[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118905-en":3,"doc-seo-118905-105":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},118905,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Machine learning for prediction of protein properties - dissertation","Machine learning frameworks for predicting protein properties are developed using geometric and physicochemical descriptors. The work focuses on functional residue and ligand-binding residue prediction, evaluating data processing choices and the impact of feature importance. Class imbalance handling is addressed through synthetic oversampling, and performance is assessed with standard evaluation metrics. XGBoost-based modeling is used for training and comparison against alternative methods, supporting interpretation via ranked influential features.","Machine learning for prediction of protein properties  \nby  \nDaniel Kool  \nA dissertation submitted to the graduate faculty  \nin partial fulfillment of the requirements for the degree of  \nDOCTOR OF PHILOSOPHY  \nMajor: Bioinformatics and Computational Biology  \nProgram of Study Committee:  \nRobert Jernigan, Major Professor  \nGuang Song  \nEric Underbakke  \nJulie Dickerson  \nXiaoqiu Huang  \nThe student author, whose presentation of the scholarship herein was approved by the program of study committee, is solely responsible for the content of this dissertation. The Graduate College will ensure this dissertation is globally accessible and will not permit alterations after a degree is conferred.  \nIowa State University  \nAmes, Iowa  \n2023  \nCopyright © Daniel Kool, 2023. All rights reserved.  \nDEDICATION  \nThis thesis is dedicated to my family and my friend Charter Geoffrey Moore.  \nTABLE OF CONTENTS  \nPage  \n[LIST OF FIGURES ....................................................................................................................... vi](LIST OF FIGURES ....................................................................................................................... vi)  \n[LIST OF TABLES...............................](LIST OF TABLES...............................).......................................................................................... xi  \nABSTRACT.................................................................................................................................. xii  \nCHAPTER 1. GENERAL INTRODUCTION....................................................................... 1  \n1.1. Organization of Thesis .................................................................................................... 1  \n1.2. Introduction ..................................................................................................................... 3  \n1.2.1. Machine Learning Models ...................................................................................... 3  \n1.2.2. Key Features ........................................................................................................... 6  \n1.2.3. Feature importance.................................................................................................. 8  \n1.3. References ..................................................................................................................... 10  \n1.4. Figures and Tables ........................................................................................................ 12  \nCHAPTER 2. FUNCTIONAL RESIDUE PREDICTIONS BASED ON GEOMETRIC AND PHYSICOCHEMICAL PROPERTIES AND COMPARISON OF DATA PROCESSING METHODS AND FEATURE IMPORTANCES ................................................ 14  \n2.1. Abstract ......................................................................................................................... 14  \n2.2. Introduction ................................................................................................................... 15  \n2.2.1. Imbalance and Oversampling ............................................................................... 17  \n2.2.2. XGBoost Model .................................................................................................... 18  \n2.2.3. Feature Importance ............................................................................................... 19  \n2.2.4. Related Work ........................................................................................................ 19  \n2.3. Materials and Methods .................................................................................................. 20  \n2.3.1. Data and Features.................................................................................................. 20  \n2.3.2. Synthetic Oversampling ........................................................................................ 23  \n2.3.3. XGBoost Model ..............................","cbCaiuBESjaCnAUv","https://ap.wps.com/l/cbCaiuBESjaCnAUv","pdf",21275679,1,220,"English","en",105,"# Chapter 1. General Introduction\n## Organization of Thesis\n## Introduction\n## Machine Learning Models\n## Key Features\n## Feature importance\n# Chapter 2. Functional Residue Predictions Based on Geometric and Physicochemical Properties\n## Imbalance and Oversampling\n## XGBoost Model\n## Feature Importance\n## Materials and Methods\n## Results and Discussion\n## Conclusion\n# Chapter 3. Ligand-Binding Residue Predictions Based on Geometric and Physicochemical Properties\n## Materials and Methods\n## Synthetic Oversampling\n## XGBoost Model","[{\"question\":\"What protein tasks does the dissertation address?\",\"answer\":\"It targets functional residue predictions and ligand-binding residue predictions using protein geometric and physicochemical properties.\"},{\"question\":\"How does the dissertation handle class imbalance in the data?\",\"answer\":\"It applies synthetic oversampling strategies to mitigate imbalance before model training and evaluation.\"},{\"question\":\"Which modeling approach is used for the prediction tasks?\",\"answer\":\"XGBoost-based models are used, alongside comparisons to other methods and analysis of performance metrics.\"}]","Machine learning for prediction of protein properties - dissertation | PDF",1785720889,554,{"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},"machine-learning-for-prediction-of-protein-properties-dissertation","",{"@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/machine-learning-for-prediction-of-protein-properties-dissertation/118905/",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},"What protein tasks does the dissertation address?","Question",{"text":75,"@type":76},"It targets functional residue predictions and ligand-binding residue predictions using protein geometric and physicochemical properties.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the dissertation handle class imbalance in the data?",{"text":80,"@type":76},"It applies synthetic oversampling strategies to mitigate imbalance before model training and evaluation.",{"name":82,"@type":73,"acceptedAnswer":83},"Which modeling approach is used for the prediction tasks?",{"text":84,"@type":76},"XGBoost-based models are used, alongside comparisons to other methods and analysis of performance metrics.","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"]