Kenneth Atz, David F. Nippa, Alex T. Müller, Vera Jost, Andrea Anelli, Michael Reutlinger, Christian Kramer, Rainer E. Martin, Uwe Grether, Gisbert Schneider and Georg Wuitschik
{"title":"几何深度学习引导的铃木反应条件评估在药物化学中的应用","authors":"Kenneth Atz, David F. Nippa, Alex T. Müller, Vera Jost, Andrea Anelli, Michael Reutlinger, Christian Kramer, Rainer E. Martin, Uwe Grether, Gisbert Schneider and Georg Wuitschik","doi":"10.1039/D4MD00196F","DOIUrl":null,"url":null,"abstract":"<p >Suzuki cross-coupling reactions are considered a valuable tool for constructing carbon–carbon bonds in small molecule drug discovery. However, the synthesis of chemical matter often represents a time-consuming and labour-intensive bottleneck. We demonstrate how machine learning methods trained on high-throughput experimentation (HTE) data can be leveraged to enable fast reaction condition selection for novel coupling partners. We show that the trained models support chemists in determining suitable catalyst-solvent-base combinations for individual transformations including an evaluation of the need for HTE screening. We introduce an algorithm for designing 96-well plates optimized towards reaction yields and discuss the model performance of zero- and few-shot machine learning. The best-performing machine learning model achieved a three-category classification accuracy of 76.3% (±0.2%) and an <em>F</em><small><sub>1</sub></small>-score for a binary classification of 79.1% (±0.9%). Validation on eight reactions revealed a receiver operating characteristic (ROC) curve (AUC) value of 0.82 (±0.07) for few-shot machine learning. On the other hand, zero-shot machine learning models achieved a mean ROC-AUC value of 0.63 (±0.16). This study positively advocates the application of few-shot machine learning-guided reaction condition selection for HTE campaigns in medicinal chemistry and highlights practical applications as well as challenges associated with zero-shot machine learning.</p>","PeriodicalId":21462,"journal":{"name":"RSC medicinal chemistry","volume":null,"pages":null},"PeriodicalIF":4.1000,"publicationDate":"2024-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Geometric deep learning-guided Suzuki reaction conditions assessment for applications in medicinal chemistry\",\"authors\":\"Kenneth Atz, David F. Nippa, Alex T. Müller, Vera Jost, Andrea Anelli, Michael Reutlinger, Christian Kramer, Rainer E. Martin, Uwe Grether, Gisbert Schneider and Georg Wuitschik\",\"doi\":\"10.1039/D4MD00196F\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p >Suzuki cross-coupling reactions are considered a valuable tool for constructing carbon–carbon bonds in small molecule drug discovery. However, the synthesis of chemical matter often represents a time-consuming and labour-intensive bottleneck. We demonstrate how machine learning methods trained on high-throughput experimentation (HTE) data can be leveraged to enable fast reaction condition selection for novel coupling partners. We show that the trained models support chemists in determining suitable catalyst-solvent-base combinations for individual transformations including an evaluation of the need for HTE screening. We introduce an algorithm for designing 96-well plates optimized towards reaction yields and discuss the model performance of zero- and few-shot machine learning. The best-performing machine learning model achieved a three-category classification accuracy of 76.3% (±0.2%) and an <em>F</em><small><sub>1</sub></small>-score for a binary classification of 79.1% (±0.9%). Validation on eight reactions revealed a receiver operating characteristic (ROC) curve (AUC) value of 0.82 (±0.07) for few-shot machine learning. On the other hand, zero-shot machine learning models achieved a mean ROC-AUC value of 0.63 (±0.16). This study positively advocates the application of few-shot machine learning-guided reaction condition selection for HTE campaigns in medicinal chemistry and highlights practical applications as well as challenges associated with zero-shot machine learning.</p>\",\"PeriodicalId\":21462,\"journal\":{\"name\":\"RSC medicinal chemistry\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.1000,\"publicationDate\":\"2024-05-31\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"RSC medicinal chemistry\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://pubs.rsc.org/en/content/articlelanding/2024/md/d4md00196f\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"BIOCHEMISTRY & MOLECULAR BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"RSC medicinal chemistry","FirstCategoryId":"3","ListUrlMain":"https://pubs.rsc.org/en/content/articlelanding/2024/md/d4md00196f","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
Geometric deep learning-guided Suzuki reaction conditions assessment for applications in medicinal chemistry
Suzuki cross-coupling reactions are considered a valuable tool for constructing carbon–carbon bonds in small molecule drug discovery. However, the synthesis of chemical matter often represents a time-consuming and labour-intensive bottleneck. We demonstrate how machine learning methods trained on high-throughput experimentation (HTE) data can be leveraged to enable fast reaction condition selection for novel coupling partners. We show that the trained models support chemists in determining suitable catalyst-solvent-base combinations for individual transformations including an evaluation of the need for HTE screening. We introduce an algorithm for designing 96-well plates optimized towards reaction yields and discuss the model performance of zero- and few-shot machine learning. The best-performing machine learning model achieved a three-category classification accuracy of 76.3% (±0.2%) and an F1-score for a binary classification of 79.1% (±0.9%). Validation on eight reactions revealed a receiver operating characteristic (ROC) curve (AUC) value of 0.82 (±0.07) for few-shot machine learning. On the other hand, zero-shot machine learning models achieved a mean ROC-AUC value of 0.63 (±0.16). This study positively advocates the application of few-shot machine learning-guided reaction condition selection for HTE campaigns in medicinal chemistry and highlights practical applications as well as challenges associated with zero-shot machine learning.