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

General General

Viscosity of Ionic Liquids: Application of the Eyring's Theory and a Committee Machine Intelligent System.

In Molecules (Basel, Switzerland)

Accurate determination of the physicochemical characteristics of ionic liquids (ILs), especially viscosity, at widespread operating conditions is of a vital role for various fields. In this study, the viscosity of pure ILs is modeled using three approaches: (I) a simple group contribution method based on temperature, pressure, boiling temperature, acentric factor, molecular weight, critical temperature, critical pressure, and critical volume; (II) a model based on thermodynamic properties, pressure, and temperature; and (III) a model based on chemical structure, pressure, and temperature. Furthermore, Eyring's absolute rate theory is used to predict viscosity based on boiling temperature and temperature. To develop Model (I), a simple correlation was applied, while for Models (II) and (III), smart approaches such as multilayer perceptron networks optimized by a Levenberg-Marquardt algorithm (MLP-LMA) and Bayesian Regularization (MLP-BR), decision tree (DT), and least square support vector machine optimized by bat algorithm (BAT-LSSVM) were utilized to establish robust and accurate predictive paradigms. These approaches were implemented using a large database consisting of 2813 experimental viscosity points from 45 different ILs under an extensive range of pressure and temperature. Afterward, the four most accurate models were selected to construct a committee machine intelligent system (CMIS). Eyring's theory's results to predict the viscosity demonstrated that although the theory is not precise, its simplicity is still beneficial. The proposed CMIS model provides the most precise responses with an absolute average relative deviation (AARD) of less than 4% for predicting the viscosity of ILs based on Model (II) and (III). Lastly, the applicability domain of the CMIS model and the quality of experimental data were assessed through the Leverage statistical method. It is concluded that intelligent-based predictive models are powerful alternatives for time-consuming and expensive experimental processes of the ILs viscosity measurement.

Mousavi Seyed Pezhman, Atashrouz Saeid, Nait Amar Menad, Hemmati-Sarapardeh Abdolhossein, Mohaddespour Ahmad, Mosavi Amir

2020-Dec-31

CMIS modeling, Eyring’s theory, artificial intelligence, artificial neural networks, ionic liquids, machine intelligent system, machine learning, viscosity

General General

How Resiliency and Hope Can Predict Stress of Covid-19 by Mediating Role of Spiritual Well-being Based on Machine Learning.

In Journal of religion and health

Nowadays, artificial intelligence (AI) and machine learning (ML) are playing a tremendous role in all aspects of human life and they have the remarkable potential to solve many problems that classic sciences are unable to solve appropriately. Neuroscience and especially psychiatry is one of the most important fields that can use the potential of AI and ML. This study aims to develop an ML-based model to detect the relationship between resiliency and hope with the stress of COVID-19 by mediating the role of spiritual well-being. An online survey is conducted to assess the psychological responses of Iranian people during the Covid-19 outbreak in the period between March 15 and May 20, 2020, in Iran. The Iranian public was encouraged to take part in an online survey promoted by Internet ads, e-mails, forums, social networks, and short message service (SMS) programs. As a whole, 755 people participated in this study. Sociodemographic characteristics of the participants, The Resilience Scale, The Adult Hope Scale, Paloutzian & Ellison's Spiritual Wellbeing Scale, and Stress of Covid-19 Scale were used to gather data. The findings showed that spiritual well-being itself cannot predict stress of Covid-19 alone, and in fact, someone who has high spiritual well-being does not necessarily have a small amount of stress, and this variable, along with hope and resiliency, can be a good predictor of stress. Our extensive research indicated that traditional analytical and statistical methods are unable to correctly predict related Covid-19 outbreak factors, especially stress when benchmarked with our proposed ML-based model which can accurately capture the nonlinear relationships between the collected data variables.

Nooripour Roghieh, Hosseinian Simin, Hussain Abir Jaafar, Annabestani Mohsen, Maadal Ameer, Radwin Laurel E, Hassani-Abharian Peyman, Pirkashani Nikzad Ghanbari, Khoshkonesh Abolghasem

2021-Jan-04

Covid-19, Hope, Machine learning, Resiliency, Spiritual well-being, Stress

Radiology Radiology

The Artificial Intelligence in Digital Pathology and Digital Radiology: Where Are We?

In Healthcare (Basel, Switzerland)

Thanks to the incredible changes promoted by Information and Communication Technology (ICT) conveyed today by electronic-health (eHealth) and mobile-health (mHealth), many new applications of both organ and cellular diagnostics are now possible [...].

Giansanti Daniele

2020-Dec-31

General General

How do Covid-19 policy options depend on end-of-year holiday contacts in Mexico City Metropolitan Area? A Modeling Study.

In medRxiv : the preprint server for health sciences

Background : With more than 20 million residents, Mexico City Metropolitan Area (MCMA) has the largest number of Covid-19 cases in Mexico and is at risk of exceeding its hospital capacity in late December 2020.

Methods : We used SC-COSMO, a dynamic compartmental Covid-19 model, to evaluate scenarios considering combinations of increased contacts during the holiday season, intensification of social distancing, and school reopening. Model parameters were derived from primary data from MCMA, published literature, and calibrated to time-series of incident confirmed cases, deaths, and hospital occupancy. Outcomes included projected confirmed cases and deaths, hospital demand, and magnitude of hospital capacity exceedance.

Findings : Following high levels of holiday contacts even with no in-person schooling, we predict that MCMA will have 1·0 million (95% prediction interval 0·5 - 1·7) additional Covid-19 cases between December 7, 2020 and March 7, 2021 and that hospitalizations will peak at 35,000 (14,700 - 67,500) on January 27, 2021, with a >99% chance of exceeding Covid-19-specific capacity (9,667 beds). If holiday contacts can be controlled, MCMA can reopen in-person schools provided social distancing is increased with 0·5 million (0·2 - 1·0) additional cases and hospitalizations peaking at 14,900 (5,600 - 32,000) on January 23, 2021 (77% chance of exceedance).

Interpretation : MCMA must substantially increase Covid-19 hospital capacity under all scenarios considered. MCMA's ability to reopen schools in mid-January 2021 depends on sustaining social distancing and that contacts during the end-of-year holiday were well controlled.

Funding : Society for Medical Decision Making, Gordon and Betty Moore Foundation, and Wadhwani Institute for Artificial Intelligence Foundation.

Research in context : Evidence before this study: As of mid-December 2020, Mexico has the twelfth highest incidence of confirmed cases of Covid-19 worldwide and its epidemic is currently growing. Mexico's case fatality ratio (CFR) - 9·1% - is the second highest in the world. With more than 20 million residents, Mexico City Metropolitan Area (MCMA) has the highest number and incidence rate of Covid-19 confirmed cases in Mexico and a CFR of 8·1%. MCMA is nearing its current hospital capacity even as it faces the prospect of increased social contacts during the 2020 end-of-year holidays. There is limited Mexico-specific evidence available on epidemic, such as parameters governing time-dependent mortality, hospitalization and transmission. Literature searches required supplementation through primary data analysis and model calibration to support the first realistic model-based Covid-19 policy evaluation for Mexico, which makes this analysis relevant and timely.Added value of this study: Study strengths include the use of detailed primary data provided by MCMA; the Bayesian model calibration to enable evaluation of projections and their uncertainty; and consideration of both epidemic and health system outcomes. The model projects that failure to limit social contacts during the end-of-year holidays will substantially accelerate MCMA's epidemic (1·0 million (95% prediction interval 0·5 - 1·7) additional cases by early March 2021). Hospitalization demand could reach 35,000 (14,700 - 67,500), with a >99% chance of exceeding current capacity (9,667 beds). Controlling social contacts during the holidays could enable MCMA to reopen in-person schooling without greatly exacerbating the epidemic provided social distancing in both schools and the community were maintained. Under all scenarios and policies, current hospital capacity appears insufficient, highlighting the need for rapid capacity expansion.Implications of all the available evidence: MCMA officials should prioritize rapid hospital capacity expansion. MCMA's ability to reopen schools in mid-January 2021 depends on sustaining social distancing and that contacts during the end-of-year holiday were well controlled.

Alarid-Escudero Fernando, Gracia Valeria, Luviano Andrea, Peralta Yadira, Reitsma Marissa B, Claypool Anneke L, Salomon Joshua A, Studdert David M, Andrews Jason R, Goldhaber-Fiebert Jeremy D

2020-Dec-22

Radiology Radiology

Biotypes of major depressive disorder: Neuroimaging evidence from resting-state default mode network patterns.

In NeuroImage. Clinical

BACKGROUND : Major depressive disorder (MDD) is heterogeneous disorder associated with aberrant functional connectivity within the default mode network (DMN). This study focused on data-driven identification and validation of potential DMN-pattern-based MDD subtypes to parse heterogeneity of the disorder.

METHODS : The sample comprised 1397 participants including 690 patients with MDD and 707 healthy controls (HC) registered from multiple sites based on the REST-meta-MDD Project in China. Baseline resting-state functional magnetic resonance imaging (rs-fMRI) data was recorded for each participant. Discriminative features were selected from DMN between patients and HC. Patient subgroups were defined by K-means and principle component analysis in the multi-site datasets and validated in an independent single-site dataset. Statistical significance of resultant clustering were confirmed. Demographic and clinical variables were compared between identified patient subgroups.

RESULTS : Two MDD subgroups with differing functional connectivity profiles of DMN were identified in the multi-site datasets, and relatively stable in different validation samples. The predominant dysfunctional connectivity profiles were detected among superior frontal cortex, ventral medial prefrontal cortex, posterior cingulate cortex and precuneus, whereas one subgroup exhibited increases of connectivity (hyperDMN MDD) and another subgroup showed decreases of connectivity (hypoDMN MDD). The hyperDMN subgroup in the discovery dataset had age-related severity of depressive symptoms. Patient subgroups had comparable demographic and clinical symptom variables.

CONCLUSIONS : Findings suggest the existence of two neural subtypes of MDD associated with different dysfunctional DMN connectivity patterns, which may provide useful evidence for parsing heterogeneity of depression and be valuable to inform the search for personalized treatment strategies.

Liang Sugai, Deng Wei, Li Xiaojing, Greenshaw Andrew J, Wang Qiang, Li Mingli, Ma Xiaohong, Bai Tong-Jian, Bo Qi-Jing, Cao Jun, Chen Guan-Mao, Chen Wei, Cheng Chang, Cheng Yu-Qi, Cui Xi-Long, Duan Jia, Fang Yi-Ru, Gong Qi-Yong, Guo Wen-Bin, Hou Zheng-Hua, Hu Lan, Kuang Li, Li Feng, Li Kai-Ming, Liu Yan-Song, Liu Zhe-Ning, Long Yi-Cheng, Luo Qing-Hua, Meng Hua-Qing, Peng Dai-Hui, Qiu Hai-Tang, Qiu Jiang, Shen Yue-Di, Shi Yu-Shu, Si Tian-Mei, Wang Chuan-Yue, Wang Fei, Wang Kai, Wang Li, Wang Xiang, Wang Ying, Wu Xiao-Ping, Wu Xin-Ran, Xie Chun-Ming, Xie Guang-Rong, Xie Hai-Yan, Xie Peng, Xu Xiu-Feng, Yang Hong, Yang Jian, Yu Hua, Yao Jia-Shu, Yao Shu-Qiao, Yin Ying-Ying, Yuan Yong-Gui, Zang Yu-Feng, Zhang Ai-Xia, Zhang Hong, Zhang Ke-Rang, Zhang Zhi-Jun, Zhao Jing-Ping, Zhou Ru-Bai, Zhou Yi-Ting, Zou Chao-Jie, Zuo Xi-Nian, Yan Chao-Gan, Li Tao

2020

Biotypes, Default mode network, Machine learning, Major depressive disorder, Resting-state fMRI

General General

DeepImmuno: Deep learning-empowered prediction and generation of immunogenic peptides for T cell immunity.

In bioRxiv : the preprint server for biology

** : T-cells play an essential role in the adaptive immune system by seeking out, binding and destroying foreign antigens presented on the cell surface of diseased cells. An improved understanding of T-cell immunity will greatly aid in the development of new cancer immunotherapies and vaccines for life threatening pathogens. Central to the design of such targeted therapies are computational methods to predict non-native epitopes to elicit a T cell response, however, we currently lack accurate immunogenicity inference methods. Another challenge is the ability to accurately simulate immunogenic peptides for specific human leukocyte antigen (HLA) alleles, for both synthetic biological applications and to augment real training datasets. Here, we proposed a beta-binomial distribution approach to derive epitope immunogenic potential from sequence alone. We conducted systematic benchmarking of five traditional machine learning (ElasticNet, KNN, SVM, Random Forest, AdaBoost) and three deep learning models (CNN, ResNet, GNN) using three independent prior validated immunogenic peptide collections (dengue virus, cancer neoantigen and SARS-Cov-2). We chose the CNN model as the best prediction model based on its adaptivity for small and large datasets, and performance relative to existing methods. In addition to outperforming two highly used immunogenicity prediction algorithms, DeepHLApan and IEDB, DeepImmuno-CNN further correctly predicts which residues are most important for T cell antigen recognition. Our independent generative adversarial network (GAN) approach, DeepImmuno-GAN, was further able to accurately simulate immunogenic peptides with physiochemical properties and immunogenicity predictions similar to that of real antigens. We provide DeepImmuno-CNN as source code and an easy-to-use web interface.

Data Availability : DeepImmuno Python3 code is available at https://github.com/frankligy/DeepImmuno . The DeepImmuno web portal is available from https://deepimmuno.herokuapp.com . The data in this article is available in GitHub and supplementary materials.

Li Guangyuan, Iyer Balaji, Prasath V B Surya, Ni Yizhao, Salomonis Nathan

2020-Dec-24