通过综合化学文库生成设计高电子亲和小分子受体

IF 4.6 3区材料科学 Q2 MATERIALS SCIENCE, MULTIDISCIPLINARY

Synthetic Metals Pub Date : 2025-10-06 DOI:10.1016/j.synthmet.2025.117986

Mudassir Hussain Tahir , Sumaira Naeem , Ihab Mohamed Moussa

{"title":"通过综合化学文库生成设计高电子亲和小分子受体","authors":"Mudassir Hussain Tahir , Sumaira Naeem , Ihab Mohamed Moussa","doi":"10.1016/j.synthmet.2025.117986","DOIUrl":null,"url":null,"abstract":"<div><div>This study presents an advanced approach for crafting small molecule acceptors using data-driven techniques. Machine learning algorithms are developed to forecast these acceptors' electron affinities using chemical characteristics. A pre-trained machine learning model is used to evaluate the electron affinity of 10,000 small molecule acceptors. Acceptors with higher electron affinity are prioritized for selection and their synthetic feasibility is subsequently evaluated. Furthermore, structural diversity of the chosen acceptors is investigated, it uncovered structural diversity among chosen small molecule acceptors. These methods effectively identify and refine new small molecule acceptors, promising significant advancements in material discovery for various applications.</div></div>","PeriodicalId":22245,"journal":{"name":"Synthetic Metals","volume":"316 ","pages":"Article 117986"},"PeriodicalIF":4.6000,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Designing high electron affinity small molecule acceptors through comprehensive chemical library generation\",\"authors\":\"Mudassir Hussain Tahir , Sumaira Naeem , Ihab Mohamed Moussa\",\"doi\":\"10.1016/j.synthmet.2025.117986\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>This study presents an advanced approach for crafting small molecule acceptors using data-driven techniques. Machine learning algorithms are developed to forecast these acceptors' electron affinities using chemical characteristics. A pre-trained machine learning model is used to evaluate the electron affinity of 10,000 small molecule acceptors. Acceptors with higher electron affinity are prioritized for selection and their synthetic feasibility is subsequently evaluated. Furthermore, structural diversity of the chosen acceptors is investigated, it uncovered structural diversity among chosen small molecule acceptors. These methods effectively identify and refine new small molecule acceptors, promising significant advancements in material discovery for various applications.</div></div>\",\"PeriodicalId\":22245,\"journal\":{\"name\":\"Synthetic Metals\",\"volume\":\"316 \",\"pages\":\"Article 117986\"},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2025-10-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Synthetic Metals\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0379677925001626\",\"RegionNum\":3,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Synthetic Metals","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0379677925001626","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

摘要

本研究提出了一种使用数据驱动技术制作小分子受体的先进方法。开发了机器学习算法来利用化学特性预测这些受体的电子亲和力。使用预训练的机器学习模型来评估10,000个小分子受体的电子亲和力。优先选择具有较高电子亲和力的受体，并随后评估其合成可行性。此外，研究了所选受体的结构多样性，揭示了所选小分子受体之间的结构多样性。这些方法有效地识别和提炼新的小分子受体，有望在各种应用的材料发现方面取得重大进展。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Designing high electron affinity small molecule acceptors through comprehensive chemical library generation

This study presents an advanced approach for crafting small molecule acceptors using data-driven techniques. Machine learning algorithms are developed to forecast these acceptors' electron affinities using chemical characteristics. A pre-trained machine learning model is used to evaluate the electron affinity of 10,000 small molecule acceptors. Acceptors with higher electron affinity are prioritized for selection and their synthetic feasibility is subsequently evaluated. Furthermore, structural diversity of the chosen acceptors is investigated, it uncovered structural diversity among chosen small molecule acceptors. These methods effectively identify and refine new small molecule acceptors, promising significant advancements in material discovery for various applications.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Synthetic Metals 工程技术-材料科学：综合

CiteScore

8.30

自引率

4.50%

发文量

189

审稿时长

33 days

期刊介绍： This journal is an international medium for the rapid publication of original research papers, short communications and subject reviews dealing with research on and applications of electronic polymers and electronic molecular materials including novel carbon architectures. These functional materials have the properties of metals, semiconductors or magnets and are distinguishable from elemental and alloy/binary metals, semiconductors and magnets.