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

General General

Modeling structure-activity relationships with machine learning to identify GSK3-targeted small molecules as potential COVID-19 therapeutics.

In Frontiers in endocrinology ; h5-index 55.0

Coronaviruses induce severe upper respiratory tract infections, which can spread to the lungs. The nucleocapsid protein (N protein) plays an important role in genome replication, transcription, and virion assembly in SARS-CoV-2, the virus causing COVID-19, and in other coronaviruses. Glycogen synthase kinase 3 (GSK3) activation phosphorylates the viral N protein. To combat COVID-19 and future coronavirus outbreaks, interference with the dependence of N protein on GSK3 may be a viable strategy. Toward this end, this study aimed to construct robust machine learning models to identify GSK3 inhibitors from Food and Drug Administration-approved and investigational drug libraries using the quantitative structure-activity relationship approach. A non-redundant dataset consisting of 495 and 3070 compounds for GSK3α and GSK3β, respectively, was acquired from the ChEMBL database. Twelve sets of molecular descriptors were used to define these inhibitors, and machine learning algorithms were selected using the LazyPredict package. Histogram-based gradient boosting and light gradient boosting machine algorithms were used to develop predictive models that were evaluated based on the root mean square error and R-squared value. Finally, the top two drugs (selinexor and ruboxistaurin) were selected for molecular dynamics simulation based on the highest predicted activity (negative log of the half-maximal inhibitory concentration, pIC50 value) to further investigate the structural stability of the protein-ligand complexes. This artificial intelligence-based virtual high-throughput screening approach is an effective strategy for accelerating drug discovery and finding novel pharmacological targets while reducing the cost and time.

Pirzada Rameez Hassan, Ahmad Bilal, Qayyum Naila, Choi Sangdun

2023

GSK3, QSAR, coronaviruses, machine learning, molecular descriptors

Pathology Pathology

A pathomic approach for tumor-infiltrating lymphocytes classification on breast cancer digital pathology images.

In Heliyon

BACKGROUND AND OBJECTIVES : The detection of tumor-infiltrating lymphocytes (TILs) could aid in the development of objective measures of the infiltration grade and can support decision-making in breast cancer (BC). However, manual quantification of TILs in BC histopathological whole slide images (WSI) is currently based on a visual assessment, thus resulting not standardized, not reproducible, and time-consuming for pathologists. In this work, a novel pathomic approach, aimed to apply high-throughput image feature extraction techniques to analyze the microscopic patterns in WSI, is proposed. In fact, pathomic features provide additional information concerning the underlying biological processes compared to the WSI visual interpretation, thus providing more easily interpretable and explainable results than the most frequently investigated Deep Learning based methods in the literature.

METHODS : A dataset containing 1037 regions of interest with tissue compartments and TILs annotated on 195 TNBC and HER2+ BC hematoxylin and eosin (H&E)-stained WSI was used. After segmenting nuclei within tumor-associated stroma using a watershed-based approach, 71 pathomic features were extracted from each nucleus and reduced using a Spearman's correlation filter followed by a nonparametric Wilcoxon rank-sum test and least absolute shrinkage and selection operator. The relevant features were used to classify each candidate nucleus as either TILs or non-TILs using 5 multivariable machine learning classification models trained using 5-fold cross-validation (1) without resampling, (2) with the synthetic minority over-sampling technique and (3) with downsampling. The prediction performance of the models was assessed using ROC curves.

RESULTS : 21 features were selected, with most of them related to the well-known TILs properties of having regular shape, clearer margins, high peak intensity, more homogeneous enhancement and different textural pattern than other cells. The best performance was obtained by Random-Forest with ROC AUC of 0.86, regardless of resampling technique.

CONCLUSIONS : The presented approach holds promise for the classification of TILs in BC H&E-stained WSI and could provide support to pathologists for a reliable, rapid and interpretable clinical assessment of TILs in BC.

Verdicchio Mario, Brancato Valentina, Cavaliere Carlo, Isgrò Francesco, Salvatore Marco, Aiello Marco

2023-Mar

Breast cancer, Digital pathology, Machine learning, Pathomics, Tumor infiltrating lymphocytes

General General

Does managerial short-termism always matter in a firm's corporate social responsibility performance? Evidence from China.

In Heliyon

Using data on Chinese A-share listed firms from 2008 to 2017, we explore how corporate social responsibility (CSR) performance is affected by managerial short-termism and what factors influence the association between the two. First, by employing text analysis in conjunction with machine learning, we construct a new managerial short-termism indicator. Using panel fixed models, we find that managerial short-termism has an adverse impact on CSR performance, and the results are consistent in a series of robustness checks. The heterogeneous test results show that the negative effect is significant only for firms with lower internal corporate governance, for firms in less competitive industries, for firms with less analyst attention, and for state-owned enterprises (SOEs). Additionally, a better institutional environment weakens the negative impact of managerial short-termism on CSR performance. The findings shed light on policy implications for emerging countries.

Xu Xiaohui, Yang Jun

2023-Mar

CSR performance, Managerial short-termism, Random forest regression

General General

Techniques of power system static security assessment and improvement: A literature survey.

In Heliyon

The secure operation of a power system depends on the available security evaluation tools and improvement techniques to tackle the disturbances or contingencies. The main objective of the survey presented in this paper is to provide a comprehensive review to the researchers, academicians, and utility engineers on the available techniques of static security assessment and improvement in modern power systems. Various performance indices are used to express the severity of limit violations from security margins typically in transmission line loading and buses voltage magnitude under a given disturbance or contingency. The accuracy and speed of computation considering uncertainties in renewable energy generation and load demand scenarios are the fundamental requirements of any security assessment tool. Conventional power flow and machine learning approaches are explored and compared for static security assessment. Although, conventional AC power flow provides accurate result, it is computationally demanding and slow process to assess the security of a power system with uncertainties and changing future operating scenarios considering simultaneous component failures. Several machine learning techniques have been studied to make fast and sufficiently accurate assessment. The application of FACTS devices to improve static security of a power system has been reviewed. To ensure the effectiveness of FACTS devices, various sensitivity and optimization approaches have been suggested for proper placement and sizing. The increasing complexity and uncertainty in power systems due to increased penetration of renewable energy resources and the introduction of new type of loads such as electric vehicles and heating loads suggests the development and application of more robust and portable security assessment tools such as deep learning algorithms and fast responding flexible security improvement mechanisms like FACTS devices.

Hailu Engidaw Abel, Nyakoe George Nyauma, Muriithi Christopher Maina

2023-Mar

FACTS device, Machine learning, Optimal allocation, Performance index, Power system uncertainties, Static security assessment, Static security improvement

General General

Scientometric and multidimensional contents analysis of PM2.5 concentration prediction.

In Heliyon

The foundation for the environmental department to take suitable measures and make a significant contribution towards improving air quality is the precise and dependable prediction of PM2.5 concentration. It is essential to review the development process and hotspots of PM2.5 concentration prediction studies over the past 20 years (2000-2021) comprehensively and quantitatively. This study used detailed bibliometric methods and CiteSpace software to visually analyze the PM2.5 pollution level. The outcomes found that the prediction research phases of PM2.5 can be broadly divided into three phases and enter the rapid growth phase after 2017. Five categories of keywords are clustered, and the forecasting data and forecasting methods are typical cluster representatives. Then, the construction and processing of PM2.5 concentration prediction datasets, the prediction methods and technical processes, and the determination of the prediction spatial-temporal scales are the main content of the analysis. In the future, it is necessary to concentrate on multi-source data fusion for PM2.5 concentration prediction at multiple spatial-temporal scales and focus on technology integration and innovative applications in forecasting models, especially the optimal use of deep machine learning methods to improve prediction accuracy and practical application conversion.

Gong Jintao, Ding Lei, Lu Yingyu, Qiong Zhang Yun Li

2023-Mar

Contents analysis, Forecasting methods, Forecasting scale, PM2.5 concentration prediction, Scientometric

General General

Optimal sizing of residential photovoltaic and battery system connected to the power grid based on the cost of energy and peak load.

In Heliyon

The use of renewable energy is necessary to achieve the goals of sustainable development, and sooner or later all countries are forced to plan and make policies for the use of this equipment. Considering the growing trend of smart systems and the ability of these systems to control and use renewable resources, it is necessary to investigate how to control and optimally use these resources in smart systems. Considering the geographical conditions and significant solar energy radiation in Iran, the most suitable option for using renewable energy in residential buildings is solar energy. Among the types of solar energy used around the world, photovoltaic panels are used more due to their wide range, being cheaper than other sources of electric power from solar energy and more durable than other sources. In order to reduce widespread losses and reduce the cost of transmission and distribution, increase efficiency, the possibility of the presence of private sector investors and increase the security and stability of the power grid, distributed production of electrical energy at consumption locations using small-scale units is the most cost-effective way to use home solar panels. Also, the production of energy from wind turbines can be done in the areas where anemometer data determine it to be suitable. The combination of solar energy and wind energy can effectively reduce the need for batteries, but studies show that this combination is only economically viable when it is used on a large scale and with high powers, which requires a lot of investment. Large initial capital is one of the biggest problems of distributed production systems, so the use of artificial intelligence methods for accurate capacity determination of renewable energy production systems becomes doubly important. The economic results show that the least cost of electricity and net price cost are 0.44 $ per kWh and 15.0 million $ respectively, when the converter size was gradually changed, with a renewable fraction of 46.7%.

Vahabi Khah Mohammad, Zahedi Rahim, Eskandarpanah Reza, Mirzaei Amir Mohammad, Farahani Omid Noudeh, Malek Iman, Rezaei Nima

2023-Mar

PV battery System, Renewable energy, Sizing, Solar energy