[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126138-en":3,"doc-seo-126138-105":31,"detail-sidebar-cat-0-en-105":93},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126138,687207022233,"Riley","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","PREDICTIVE MODEL OF PDP OXIDATION REACTION WITH MACHINE LEARNING APPROACH","A machine learning–based predictive model for identifying reactive sites of a substrate using the PDP catalyst was under development. The author generated computation data using DFT methods, including feature inputs derived from Gaussian calculations. The model used NPA charges, IR frequencies, and computed NMR descriptors, each tied to underlying chemical properties of the substrate. The approach aims to support synthesis planning in the pharmaceutical industry and describes the workflow, descriptors, and substrate set.","PREDICTIVE MODEL OF PDP OXIDATION REACTION WITH MACHINE LEARNING APPROACH  \nBY  \nMINXING ZHANG  \nTHESIS  \nSubmitted in partial fulfillment of the requirements for the degree of Master of Science in Chemistry in the Graduate College of the University of Illinois Urbana-Champaign, 2023  \nUrbana, Illinois  \nAdviser:  \nProfessor M. Christina White  \nABSTRACT  \nA new machine learning based model, predicting reactive site of substrate using PDP  \ncatalyst, was under construction. My job was to generate computation data using DFT methods.  \nOne set of features the model would use was computational data generated by Gaussian. The  \nnew model took NPA charges, IR frequency, and calculated NMR data as input. Each descriptor  \nalso directly reflected the fundamental chemical property of the substrate. This new model could  \npotentially empower the synthesis planning for pharmaceutical industry. The text would discuss  \nthe operation process, the use of each major descriptor, and the substrate set.  \nACKNOWLEDGMENTS  \nThe help from my mentors, Chiyoung Ahn and Sven Kaster was greatly appreciated. And, thanks to everyone in the White Group for their support.  \nTABLE OF CONTENTS  \nCHAPTER 1: COMPUTATIONAL CALCULATION WITH GAUSSIAN..................................1  \nIntroduction .............................................................................................................................. 1  \nShort Summary of Work ..........................................................................................................7  \nStandard Operating Procedures................................................................................................9  \nDiscussion of the Results .......................................................................................................20  \nSubstrate Training Set ............................................................................................................35  \nConclusion .............................................................................................................................49  \nREFERENCES ..............................................................................................................................50  \nCHAPTER 1: COMPUTATIONAL CALCULATION WITH GAUSSIAN Introduction  \nAlcohol groups had rich pharmaceutical reactivity. Late-stage C-H oxidations showed great interest in drug development. Editing at atomistic scale and adding alcohol groups at specific sites changed the reactivity and functionality significantly [1] . Given Erythromycin A asan example. The reactivity increased by 6-fold after inserting alcohol group at 6’-position of 6-deoxy Erythromycin A [2] .  \nFigure 1 C-H Oxidation of 6-deoxy Erythromycin A  \nThe White group demonstrated oxidation with the use of PDP catalyst in various types of substrates. PDP C-H oxidation system showed tolerance of various functional groups including aromatic, amide, and heterocycles. By changing the metal core and/or PDP ligand, the site selective of reaction could be controlled [3-11] . The site selectivity of the reaction was determined by electronic, steric, stereoelectronic and directing group effect. Sometimes, when substrate was chiral, the chirality of catalyst could also affect the site selectivity.  \nFigure 2 Advantages of PDP Catalyst  \nThe product could be predicted by an organic chemist after training. However, oxidation site prediction with high certainty could be challenging when there were multiple potential oxidizable sites. For a general pharmaceutical company, it would be unpractical to predict the product with given conditions and an untested substrate without specific knowledge. It could be helpful if one could use software to predict the product of a new substrate. Previously, a predictive model was built with limited substrate scope [3] . In this model, only one electronic parameter was used. A-value was used for steric parameter. It was structure-dependent and did not represe","cbCaib6NzY46IbKh","https://ap.wps.com/l/cbCaib6NzY46IbKh","pdf",2695557,6,1,57,"English","en",105,"# CHAPTER 1: COMPUTATIONAL CALCULATION WITH GAUSSIAN\n## Introduction\n## Short Summary of Work\n## Standard Operating Procedures\n## Discussion of the Results\n## Substrate Training Set\n## Conclusion\n# REFERENCES","[{\"question\":\"What problem does the machine learning model address in PDP oxidation chemistry?\",\"answer\":\"It predicts reactive (oxidation) sites on a substrate using the PDP catalyst by learning from computed chemical descriptors.\"},{\"question\":\"What computational methods and data sources are used to build the model features?\",\"answer\":\"DFT computation data were generated using DFT methods, and one feature set was produced from Gaussian outputs.\"},{\"question\":\"Which descriptors are used as inputs for the predictive model?\",\"answer\":\"The model uses NPA charges, IR frequency information, and calculated NMR data as input descriptors.\"}]","PREDICTIVE MODEL OF PDP OXIDATION REACTION WITH MACHINE LEARNING APPROACH | PDF",1785903351,144,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"predictive-model-of-pdp-oxidation-reaction-with-machine-learning-approach","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/predictive-model-of-pdp-oxidation-reaction-with-machine-learning-approach/126138/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What problem does the machine learning model address in PDP oxidation chemistry?","Question",{"text":77,"@type":78},"It predicts reactive (oxidation) sites on a substrate using the PDP catalyst by learning from computed chemical descriptors.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What computational methods and data sources are used to build the model features?",{"text":82,"@type":78},"DFT computation data were generated using DFT methods, and one feature set was produced from Gaussian outputs.",{"name":84,"@type":75,"acceptedAnswer":85},"Which descriptors are used as inputs for the predictive model?",{"text":86,"@type":78},"The model uses NPA charges, IR frequency information, and calculated NMR data as input descriptors.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":108,"slug":139},19,"General","general"]