Computer Experts Research Articles

Computational application of internationally harmonized defined approaches to skin sensitization: DASS App.

Chemically induced skin sensitization, or allergic contact dermatitis, is a common occupational and public health issue. Regulatory authorities require an assessment of potential to cause skin sensitization for many chemical products. Defined approaches for skin sensitization (DASS) identify potential chemical skin sensitizers by integrating data from multiple non-animal tests based on human cells, molecular targets, and computational model predictions using standardized data interpretation procedures. While several DASS are internationally accepted by regulatory agencies, the data interpretation procedures vary in logical complexity, and manual application can be time-consuming or prone to error. We developed the DASS App, an open-source web application, to facilitate user application of three regulatory testing strategies for skin sensitization assessment: the Two-out-of-Three (2o3), the Integrated Testing Strategy (ITS), and the Key Event 3/1 Sequential Testing Strategy (KE 3/1 STS) without the need for software downloads or computational expertise. The application supports upload and analysis of user-provided data, includes steps to identify inconsistencies and formatting issues, and provides predictions in a downloadable format. This open-access web-based implementation of internationally harmonized regulatory guidelines for an important public health endpoint is designed to support broad user uptake and consistent, reproducible application. The DASS App is freely accessible via https://ntp.niehs.nih.gov/go/952311 and all scripts are available on GitHub ( https://github.com/NIEHS/DASS ).

ViralWasm: a client-side user-friendly web application suite for viral genomics.

The genomic surveillance of viral pathogens such as SARS-CoV-2 and HIV-1 has been critical to modern epidemiology and public health, but the use of sequence analysis pipelines requires computational expertise, and web-based platforms require sending potentially sensitive raw sequence data to remote servers. We introduce ViralWasm, a user-friendly graphical web application suite for viral genomics. All ViralWasm tools utilize WebAssembly to execute the original command line tools client-side directly in the web browser without any user setup, with a cost of just 2-3x slowdown with respect to their command line counterparts. The ViralWasm tool suite can be accessed at: https://niema-lab.github.io/ViralWasm.

Impact of unstable environment on the brain drain of highly skilled professionals, healthcare workers, researchers, and research productivity in Pakistan.

The geo-strategic position of Pakistan on the world map is incredibly important and idyllic as the country is considered the gateway to central Asia. Pakistan has faced political instability for the last three decades, causing a brain drain and adversely affecting socioeconomic growth. This study aims to investigate the impact of an unstable environment on the brain drain of highly skilled professionals, healthcare workers, researchers, and research productivity in Pakistan from January 2000 to December 2022. The data were recorded from the World Bank, the Higher Education Commission (HEC) Pakistan, the Pakistan Medical and Dental Council (PMDC), the Bureau of Emigration and Overseas Employment (BEOS), Pakistan, Academic Ranking of World Universities (ARWU), and Web of Science Clarivate Analytics. Initially, 32 documents were selected in this study, and finally, eight fact sheets, official government websites, and international organizations were included. The result revealed that due to political instability, in 2022 about 832,339 highly qualified and accomplished experts headed abroad, among them 17976 (2.15%) were highly qualified and 20865 (2.50%) were highly competent professionals. These include accountants 7197 (0.86%), engineers 6,093 (0.73%), agricultural experts 3,110 (0.37%), doctors 2,464 (0.29%), computer experts 2,147 (0.25%), nurses and paramedics 1768 (0.21%), technicians 23347 (2.80%), electricians 20322 (2.44%), and schools and university faculty 1004 (0.12%). Pakistan has a total of 380 Higher Education Commission-indexed academic journals, among them 11 (2.89%) academic journals were indexed in the Web of Science and 23 journals were placed in the Web of Science emerging indexing. Among these journals, only one journal surpassed the impact factor of more than 2.0. The quartile ranking of Pakistani journals is 01 journal in Q2; 02 in Q3; and the remaining 08 journals in Q4. From August 1947 to December 2022, Pakistan produced a total of 259249 research articles, and from January 2000 to December 2022, the number of articles published was 248457 (95.83%). Since the last 22 years, the trend of research publications was continuously increased; however, the rising trend decreased in 2022 with a declined rate of 1263 (3.42%). The unstable sociopolitical environment in Pakistan caused a brain drain of highly qualified and skilled professionals and impaired the global standing of universities, academic journals, and research productivity in Pakistan. Pakistan must resolve the instability and establish sustainable policies to minimize the brain drain of highly qualified and skilled experts and convalesce their academic institutes and their research productivity for the development of the nation.

An approach to logical-mathematical computer modeling of linear and nonlinear dynamical systems

The paper deals with the problem of modeling linear and nonlinear dynamical systems using information technologies and programming. The processes of modeling, synthesis and inference of solutions to problems are considered, and the possibility of their integration within the described approach is shown. The substantive aspects of the development of special mathematical and algorithmic support for the construction of a software system for the analysis and processing of expert information for the purposes of automated synthesis and inference of solutions are briefly outlined. The aim of the work is to create a new approach of logical-mathematical computer modeling of linear and nonlinear dynamical systems and to develop a prototype of a software computational expert system based on it. As a result of the research, a universal approach of logical-mathematical computer modeling of linear and nonlinear dynamical systems has been developed and proposed. The proposed approach can be used to organize the process of computer modeling and automated synthesis of task solutions with the output of their results. The mathematical model of the knowledge base and process of its construction for the selected subject area, as well as the algorithm for outputting solutions to problems with its software implementation in the Python programming language, are shown. Examples of solution output for various linear and nonlinear problems are given. The developed prototype of the software computational expert system using the proposed logical- mathematical approach will significantly simplify the process of modeling dynamical systems and make the solution of problems' simpler and more understandable.

Analysis of Job Competency Needs of Computer and Information Engineering Program by Referring to KKNI in Vocational Schools

This study aims to determine (1) the need for work competency in Computer and Network Engineering Skills Package based on the KKNI. (2) The relevance level of Computer and Network Engineering Expertise Package based on KKNI. This type of research uses a mixed method approach to the Concurrent Embedded Design model, using data collection techniques of observation, interviews, essays, triangulation and questionnaires. The results of the study indicate that the work competency requirements of the TKJ SMKN Makassar City expertise package refer to KKNI: 1) Preparing the optical fiber supporting tools and materials; 2) Installing fiber optic cable networks; 3) Carry out fiber optic network cable tester; 4) Configuring the management switch on the network; 5) Designing network topology; 6) Configuring routing on network devices in an autonomous system; 7) Change the device according to your needs; 8) Routing using a Cisco router. The relevance level of the competency package of TKJ SMKN Makassar City referring to KKNI shows an average score of 116.32 in the Very Relevant category. The percentage frequency with a value of 52% states the Relevant category and the frequency of a percentage with a value of 48% in the Very Relevant category. Based on these results, the Computer and Network Engineering expertise package of the Makassar City Vocational School reforms the equipment and practice materials of the computer network and meets the competency needs of the TKJ expertise package to achieve work competency based on the KKNI

OntoFoCE and ObE Forensics. Email-traceability supporting tools for digital forensics

This paper shows the research conducted to respond to a continuous requirement of justice regarding the application of scientifically supported forensic tools. Considering ontological engineering as the appropriate framework to respond to this requirement, the article presents OntoFoCE (Spanish abbreviation for Ontology for Electronic Mail Forensics), a specific ontology for the forensic analysis of emails. The purpose of this ontology is to help the computer expert in the validation of an email presented as judicial evidence. OntoFoCE is the fundamental component of the ObE Forensics (Ontology-based Email Forensics) tool. Although there are numerous forensic tools to analyze emails, the originality of the one proposed here lies in the implementation of semantic technologies to represent the traceability of the email transmission process. From that point on, it is possible to provide answers to the items of digital evidence subject to the expert examination. These answers make it possible to support these evidence items in the forensic analysis of an email and to guarantee the gathering of scientifically and technically accepted results that are valid for justice. Thus, the research question that is tried to be answered is: Is it possible to apply ontological engineering as a scientific support to design and develop a forensic tool that allows automatic answers to the evidence items subject to the expert examination in the forensic analysis of emails? 

Editorial

Dear Readers,  At the end of this year, it gives me great pleasure to announce the eleventh regular issue of 2023. In this issue, various topical aspects of computer science are covered in 6 articles by 18 authors from 7 countries (Argentina, Brazil, China, France, Germany, Spain, and Turkey). I would like to thank all the authors for their sound research and the editorial board for the highly valuable review effort and comments for improvement. These contributions, together with the generous support of the consortium members, sustain the quality of our journal. I am looking forward to continuing my work as Managing Editor-in-Chief with the J.UCS community.  In an ongoing effort to further strengthen our journal, I would like to expand the editorial board: If you are a tenured associate professor or above with a strong publication record, you are welcome to apply to join our editorial board. We are also interested in high-quality proposals for special issues on new topics and trends. Please consider yourself and encourage your colleagues to submit high-quality articles or special issue proposals for our journal. Finally, we are looking for further financial support from potential consortium members to cover the costs of publishing the journal next year.  In this regular issue, I am very pleased to introduce the following 6 accepted articles: F. Kebire Bardak, M. Nuri Seyman, and Feyzullah Temurtaş from Turkey present in their research a hybrid algorithm for emotion classification based on electroencephalogram signals, which is composed of a radial basis function neural network and a probabilistic neural network. In a collaborative research effort between Spain and France, Anita Herrera, Ángel Arroyo, Alfredo Jiménez and Álvaro Herrero conduct a comprehensive review of the different techniques and models with regard to Artificial Intelligence when applied to the tourism industry. In a collaboration between researchers from Brazil and Germany, Ana Cristina Alves de Oliveira, Marco Aurélio Spohn, Christof Fetzer, Le Quoc Do, and André Martin aim to address the cost problem of DaaS by developing a model that optimizes the cost of querying distributed data sources over virtual machines spread across multisite data centers. Herminia Beatriz Parra and Marcela Vegetti from Argentina present in their article OntoFoCE, Ontology for Electronic Mail Forensics, which is a specific ontology for the forensic analysis of emails to help the computer expert in validating an email presented as judicial evidence. Valdicélio Santos and Michel S. Soares from Brazil propose a framework, and then the design and further evaluation of a web-based application to support software architects in using the activities and tasks of the architecture conceptualization clause based on the ISO/IEC/IEEE 42020 framework. Last but not least, Yunwu Xu and Yan Li from China contribute to the improvement of an existing wireless sensor network coverage optimization method which is based on the pigeon-inspired optimization algorithm.  Season greetings to all of you, relaxing holidays and ‘Enjoy Reading’!  Cordially,  Christian Gütl, Managing Editor  Graz University of Technology, Graz, Austria

Data Visualization Analysis in the Management Information System for Submitting Credit Scores for Education Personnel

Education staff have an important role in facilitating the implementation of the tridharma of higher education and are an indicator of educational administration success. This study looks at how data visualization was implemented in the Management Information System for Submitting Credit Scores for Education Personnel. The research is primarily concerned with the Functional Position of Intermediate Expert Computer Staff. The study's goal is to create web-based data visualization tools to enable submitting and assessing credit scores for Intermediate Computer Experts easier, thereby meeting the requirement for efficiency and accuracy in the promotion and position process. This study employs a research and development (R&D) methodology with an iterative prototype approach. The initial step involves a needs analysis, including an in-depth understanding of the Associate Computer Expert promotion process and the associated administrative requirements. Next, a web-based data visualization prototype was designed, which included an intuitive user interface, database integration, and a credit number calculation algorithm. The prototype was then implemented and tested on a limited basis in the IPDN environment. The proposed system is designed to provide easy access, facilitate data verification, and enable computerized sorting and calculation of credit numbers. The main contribution of this research lies in developing information technology solutions that can increase the transparency and effectiveness of administrative processes in the IPDN environment. It is hoped that the output of this research can provide conceptual and practical contributions to managing the credit figures for educational staff and provide a basis for developing similar systems in other educational institutions.

SurviveR: a flexible shiny application for patient survival analysis

Kaplan–Meier (KM) survival analyses based on complex patient categorization due to the burgeoning volumes of genomic, molecular and phenotypic data, are an increasingly important aspect of the biomedical researcher’s toolkit. Commercial statistics and graphing packages for such analyses are functionally limited, whereas open-source tools have a high barrier-to-entry in terms of understanding of methodologies and computational expertise. We developed surviveR to address this unmet need for a survival analysis tool that can enable users with limited computational expertise to conduct routine but complex analyses. surviveR is a cloud-based Shiny application, that addresses our identified unmet need for an easy-to-use web-based tool that can plot and analyse survival based datasets. Integrated customization options allows a user with limited computational expertise to easily filter patients to enable custom cohort generation, automatically calculate log-rank test and Cox hazard ratios. Continuous datasets can be integrated, such as RNA or protein expression measurements which can be then used as categories for survival plotting. We further demonstrate the utility through exemplifying its application to a clinically relevant colorectal cancer patient dataset. surviveR is a cloud-based web application available at https://generatr.qub.ac.uk/app/surviveR, that can be used by non-experts users to perform complex custom survival analysis.

From pixels to insights: Machine learning and deep learning for bioimage analysis.

Bioimage analysis plays a critical role in extracting information from biological images, enabling deeper insights into cellular structures and processes. The integration of machine learning and deep learning techniques has revolutionized the field, enabling the automated, reproducible, and accurate analysis of biological images. Here, we provide an overview of the history and principles of machine learning and deep learning in the context of bioimage analysis. We discuss the essential steps of the bioimage analysis workflow, emphasizing how machine learning and deep learning have improved preprocessing, segmentation, feature extraction, object tracking, and classification. We provide examples that showcase the application of machine learning and deep learning in bioimage analysis. We examine user-friendly software and tools that enable biologists to leverage these techniques without extensive computational expertise. This review is a resource for researchers seeking to incorporate machine learning and deep learning in their bioimage analysis workflows and enhance their research in this rapidly evolving field.

TidyGEO: preparing analysis-ready datasets from Gene Expression Omnibus.

TidyGEO is a Web-based tool for downloading, tidying, and reformatting data series from Gene Expression Omnibus (GEO). As a freely accessible repository with data from over 6 million biological samples across more than 4000 organisms, GEO provides diverse opportunities for secondary research. Although scientists may find assay data relevant to a given research question, most analyses require sample-level annotations. In GEO, such annotations are stored alongside assay data in delimited, text-based files. However, the structure and semantics of the annotations vary widely from one series to another, and many annotations are not useful for analysis purposes. Thus, every GEO series must be tidied before it is analyzed. Manual approaches may be used, but these are error prone and take time away from other research tasks. Custom computer scripts can be written, but many scientists lack the computational expertise to create such scripts. To address these challenges, we created TidyGEO, which supports essential data-cleaning tasks for sample-level annotations, such as selecting informative columns, renaming columns, splitting or merging columns, standardizing data values, and filtering samples. Additionally, users can integrate annotations with assay data, restructure assay data, and generate code that enables others to reproduce these steps.

Scaling up single-cell RNA-seq data analysis with CellBridge workflow.

Single-cell RNA sequencing (scRNA-seq) has revolutionized the study of gene expression at the individual cell level, unraveling unprecedented insights into cellular heterogeneity. However, the analysis of scRNA-seq data remains a challenging and time-consuming task, often demanding advanced computational expertise, rendering it impractical for high-volume environments and applications. We present CellBridge, an automated workflow designed to simplify the standard procedures entailed in scRNA-seq data analysis, eliminating the need for specialized computational expertise. CellBridge utilizes state-of-the-art computational methods, integrating a range of advanced functionalities, covering the entire process from raw unaligned sequencing reads to cell type annotation. Hence, CellBridge accelerates the pace of discovery by seamlessly enabling insights into vast volumes of scRNA-seq data, without compromising workflow control and reproducibility. The source code, detailed documentation, and materials required to reproduce the results are available on GitHub and archived in Zenodo. For the CellBridge pre-processing step (v1.0.0), access the GitHub repository at https://github.com/Sanofi-Public/PMCB-ToBridge and the Zenodo archive at https://zenodo.org/records/10246161. For the CellBridge processing step (v1.0.0), visit the GitHub repository at https://github.com/Sanofi-Public/PMCB-CellBridge and the Zenodo archive at https://zenodo.org/records/10246046.

The NeuGRID Workflow: a “Swiss Army knife” for MRI processing

AbstractBackgroundThe advent of big data and artificial intelligence has energized the neuroimaging community with powerful processing tools and the need for large‐scale computational resources for data analysis has increased. Not all neuroscientists have access to extensive resources or have sufficient expertise to configure these libraries, making them difficult to use.MethodA collection of popular MRI scan processing software, (i.e.: Fsl, FreeSurfer, Ants, SPM, Adaboost, Neuromorphometrics, LPA, Tracula) was selected as a proof of concept to be included in the NeuGRID Workflow to produce an advanced tool for group analysis and biomarkers assessment.ResultThe NeuGRID Workflow was designed to allow the user to build a custom MRI processing pipeline by means of a layered structure (Fig.1) available for users at the URL https://neugrid2.eu/index.php/workflowgroup. In the first layer, the user must upload a compressed file containing T13D, FLAIR, and DWI scans of subjects. In the second layer, the user selects which kind of MRI sequence to process. If DICOMs were uploaded, the third layer provides tools to convert DICOMs into NIFTI, the default format for all subsequent workflow processes. All DICOMs are anonymized upon upload. The fourth layer allows the user to choose how images are preprocessed, and the preprocessing pipelines can be customized for different modalities. In the final layer, the user can choose how to analyze the images to calculate volume, thickness, area and curvature of brain regions, quantify white‐matter lesions and reconstruct major white‐matter pathways. The triggered job is efficiently parallelized using a Sun Grid Engine scheduler to reduce computation time. After the scans are processed in the NeuGRID cluster (450 CPUs, 2.5TB memory, 400TB storage), the user is notified by email that the job is finished and the results can be downloaded.ConclusionThe NeuGRID Workflow is a practical tool that allows researchers without computational resources and/or expertise to design a custom pipeline to process large amounts of data from anywhere using a traditional laptop or personal computer. The collection of heterogeneous tools provides a high degree of freedom in pipeline design, making NeuGRID Workflow a Swiss Army knife for MRI processing

Expert Systems in HRM : A Digital Construction

The main objective of this research is to carefully describe the role of Expert Systems (ES) in human resource management discourse. What logical constructs must be built when there is a desire to empower the capabilities of computational expert systems in their pragmatic use. Human Resource Expert Systems (HRES) can mimic the decision-making capabilities of a Human Resource Expert (HRE). The design and development of HRES depends on top management initiative and support. The implementation of HRES should be holistic, with maximum participation from all departments in the organization. This study uses a qualitative descriptive method, with a literature study approach. The main data is drawn from a variety of selected journal papers, taken from reputable journals. Other sources that are compatible with the research, such as news, academic papers, videos and other documents. The study found that there is a challenge to reduce the fear of computers in HR functions and resistance to change. HRES can increase productivity levels by assisting HR managers in making rational decisions to solve unstructured HR related problems. The emphasis is on organizational change and bold initiatives to further implement ES in the HR domain and overcome challenges. This paper aims to analyse the focus areas of HRES and the functions where HRES faces limitations and challenges.

Automatic Classification of Spectra with IEF-SCNN

Telescopes such as the Large Sky Area Multi-Object Spectroscopic Telescope and the Sloan Digital Sky Survey have produced an extensive collection of spectra, challenging the feasibility of manual classification in terms of accuracy and efficiency. To overcome these limitations, machine learning techniques are increasingly being utilized for automated spectral classification. However, these approaches primarily treat spectra as frequency domain signals, and lack robustness in low signal-to-noise ratio (S/N) scenarios and for small datasets of rare celestial objects. Moreover, they frequently neglect nuanced expert astronomical understanding. In this study, we draw inspiration from the human spectral discrimination process and propose a new model called the Image-EFficientNetV2-Spectrum Convolutional Neural Network (IEF-SCNN). IEF-SCNN combines spectral images using EfficientNetV2 with one-dimensional (1D) spectra through a 1DCNN. This integration effectively incorporates astronomical expertise into the classification process. Specifically, we plot the spectrum as an image and then classify it in a way that incorporates an attention mechanism. This attention mechanism mimics human observation of images for classification, selectively emphasizing relevant information while ignoring irrelevant details. Experimental data demonstrate that IEF-SCNN outperforms existing models in terms of the F1-score and accuracy metrics, particularly for low S/N (<6) data. Using progressive learning and an attention mechanism, the model trained on 12,000 M-class stars with an S/N below 6 achieved an accuracy of 87.38% on a 4000-sample test set. This surpasses traditional models (support vector machine with 83.15% accuracy, random forest with 65.40%, and artificial neural network with 84.40%) and the 1D stellar spectral CNN (85.65% accuracy). This research offers a foundation for the development of innovative methods for the automated identification of specific celestial objects, and can promote the creation of user-friendly software for astronomers who may not have computational expertise.

Designing Interactive Multimedia-Based Learning Media Using Augmented Reality in Basic Computer and Networking Subjects Computer and Basic Networking for School Expertise Package Vocational High School

Learning infrastructure is one of the supporting factors for vocational high school learning activities for the Computer and Informatics Engineering expertise program. Less effective learning media used by teachers as well as understanding and activeness of students in the learning process of this research background. The main objective of this research is to design and implement interactive multimedia based on Augmented reality with Auditory, Intellectually, and Repetition (AIR) learning models to determine the cognitive enhancement of students in learning network topology on basic computer and network subjects. Augmented reality-based interactive multimedia uses a comprehensive life cycle development model (SHM) and the research method used is quantitative with a sample of class X (ten) Multimedia students of SMK Negeri 1 Cipatat. From this research, the results obtained: (1) interactive multimedia is good and suitable for use. Obtained media value of 82% and material of 90.74% which is very well interpreted by media experts and subject teachers. (2) Interactive multimedia can improve students' cognitive with the acquisition of an average value of 0.697 with criteria that have "medium" criteria. (3) the students responded to the interactive multimedia learning media based on Augmented Reality, which was quite good, with a value of 80.24% and included in the “very good” category.

DESIGN AN E-CATALOG ON INSTAGRAM USING CORELDRAW AS THE ADVERTISING

This research aims to provide complete information about Rumah Kinasih's products by developing E-Catalog as an advertising medium on Instagram. The research design used was Action Research. The research procedure consists of planning, action, observation, and reflection. Research data were collected through questionnaires distributed to 1 Owner, 2 marketing experts, 2 computer experts, 10 consumers, and 20 potential customers. The effectiveness of the design is measured using the EPIC Model (Emphaty, Persuasion, Impact, Communication). This is due to the attractive and creative design of the E-Catalog which provides detailed or information related to the products offered by Rumah Kinasih, Blitar Regency. The conclusion which could be inferred is that the E-Catalog product is very effective to be used as Instagram advertising media at Rumah Kinasih, Blitar Regency.

Magnetic Resonance Imaging-Based Reference Values for Two-Dimensional Quantitative Brain Metrics in a Cohort of Extremely Preterm Infants

Introduction: Cerebral magnetic resonance imaging (cMRI) is an important diagnostic tool in neonatology. In addition to qualitative analysis, quantitative measurements may help identify infants with impaired brain growth. This study aimed to create reference values for brain metrics of various brain areas in neonates without major brain injuries born before 28 weeks of gestation. Methods: This retrospective study analyzes cMRI imaging data of high-risk patients without severe brain pathologies at term-equivalent age, collected over 4 years since November 2017. Nineteen brain areas were measured, reference values created, and compared to published values from fetal and postnatal MRI. Furthermore, correlations between brain metrics and gestational age at birth were evaluated. Results: A total of 174 cMRI examinations were available for analysis. Reference values including cut-offs for impaired brain growth were established for different gestational age groups. There was a significant correlation between gestational age at birth and larger “tissue” parameters, as well as smaller “fluid” parameters, including intracerebral and extracerebral spaces. Discussion: With quantitative brain metrics infants with impaired brain growth might be detected earlier. Compared to preexisting reference values, these are the first of a contemporary collective of extremely preterm neonates without severe brain injuries. Measurements can be easily performed by radiologists as well as neonatologists without specialized equipment or computational expertise. Conclusion: Two-dimensional cMRI brain measurements at term-equivalent age represent an easy and reliable approach for the evaluation of brain size and growth in infants at high risk for neurodevelopmental impairment.

TFNetPropX: A Web-Based Comprehensive Analysis Tool for Exploring Condition-Specific RNA-Seq Data Using Transcription Factor Network Propagation

Understanding condition-specific biological mechanisms from RNA-seq data requires comprehensive analysis of gene expression data, from the gene to the network level. However, this requires computational expertise, which limits the accessibility of data analysis for understanding biological mechanisms. Therefore, the development of an easy-to-use and comprehensive analysis system is essential. In response to this issue, we present TFNetPropX, a user-friendly web-based platform designed to perform gene-level, gene-set-level, and network-level analysis of RNA-seq data under two different conditions. TFNetPropX performs comprehensive analysis, from DEG analysis to network propagation, to predict TF-affected genes with a single request, and provides users with an interactive web-based visualization of the results. To demonstrate the utility of our system, we performed analysis on two TF knockout RNA-seq datasets and effectively reproduced biologically significant findings. We believe that our system will make it easier for biological researchers to gain insights from different perspectives, allowing them to develop diverse hypotheses and analyses.

Deep homogenization networks for elastic heterogeneous materials with two- and three-dimensional periodicity

We present a deep learning framework that leverages computational homogenization expertise to predict the local stress field and homogenized moduli of heterogeneous materials with two- and three-dimensional periodicity, which is named physics-informed Deep Homogenization Networks (DHN). To this end, the displacement field of a repeating unit cell is expressed as two-scale expansion in terms of averaging and fluctuating contributions dependent on the global and local coordinates, respectively, under arbitrary multi-axial loading conditions. The latter is regarded as a mesh-free periodic domain estimated using fully connected neural network layers by minimizing residuals of Navier's displacement equations of anisotropic microstructured materials for specified macroscopic strains with the help of automatic differentiation. Enabled by the novel use of a periodic layer, the boundary conditions are encoded directly in the DHN architecture which ensures exact satisfaction of the periodicity conditions of displacements and tractions without introducing additional penalty terms. To verify the proposed model, the local field variables and homogenized moduli were examined for various composites against the finite-element technique. We also demonstrate the feasibility of the proposed framework for simulating unit cells with locally irregular fibers via transfer learning and find a significant enhancement in the accuracy of stress field recovery during neural network retraining.