[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-657147-105":59,"doc-detail-657147-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","glamour-graph-learning-over-macromolecule-representations-interpretable-supervised-learning-framework-for-macromolecules","GLAMOUR: Graph Learning Over Macromolecule Representations - interpretable supervised learning framework for macromolecules","","Near-infinite macromolecular diversity from monomer choices, linkages, and polymer topologies enables ubiquity while blocking general machine learning that treats macromolecules as inputs. GLAMOUR introduces a chemistry-informed graph representation for macromolecules to quantify structural similarity and support interpretable supervised learning. It combines chemical similarity via cheminformatic fingerprints with exact graph edit distances or graph kernels, then couples the representation to supervised GNNs for structure-property learning in glycans and anti-microbial peptides.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/glamour-graph-learning-over-macromolecule-representations-interpretable-supervised-learning-framework-for-macromolecules/657147/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/glamour-graph-learning-over-macromolecule-representations-interpretable-supervised-learning-framework-for-macromolecules/657147.png","ImageObject",300,407,{"name":92,"@type":93},"SALUTone","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-26",true,{"@type":102,"interactionType":103,"userInteractionCount":8},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does GLAMOUR aim to solve in macromolecule machine learning?","Question",{"text":112,"@type":113},"It addresses how vast macromolecular diversity makes it difficult to develop general machine learning methods that work with macromolecules as inputs.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does GLAMOUR represent macromolecules?",{"text":117,"@type":113},"It converts macromolecule structures into parsed text files and then builds network graphs where monomers are nodes and bonds are edges, with node/edge attributes as molecular fingerprints.",{"name":119,"@type":110,"acceptedAnswer":120},"How are structural similarity and learning connected in GLAMOUR?",{"text":121,"@type":113},"Similarity is computed using exact graph edit distance and graph kernels, and the resulting graph representation is coupled with supervised GNN models to learn structure-property relationships, while attribution highlights important regions and substructures.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},657147,1792974907,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":8,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144},5909897206756,"https://ap-avatar.wpscdn.com/avatar/5600152dbe4a7e99502?x-image-process=image/resize,m_fixed,w_180,h_180&k=1792654152478566863","arXiv :2103 .02565v3 [ cs .LG] 23 Aug 2021  \nGLAMOUR: GRAPH LEARNING OVER MACROMOLECULE REPRESENTATIONS  \nSomesh Mohapatra, Joyce An & Rafael Gmez-Bombarelli􀀃 Department of Materials Science and Engineering Massachusetts Institute of Technology  \nCambridge, MA 02139, USA  \nfsomeshm, joycean,[rafagb](rafagbg@mit.edu)[g](rafagbg@mit.edu)[@mit.edu](rafagbg@mit.edu)  \nABSTRACT  \nThe near-infinite chemical diversity of natural and artificial macromolecules arises from the vast range of possible component monomers, linkages, and polymers topologies. This enormous macromolecular diversity contributes to the ubiquity and indispensability of macromolecules but hinders the development of general machine learning methods with macromolecules as input. To address this, we developed GLAMOUR, a framework for chemistry-informed graph representation of macromolecules that enables quantifying structural similarity, and interpretable supervised learning for macromolecules.  \n1 INTRODUCTION  \nMachine learning (ML) applications to individual macromolecule classes, such as proteins, have been very successful but typically rely on sequence-based representations that effectively capture structures with linear architectures (Schissel et al., 2021; Alley et al., 2019) . However, these methods do not extend to macromolecules with complex topologies, such as glycans and biohybrid sequence-defined polymers, which exhibit non-linear structure and higher levels of monomer and linkage diversity. Graphs are a natural and more general macromolecule representation, with nodes representing monomers and edges representing connecting bonds. ML over graph representations has achieved state-of-the-art results across several fields (Hamilton et al., 2017) (see Section A for a survey of the field) and in chemistry and life sciences, graph neural networks (GNNs) have become the modern workhorse for molecular property prediction (Yang et al., 2019; Jin et al., 2020) . Attribution methods are compatible with GNNs to highlight how input features are relevant to model predictions of target properties, such as molecular olfactory descriptors (Sanchez-Lengeling et al., 2020; 2019) .  \nIn this work, we developed a graph representation for macromolecules. The representation generalizes ideas of macromolecule similarity from sequence alignment to structural similarity between complex topologies. Using chemical similarity between monomers through cheminformatic fingerprints and exact graph edit distances (GED) or graph kernels to compare topologies, it allows for quantification of the chemical and structural similarity of two arbitrary macromolecule topologies. Further, the representation was coupled to supervised GNN models to learn structure-property relationships in glycans and anti-microbial peptides. The graph representation handles linear, branched and cyclic topologies along with any monomer composition. Attribution methods highlight the regions of the macromolecules and the substructures within the monomers that are most responsible for the predicted properties.  \n2 RESULTS AND DISCUSSION  \nWe developed a generalized text file system to convert a macromolecule structure into a machinereadable format (Figure 1A, Section C) . The text file has three sections – SMILES, MONOMERS,  \nand BONDS, inspired by the PDB file format (Berman, 2000) . Under SMILES, monomer and bond  \n􀀃 Corresponding author: [rafagb@mit.edu](rafagb@mit.edu).  \nFigure 1: Macromolecules represented as graphs enable similarity computation and interpretable machine learning. A. Macromolecular structures are converted into text files. The text files are parsed into network graphs, where monomers are nodes and bonds are edges. Each text file enumerates SMILES for monomers and bonds, node indices corresponding to monomers, and pairs of node indices for bonds. Node and edge attributes are fingerprints of respective molecules. B. Pair-wise similarity matrix obtained for the library of macromolecules, and dimensionality reduct","cbCaioljshqxhczr","https://ap.wps.com/l/cbCaioljshqxhczr","pdf",12388057,41,"English","# Abstract\n# Introduction\n# Results and Discussion","[{\"question\":\"What problem does GLAMOUR aim to solve in macromolecule machine learning?\",\"answer\":\"It addresses how vast macromolecular diversity makes it difficult to develop general machine learning methods that work with macromolecules as inputs.\"},{\"question\":\"How does GLAMOUR represent macromolecules?\",\"answer\":\"It converts macromolecule structures into parsed text files and then builds network graphs where monomers are nodes and bonds are edges, with node/edge attributes as molecular fingerprints.\"},{\"question\":\"How are structural similarity and learning connected in GLAMOUR?\",\"answer\":\"Similarity is computed using exact graph edit distance and graph kernels, and the resulting graph representation is coupled with supervised GNN models to learn structure-property relationships, while attribution highlights important regions and substructures.\"}]","GLAMOUR: Graph Learning Over Macromolecule Representations - interpretable supervised learning framework for macromolecules | PDF",103]