[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-125429-105":59,"doc-detail-125429-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","comprehensive-machine-learning-boosts-structure-based-virtual-screening-for-parp1-inhibitors","COMPREHENSIVE MACHINE LEARNING BOOSTS - Structure-Based Virtual Screening for PARP1 Inhibitors","","Target-specific machine learning scoring functions (ML SFs) are developed and evaluated to improve structure-based virtual screening for PARP1, a validated DNA repair target implicated in BRCA-mutated cancers. Existing PARP1 inhibitors suffer from selectivity and toxicity limitations, motivating ML-guided discovery of improved chemotypes. Bioactivity data from ChEMBL are paired with property-matched decoys and ligands are docked using Smina. Five ML models are trained with multiple fingerprint features (including PLEC, GRID, and Morgan), benchmarked by EF1% and precision-recall. Target-specific ML SFs outperform generic baselines, with a PLEC-trained SVM regressor delivering EF1%=38.8 and NEF1%=0.764, and strong generalisation on a dissimilar test set.",{"@graph":69,"@context":123},[70,84,106],{"@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/comprehensive-machine-learning-boosts-structure-based-virtual-screening-for-parp1-inhibitors/125429/",{"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/comprehensive-machine-learning-boosts-structure-based-virtual-screening-for-parp1-inhibitors/125429.png","ImageObject",300,407,{"name":92,"@type":93},"Genevieve","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-17","2026-08-05",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What is the main goal of the study on PARP1 inhibitors?","Question",{"text":113,"@type":114},"To develop and evaluate target-specific machine learning scoring functions that enhance structure-based virtual screening for PARP1.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How were training data and decoys prepared for model development?",{"text":118,"@type":114},"Bioactivity data from ChEMBL were combined with property-matched decoys generated using DeepCoy, and ligands were docked using the PARP1 crystal structure with Smina.",{"name":120,"@type":111,"acceptedAnswer":121},"Which model and feature set produced the best virtual screening performance?",{"text":122,"@type":114},"A SVM regressor trained on PLEC fingerprints achieved the top results, with EF1%=38.8 and NEF1%=0.764.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},125429,1785898860,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":8,"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":130,"read_time":81},962085564549,"https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","Abstracts  \nAims: Developing and evaluating target-specific machine learning (ML) scoring functions (SFs) to enhance structure-based virtual screening for Poly (ADP-ribose) polymerase 1 (PARP1), a key DNA repair enzyme and validated target in BRCA-mutated cancers. Existing PARP1 inhibitors face limitations in selectivity and toxicity, motivating ML-driven strategies for identifying improved chemotypes [1] .  \nMethods: Bioactivity data from ChEMBL were combined with property-matched decoys generated using DeepCoy. Ligands were docked into the PARP1 crystal structure with Smina, and training and test sets were prepared. Five ML algorithms, random forest, extreme gradient boosting, support vector machines (SVM), and neural network models, were trained in regression and classification modes using multiple featurisation techniques, including protein-ligand extended connectivity (PLEC) fingerprints, GRID, and Morgan fingerprints, as described in our recent publication  \n[2] . Models were benchmarked against generic SFs using enrichment factor (EF1%), normalised EF1% (NEF1%) and precisionrecall curves.  \nResults and conclusions: Target-specific ML SFs consistently surpassed generic approaches, with a SVM regressor trained on PLEC fingerprints achieving the best performance (EF1%=38.8, NEF1%=0 . 764) . Models retained strong predictive ability on a structurally dissimilar test set, confirming generalisation and recovery of diverse inhibitors. These results demonstrate that MLtailored SFs substantially improve virtual screening for PARP1 and provide an effective route toward novel, selective anticancer compounds.  \nReferences  \n1. Franzese E. , Centonze S. , Diana A. , Carlino F. , Guerrera LP. , Di Napoli M. , et al. ‘PARP inhibitors in ovarian cancer.’ Cancer Treatment Reviews. 2019;73:1–9 .  \n2. Caba K. , Tran-Nguyen VK. , Rahman T. , Ballester P.J.‘Comprehensive machine learning boosts structure-based virtual screening for PARP1 inhibitors.’ J Cheminform. 2024;16 .  \nAbstract citation ID: bbaf631.064  \nCOMPREHENSIVE MACHINE LEARNING BOOSTS  \nSTRUCTURE-BASED VIRTUAL SCREENING FOR  \nPARP1 INHIBITORS  \nKlaudia Caba1, Viet-Khoa Tran-Nguyen2, Taufiq Rahman3, Pedro J. Ballester1  \n1 Department of Bioengineering, Imperial College London, United Kingdom  \n2 Unité de Biologie Fonctionnelle et Adaptative, Université Paris Cité, France  \n3 Department of Pharmacology, University of Cambridge, United Kingdom  \nBriefings in Bioinformatics, Volume 26, Supplement 1, 2025 i37","cbCaiqhE2A7EdI1w","https://ap.wps.com/l/cbCaiqhE2A7EdI1w","pdf",39180,"English","# Abstract\n## Aims\n## Methods\n## Results and conclusions\n# References","[{\"question\":\"What is the main goal of the study on PARP1 inhibitors?\",\"answer\":\"To develop and evaluate target-specific machine learning scoring functions that enhance structure-based virtual screening for PARP1.\"},{\"question\":\"How were training data and decoys prepared for model development?\",\"answer\":\"Bioactivity data from ChEMBL were combined with property-matched decoys generated using DeepCoy, and ligands were docked using the PARP1 crystal structure with Smina.\"},{\"question\":\"Which model and feature set produced the best virtual screening performance?\",\"answer\":\"A SVM regressor trained on PLEC fingerprints achieved the top results, with EF1%=38.8 and NEF1%=0.764.\"}]","COMPREHENSIVE MACHINE LEARNING BOOSTS - Structure-Based Virtual Screening for PARP1 Inhibitors | PDF"]