[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-290598-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-290598-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","machine-learning-in-predictive-toxicology-investigating-developmental-and-reproductive-toxicity-with-transfer-learning","Machine learning in predictive toxicology: investigating developmental and reproductive toxicity with transfer learning","","Machine learning supports predictive toxicology by providing faster, reasonably accurate in silico alternatives as some sectors phase out animal testing. The work targets key developmental and reproductive toxicity endpoints used in next-generation risk assessments and argues that model performance is constrained by training data quality. Chapter 3 evaluates transfer learning suitability using Tanimoto similarity, linking test accuracy likelihood to predicted accuracy or dataset similarity thresholds. Chapter 4 builds a dedicated database, trains new models, and investigates transfer mechanisms through identified receptor binding candidates.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/machine-learning-in-predictive-toxicology-investigating-developmental-and-reproductive-toxicity-with-transfer-learning/290598/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/machine-learning-in-predictive-toxicology-investigating-developmental-and-reproductive-toxicity-with-transfer-learning/290598.png","ImageObject",300,407,{"name":42,"@type":43},"Ezra","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-01","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",10,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is machine learning used in predictive toxicology in this thesis?","Question",{"text":63,"@type":64},"To provide an alternative to animal testing by generating toxicity predictions quickly with reasonable accuracy, using in silico machine learning methods.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the thesis assess the suitability of transfer learning in Chapter 3?",{"text":68,"@type":64},"It investigates Tanimoto similarity and finds that when predicted test accuracy (P) or average dataset similarity (S) is 70% or more, the model is likely to achieve high test accuracy on the test dataset.",{"name":70,"@type":61,"acceptedAnswer":71},"What does Chapter 4 contribute and what performances were reported?",{"text":72,"@type":64},"It creates a new database for developmental and reproductive toxicity to train newer models, reporting about 68% accuracy for developmental toxicity and about 80% accuracy for reproductive toxicity, and it explores transfer mechanisms via receptor binding candidates.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},290598,1789642159,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":55,"slug":125},"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":80,"read_time":144,"preview_page_count":4},1099514068035,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Machine learning in predictive toxicology: investigating developmental and reproductive toxicity with transfer  \nlearning  \nby  \nWang Wei How Marcus (mwhw3) Robinson College  \nSupervisor: Professor Jonathan M Goodman  \nThis thesis is submitted for the degree of Doctor of Philosophy in Chemistry  \nYusuf Hamied Department of Chemistry  \nUniversity of Cambridge  \nSubmitted 07/2023  \nThis thesis is the result of my own work and includes nothing which is the outcome of work done in collaboration except as declared in the preface and specified in the text. It is not substantially the same as any work that has already been submitted, or, is being concurrently submitted, for any degree, diploma or other qualification at the University of Cambridge or anyother University or similar institution except as declared in the preface and specified in the text. It does not exceed the prescribed word limit for the relevant Degree Committee.  \nAbstract  \nMachine learning in predictive toxicology: investigating developmental and reproductive toxicity with transfer learning  \nWang Wei How Marcus  \nThe toxicity of a compound has always been a major concern in risk assessments of new products or drugs. In the field of predictive toxicology, with animal testing being phased out in some sectors, there is an urgent need for alternative methods for determining toxicity. An insilico method such as machine learning is one such popular choice given that the results can be obtained quickly with reasonable accuracy. Over the years, a number of machine learning models have been trained for various important human targets. However, machine learning models are limited by the quality of the data used to train them. In this work, the focus is on important toxicity endpoints that are being evaluated by next-generation risk assessments, including developmental and reproductive toxicity. Chapter 3 of this work investigates the use of Tanimoto similarity to determine the suitability of using transfer learning. It was found that when the predicted test accuracy (P) or the average similarity between datasets (S) is 70% or more, the machine learning model is likely to have high test accuracy when predicting on the test dataset. In Chapter 4, the creation of a new database for developmental and reproductive toxicity allows for newer machine learning models tobe trained whose performances have been reported in this work. Models with about 68% accuracy for developmental toxicity and 80% for reproductive toxicity were trained. The suitability of transfer learning using the models for the two toxicity endpoints has also been investigated and several receptor bindings have been identified as possible mechanisms leading to developmental toxicity or reproductive toxicity.  \nPreface  \nAs I am writing this, I look back fondly on the memories of the journey thus far. Being an international student, it can be said that one is alone in a foreign land. Fortunately, the support provided along the way has made it more manageable.  \nMy supervisor, Jonathan, could always be counted on for timely help and assistance when it was required. His always optimistic approach to life and problems have brightened up rainy days more than once. I sincerely thank him for all the help he has provided on this challenging journey.  \nI would also like to extend my thanks to my colleagues who were very helpful with their insights and discussions, in particular Dr Timothy E. H. Allen for his useful criticisms and discussion about part of Chapter 2 content. In addition, I thank Dr Katarzyna R. Przybylak who has provided the EPA Integrated Chemical Environment (ICE) data in Chapter 4 as well as for her assistance and support.  \nI also thank my family, who have always been supportive of this pursuit. Without them, I would not have made it this far. Just knowing that they are supporting me keeps me motivated when things do not go smoothly.  \nTable of Contents  \nChapter 1: Thesis overview.......................","cbCaigheMCJRCy4L","https://ap.wps.com/l/cbCaigheMCJRCy4L","pdf",11060507,232,"English","# Chapter 1: Thesis overview\n# Chapter 2: Machine learning in predictive toxicology; recent applications and future directions for classification models\n## 2.1 Introduction\n## 2.2 Validation methods\n## 2.2.1 Hold-out validation\n## 2.2.2 k-fold cross-validation\n## 2.2.3 Leave-one-out cross-validation\n## 2.2.4 Leave-many-out cross-validation\n## 2.2.5 Monte Carlo cross-validation\n## 2.3 Search protocol\n## 2.4 Model types\n## 2.4.1 Regression models\n## 2.4.2 k-nearest neighbours (kNNs)\n## 2.4.3 Decision trees (DT)\n## 2.4.4 Naive Bayes (NB)","[{\"question\":\"Why is machine learning used in predictive toxicology in this thesis?\",\"answer\":\"To provide an alternative to animal testing by generating toxicity predictions quickly with reasonable accuracy, using in silico machine learning methods.\"},{\"question\":\"How does the thesis assess the suitability of transfer learning in Chapter 3?\",\"answer\":\"It investigates Tanimoto similarity and finds that when predicted test accuracy (P) or average dataset similarity (S) is 70% or more, the model is likely to achieve high test accuracy on the test dataset.\"},{\"question\":\"What does Chapter 4 contribute and what performances were reported?\",\"answer\":\"It creates a new database for developmental and reproductive toxicity to train newer models, reporting about 68% accuracy for developmental toxicity and about 80% accuracy for reproductive toxicity, and it explores transfer mechanisms via receptor binding candidates.\"}]","Machine learning in predictive toxicology: investigating developmental and reproductive toxicity with transfer learning | PDF",585]