[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123481-en":3,"doc-seo-123481-105":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},123481,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Bacteria-Specific Feature Selection for Enhanced Antimicrobial Peptide Activity Predictions Using Machine-Learning Methods","Antimicrobial peptides (AMPs) are short molecules produced by immune responses and are central to combating infections. While machine learning can predict AMP activity from sequence, most models are not bacterium-specific because they ignore bacterial features such as membrane chemical composition and structure. This study trains supervised machine-learning models on data for peptides targeting E. coli and A. baumannii, using LASSO regression and SVM-based selection to identify key descriptors and then applying Support Vector classifiers and Logistic Regression to distinguish active from inactive AMPs. Results support recommendations for designing more effective antibacterial therapies.","Bacteria-Specific Feature Selection for Enhanced Antimicrobial Peptide Activity Predictions Using Machine-Learning Methods  \nHamid Teimouri,†,‡ Angela Medvedeva,†,‡ and Anatoly B. Kolomeisky ∗ ,†,‡,¶ , §  \n†Department of Chemistry, Rice University, Houston, Texas 77005, USA ‡Center for Theoretical Biological Physics, Rice University, Houston, Texas 77005, USA ¶Department of Chemical and Biomolecular Engineering, Rice University, Houston, Texas  \n77005, USA  \n§Department of Physics and Astronomy, Rice University, Houston, Texas 77005, USA  \nE-mail: [tolya@rice.edu](tolya@rice.edu)  \nAbstract  \nThere are several classes of short peptide molecules, known as antimicrobial peptides (AMPs), which are produced during the immune responses of living organisms against various infections. In recent years, substantial progress has been achieved in applying machine-learning methods to predict the activities of AMPs against bacteria. In most studies, however, the outcome is not bacterium-specific since the specific features of bacteria, such as chemical composition and structure of membranes, are not considered. To overcome this problem, we developed a new computational approach that allowed us to train several supervised machine-learning models using a specific set of data associated with peptides targeting bacteria E. coli and A. baumannii. We utilized the Least Absolute Shrinkage and Selection Operator (LASSO) regression and Support Vector  \nMachine (SVM) techniques to select, among more than 1500 physio-chemical descriptors, the most important features that can be used to classify a peptide as antimicrobial or ineffective against those species of bacteria. The classification of active versus inactive AMPs using the Support Vector classifiers and Logistic Regression methods has been performed. This computational study allows us to make recommendations of how to design more efficient antibacterial drug therapies.  \n\n| Sequence | Activity |\n| --- | --- |\n| YGLGLVGPYLIP | 1 |\n| AYGLVGAYGLVPYLI | 0 |\n| AYGLVGAYGL | 1 |\n\nClassification models  \n􀀡 = 􀀣 (􀀥)  \nactivity features  \nAMP (1)  \nnonAMP (0)  \nTOC graph  \nIntroduction  \nAntimicrobial peptides (AMPs), which can be produced by both eukaryotic and prokaryotic organisms, play an important role in immune systems of mammals and plants. 1–3 It is well known that AMPs have a net positive charge and are in general amphipathic, i.e., they have both hydrophobic and hydrophilic spatially separated segments. These characteristics allow them to attach to anionic (negatively-charged) bacterial membranes and exhibit their antibacterial activity. Thus, the antimicrobial functioning is primarily dependent on the specific interactions between AMPs, particularly the N-terminus of these molecules, 4 and bacterial membranes, 5 such that a certain peptide can disrupt the membrane of a specific bacterium while it might not be active against other bacteria. 6 This is confirmed by the observations that larger fractions of anionic lipids in bacterial membranes result in increased membrane disruption and permeabilization by cationic AMPs. 7  \nMachine-learning methods have been widely employed in studying AMPs, and they primarily aim at predicting the antimicrobial activity of an arbitrary peptide from its amino-acid sequence. 8,9 The performance and reliability of such approaches are mainly dependent on the training data, so many prediction tools have been developed in conjunction with AMP databases. 10–14 These tools can in turn be used to classify newly-discovered peptides as antimicrobial or active against another target such as cancer or fungi, 15 but the predictions are not bacterium-specific. Previous machine-learning models were mainly trained based on dataset composed of AMP activity data targeting mixed species of bacteria. 8 Recently, a new machine-learning pipeline approach was developed that predicts the antimicrobial activity of peptides targeting separately gram-positive and gram-negative bacteria. 16","cbCaibGseF84Su3y","https://ap.wps.com/l/cbCaibGseF84Su3y","pdf",588351,1,30,"English","en",105,"# Introduction\n## Antimicrobial peptides and membrane interactions\n## Limits of existing machine-learning predictors\n## Rationale for bacterium-specific modeling\n# Classification models\n## Feature selection with LASSO and descriptor filtering\n## Active vs inactive AMP prediction approaches","[{\"question\":\"Why are most existing antimicrobial peptide predictors not bacterium-specific?\",\"answer\":\"Because they typically predict activity from peptide sequence using training data that mixes bacterial targets, without explicitly incorporating bacterium-specific features such as membrane composition and structure.\"},{\"question\":\"What bacterial species and peptide data does this study focus on?\",\"answer\":\"The approach trains models using peptides targeting E. coli and A. baumannii.\"},{\"question\":\"How are important peptide descriptors selected in the proposed method?\",\"answer\":\"The method uses LASSO regression and SVM techniques to select the most important features from a large set of physio-chemical descriptors.\"}]","Bacteria-Specific Feature Selection for Enhanced Antimicrobial Peptide Activity Predictions Using Machine-Learning Methods | PDF",1785816761,76,{"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},"bacteria-specific-feature-selection-for-enhanced-antimicrobial-peptide-activity-predictions-using-machine-learning-methods","",{"@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/bacteria-specific-feature-selection-for-enhanced-antimicrobial-peptide-activity-predictions-using-machine-learning-methods/123481/",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},"Why are most existing antimicrobial peptide predictors not bacterium-specific?","Question",{"text":75,"@type":76},"Because they typically predict activity from peptide sequence using training data that mixes bacterial targets, without explicitly incorporating bacterium-specific features such as membrane composition and structure.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What bacterial species and peptide data does this study focus on?",{"text":80,"@type":76},"The approach trains models using peptides targeting E. coli and A. baumannii.",{"name":82,"@type":73,"acceptedAnswer":83},"How are important peptide descriptors selected in the proposed method?",{"text":84,"@type":76},"The method uses LASSO regression and SVM techniques to select the most important features from a large set of physio-chemical descriptors.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":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":21,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]