• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

分子自动纠错以促进分子设计。

Molecule auto-correction to facilitate molecular design.

机构信息

Laboratory of Medicinal Chemistry, Department of Pharmaceutical Sciences, University of Antwerp, Universiteitslaan 1, 2610, Wilrijk, Belgium.

出版信息

J Comput Aided Mol Des. 2024 Feb 16;38(1):10. doi: 10.1007/s10822-024-00549-1.

DOI:10.1007/s10822-024-00549-1
PMID:38363377
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10873457/
Abstract

Ensuring that computationally designed molecules are chemically reasonable is at best cumbersome. We present a molecule correction algorithm that morphs invalid molecular graphs into structurally related valid analogs. The algorithm is implemented as a tree search, guided by a set of policies to minimize its cost. We showcase how the algorithm can be applied to molecular design, either as a post-processing step or as an integral part of molecule generators.

摘要

确保计算设计的分子在化学上是合理的,这最多也就是一件繁琐的事情。我们提出了一种分子修正算法,可以将无效的分子图转化为结构相关的有效类似物。该算法实现为树搜索,由一组策略指导,以最小化其成本。我们展示了该算法如何应用于分子设计,无论是作为后处理步骤还是作为分子生成器的一个组成部分。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/b5771ce5eee4/10822_2024_549_Fig16_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/ebd97ad45146/10822_2024_549_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/e6a0b41ac71a/10822_2024_549_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/a0b8d943d986/10822_2024_549_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/a3a5eeeee481/10822_2024_549_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/7d4d852143c4/10822_2024_549_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/b1623f0903b0/10822_2024_549_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/9b26c1d2907f/10822_2024_549_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/321fcc3c8f77/10822_2024_549_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/cdbb2fbc667b/10822_2024_549_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/e64c1b83d6cb/10822_2024_549_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/755552d1fe2b/10822_2024_549_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/407a0d6a9c27/10822_2024_549_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/b26f04559cd7/10822_2024_549_Fig13_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/1e36f46134f4/10822_2024_549_Fig14_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/cf856b58c572/10822_2024_549_Fig15_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/b5771ce5eee4/10822_2024_549_Fig16_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/ebd97ad45146/10822_2024_549_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/e6a0b41ac71a/10822_2024_549_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/a0b8d943d986/10822_2024_549_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/a3a5eeeee481/10822_2024_549_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/7d4d852143c4/10822_2024_549_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/b1623f0903b0/10822_2024_549_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/9b26c1d2907f/10822_2024_549_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/321fcc3c8f77/10822_2024_549_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/cdbb2fbc667b/10822_2024_549_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/e64c1b83d6cb/10822_2024_549_Fig10_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/755552d1fe2b/10822_2024_549_Fig11_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/407a0d6a9c27/10822_2024_549_Fig12_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/b26f04559cd7/10822_2024_549_Fig13_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/1e36f46134f4/10822_2024_549_Fig14_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/cf856b58c572/10822_2024_549_Fig15_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d03b/10873457/b5771ce5eee4/10822_2024_549_Fig16_HTML.jpg

相似文献

1
Molecule auto-correction to facilitate molecular design.分子自动纠错以促进分子设计。
J Comput Aided Mol Des. 2024 Feb 16;38(1):10. doi: 10.1007/s10822-024-00549-1.
2
A graph-based genetic algorithm and its application to the multiobjective evolution of median molecules.一种基于图的遗传算法及其在中位分子多目标进化中的应用。
J Chem Inf Comput Sci. 2004 May-Jun;44(3):1079-87. doi: 10.1021/ci034290p.
3
A Turing Test for Molecular Generators.分子生成器的图灵测试。
J Med Chem. 2020 Oct 22;63(20):11964-11971. doi: 10.1021/acs.jmedchem.0c01148. Epub 2020 Oct 12.
4
Computer-aided drug designing.计算机辅助药物设计
Methods Mol Biol. 2014;1168:313-21. doi: 10.1007/978-1-4939-0847-9_18.
5
Acceleration of Inverse Molecular Design by Using Predictive Techniques.利用预测技术加速逆分子设计。
J Chem Inf Model. 2019 Jun 24;59(6):2587-2599. doi: 10.1021/acs.jcim.8b00654. Epub 2019 May 15.
6
EvoMD: an algorithm for evolutionary molecular design.EvoMD:一种进化分子设计算法。
IEEE/ACM Trans Comput Biol Bioinform. 2011 Jul-Aug;8(4):987-1003. doi: 10.1109/TCBB.2010.100.
7
UnCorrupt SMILES: a novel approach to de novo design.未腐败的SMILES:一种全新的从头设计方法。
J Cheminform. 2023 Feb 14;15(1):22. doi: 10.1186/s13321-023-00696-x.
8
Chemoinformatics - similarity and diversity in chemical libraries.化学信息学——化学文库中的相似性与多样性
Curr Opin Biotechnol. 2000 Feb;11(1):85-8. doi: 10.1016/s0958-1669(99)00059-2.
9
State-of-the-art technology in modern computer-aided drug design.现代计算机辅助药物设计中的最新技术。
Brief Bioinform. 2013 Nov;14(6):745-52. doi: 10.1093/bib/bbs063. Epub 2012 Nov 12.
10
Exact parallel maximum clique algorithm for general and protein graphs.通用图和蛋白质图的精确并行最大团算法。
J Chem Inf Model. 2013 Sep 23;53(9):2217-28. doi: 10.1021/ci4002525. Epub 2013 Sep 5.

引用本文的文献

1
SMILES all around: structure to SMILES conversion for transition metal complexes.处处皆有SMILES:过渡金属配合物的结构到SMILES的转换
J Cheminform. 2025 Apr 28;17(1):63. doi: 10.1186/s13321-025-01008-1.

本文引用的文献

1
A molecule perturbation software library and its application to study the effects of molecular design constraints.一个分子扰动软件库及其在研究分子设计限制效应方面的应用。
J Cheminform. 2023 Sep 26;15(1):89. doi: 10.1186/s13321-023-00761-5.
2
Combatting over-specialization bias in growing chemical databases.应对不断增长的化学数据库中的过度专业化偏差。
J Cheminform. 2023 May 19;15(1):53. doi: 10.1186/s13321-023-00716-w.
3
Computer-aided multi-objective optimization in small molecule discovery.小分子发现中的计算机辅助多目标优化
Patterns (N Y). 2023 Feb 10;4(2):100678. doi: 10.1016/j.patter.2023.100678.
4
Critical assessment of synthetic accessibility scores in computer-assisted synthesis planning.计算机辅助合成规划中合成可及性分数的批判性评估
J Cheminform. 2023 Jan 14;15(1):6. doi: 10.1186/s13321-023-00678-z.
5
LEADD: Lamarckian evolutionary algorithm for de novo drug design.LEADD:用于从头药物设计的拉马克进化算法。
J Cheminform. 2022 Jan 15;14(1):3. doi: 10.1186/s13321-022-00582-y.
6
Retrosynthetic accessibility score (RAscore) - rapid machine learned synthesizability classification from AI driven retrosynthetic planning.逆合成可及性分数(RAscore)——基于人工智能驱动的逆合成规划的快速机器学习合成性分类。
Chem Sci. 2021 Jan 22;12(9):3339-3349. doi: 10.1039/d0sc05401a.
7
AutoGrow4: an open-source genetic algorithm for de novo drug design and lead optimization.AutoGrow4:一种用于从头药物设计和先导化合物优化的开源遗传算法。
J Cheminform. 2020 Apr 17;12(1):25. doi: 10.1186/s13321-020-00429-4.
8
CReM: chemically reasonable mutations framework for structure generation.CReM:用于结构生成的化学合理突变框架
J Cheminform. 2020 Apr 22;12(1):28. doi: 10.1186/s13321-020-00431-w.
9
On failure modes in molecule generation and optimization.关于分子生成和优化中的失效模式。
Drug Discov Today Technol. 2019 Dec;32-33:55-63. doi: 10.1016/j.ddtec.2020.09.003. Epub 2020 Oct 24.
10
AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning.人工智能合成路线搜索工具(AiZynthFinder):一款用于逆合成规划的快速、强大且灵活的开源软件。
J Cheminform. 2020 Nov 17;12(1):70. doi: 10.1186/s13321-020-00472-1.