Reaction Impurity Prediction using a Data Mining Approach**

Arun, Adarsh; Guo, Zhen; Sung, Simon; Lapkin, Alexei A.

doi:10.1002/cmtd.202200062

Cited by 5 publications

(4 citation statements)

References 43 publications

(84 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Heuristic Step: ChemBalancer. ChemBalancer was partially adapted from Arun et al's balancing algorithm, 14 which was originally proposed as a step to identify chemical impurities produced in reactions. The workflow of Chem-Balancer is shown and summarized in Figure 2.…”

Section: ■ Methodsmentioning

confidence: 99%

Completing and Balancing Database Excerpted Chemical Reactions with a Hybrid Mechanistic-Machine Learning Approach

Zhang,

Arun,

Lapkin

2024

ACS Omega

Self Cite

View full text Add to dashboard Cite

Computer-aided synthesis planning (CASP) development of reaction routes requires an understanding of complete reaction structures. However, most reactions in the current databases are missing reaction coparticipants. Although reaction prediction and atom mapping tools can predict major reaction participants and trace atom rearrangements in reactions, they fail to identify the missing molecules to complete reactions. This is because these approaches are data-driven models trained on the current reaction databases, which comprise incomplete reactions. In this work, a workflow was developed to tackle the reaction completion challenge. This includes a heuristic-based method to identify balanced reactions from reaction databases and complete some imbalanced reactions by adding candidate molecules. A machine learning masked language model (MLM) was trained to learn from simplified molecular input line entry system (SMILES) sentences of these completed reactions. The model predicted missing molecules for the incomplete reactions, a workflow analogous to predicting missing words in sentences. The model is promising for the prediction of small-and middle-sized missing molecules in incomplete reaction records. The workflow combining both the heuristic and machine learning methods completed more than half of the entire reaction space.

show abstract

Section: ■ Methodsmentioning

confidence: 99%

Completing and Balancing Database Excerpted Chemical Reactions with a Hybrid Mechanistic-Machine Learning Approach

Zhang,

Arun,

Lapkin

2024

ACS Omega

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, the interpretability and transparency of data mining results are crucial for building trust among stakeholders and understanding complex data analyses. The challenges of data quality and preprocessing are also significant, as inadequate data handling can significantly impact data mining outcomes [ 310 , 311 , 312 , 313 , 314 , 315 , 316 ].…”

Section: Introductionmentioning

confidence: 99%

A 30-Year Review on Nanocomposites: Comprehensive Bibliometric Insights into Microstructural, Electrical, and Mechanical Properties Assisted by Artificial Intelligence

Gomes Souza,

Bhansali,

Pal

et al. 2024

Materials

View full text Add to dashboard Cite

From 1990 to 2024, this study presents a groundbreaking bibliometric and sentiment analysis of nanocomposite literature, distinguishing itself from existing reviews through its unique computational methodology. Developed by our research group, this novel approach systematically investigates the evolution of nanocomposites, focusing on microstructural characterization, electrical properties, and mechanical behaviors. By deploying advanced Boolean search strategies within the Scopus database, we achieve a meticulous extraction and in-depth exploration of thematic content, a methodological advancement in the field. Our analysis uniquely identifies critical trends and insights concerning nanocomposite microstructure, electrical attributes, and mechanical performance. The paper goes beyond traditional textual analytics and bibliometric evaluation, offering new interpretations of data and highlighting significant collaborative efforts and influential studies within the nanocomposite domain. Our findings uncover the evolution of research language, thematic shifts, and global contributions, providing a distinct and comprehensive view of the dynamic evolution of nanocomposite research. A critical component of this study is the “State-of-the-Art and Gaps Extracted from Results and Discussions” section, which delves into the latest advancements in nanocomposite research. This section details various nanocomposite types and their properties and introduces novel interpretations of their applications, especially in nanocomposite films. By tracing historical progress and identifying emerging trends, this analysis emphasizes the significance of collaboration and influential studies in molding the field. Moreover, the “Literature Review Guided by Artificial Intelligence” section showcases an innovative AI-guided approach to nanocomposite research, a first in this domain. Focusing on articles from 2023, selected based on citation frequency, this method offers a new perspective on the interplay between nanocomposites and their electrical properties. It highlights the composition, structure, and functionality of various systems, integrating recent findings for a comprehensive overview of current knowledge. The sentiment analysis, with an average score of 0.638771, reflects a positive trend in academic discourse and an increasing recognition of the potential of nanocomposites. Our bibliometric analysis, another methodological novelty, maps the intellectual domain, emphasizing pivotal research themes and the influence of crosslinking time on nanocomposite attributes. While acknowledging its limitations, this study exemplifies the indispensable role of our innovative computational tools in synthesizing and understanding the extensive body of nanocomposite literature. This work not only elucidates prevailing trends but also contributes a unique perspective and novel insights, enhancing our understanding of the nanocomposite research field.

show abstract

Section: Introductionmentioning

confidence: 99%

Advancements in Nanocomposites: An In-depth Exploration of Microstructural, Electrical, and Mechanical Dynamics

Gomes Souza Jr,

Bhansali,

Pal

et al. 2024

Preprint

View full text Add to dashboard Cite

This research presents a comprehensive bibliometric and sentiment analysis of nanocomposite literature from 1990 to 2024. Employing cutting-edge computational methods, the study delves deep into the progression of microstructural characterization, electrical properties, and mechanical behaviors of nanocomposites. The analysis utilizes advanced Boolean search strategies from the Scopus database, ensuring a thorough extraction of thematic content. The results explore various themes and insights, shedding light on trends evident in the Scopus database, particularly the prominence of research on nanocomposite microstructure, electrical attributes, and mechanical performance. The paper also offers textual analytics and bibliometric data, showcasing critical collaborative efforts and influential studies. Significant discoveries encompass the evolution of research language, shifts in thematic focus, and global contributions, providing a comprehensive perspective on the current landscape of nanocomposite research and its dynamic evolution. Moving forward, the "State-of-the-Art and Gaps Extracted from Results and Discussions" section of the paper delves into the most recent advancements in nanocomposite research. It delves into various types of nanocomposites, with a particular emphasis on their microstructural characteristics, electrical properties, mechanical dynamics, and the application of nanocomposite films. This section identifies key research themes, traces historical progress, and highlights emerging trends while underscoring the significance of collaboration and the influence of pivotal studies that have shaped the field. Lastly, in the "Literature Review Guided by Artificial Intelligence" section, the paper introduces a revised approach for researching nanocomposites through AI-guided techniques. This approach prioritizes articles published in 2023 based on citation frequency. Here, the focus is on exploring the relationship between nanocomposites and their electrical properties, emphasizing their fundamental interactions and impact on electrical characteristics. Various nanocomposite systems are covered, highlighting their composition, structure, and functionality. Findings from recent studies are integrated to provide a comprehensive overview of the current state of knowledge in this area. Notably, the sentiment analysis, anchored by an average sentiment score of 0.638771, underscores a positive trajectory in academic discourse, emphasizing the growing recognition of the potential of nanocomposites. The bibliometric exploration maps the intellectual domain, emphasizing pivotal research themes and the influence of crosslinking time on nanocomposite attributes. While this study is thorough, it acknowledges its limitations and advocates for broader database inclusion in future research endeavors. This work elucidates the prevailing trends in nanocomposite research, emphasizing the indispensable role of computational tools in comprehending this vast wealth of information.

show abstract

Reaction Impurity Prediction using a Data Mining Approach**

Cited by 5 publications

References 43 publications

Completing and Balancing Database Excerpted Chemical Reactions with a Hybrid Mechanistic-Machine Learning Approach

Completing and Balancing Database Excerpted Chemical Reactions with a Hybrid Mechanistic-Machine Learning Approach

A 30-Year Review on Nanocomposites: Comprehensive Bibliometric Insights into Microstructural, Electrical, and Mechanical Properties Assisted by Artificial Intelligence

Advancements in Nanocomposites: An In-depth Exploration of Microstructural, Electrical, and Mechanical Dynamics

Contact Info

Product

Resources

About