{"id":62,"date":"2025-04-10T17:59:19","date_gmt":"2025-04-10T17:59:19","guid":{"rendered":"http:\/\/localhost\/wordpress\/valancelabs\/?p=62"},"modified":"2025-05-13T16:07:09","modified_gmt":"2025-05-13T16:07:09","slug":"introducing-molgps-a-foundational-gnn-for-molecular-property-prediction","status":"publish","type":"post","link":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/","title":{"rendered":"Introducing MolGPS \u2014 A Foundational GNN for Molecular Property Prediction"},"content":{"rendered":"<figure class=\"wp-block-video\"><video height=\"990\" style=\"aspect-ratio: 1440 \/ 990;\" width=\"1440\" controls poster=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-1000001444.png\" src=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Powered-by-Recursion_ver1.mp4\"><\/video><\/figure>\n\n\n\n<div class=\"fifty_fifty\">\n    <div class=\"container\">\n        <div class=\"left__col\">\n            <h2><span>On the Scalability<\/span> of GNNs for Molecular Graphs<\/h2>\n                    <\/div>\n        <div class=\"right__col\">\n            <div class=\"desc\">\n                <p>Scaling deep learning models has been at the heart of recent revolutions in language modeling and image generation. Practitioners have observed a strong relationship between model size, dataset size, and performance. However, structure-based architectures such as Graph Neural Networks (GNNs) are yet to show the benefits of scale mainly due to the lower efficiency of sparse operations, large data requirements, and lack of clarity about the effectiveness of various architectures.\u2028\u2028<\/p>\n<p>We address this drawback of GNNs by studying their scaling behavior. Specifically, we analyze message-passing networks, graph Transformers, and hybrid architectures on the largest public collection of 2D molecular graphs. For the first time, we observe that GNNs benefit tremendously from the increasing width, number of molecules, number of labels, and diversity in the pretraining datasets.\u2028\u2028<\/p>\n<p>We&#8217;re excited to introduce MolGPS, a 3B parameter model for various molecular property prediction tasks. We hope that this work will pave the way for an era where foundational GNNs drive pharmaceutical drug discovery. Not only does the model&#8217;s performance scale with parameters, but it also benefits tremendously from integrating high-level phenomics data into the mix.<\/p>            <\/div>\n        <\/div>\n    <\/div>\n<\/div>\n\n\n<div class=\"wp-block-columns blurred_container is-layout-flex wp-container-core-columns-is-layout-9d6595d7 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<div class=\"title__desc\">\n    <div class=\"container\">\n        <h2><span>Model Details<\/span> and Performance<\/h2>\n                    <div class=\"desc\">\n                <p>MolGPS was trained on the <a href=\"https:\/\/arxiv.org\/abs\/2310.04292\" target=\"_blank\" rel=\"noopener\">LargeMix<\/a> dataset mixture consisting of 5 million molecules grouped into 5 different tasks with each task having multiple labels. LargeMix contains datasets like the L1000_VCAP and L1000_MCF7 (transcriptomics), PCBA_1328 (bioassays), PCQM4M_G25 and PCGM4M_N4 (DFT simulations).<\/p>            <\/div>\n            <\/div>\n<\/div>\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"920\" height=\"349\" src=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325822-1.png\" alt=\"\" class=\"wp-image-145\" srcset=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325822-1.png 920w, https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325822-1-300x114.png 300w, https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325822-1-768x291.png 768w, https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325822-1-18x7.png 18w\" sizes=\"auto, (max-width: 920px) 100vw, 920px\" \/><\/figure>\n\n\n\n<p>We also added a classification dataset using a subset of our Recursion&#8217;s phenomics data. This dataset was created by using a pre-trained masked auto-encoder clustering the phenomics images into 6,000 different classes, which are then used for binary classification.<\/p>\n\n\n\n<p>MolGPS was first pretrained using a common multi-task supervised learning strategy and was then finetuned (or probed) for various molecular property prediction tasks to evaluate performance. We benchmarked the performance of MolGPS on the Therapeutics Data Commons (TDC), MoleculeNet, and Polaris benchmarks.<\/p>\n\n\n\n<div class=\"title__desc\">\n    <div class=\"container\">\n        <h2>Therapeutics Data Common (TDC) and <span>MoleculeNet<\/span><\/h2>\n            <\/div>\n<\/div>\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"920\" height=\"623\" src=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-1000001489.png\" alt=\"\" class=\"wp-image-148\" srcset=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-1000001489.png 920w, https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-1000001489-300x203.png 300w, https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-1000001489-768x520.png 768w, https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-1000001489-18x12.png 18w\" sizes=\"auto, (max-width: 920px) 100vw, 920px\" \/><\/figure>\n\n\n\n<p>Our study focuses on the 22 ADMET (absorption, distribution, metabolism, excretion, and toxicity) tasks available in TDC. This benchmark has been around for years with continuous submissions from various groups, including both deep-learning models and traditional machine learning at the top of the benchmark, with a total of 8 models sharing the top positions across all 22 tasks. Simply by scaling our model, we found that MolGPS outperforms SOTA on 12\/22 tasks.<\/p>\n\n\n\n<p>We investigate 4 datasets from MoleculeNet that are commonly used in similar studies: BACE (that assesses the binding outcomes of a group of inhibitors targeting \u03b2-secretase), BBBP (the Blood-Brain Barrier Penetration that assesses if a molecule can penetrate the central nervous system), Clintox (which is relevant to the toxicity of molecular compounds, and Sider (the Side Effect Resource which contains information about adverse drug reactions in a database of marketed drugs). We found that MolGPS outperforms SOTA (all self-supervised or quantum-based self-supervised pre-trained models) on all 4 tasks.<\/p>\n\n\n\n<div class=\"title__desc\">\n    <div class=\"container\">\n        <h2><\/h2>\n                    <div class=\"desc\">\n                <h2><a href=\"https:\/\/polarishub.io\/\" target=\"_blank\" rel=\"noopener\">Polaris<\/a><\/h2>            <\/div>\n            <\/div>\n<\/div>\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"920\" height=\"444\" src=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-1000001491.png\" alt=\"\" class=\"wp-image-152\" srcset=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-1000001491.png 920w, https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-1000001491-300x145.png 300w, https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-1000001491-768x371.png 768w, https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-1000001491-18x9.png 18w\" sizes=\"auto, (max-width: 920px) 100vw, 920px\" \/><\/figure>\n\n\n\n<p>While TDC and MoleculeNet are commonly used benchmarks for open-source drug discovery evaluation, we note that they suffer from data collection and processing biases across dissimilar molecules. These limitations have been described previously in\u00a0<a href=\"https:\/\/practicalcheminformatics.blogspot.com\/2023\/08\/we-need-better-benchmarks-for-machine.html\">conversations<\/a>\u00a0throughout the community.\u2028\u2028<\/p>\n\n\n\n<p>Polaris\u00a0is a new collection of benchmarks and datasets curated through a standardized evaluation protocol developed by an\u00a0<a href=\"https:\/\/polarishub.io\/guidelines\/small-molecules\">industry consortium<\/a>\u00a0of biotech&#8217;s and pharmaceutical companies. We investigated the performance of MolGPS on 12 ADMET and binding prediction tasks and found that MolGPS outperforms SOTA on 11\/12 tasks.<\/p>\n<\/div>\n<\/div>\n\n\n\n<div class=\"fifty_fifty\">\n    <div class=\"container\">\n        <div class=\"left__col\">\n            <h2><span>Scaling<\/span> Experiments<\/h2>\n                            <div class=\"image_under_title\">\n                    <img loading=\"lazy\" decoding=\"async\" width=\"380\" height=\"344\" src=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Group-37666.png\" class=\"attachment-full size-full\" alt=\"\" srcset=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Group-37666.png 380w, https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Group-37666-300x272.png 300w, https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Group-37666-13x12.png 13w\" sizes=\"auto, (max-width: 380px) 100vw, 380px\" \/>                <\/div>\n                    <\/div>\n        <div class=\"right__col\">\n            <div class=\"desc\">\n                <p>In the following experiments, we look at the performance of MolGPS while increasing the width such that the parameter count goes up from 1M to 3B parameters. To properly assess the benefits of scale, we evaluate the performance of the model when probing the 22 downstream tasks from TDC. Here, the hyper-parameter search is done with 10M parameters, and width scaling is done in a zero-shot setting using the muTransfer technique.<\/p>\n<p><br \/>We also observe that GNNs benefit tremendously from increasing the model&#8217;s width and that the gains are consistent and linear to the logarithm of the parameter count. Indeed, there appears to be no slowdown in the scaling curve, hinting that we could continue to improve the performance with larger and larger models, similar to those found in large language models (LLMs).<\/p>\n<p><br \/>Further, we note that MolGPS shows significant improvement over the performance achieved by the TDC baselines. This represents the best model performance per task from when TDC was first introduced in 2021. Note that on the y-axis, a value of 0 represents the average of all submissions to the TDC benchmark. Compared to the latest SOTA on TDC, our ensemble model passes the line of the best model per task, meaning that it is generally better to just use MolGPS rather than try all 30+ methods that are part of the TDC bencmark.<\/p>\n<p><br \/>We also note that the model reaches a limit when scaling on public data only, but the addition of private phenomics data pushes the boundary of scale and performance much further.<br \/>Above, we report the \u201cnormalized performance\u201d representing the average of the z-score across the 22 tasks from TDC. The z-score is computed based on the model\u2019s performance relative to the leaderboard for a task, adjusted for the polarity of the task metric, i.e., multiplied by -1 if \u201clower is better\u201d.<\/p>            <\/div>\n        <\/div>\n    <\/div>\n<\/div>\n\n\n<div class=\"fifty_fifty\">\n    <div class=\"container\">\n        <div class=\"left__col\">\n            <h2>Molecules vs. <span>language<\/span><\/h2>\n                    <\/div>\n        <div class=\"right__col\">\n            <div class=\"desc\">\n                <p>In the context of LLMs, our scaling experiment results may seem surprising given our models are only trained on a few million data points (molecules) while LLMs are typically trained on larger datasets comprising trillions of tokens. To better understand the performance increase and gap in dataset size, it\u2019s helpful to draw a few analogies between molecules and language.<\/p>\n<p><br \/>In our setting, molecules are analogous to sentences in language processing, while the atoms and bonds are analogous to tokens. Moreover, the task is supervised and some molecules have thousands of associated labels coming from experimental data. This allows the learned molecular embeddings to be much richer than such derived from simply retrieving a missing token.<\/p>            <\/div>\n        <\/div>\n    <\/div>\n<\/div>\n\n<div class=\"blog_cta\">\n    <div class=\"container\">\n        <div class=\"bg\">\n            <img decoding=\"async\" src=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/themes\/valancelabs\/src\/images\/blog_cta_bg.png\" alt=\"Backgroung image\">\n        <\/div>\n\n        <div class=\"content\">\n            <h2>Want to learn more about MolGPS?<\/h2>\n                            <div class=\"desc\">\n                    Get in touch with our team.                <\/div>\n                                        <a href=\"#\" class=\"read_more\">\n                    Contact Us                    <svg width=\"24\" height=\"24\" viewbox=\"0 0 24 24\" fill=\"none\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\">\n                    <path d=\"M5 12H19M19 12L13 6M19 12L13 18\" stroke=\"white\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\"\/>\n                    <\/svg>\n                <\/a>\n                    <\/div>\n        \n    <\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>Scaling deep learning models has been at the heart of recent revolutions in language modeling and image generation. Practitioners have observed a strong relationship&#8230;<\/p>","protected":false},"author":1,"featured_media":133,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[3],"class_list":["post-62","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized","tag-blog"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.0 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Introducing MolGPS \u2014 A Foundational GNN for Molecular Property Prediction - Valance Labs<\/title>\n<meta name=\"robots\" content=\"noindex, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Introducing MolGPS \u2014 A Foundational GNN for Molecular Property Prediction - Valance Labs\" \/>\n<meta property=\"og:description\" content=\"Scaling deep learning models has been at the heart of recent revolutions in language modeling and image generation. Practitioners have observed a strong relationship...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/valancelabs.digitalhero.uk.com\/fr\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/\" \/>\n<meta property=\"og:site_name\" content=\"Valance Labs\" \/>\n<meta property=\"article:published_time\" content=\"2025-04-10T17:59:19+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-05-13T16:07:09+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325827.png\" \/>\n\t<meta property=\"og:image:width\" content=\"680\" \/>\n\t<meta property=\"og:image:height\" content=\"791\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"sys_superadmin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"sys_superadmin\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/\",\"url\":\"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/\",\"name\":\"Introducing MolGPS \u2014 A Foundational GNN for Molecular Property Prediction - Valance Labs\",\"isPartOf\":{\"@id\":\"https:\/\/valancelabs.digitalhero.uk.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325827.png\",\"datePublished\":\"2025-04-10T17:59:19+00:00\",\"dateModified\":\"2025-05-13T16:07:09+00:00\",\"author\":{\"@id\":\"https:\/\/valancelabs.digitalhero.uk.com\/#\/schema\/person\/0651e72662219abacb5d99e1caf27439\"},\"breadcrumb\":{\"@id\":\"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/#primaryimage\",\"url\":\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325827.png\",\"contentUrl\":\"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325827.png\",\"width\":680,\"height\":791},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/valancelabs.digitalhero.uk.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Introducing MolGPS \u2014 A Foundational GNN for Molecular Property Prediction\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/valancelabs.digitalhero.uk.com\/#website\",\"url\":\"https:\/\/valancelabs.digitalhero.uk.com\/\",\"name\":\"Valance Labs\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/valancelabs.digitalhero.uk.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/valancelabs.digitalhero.uk.com\/#\/schema\/person\/0651e72662219abacb5d99e1caf27439\",\"name\":\"sys_superadmin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/valancelabs.digitalhero.uk.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/113bcd80fc1b77846a4a1c6ab17ba30b1d3bef0ff7bf04e5754a416a45008ba8?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/113bcd80fc1b77846a4a1c6ab17ba30b1d3bef0ff7bf04e5754a416a45008ba8?s=96&d=mm&r=g\",\"caption\":\"sys_superadmin\"},\"sameAs\":[\"https:\/\/valancelabs.digitalhero.uk.com\"],\"url\":\"https:\/\/valancelabs.digitalhero.uk.com\/fr\/author\/sys_superadmin\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Introducing MolGPS \u2014 A Foundational GNN for Molecular Property Prediction - Valance Labs","robots":{"index":"noindex","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"og_locale":"fr_FR","og_type":"article","og_title":"Introducing MolGPS \u2014 A Foundational GNN for Molecular Property Prediction - Valance Labs","og_description":"Scaling deep learning models has been at the heart of recent revolutions in language modeling and image generation. Practitioners have observed a strong relationship...","og_url":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/","og_site_name":"Valance Labs","article_published_time":"2025-04-10T17:59:19+00:00","article_modified_time":"2025-05-13T16:07:09+00:00","og_image":[{"width":680,"height":791,"url":"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325827.png","type":"image\/png"}],"author":"sys_superadmin","twitter_card":"summary_large_image","twitter_misc":{"\u00c9crit par":"sys_superadmin","Dur\u00e9e de lecture estim\u00e9e":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/","url":"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/","name":"Introducing MolGPS \u2014 A Foundational GNN for Molecular Property Prediction - Valance Labs","isPartOf":{"@id":"https:\/\/valancelabs.digitalhero.uk.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/#primaryimage"},"image":{"@id":"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/#primaryimage"},"thumbnailUrl":"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325827.png","datePublished":"2025-04-10T17:59:19+00:00","dateModified":"2025-05-13T16:07:09+00:00","author":{"@id":"https:\/\/valancelabs.digitalhero.uk.com\/#\/schema\/person\/0651e72662219abacb5d99e1caf27439"},"breadcrumb":{"@id":"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/#primaryimage","url":"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325827.png","contentUrl":"https:\/\/valancelabs.digitalhero.uk.com\/wp-content\/uploads\/2025\/04\/Frame-2087325827.png","width":680,"height":791},{"@type":"BreadcrumbList","@id":"https:\/\/valancelabs.digitalhero.uk.com\/introducing-molgps-a-foundational-gnn-for-molecular-property-prediction\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/valancelabs.digitalhero.uk.com\/"},{"@type":"ListItem","position":2,"name":"Introducing MolGPS \u2014 A Foundational GNN for Molecular Property Prediction"}]},{"@type":"WebSite","@id":"https:\/\/valancelabs.digitalhero.uk.com\/#website","url":"https:\/\/valancelabs.digitalhero.uk.com\/","name":"Valance Labs","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/valancelabs.digitalhero.uk.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Person","@id":"https:\/\/valancelabs.digitalhero.uk.com\/#\/schema\/person\/0651e72662219abacb5d99e1caf27439","name":"sys_superadmin","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/valancelabs.digitalhero.uk.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/113bcd80fc1b77846a4a1c6ab17ba30b1d3bef0ff7bf04e5754a416a45008ba8?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/113bcd80fc1b77846a4a1c6ab17ba30b1d3bef0ff7bf04e5754a416a45008ba8?s=96&d=mm&r=g","caption":"sys_superadmin"},"sameAs":["https:\/\/valancelabs.digitalhero.uk.com"],"url":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/author\/sys_superadmin\/"}]}},"_links":{"self":[{"href":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/wp-json\/wp\/v2\/posts\/62","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/wp-json\/wp\/v2\/comments?post=62"}],"version-history":[{"count":25,"href":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/wp-json\/wp\/v2\/posts\/62\/revisions"}],"predecessor-version":[{"id":273,"href":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/wp-json\/wp\/v2\/posts\/62\/revisions\/273"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/wp-json\/wp\/v2\/media\/133"}],"wp:attachment":[{"href":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/wp-json\/wp\/v2\/media?parent=62"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/wp-json\/wp\/v2\/categories?post=62"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/valancelabs.digitalhero.uk.com\/fr\/wp-json\/wp\/v2\/tags?post=62"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}