[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119544-en":3,"doc-seo-119544-105":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},119544,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",7,"Healthcare","Machine learning predicts distinct biotypes of amyotrophic lateral sclerosis","Amyotrophic lateral sclerosis (ALS) is a universally fatal neurodegenerative disease with no cure, and its clinical heterogeneity and multiple proposed mechanisms have hindered effective therapies. The study analyzed bulk transcriptomes from 297 patients and single-cell transcriptomes from 23 patients using unsupervised machine learning to identify three ALS groups: synaptic dysfunction, neuronal regeneration, and neuronal degeneration. Distinct transcriptional dysregulation patterns suggested novel therapeutic targets. A supervised model achieved ~80% accuracy in predicting ALS subtype from demographic and clinical data.","[www.nature.com/ejhg](www.nature.com/ejhg)  \nARTICLE OPEN   \nMachine learning predicts distinct biotypes of amyotrophic lateral sclerosis  \nNicholas Pasternack 1,2, Ole Paulsen2 and Avindra Nath 1 ✉  \nThis is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply 2025  \n|  |  |  |\n| --- | --- | --- |\n|  | Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease that is universally fatal and has no cure. Heterogeneity of clinical presentation, disease onset, and proposed pathological mechanisms are key reasons why developing impactful therapies for ALS has been challenging. Here we analyzed data from two postmortem cohorts: one with bulk transcriptomes from 297 ALS patients and a separate cohort of single cell transcriptomes from 23 ALS patients. Using unsupervised machine learning, we found three groups of ALS patients characterized by synaptic dysfunction (34%), neuronal regeneration (47%), and neuronal degeneration (19%) . Each of these ALS subtypes had unique patterns of transcriptional dysregulation that could represent novel therapeutic targets. We then developed a supervised machine learning model that was about 80% accurate at predicting ALS subtype based on patient demographic and clinical data. Together, we established three biologically distinct subtypes of ALS that can be predicted by |  |\n|  |  |  |\n|  |  |  |\n|  |  |  |\n|  |  |  |\n|  |  |  |\n|  |  |  |\n|  |  |  |\n|  |  |  |\n| clinical and demographic data. |  |  |\n|  | European Journal of Human Genetics (2025) 33:1290–1299; [https://doi.org/10.1038/s41431-025-01920-y](https://doi.org/10.1038/s41431-025-01920-y) |  |\n|  |  |  |\n\nINTRODUCTION  \nAmyotrophic lateral sclerosis (ALS) or Motor Neurone Disease is a fatal neurodegenerative disease that results in the degeneration of both upper motor neurons and lower motor neurons, with a usual age of onset between 50 and 65 years [1] . ALS patients have a heterogeneous presentation, with multiple underlying pathophysiological mechanisms, which make developing impactful disease course-modifying therapies and reliable biomarkers challenging. This is further complicated by the substantial number of genetic mutations that have been implicated in the disease, which have their own unique pathophysiology. However, most cases are sporadic. Hence, identifying biotypes of ALS based on underlying pathophysiological mechanisms may be key to developing diagnostics and targeted therapies [2, 3] . Past attempts to classify ALS based on site of onset of motor symptoms, rate of progression, age of onset, and other demographic features have some prognostic value but have failed to elucidate distinct pathophysiological mechanisms. Recent developments in RNA sequencing (RNA-seq) and bioinformatics have started to provide unique insight into the pathophysiology of ALSand the heterogeneity associated with it. Using this approach, one study described three transcriptionally distinct subpopulations of ALS characterized by oxidative stress, glial cell activation, or transposable element activation [4] .  \nWe used machine learning tools to identify clusters of ALS patients that display similar pathophysiological processes based on RNA-seq. This allowed us to process data from a large sample size and do so in an unbiased manner. We included additional tools to analyze endogenous retroviral transcripts since they have been previously implicated in the pathophysiology of ALS [5–10] . Furthermore, we analyzed both cortical and spinal cord samples,  \nas well as ALS patients only and ALS patients and unaffected controls. Using these approaches, we have defined three pathophysiologically distinct subtypes of ALS which relate to synaptic dysfunction, neuronal regeneration, and neuronal degeneration. We determined the relevance of these clusters to biological pathways, cell types, and transcriptional regulators of interest. This has allowed us to identify potential therapeutic targets unique to ","cbCaikExYYhHOPNC","https://ap.wps.com/l/cbCaikExYYhHOPNC","pdf",2766333,1,10,"English","en",105,"# Abstract\n## Introduction\n## Results: Unsupervised clustering reveals three transcriptionally distinct ALS patient populations\n## Results: Machine-learning prediction of ALS subtypes","[{\"question\":\"What data types were used to analyze ALS biotypes in this study?\",\"answer\":\"The study used bulk transcriptomes from 297 ALS patients and single-cell transcriptomes from 23 ALS patients.\"},{\"question\":\"How many ALS biotypes were identified, and what characterizes each?\",\"answer\":\"Three biotypes were identified: synaptic dysfunction (34%), neuronal regeneration (47%), and neuronal degeneration (19%), each with distinct transcriptional dysregulation patterns.\"},{\"question\":\"How accurate was the supervised machine learning model for ALS subtype prediction?\",\"answer\":\"The supervised classifier was about 80% accurate at predicting the ALS subtype using patient demographic and clinical data.\"}]","Machine learning predicts distinct biotypes of amyotrophic lateral sclerosis | PDF",1785724868,25,{"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-predicts-distinct-biotypes-of-amyotrophic-lateral-sclerosis","",{"@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/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-predicts-distinct-biotypes-of-amyotrophic-lateral-sclerosis/119544/",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 data types were used to analyze ALS biotypes in this study?","Question",{"text":75,"@type":76},"The study used bulk transcriptomes from 297 ALS patients and single-cell transcriptomes from 23 ALS patients.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How many ALS biotypes were identified, and what characterizes each?",{"text":80,"@type":76},"Three biotypes were identified: synaptic dysfunction (34%), neuronal regeneration (47%), and neuronal degeneration (19%), each with distinct transcriptional dysregulation patterns.",{"name":82,"@type":73,"acceptedAnswer":83},"How accurate was the supervised machine learning model for ALS subtype prediction?",{"text":84,"@type":76},"The supervised classifier was about 80% accurate at predicting the ALS subtype using patient demographic and clinical data.","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},[93,97,101,105,110,115,118,123,128,131,134],{"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":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":116,"slug":117},40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]