[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121382-en":3,"doc-seo-121382-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121382,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Identification of Influential Features by Machine Learning Models to Predict Antibiotic Resistance - Thesis","Clinics have cataloged a rise in antibiotic drug resistance in bacteria, creating a global public health challenge. Existing culture-based assays for determining drug resistance profiles are time-consuming and rely on known local populations. This thesis applies machine learning models that use predictive factors to identify resistant strains, with the goal of ranking which genomic factors are most influential. Using public E. coli and Pseudomonas WGS datasets, models are trained and compared to determine performance, then feature rankings are derived from the best model.","Identification of Influential Features by Machine Learning Models to Predict Antibiotic Resistance  \nA Thesis submitted to the faculty of  \nSan Francisco State University  \nIn partial fulfillment of  \nthe requirements for  \nthe Degree  \nMaster of Science  \nIn  \nBiology: Cell and Molecular Biology  \nby  \nJameel Ali  \nSan Francisco, California  \nMay 2024  \nCopyright by Jameel Ali 2024  \nCertification of Approval  \nI certify that I have read “Identification of Influential Features by Machine Learning Models to Predict Antibiotic Resistance” by Jameel Ali, and that in my opinion this work meets the criteria for approving a thesis submitted in partial fulfillment of the requirement for the degree Master of Science in Biology: Cell and Molecular Biology at San Francisco State University.  \n\n| Pleuni Pennings, Ph.D.\u003Cbr>Professor,\u003Cbr>Thesis Committee Chair |\n| --- |\n| Scott Roy, Ph.D.\u003Cbr>Professor |\n\nCathy Samayoa, Ph.D. Associate Professor  \nAbstract  \nClinics have cataloged a rise in antibiotic drug resistance in bacteria resulting in a global public health concern. Researchers found the key to controlling the spread of resistant strains of bacteria is accurate and efficient detection. However, the current method to establish drug resistance profiles are time-consuming culture-based assays based on known local bacterial populations. To address the need for a better detection method, machine learning models have been applied as a solution. The models require predictive factors, such as genomic data, to perform their analyses. However, it is not understood what predictive factors hold the most influence in identifying drug resistance strains. By understanding which factors are most influential, we can optimize models to identify drug resistant strains with greater accuracy. Our goal is to rank the most influential factors used by the machine learning models to identify drug resistant strains. Using publicly available E. coli and Pseudomonas Whole Genome Sequencing (WGS) datasets, we will compile the factors that will be used to train and test the models. We then compared the predictive performances of the models to determine the best performing model. From the best performing model, we ranked the factors based on their predictive influence in the analysis. We found genes that are associated with drug resistance to hold the most influence. We intended to use this study to add to the growing body of research where machine learning is used to improve patient outcomes.  \nAcknowledgements  \nI would like to extend a heartfelt thanks for the many individuals who helped and supported the completion of this thesis including Faye Orcales, Lucy Moctezuma, Meris Johnson-Hagler, John Matthew Suntay, Kristiene Recto, Dr. Pleuni Pennings, Dr. Scott Roy, Dr. Cathy Samayoa and many other individuals.  \nTable of Contents  \nList of Figures vii  \nList of Appendices viii  \nIntroduction 1  \nMethods 4  \nIsolates 4  \nPan-Genome Determination 5  \nPopulation Structure Calculation 5  \nMachine Learning Models 6  \nLabels, Features, and Predictions 6  \nResults 8  \nDiscussion 19  \nBibliography 24  \nAppendices 30  \nList of Figures  \nFigure 1. Total \\# of Resistant vs Susceptible Isolates .............................................................. 10  \nFigure 2. Prediction of Antibiotic Resistance from E. coli Pan-Genome Data .................... 12  \nFigure 3. Prediction of Antibiotic Resistance from P. aeruginosa Pan-Genome Data ......... 14  \nFigure 4. Prediction of Antibiotic Resistance from Gradient Boosted Trees ........................ 16  \nFigure 5. E. coli and P. aeruginosa Feature Importance ........................................................ 18  \nList of Appendices  \nAppendix A: Supplementary Tables ......................................................................................... 30  \nAppendix B: Data Availability................................................................................................... 31  \nIntroduction  \nIn the Un","cbCaioTtvsqtxYJm","https://ap.wps.com/l/cbCaioTtvsqtxYJm","pdf",2118918,1,39,"English","en",105,"# Introduction\n# Methods\n## Isolates\n## Pan-Genome Determination\n## Population Structure Calculation\n## Machine Learning Models\n## Labels, Features, and Predictions\n# Results\n# Discussion\n# Bibliography\n# Appendices\n## Appendix A: Supplementary Tables\n## Appendix B: Data Availability","[{\"question\":\"Why are culture-based assays insufficient for identifying antibiotic resistance?\",\"answer\":\"Culture-based assays are time-consuming and depend on known local bacterial populations, limiting speed and efficiency when resistance patterns evolve.\"},{\"question\":\"What is the main objective of this thesis?\",\"answer\":\"To rank the most influential predictive factors used by machine learning models for identifying antibiotic-resistant strains.\"},{\"question\":\"How were predictive factors evaluated in the study?\",\"answer\":\"The study trained and tested machine learning models using publicly available E. coli and Pseudomonas whole genome sequencing datasets, selected the best-performing model, and then ranked factors by predictive influence.\"}]","Identification of Influential Features by Machine Learning Models to Predict Antibiotic Resistance - Thesis | PDF",1785735395,98,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"identification-of-influential-features-by-machine-learning-models-to-predict-antibiotic-resistance-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/identification-of-influential-features-by-machine-learning-models-to-predict-antibiotic-resistance-thesis/121382/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are culture-based assays insufficient for identifying antibiotic resistance?","Question",{"text":75,"@type":76},"Culture-based assays are time-consuming and depend on known local bacterial populations, limiting speed and efficiency when resistance patterns evolve.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the main objective of this thesis?",{"text":80,"@type":76},"To rank the most influential predictive factors used by machine learning models for identifying antibiotic-resistant strains.",{"name":82,"@type":73,"acceptedAnswer":83},"How were predictive factors evaluated in the study?",{"text":84,"@type":76},"The study trained and tested machine learning models using publicly available E. coli and Pseudomonas whole genome sequencing datasets, selected the best-performing model, and then ranked factors by predictive influence.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]