Haiyan Gong , Lingwei Ma , Diandian Liu , Dawei Zhang
{"title":"AI-driven discovery of high-performance corrosion inhibitors using a BERT-GPT framework for molecular generation","authors":"Haiyan Gong , Lingwei Ma , Diandian Liu , Dawei Zhang","doi":"10.1016/j.corsci.2025.113327","DOIUrl":null,"url":null,"abstract":"<div><div>The discovery of high-efficiency corrosion inhibitors is constrained by the structural diversity of existing molecular entities. This study introduces a framework that integrates BERT and GPT models to predict, screen, and generate molecules with potential corrosion inhibiting properties. Predictive models for inhibition efficiency (IE) and toxicity on carbon steel surfaces in 1 M HCl environments were built by utilizing chemical language embeddings and molecular descriptors. The screening of the PubChem library identified 1,336,971 candidate molecules with a predicted IE greater than 90 % at a 1 mM concentration and a predicted LD50 (lethal dose for 50 % of test animals) exceeding 2000 mg/kg (indicating low acute toxicity). Scaffold analysis highlighted an enrichment of critical scaffold, particularly 6 imidazole scaffolds in conjunction with property constraints (IE = 90 %, LD50 = 1000 mg/kg), informed the conditional generation of molecules using MolGPT. A total of 310,962 valid molecules were generated, with 25.17 % (78,258 molecules) satisfying all specified conditions, which is much higher than the hit ratio (4.08 %) of screening from PubChem database. This study demonstrates an AI-driven molecular generation for corrosion inhibitor discovery.</div></div>","PeriodicalId":290,"journal":{"name":"Corrosion Science","volume":"257 ","pages":"Article 113327"},"PeriodicalIF":7.4000,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Corrosion Science","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0010938X25006559","RegionNum":1,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
The discovery of high-efficiency corrosion inhibitors is constrained by the structural diversity of existing molecular entities. This study introduces a framework that integrates BERT and GPT models to predict, screen, and generate molecules with potential corrosion inhibiting properties. Predictive models for inhibition efficiency (IE) and toxicity on carbon steel surfaces in 1 M HCl environments were built by utilizing chemical language embeddings and molecular descriptors. The screening of the PubChem library identified 1,336,971 candidate molecules with a predicted IE greater than 90 % at a 1 mM concentration and a predicted LD50 (lethal dose for 50 % of test animals) exceeding 2000 mg/kg (indicating low acute toxicity). Scaffold analysis highlighted an enrichment of critical scaffold, particularly 6 imidazole scaffolds in conjunction with property constraints (IE = 90 %, LD50 = 1000 mg/kg), informed the conditional generation of molecules using MolGPT. A total of 310,962 valid molecules were generated, with 25.17 % (78,258 molecules) satisfying all specified conditions, which is much higher than the hit ratio (4.08 %) of screening from PubChem database. This study demonstrates an AI-driven molecular generation for corrosion inhibitor discovery.
期刊介绍:
Corrosion occurrence and its practical control encompass a vast array of scientific knowledge. Corrosion Science endeavors to serve as the conduit for the exchange of ideas, developments, and research across all facets of this field, encompassing both metallic and non-metallic corrosion. The scope of this international journal is broad and inclusive. Published papers span from highly theoretical inquiries to essentially practical applications, covering diverse areas such as high-temperature oxidation, passivity, anodic oxidation, biochemical corrosion, stress corrosion cracking, and corrosion control mechanisms and methodologies.
This journal publishes original papers and critical reviews across the spectrum of pure and applied corrosion, material degradation, and surface science and engineering. It serves as a crucial link connecting metallurgists, materials scientists, and researchers investigating corrosion and degradation phenomena. Join us in advancing knowledge and understanding in the vital field of corrosion science.