle inventory (LCI) analysis.

Methods

We analyze the ILCD guidance by comparing different statements in the handbook with each other and with previous research in this area.

Results and discussion

We find that the ILCD handbook is internally inconsistent when it comes to recommendations on how to choose between attributional and consequential modeling. We also find that the handbook is inconsistent with much of previous research in this matter, and also in the recommendations on how to choose between average and marginal data in the LCI.

Conclusions

Because of the inconsistencies in the ILCD handbook, we recommend that the handbook be revised.

     

Discovery of A-type procyanidin dimers in yellow raspberries by untargeted metabolomics and correlation based data analysis

Introduction

Raspberries are becoming increasingly popular due to their reported health beneficial properties. Despite the presence of only trace amounts of anthocyanins, yellow varieties seems to show similar or better effects in comparison to conventional raspberries.

Objectives

The aim of this work is to characterize the metabolic differences between red and yellow berries, focussing on the compounds showing a higher concentration in yellow varieties.

Methods

The metabolomic profile of 13 red and 12 yellow raspberries (of different varieties, locations and collection dates) was determined by UPLC–TOF-MS. A novel approach based on Pearson correlation on the extracted ion chromatograms was implemented to extract the pseudospectra of the most relevant biomarkers from high energy LC–MS runs. The raw data will be made publicly available on MetaboLights (MTBLS333).

Results

Among the metabolites showing higher concentration in yellow raspberries it was possible to identify a series of compounds showing a pseudospectrum similar to that of A-type procyanidin polymers. The annotation of this group of compounds was confirmed by specific MS/MS experiments and performing standard injections.

Conclusions

In berries lacking anthocyanins the polyphenol metabolism might be shifted to the formation of a novel class of A-type procyanidin polymers.

     

Quantifying and filtering knowledge generated by literature based discovery

Background

Literature based discovery (LBD) automatically infers missed connections between concepts in literature. It is often assumed that LBD generates more information than can be reasonably examined.

Methods

We present a detailed analysis of the quantity of hidden knowledge produced by an LBD system and the effect of various filtering approaches upon this. The investigation of filtering combined with single or multi-step linking term chains is carried out on all articles in PubMed.

Results

The evaluation is carried out using both replication of existing discoveries, which provides justification for multi-step linking chain knowledge in specific cases, and using timeslicing, which gives a large scale measure of performance.

Conclusions

While the quantity of hidden knowledge generated by LBD can be vast, we demonstrate that (a) intelligent filtering can greatly reduce the number of hidden knowledge pairs generated, (b) for a specific term, the number of single step connections can be manageable, and (c) in the absence of single step hidden links, considering multiple steps can provide valid links.