Pub Date : 2025-02-01DOI: 10.1016/j.softx.2025.102053
Ivan Jiron Araya , Michel Campos , Freddy I. Chan-Puc , Rafael Martínez-Peláez , Carlos Pon Soto , Homero Toral-Cruz
ConfSync is a specialized open-source tool for simulating synchronization of Tree Parity Machines (TPMs). This new tool introduces advanced verification models, including hash-based, matrix-based and polynomial function methods for synaptic weight comparison. With these enhancements, researchers and students can observe how different parameters and learning rules (Hebbian, Anti-Hebbian, Random-Walk) affect TPM synchronization, providing a greater understanding of neural synchronization and key exchange mechanisms. ConfSync automates stimulus and weight generation, output computation, and synaptic updates while providing comprehensive data export for thorough analysis and educational exploration of secure communication systems.
{"title":"ConfSync: Confirmation of mutual synchronization of the TPMs in Python","authors":"Ivan Jiron Araya , Michel Campos , Freddy I. Chan-Puc , Rafael Martínez-Peláez , Carlos Pon Soto , Homero Toral-Cruz","doi":"10.1016/j.softx.2025.102053","DOIUrl":"10.1016/j.softx.2025.102053","url":null,"abstract":"<div><div>ConfSync is a specialized open-source tool for simulating synchronization of Tree Parity Machines (TPMs). This new tool introduces advanced verification models, including hash-based, matrix-based and polynomial function methods for synaptic weight comparison. With these enhancements, researchers and students can observe how different parameters and learning rules (Hebbian, Anti-Hebbian, Random-Walk) affect TPM synchronization, providing a greater understanding of neural synchronization and key exchange mechanisms. ConfSync automates stimulus and weight generation, output computation, and synaptic updates while providing comprehensive data export for thorough analysis and educational exploration of secure communication systems.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"29 ","pages":"Article 102053"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143093061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.softx.2024.102000
Lukáš Sýkora, Tomáš Kliegr
The action-rules package provides an efficient method for mining action rules using the Action-Apriori algorithm, a modification of the traditional Apriori algorithm tailored specifically for action rule mining. Designed to generate counterfactual explanations, this Python package enables researchers and practitioners to discover actionable insights by integrating user-defined parameters directly into the rule generation process, reducing computational overhead. The action-rules package supports optional GPU acceleration to further speed up processing on large datasets. The package provides a user-friendly API, as well as a command-line interface for versatile use. The package supports the customization of stable and flexible attributes, as well as separate minimum support and confidence thresholds for both the desired and undesired components of the rules. Comprehensive documentation, including a Jupyter Notebook example, is provided to facilitate ease of use for both novice and expert users.
{"title":"action-rules: GPU-accelerated Python package for counterfactual explanations and recommendations","authors":"Lukáš Sýkora, Tomáš Kliegr","doi":"10.1016/j.softx.2024.102000","DOIUrl":"10.1016/j.softx.2024.102000","url":null,"abstract":"<div><div>The <span>action-rules</span> package provides an efficient method for mining action rules using the Action-Apriori algorithm, a modification of the traditional Apriori algorithm tailored specifically for action rule mining. Designed to generate counterfactual explanations, this Python package enables researchers and practitioners to discover actionable insights by integrating user-defined parameters directly into the rule generation process, reducing computational overhead. The <span>action-rules</span> package supports optional GPU acceleration to further speed up processing on large datasets. The package provides a user-friendly API, as well as a command-line interface for versatile use. The package supports the customization of stable and flexible attributes, as well as separate minimum support and confidence thresholds for both the desired and undesired components of the rules. Comprehensive documentation, including a Jupyter Notebook example, is provided to facilitate ease of use for both novice and expert users.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"29 ","pages":"Article 102000"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Anomaly detection is a recognized problem with high significance and impact in many real-world settings. Continual anomaly detection is an emerging paradigm that allows for the design of anomaly detection methods capable of adapting to new challenges in dynamic environments while retaining past knowledge. In this paper, we propose pyCLAD, the first software framework providing foundations for the design of new continual anomaly detection scenarios, strategies, and evaluation protocols, while streamlining the execution of experimental workflows with high reproducibility standards.
{"title":"pyCLAD: The universal framework for continual lifelong anomaly detection","authors":"Kamil Faber , Bartlomiej Sniezynski , Nathalie Japkowicz , Roberto Corizzo","doi":"10.1016/j.softx.2024.101994","DOIUrl":"10.1016/j.softx.2024.101994","url":null,"abstract":"<div><div>Anomaly detection is a recognized problem with high significance and impact in many real-world settings. Continual anomaly detection is an emerging paradigm that allows for the design of anomaly detection methods capable of adapting to new challenges in dynamic environments while retaining past knowledge. In this paper, we propose pyCLAD, the first software framework providing foundations for the design of new continual anomaly detection scenarios, strategies, and evaluation protocols, while streamlining the execution of experimental workflows with high reproducibility standards.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"29 ","pages":"Article 101994"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.softx.2024.102018
Jian Liu , Yuxin Chen , Hao Ding
The rapid proliferation of Internet of Things (IoT) devices has dramatically increased the demand for efficient data processing, making caching a critical solution for achieving high-performance and cost-effective storage in edge environments. However, small-scale edge devices often suffer from severe resource constraints. Furthermore, there is a scarcity of academic analyses addressing how various caching algorithms perform in such environments. To bridge this knowledge gap, we have proposed a cache simulation framework, CacheSim, as an open-source software solution for caching evaluation. CacheSim provides comprehensive metrics, including hit rate, performance, CPU usage, and power consumption, offering researchers valuable insights into the efficiency of different caching strategies. Through this platform, we aim to stimulate innovation in caching algorithms, encouraging the development of techniques optimized for the unique challenges posed by edge devices.
{"title":"CacheSim: A cache simulation framework for evaluating caching algorithms on resource-constrained edge devices","authors":"Jian Liu , Yuxin Chen , Hao Ding","doi":"10.1016/j.softx.2024.102018","DOIUrl":"10.1016/j.softx.2024.102018","url":null,"abstract":"<div><div>The rapid proliferation of Internet of Things (IoT) devices has dramatically increased the demand for efficient data processing, making caching a critical solution for achieving high-performance and cost-effective storage in edge environments. However, small-scale edge devices often suffer from severe resource constraints. Furthermore, there is a scarcity of academic analyses addressing how various caching algorithms perform in such environments. To bridge this knowledge gap, we have proposed a cache simulation framework, <em>CacheSim</em>, as an open-source software solution for caching evaluation. CacheSim provides comprehensive metrics, including hit rate, performance, CPU usage, and power consumption, offering researchers valuable insights into the efficiency of different caching strategies. Through this platform, we aim to stimulate innovation in caching algorithms, encouraging the development of techniques optimized for the unique challenges posed by edge devices.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"29 ","pages":"Article 102018"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.softx.2024.102033
Giuseppe Abrami, Markos Genios, Filip Fitzermann, Daniel Baumartz, Alexander Mehler
Processing large amounts of natural language text using machine learning-based models is becoming important in many disciplines. This demand is being met by a variety of approaches, resulting in the heterogeneous deployment of separate, partly incompatible, not natively scalable applications. To overcome the technological bottleneck involved, we have developed Docker Unified UIMA Interface, a system for the standardized, parallel, platform-independent, distributed and microservices-based solution for processing large and extensive text corpora with any NLP method. We present DUUI as a framework that enables automated orchestration of GPU-based NLP processes beyond the existing Docker Swarm cluster variant, and in addition to the adaptation to new runtime environments such as Kubernetes. Therefore, a new driver for DUUI is introduced, which enables the lightweight orchestration of DUUI processes within a Kubernetes environment in a scalable setup. In this way, the paper opens up novel text-technological perspectives for existing practices in disciplines that deal with the scientific analysis of large amounts of data based on NLP.
{"title":"Docker Unified UIMA Interface: New perspectives for NLP on big data","authors":"Giuseppe Abrami, Markos Genios, Filip Fitzermann, Daniel Baumartz, Alexander Mehler","doi":"10.1016/j.softx.2024.102033","DOIUrl":"10.1016/j.softx.2024.102033","url":null,"abstract":"<div><div>Processing large amounts of natural language text using machine learning-based models is becoming important in many disciplines. This demand is being met by a variety of approaches, resulting in the heterogeneous deployment of separate, partly incompatible, not natively scalable applications. To overcome the technological bottleneck involved, we have developed <span>Docker Unified UIMA Interface</span>, a system for the standardized, parallel, platform-independent, distributed and microservices-based solution for processing large and extensive text corpora with any NLP method. We present <span>DUUI</span> as a framework that enables automated orchestration of GPU-based NLP processes beyond the existing Docker Swarm cluster variant, and in addition to the adaptation to new runtime environments such as Kubernetes. Therefore, a new driver for <span>DUUI</span> is introduced, which enables the lightweight orchestration of <span>DUUI</span> processes within a Kubernetes environment in a scalable setup. In this way, the paper opens up novel text-technological perspectives for existing practices in disciplines that deal with the scientific analysis of large amounts of data based on NLP.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"29 ","pages":"Article 102033"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.softx.2025.102058
Vartul Shrivastava , Shekhar Shukla
In the prevailing technological paradigm, there exists various toolkits which researchers and practitioners can leverage to use Fuzzy Cognitive Maps (FCMs). However, a systematic management toolkit that encompasses security mechanisms, Kosko simulations, and what-if scenario analysis with AI-enabled inference remains scarce. To address this, we introduce FCM-VSS (Fuzzy Cognitive Maps – Visualizer, Simulator, and Summarizer), a robust web application that integrates Advanced Encryption Standard - Galois Counter Mode (AES-GCM) security, locally hosted Ollama-based AI agents for FCM summarization, and customizable Kosko inference mechanisms. This paper outlines FCM-VSS's architecture and web implementation, emphasizing on its potential as a secure, AI-powered FCM management tool.
{"title":"FCM-VSS: An AI powered secured fuzzy cognitive maps management toolkit for visualization, simulation and summarization","authors":"Vartul Shrivastava , Shekhar Shukla","doi":"10.1016/j.softx.2025.102058","DOIUrl":"10.1016/j.softx.2025.102058","url":null,"abstract":"<div><div>In the prevailing technological paradigm, there exists various toolkits which researchers and practitioners can leverage to use Fuzzy Cognitive Maps (FCMs). However, a systematic management toolkit that encompasses security mechanisms, Kosko simulations, and what-if scenario analysis with AI-enabled inference remains scarce. To address this, we introduce FCM-VSS (Fuzzy Cognitive Maps – Visualizer, Simulator, and Summarizer), a robust web application that integrates Advanced Encryption Standard - Galois Counter Mode (AES-GCM) security, locally hosted Ollama-based AI agents for FCM summarization, and customizable Kosko inference mechanisms. This paper outlines FCM-VSS's architecture and web implementation, emphasizing on its potential as a secure, AI-powered FCM management tool.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"29 ","pages":"Article 102058"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143092184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.softx.2025.102038
J. Bumberger , M. Abbrent , N. Brinckmann , J. Hemmen , R. Kunkel , C. Lorenz , P. Lünenschloss , B. Palm , T. Schnicke , C. Schulz , H. van der Schaaf , D. Schäfer
Addressing the challenges posed by climate change, biodiversity loss, and environmental pollution requires comprehensive monitoring and effective data management strategies that support real-time analysis and applicable across various scales in environmental system science. This paper introduces a versatile and transferable digital ecosystem for managing time series data, designed to adhere to the FAIR principles (Findable, Accessible, Interoperable, and Reusable). The system is highly adaptable, cloud-ready, and suitable for deployment in a wide range of settings, from small-scale projects to large-scale monitoring initiatives. The ecosystem comprises three core components: the Sensor Management System (SMS) for detailed metadata registration and management; time.IO, a platform for efficient time series data storage, transfer, and real-time visualization; and the System for Automated Quality Control (SaQC), which ensures data integrity through real-time analysis and quality assurance. With its modular and scalable architecture, the ecosystem enables automated workflows, enhances data accessibility, and supports seamless integration into larger research infrastructures, including digital twins and advanced environmental models. The use of standardized protocols and interfaces ensures that the ecosystem can be easily transferred and deployed across different environments and institutions. This approach enhances data accessibility for a broad spectrum of stakeholders, including researchers, policymakers, and the public, while fostering collaboration and advancing scientific research in environmental monitoring.
{"title":"Digital ecosystem for FAIR time series data management in environmental system science","authors":"J. Bumberger , M. Abbrent , N. Brinckmann , J. Hemmen , R. Kunkel , C. Lorenz , P. Lünenschloss , B. Palm , T. Schnicke , C. Schulz , H. van der Schaaf , D. Schäfer","doi":"10.1016/j.softx.2025.102038","DOIUrl":"10.1016/j.softx.2025.102038","url":null,"abstract":"<div><div>Addressing the challenges posed by climate change, biodiversity loss, and environmental pollution requires comprehensive monitoring and effective data management strategies that support real-time analysis and applicable across various scales in environmental system science. This paper introduces a versatile and transferable digital ecosystem for managing time series data, designed to adhere to the FAIR principles (Findable, Accessible, Interoperable, and Reusable). The system is highly adaptable, cloud-ready, and suitable for deployment in a wide range of settings, from small-scale projects to large-scale monitoring initiatives. The ecosystem comprises three core components: the Sensor Management System (SMS) for detailed metadata registration and management; time.IO, a platform for efficient time series data storage, transfer, and real-time visualization; and the System for Automated Quality Control (SaQC), which ensures data integrity through real-time analysis and quality assurance. With its modular and scalable architecture, the ecosystem enables automated workflows, enhances data accessibility, and supports seamless integration into larger research infrastructures, including digital twins and advanced environmental models. The use of standardized protocols and interfaces ensures that the ecosystem can be easily transferred and deployed across different environments and institutions. This approach enhances data accessibility for a broad spectrum of stakeholders, including researchers, policymakers, and the public, while fostering collaboration and advancing scientific research in environmental monitoring.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"29 ","pages":"Article 102038"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143127779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.softx.2025.102070
Damian Frąszczak, Edyta Frąszczak
Web2Vec is a Python library designed to simplify website analysis by converting websites into vector representations through feature extraction from their content and structure. Utilizing Scrapy-based web crawlers, it automates data collection and supports both single-page analysis and large-scale crawling. This flexibility allows users to adapt the library to their specific needs, whether for quick, focused analysis or systematic data collection. Integrating over 200 website parameters into a single, easy-to-use framework, Web2Vec simplifies analytical tasks, making it a valuable resource across various fields. By serving as a centralized code repository for researchers, it eliminates the need to repeatedly implement similar code, providing an all-in-one integrator to streamline workflows and save time.
{"title":"Web2Vec: A python library for website-to-vector transformation","authors":"Damian Frąszczak, Edyta Frąszczak","doi":"10.1016/j.softx.2025.102070","DOIUrl":"10.1016/j.softx.2025.102070","url":null,"abstract":"<div><div>Web2Vec is a Python library designed to simplify website analysis by converting websites into vector representations through feature extraction from their content and structure. Utilizing Scrapy-based web crawlers, it automates data collection and supports both single-page analysis and large-scale crawling. This flexibility allows users to adapt the library to their specific needs, whether for quick, focused analysis or systematic data collection. Integrating over 200 website parameters into a single, easy-to-use framework, Web2Vec simplifies analytical tasks, making it a valuable resource across various fields. By serving as a centralized code repository for researchers, it eliminates the need to repeatedly implement similar code, providing an all-in-one integrator to streamline workflows and save time.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"29 ","pages":"Article 102070"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143128001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.softx.2025.102057
Nornina J. Dia , Joseph C. Sieras , Suhaina A. Khalid , Amer Hussien T. Macatotong , Jeffrey M. Mondejar , Elizabeth R. Genotiva , Reymark D. Delena
Students’ attrition is a critical challenge in higher education, and the EduGuard RetainX software represents a transformative solution. To accurately identify at-risk students, this innovative platform harnesses advanced predictive analytics with knowledge of the personal and institutional costs of student dropout. Using the software, educators can provide students with tailored, student-centric support early on. In addition, the software fosters a collaborative, data-driven culture that allows a wide range of stakeholders to contribute to student success initiatives. The platform has demonstrated significant positive effects and real advantages, as shown by thorough evaluations of its usability using Dowding and Merrill's usability checklist, where it achieved an 89 % usability score. Further, by enabling a shift towards evidence-based practices and a relentless focus on supporting academic achievement and student persistence, the software is poised to completely reshape the higher education landscape.
{"title":"EduGuard RetainX: An advanced analytical dashboard for predicting and improving student retention in tertiary education","authors":"Nornina J. Dia , Joseph C. Sieras , Suhaina A. Khalid , Amer Hussien T. Macatotong , Jeffrey M. Mondejar , Elizabeth R. Genotiva , Reymark D. Delena","doi":"10.1016/j.softx.2025.102057","DOIUrl":"10.1016/j.softx.2025.102057","url":null,"abstract":"<div><div>Students’ attrition is a critical challenge in higher education, and the EduGuard RetainX software represents a transformative solution. To accurately identify at-risk students, this innovative platform harnesses advanced predictive analytics with knowledge of the personal and institutional costs of student dropout. Using the software, educators can provide students with tailored, student-centric support early on. In addition, the software fosters a collaborative, data-driven culture that allows a wide range of stakeholders to contribute to student success initiatives. The platform has demonstrated significant positive effects and real advantages, as shown by thorough evaluations of its usability using Dowding and Merrill's usability checklist, where it achieved an 89 % usability score. Further, by enabling a shift towards evidence-based practices and a relentless focus on supporting academic achievement and student persistence, the software is poised to completely reshape the higher education landscape.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"29 ","pages":"Article 102057"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143128002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-01DOI: 10.1016/j.softx.2025.102060
Rahil Ashtari Mahini , Gerardo Casanola-Martin , Stephen Szwiec , Simone A. Ludwig , Bakhtiyor Rasulev
Quantitative Structure-Activity/Property Relationship (QSAR/QSPR) is a machine learning approach to predict chemical and physical properties of pure compounds; however, it has limited application in multi-component compounds. The complex and layered nature of multi-component materials presents challenges in computing molecular representation, thus limiting the application of QSAR and QSPR. In this study, a new method has been proposed to derive numerical representation based on a combinatorial approach. It calculates all the possible interactions between different components in reaction using the Cartesian product over sets of descriptors of constituents, considering each multi-component material as a mixture system. A Python package was developed to calculate mixture descriptors based on this arithmetic equation, which can be used in machine learning-based QSAR and QSPR models.
{"title":"CombinatorixPy: Advancing mixture descriptors for computational chemistry","authors":"Rahil Ashtari Mahini , Gerardo Casanola-Martin , Stephen Szwiec , Simone A. Ludwig , Bakhtiyor Rasulev","doi":"10.1016/j.softx.2025.102060","DOIUrl":"10.1016/j.softx.2025.102060","url":null,"abstract":"<div><div>Quantitative Structure-Activity/Property Relationship (QSAR/QSPR) is a machine learning approach to predict chemical and physical properties of pure compounds; however, it has limited application in multi-component compounds. The complex and layered nature of multi-component materials presents challenges in computing molecular representation, thus limiting the application of QSAR and QSPR. In this study, a new method has been proposed to derive numerical representation based on a combinatorial approach. It calculates all the possible interactions between different components in reaction using the Cartesian product over sets of descriptors of constituents, considering each multi-component material as a mixture system. A Python package was developed to calculate mixture descriptors based on this arithmetic equation, which can be used in machine learning-based QSAR and QSPR models.</div></div>","PeriodicalId":21905,"journal":{"name":"SoftwareX","volume":"29 ","pages":"Article 102060"},"PeriodicalIF":2.4,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143128005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号