Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

A Comparative Analysis of Allergen Proteins between Plants and Animals Using Several Computational Tools and Chou's PseAAC Concept.

In International archives of allergy and immunology

BACKGROUND : A large number of allergens are derived from plant and animal proteins. A major challenge for researchers is to study the possible allergenic properties of proteins. The aim of this study was in silico analysis and comparison of several physiochemical and structural features of plant- and animal-derived allergen proteins, as well as classifying these proteins based on Chou's pseudo-amino acid composition (PseAAC) concept combined with bioinformatics algorithms.

METHODS : The physiochemical properties and secondary structure of plant and animal allergens were studied. The classification of the sequences was done using the PseAAC concept incorporated with the deep learning algorithm. Conserved motifs of plant and animal proteins were discovered using the MEME tool. B-cell and T-cell epitopes of the proteins were predicted in conserved motifs. Allergenicity and amino acid composition of epitopes were also analyzed via bioinformatics servers.

RESULTS : In comparison of physiochemical features of animal and plant allergens, extinction coefficient was different significantly. Secondary structure prediction showed more random coiled structure in plant allergen proteins compared with animal proteins. Classification of proteins based on PseAAC achieved 88.24% accuracy. The amino acid composition study of predicted B- and T-cell epitopes revealed more aliphatic index in plant-derived epitopes.

CONCLUSIONS : The results indicated that bioinformatics-based studies could be useful in comparing plant and animal allergens.

Behbahani Mandana, Rabiei Parisa, Mohabatkar Hassan


Allergen, Epitope prediction, Physiochemical properties, PseAAC, Secondary structure

General General

RegQCNET: Deep quality control for image-to-template brain MRI affine registration.

In Physics in medicine and biology

Affine registration of one or several brain image(s) onto a common reference space is a necessary prerequisite for many image processing tasks, such as brain segmentation or functional analysis. Manual assessment of registration quality is a tedious and time-consuming task, especially in studies comprising a large amount of data. An automated and reliable quality control (QC) becomes mandatory. Moreover, the computation time of the QC must be also compatible with the processing of massive datasets. Therefore, an automated deep neural network approaches appear as a method of choice to automatically assess registration quality. In the current study, a compact 3D convolutional neural network (CNN), referred to as RegQCNET, is introduced to quantitatively predict the amplitude of an affine registration mismatch between a registered image and a reference template. This quantitative estimation of registration error is expressed using metric unit system. Therefore, a meaningful task-specific threshold can be manually or automatically defined in order to distinguish usable and non-usable images. The robustness of the proposed RegQCNET is first analyzed on lifespan brain images undergoing various simulated spatial transformations and intensity variations between training and testing. Secondly, the potential of RegQCNET to classify images as usable or non-usable is evaluated using both manual and automatic thresholds. During our experiments, automatic thresholds are estimated using several computer-assisted classification models (logistic regression, support vector machine, naïve bayes and random forest) through cross-validation. To this end we used expert's visual quality control estimated on a lifespan cohort of 3953 brains. Finally, the RegQCNET accuracy is compared to usual image features such as image correlation coefficient and mutual information. Results show that the proposed deep learning QC is robust, fast and accurate to estimate affine registration error in processing pipeline.

Denis de Senneville Baudouin, Manjon Jose V, Coupé Pierrick


Deep Neural Network, Image-to-template registration, Quality Control

General General

A review of Cloud computing technologies for comprehensive microRNA analyses.

In Computational biology and chemistry

Cloud computing revolutionized many fields that require ample computational power. Cloud platforms may also provide huge support for microRNA analysis mainly through disclosing scalable resources of different types. In Clouds, these resources are available as services, which simplifies their allocation and releasing. This feature is especially useful during the analysis of large volumes of data, like the one produced by next generation sequencing experiments, which require not only extended storage space but also a distributed computing environment. In this paper, we show which of the Cloud properties and service models can be especially beneficial for microRNA analysis. We also explain the most useful services of the Cloud (including storage space, computational power, web application hosting, machine learning models, and Big Data frameworks) that can be used for microRNA analysis. At the same time, we review several solutions for microRNA and show that the utilization of the Cloud in this field is still weak, but can increase in the future when the awareness of their applicability grows.

Mrozek Dariusz


Big Data, Bioinformatics, Cloud computing, Data analysis, MiRNA, MicroRNA

Public Health Public Health

Prediction of suicide among 372,813 individuals under medical check-up.

In Journal of psychiatric research ; h5-index 59.0

BACKGROUND : Suicide is a serious social and public health problem. Social stigma and prejudice reduce the accessibility of mental health care services for high-risk groups, resulting in them not receiving interventions and committing suicide. A suicide prediction model is necessary to identify high-risk groups in the general population.

METHODS : We used national medical check-up data from 2009 to 2015 in Korea. The latest medical check-up data for each subject was set as an index point. Analysis was undertaken for an overall follow-up period (index point to the final tracking period) as well as for a one-year follow-up period. The training set was cross-validated fivefold. The predictive model was trained using a random forest algorithm, and its performance was measured using a separate test set not included in the training.

RESULTS : The analysis covered 372,813 individuals, with an average (SD) overall follow-up duration of 1.52 (1.52) years. When we predicted suicide during the overall follow-up period, the area under the receiver operating characteristic curve (AUC) was 0.849, sensitivity was 0.817, and specificity was 0.754. The performance of the predicted suicide risk model for one year from the index point was AUC 0.818, sensitivity 0.788, and specificity 0.657.

CONCLUSIONS : This is probably the first suicide predictive model using machine learning based on medical check-up data from the general population. It could be used to screen high-risk suicidal groups from the population through routine medical check-ups. Future studies may test preventive interventions such as exercise and alcohol in these high-risk groups.

Cho Seo-Eun, Geem Zong Woo, Na Kyoung-Sae


Artificial intelligence, Big data, Machine learning, Suicide

General General

Structure Reversal of Online Public Opinion for the Heterogeneous Health Concerns under NIMBY Conflict Environmental Mass Events in China.

In Healthcare (Basel, Switzerland)

Public opinions play an important role in the formation of Not in My Back Yard (NIMBY) conflict environmental mass events. Due to the continual interactions between affected groups and the corresponding government responses surrounding the public interests related to health, online public opinion structure reversal arises frequently in NIMBY conflict events, which pose a serious threat to social public security. To explore the underlying mechanism, this paper introduces an improved dynamic model which considers multiple heterogeneities in health concerns and social power of individuals and in government's ability. The experimental results indicate that the proposed model can provide an accurate description of the entire process of online public opinion structure reversal in NIMBY conflict environmental mass incidents on the Internet. In particular, the proportion of the individual agents without health interest appeals will delay the online public opinion structure reversal, and the upper threshold remains within regulatory limits from 0.4 to 0.5. Unlike some previous results that show that the guiding powers of the opinion leaders varied over its ratio in a fixed-sized group, our results suggest that the impact of opinion leaders is of no significant difference for the time of structure reversal after it increased to about 6%. Furthermore, a double threshold effect of online structure reversal during the government's response process was observed. The findings are beneficial for understanding and explaining the process of online public opinion structure reversal in NIMBY conflict environmental mass incidents, and provides theoretical and practical implications for guiding public or personal health opinions on the Internet and for a governments' effective response to them.

Hou Jundong, Yu Tongyang, Xiao Renbin


NIMBY conflict, agent-based model, heterogeneous health concerns, online public opinion structure reversal

General General

COVID-19 pandemic changes the food consumption patterns.

In Trends in food science & technology

Background : The COVID-19 pandemic affects all aspects of human life including their food consumption. The changes in the food production and supply processes introduce changes to the global dietary patterns.

Scope and Approach : To study the COVID-19 impact on food consumption process, we have analyzed two data sets that consist of food preparation recipes published before (69,444) and during the quarantine (10,009) period. Since working with large data sets is a time-consuming task, we have applied a recently proposed artificial intelligence approach called DietHub. The approach uses the recipe preparation description (i.e. text) and automatically provides a list of main ingredients annotated using the Hansard semantic tags. After extracting the semantic tags of the ingredients for every recipe, we have compared the food consumption patterns between the two data sets by comparing the relative frequency of the ingredients that compose the recipes.

Key Findings and Conclusions : Using the AI methodology, the changes in the food consumption patterns before and during the COVID-19 pandemic are obvious. The highest positive difference in the food consumption can be found in foods such as "Pulses/ plants producing pulses", "Pancake/Tortilla/Outcake", and "Soup/pottage", which increase by 300%, 280%, and 100%, respectively. Conversely, the largest decrease in consumption can be food for food such as "Order Perciformes (type of fish)", "Corn/cereals/grain", and "Wine-making", with a reduction of 50%, 40%, and 30%, respectively. This kind of analysis is valuable in times of crisis and emergencies, which is a very good example of the scientific support that regulators require in order to take quick and appropriate response.

Eftimov Tome, Popovski Gorjan, Petković Matej, Seljak Barbara Koroušić, Kocev Dragi


Artificial intelligence, COVID-19 pandemic, Dietary habits analysis, Food consumption, Food semantic annotation