[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123201-en":3,"doc-seo-123201-105":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},123201,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","Predicting Loss-of-Function Impact of Genetic Mutations - A Machine Learning Approach","Next-generation sequencing (NGS) has reduced genome sequencing costs, enabling broader medical research using large-scale omics data. Identifying damaging loss-of-function (LoF) mutations within high-dimensional genomic features is critical for variant interpretation. This study trains machine learning models using mutation attributes such as chromosomal position, amino-acid changes, and codon changes to predict LoFtool scores, which quantify gene intolerance to loss-of-function mutations. Feature selection via f-regression is combined with models including KNN, SVM, RANSAC, decision trees, random forest, and XGBoost, evaluated with five-fold cross-validation.","arXiv :2402 .00054v1 [ q-bio .GN] 26 Jan 2024  \nPredicting Loss-of-Function Impact of Genetic Mutations: A  \nMachine Learning Approach  \nArshmeet Kaur, Morteza Sarmadi ∗†‡ February 2, 2024  \nAbstract  \nThe innovation of next-generation sequencing (NGS) techniques has significantly reduced the price of genome sequencing, lowering barriers to future medical research; it is now feasible to apply genome sequencing to studies where it would have previously been cost-inefficient. Identifying damaging or pathogenic mutations in vast amounts of complex, high-dimensional genome sequencing data may be of particular interest for researchers. Thus, this paper’s aims were to train machine learning models on the attributes of a genetic mutation to predict LoFtool scores (which measure a gene’s intolerance to loss-of-function mutations) . These attributes included, but were not limited to, the position of a mutation on a chromosome, changes in amino acids, and changes in codons caused by the mutation. Models were built using the univariate feature selection technique f-regression combined with K-nearest neighbors (KNN), Support Vector Machine (SVM), Random Sample Consensus (RANSAC), Decision Trees, Random Forest, and Extreme Gradient Boosting (XGBoost) . These models were evaluated using five-fold cross-validated averages of r-squared, mean squared error, root mean squared error, mean absolute error, and explained variance. The findings of this study include the training of multiple models with testing set r-squared values of 0.97 .  \n1 Introduction  \nLast year, Ultima Genomics announced that it could sequence a human genome for just one hundred dollars per person [1] . The reduced cost of genome sequencing means it may now be possible for research in the medical field to collect “omics” data (i.e. , genomics, epigenomics, transcriptomics, epitranscriptomics, proteomics, and metabolomics) where it otherwise would have been too expensive to do so. With the generation of potentially vast amounts of data comes the need to develop informatics tools capable of handling and analyzing it. Machine learning and deep learning posea solution [2] . Training machine-learning tools that can identify pathogenic variants in a genome sequence is potentially useful to researchers; previous research in the field of prediction of genetic pathogenicity has been focused on developing deep/machine learning models to predict mutations’  \n∗ Date of submission: Jan 26, 2024  \n†Arshmeet Kaur is with Evergreen Valley College, 3095 Yerba Buena Rd, San Jose, CA 95135 (e-mail: [Arka7783@stu.evc.edu](Arka7783@stu.evc.edu)).  \n‡Dr. Morteza Sarmadi, PhD and PostDoc at Massachusetts Institute of Technology 77 Massachusetts Ave, Cambridge, MA 02139 (Major: Bioengineering, Minor: Data Science), is an Research and Development scientist at  \nGilead Sciences: 333 Lakeside Dr, Foster City, CA 94404 ([e-mail: mortezanear@yahoo.com](e-mail: mortezanear@yahoo.com)).  \nfunctional effects. For example, methods like FATHMM-MKL and CADD are designed to predict functional consequences of coding and non-coding variants [3] . MetaRNN (developed in [4]) is a deep learning method that distinguishes between benign and pathogenic rare mutations. Other research has focused on datasets of a specific disease, such as PathoPredictor, an ensemble method made for cardiomyopathy, epilepsy, or RASopathies [5] . Some studies test the generalizability of models by using existing methods on clinical data [6] .  \nThe aim of this paper was to train machine learning models to predict LoFtool scores. To create the LoFtool gene score, researchers retrieved all high-confident loss-of-function mutations (defined as those that disrupt protein structure [7]) from Fadista et al.’s 60,706 record Exome Aggregation Consortium dataset [8] . LoFtool provides a score that quantifies how intolerant a certain gene is to loss-of-function variants– in other words, how susceptible a gene is to disease if mutated. It ranks the ","cbCaifOHqDAJd6Hf","https://ap.wps.com/l/cbCaifOHqDAJd6Hf","pdf",4297432,1,13,"English","en",105,"# Abstract\n# Introduction\n## Background and motivation\n## LoFtool scoring rationale\n# Methods\n## Original dataset\n## Data attributes and CLASS labeling\n## Model training and evaluation","[{\"question\":\"What problem does the study address regarding genetic mutations?\",\"answer\":\"The study targets the ability to predict the functional impact of genetic mutations, specifically loss-of-function (LoF) effects, from high-dimensional genomic attributes.\"},{\"question\":\"How are LoFtool scores defined and why are they important?\",\"answer\":\"LoFtool scores quantify how intolerant a gene is to loss-of-function variants by ranking its percentile intolerance, helping researchers assess gene-level susceptibility to disease.\"},{\"question\":\"Which machine learning models and evaluation metrics are used?\",\"answer\":\"Models include KNN, SVM, RANSAC, decision trees, random forest, and XGBoost, with performance assessed using five-fold cross-validated r-squared, MSE, RMSE, MAE, and explained variance.\"}]","Predicting Loss-of-Function Impact of Genetic Mutations - A Machine Learning Approach | PDF",1785815192,33,{"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},"predicting-loss-of-function-impact-of-genetic-mutations-a-machine-learning-approach","",{"@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/predicting-loss-of-function-impact-of-genetic-mutations-a-machine-learning-approach/123201/",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","2026-08-04",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 problem does the study address regarding genetic mutations?","Question",{"text":75,"@type":76},"The study targets the ability to predict the functional impact of genetic mutations, specifically loss-of-function (LoF) effects, from high-dimensional genomic attributes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are LoFtool scores defined and why are they important?",{"text":80,"@type":76},"LoFtool scores quantify how intolerant a gene is to loss-of-function variants by ranking its percentile intolerance, helping researchers assess gene-level susceptibility to disease.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning models and evaluation metrics are used?",{"text":84,"@type":76},"Models include KNN, SVM, RANSAC, decision trees, random forest, and XGBoost, with performance assessed using five-fold cross-validated r-squared, MSE, RMSE, MAE, and explained variance.","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"]