{"id":60216,"date":"2024-02-08T00:00:37","date_gmt":"2024-02-07T16:00:37","guid":{"rendered":"https:\/\/www.science.nus.edu.sg\/?p=60216"},"modified":"2024-02-22T22:22:04","modified_gmt":"2024-02-22T14:22:04","slug":"deep-learning-for-real-time-molecular-imaging","status":"publish","type":"post","link":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/","title":{"rendered":"Deep learning for real-time molecular imaging"},"content":{"rendered":"<p><span lang=\"EN-GB\" style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\">National University of Singapore (NUS) researchers have demonstrated that deep learning allows them to observe the dynamics of single molecules more precisely and with less data than traditional evaluation methods. They used convolutional neural networks (CNNs) to observe the movement of single molecules in artificial systems, cells and small organisms. This method promises to accelerate single-molecule measurements in complex systems and make it more accessible to a wider range of researchers.<\/span><\/p>\n<p><span lang=\"EN-GB\" style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\">A single molecule is the most basic unit observable in biological systems. Understanding its behaviour and interactions unlocks insights into the functioning of biological systems, paving the way for strategic interventions in diseases. One of the most powerful ways to observe single molecules is fluorescence spectroscopy. This is due to its strong signal and specificity, which allows only labelled molecules to be observed. For over 50 years, Fluorescence Correlation Spectroscopy (FCS) has been used in this field, measuring the mobility and interaction of molecules with high accuracy and precision. A recent extension of this technique, Imaging FCS, extends its capabilities to characterise mobilities, concentrations and interactions among other parameters in whole images . Despite its capabilities, Imaging FCS poses challenges as it requires large amounts of data (about 100 MB for every measurement). This requires extensive computational processing, which results in slow evaluations.<\/span><\/p>\n<p><span lang=\"EN-GB\" style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\">A research team, led by Professor Thorsten WOHLAND from both the Department of Biological Sciences and the Department of Chemistry, and Professor Adrian R\u00d6LLIN, from the Department of Statistics and Data Science, both from NUS, used deep learning methods to reduce the amount of data required for a measurement (about 5 MB per measurement) while achieving comparable results to traditional methods. The technique uses two CNNs, called FCSNet and ImFCSNet developed by Dr Wai Hoh TANG and Mr Shao Ren SIM, members of the research team. CNNs represent a type of deep learning algorithm suited for analysing visual data. They employ multiple layers of specialised filters that scan across the image for specific features, such as edges, textures and colours. By progressively extracting and combining these features together, they build up a better understanding of the image, allowing them to recognise patterns and objects within the visual data. <\/span><\/p>\n<p><span lang=\"EN-GB\" style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\">Both the FCSNet and ImFCSNet based methods are more precise than traditional FCS methods in terms of diffusion coefficients, but they have different trade-offs for data requirements and spatial resolution. By utilising less data, these techniques can potentially shorten the evaluation time by orders of magnitude, especially for large datasets or complex systems.<\/span><\/p>\n<p><span lang=\"EN-GB\" style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\">Their findings have been published in the <i>Biophysical Journal<\/i>.<\/span><\/p>\n<p><span lang=\"EN-GB\" style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\">Prof Wohland said, \u201cThese CNNs are trained on simulated data and can predict diffusion coefficients from much smaller datasets compared to traditional FCS methods. They are also model agnostic and can be used with any microscope setup.\u201d<\/span><\/p>\n<p><span lang=\"EN-GB\" style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\">Dr Tang added, &#8220;CNNs revolutionise data analysis, offering accelerated and simplified evaluation processes. While it is important to validate their performance, CNNs have the potential to make powerful techniques available to the wider research community.&#8221;<\/span><\/p>\n<p><span lang=\"EN-GB\" style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\">The team hopes that their technique can open new possibilities to accelerate single-molecule research and make the technology accessible to a wider range of users. The CNNs do not require expert inputs and are poised to democratise FCS.<\/span><\/p>\n<p><img fetchpriority=\"high\" decoding=\"async\" width=\"1123\" height=\"755\" src=\"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218_1.jpg\" alt=\"\" class=\"alignnone size-full wp-image-59394\" srcset=\"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218_1.jpg 1123w, https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218_1-300x202.jpg 300w, https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218_1-1024x688.jpg 1024w, https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218_1-768x516.jpg 768w\" sizes=\"(max-width: 1123px) 100vw, 1123px\" \/><\/p>\n<p><span style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\"><span lang=\"EN-GB\">Figure<\/span><span lang=\"EN-GB\">: (a) FCSNet is a convolutional neural network (CNN), which takes in the autocorrelation function <\/span> <span lang=\"EN-GB\">\u00a0<\/span><span lang=\"EN-GB\">of a measurement as an input to predict the diffusion coefficient. (b) FCSNet allows evaluations in complex samples with a precision as good, or better than traditional Imaging FCS methods, as shown by the heatmaps. [Credit: Biophysical Journal]<\/span><\/span><\/p>\n<p><span style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\"><b><span lang=\"EN-GB\">\u00a0<\/span><\/b><\/span><\/p>\n<p><span style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\"><b><span lang=\"EN-GB\">References:<\/span><\/b><\/span><\/p>\n<p><span style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\"><span lang=\"EN-GB\">[1]\u00a0 <\/span><span lang=\"EN-GB\">JW Krieger; AP\u00a0 Singh; N Bag;\u00a0 CS Garbe; TE Saunders; J Langowski; T Wohland*, &#8220;Imaging fluorescence (cross-) correlation spectroscopy in live cells and organisms&#8221; Nature Protocols Volume: 10 Issue: 12 Page: 1948-1974 DOI: 10.1038\/nprot.2015.100 Published: 2015.<\/span><\/span><\/p>\n<p><span style=\"font-family: arial, helvetica, sans-serif; font-size: 16px;\"><span lang=\"EN-GB\">[2]\u00a0 WH Tang; SR Sim; DYK Aik; AVS Nelanuthala; T Athilingam; A R\u00f6llin; T Wohland*, &#8220;Deep learning reduces data requirements and allows real-time measurements in Imaging FCS&#8221; Biophysical Journal DOI: 10.1016\/j.bpj.2023.11.3403 Published: 2024.<\/span><span lang=\"EN-US\"><\/span><\/span><\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>National University of Singapore (NUS) researchers have demonstrated that deep learning allows them to observe the dynamics of single molecules&#8230;<\/p>\n","protected":false},"author":16,"featured_media":59393,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[17,13],"tags":[],"class_list":["post-60216","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-data-science","category-research-news"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v23.6 (Yoast SEO v23.6) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Deep learning for real-time molecular imaging - NUS Faculty of Science<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Deep learning for real-time molecular imaging\" \/>\n<meta property=\"og:description\" content=\"National University of Singapore (NUS) researchers have demonstrated that deep learning allows them to observe the dynamics of single molecules...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/\" \/>\n<meta property=\"og:site_name\" content=\"NUS Faculty of Science\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/NUSFacultyofScience\/\" \/>\n<meta property=\"article:published_time\" content=\"2024-02-07T16:00:37+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-02-22T14:22:04+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"667\" \/>\n\t<meta property=\"og:image:height\" content=\"537\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"SOH Kok Hoe\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"SOH Kok Hoe\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/\"},\"author\":{\"name\":\"SOH Kok Hoe\",\"@id\":\"https:\/\/www.science.nus.edu.sg\/#\/schema\/person\/7d763fa59b757623726b1c72282de82b\"},\"headline\":\"Deep learning for real-time molecular imaging\",\"datePublished\":\"2024-02-07T16:00:37+00:00\",\"dateModified\":\"2024-02-22T14:22:04+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/\"},\"wordCount\":658,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/www.science.nus.edu.sg\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218.jpg\",\"articleSection\":[\"Data science\",\"Research News\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/\",\"url\":\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/\",\"name\":\"Deep learning for real-time molecular imaging - NUS Faculty of Science\",\"isPartOf\":{\"@id\":\"https:\/\/www.science.nus.edu.sg\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218.jpg\",\"datePublished\":\"2024-02-07T16:00:37+00:00\",\"dateModified\":\"2024-02-22T14:22:04+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#primaryimage\",\"url\":\"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218.jpg\",\"contentUrl\":\"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218.jpg\",\"width\":667,\"height\":537},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.science.nus.edu.sg\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Deep learning for real-time molecular imaging\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.science.nus.edu.sg\/#website\",\"url\":\"https:\/\/www.science.nus.edu.sg\/\",\"name\":\"NUS Faculty of Science\",\"description\":\"Leading in Science Education, Research and Innovation to Transform Our Future\",\"publisher\":{\"@id\":\"https:\/\/www.science.nus.edu.sg\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.science.nus.edu.sg\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.science.nus.edu.sg\/#organization\",\"name\":\"NUS Faculty of Science\",\"url\":\"https:\/\/www.science.nus.edu.sg\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.science.nus.edu.sg\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2022\/06\/fos-logo-768x190-1.png\",\"contentUrl\":\"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2022\/06\/fos-logo-768x190-1.png\",\"width\":768,\"height\":190,\"caption\":\"NUS Faculty of Science\"},\"image\":{\"@id\":\"https:\/\/www.science.nus.edu.sg\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/www.facebook.com\/NUSFacultyofScience\/\",\"https:\/\/www.instagram.com\/nus.fos\/?hl=en\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.science.nus.edu.sg\/#\/schema\/person\/7d763fa59b757623726b1c72282de82b\",\"name\":\"SOH Kok Hoe\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.science.nus.edu.sg\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/9b9160c6f1e2f411cd00f9372bf78344?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/9b9160c6f1e2f411cd00f9372bf78344?s=96&d=mm&r=g\",\"caption\":\"SOH Kok Hoe\"},\"url\":\"https:\/\/www.science.nus.edu.sg\/blog\/author\/scisohkh\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Deep learning for real-time molecular imaging - NUS Faculty of Science","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/","og_locale":"en_US","og_type":"article","og_title":"Deep learning for real-time molecular imaging","og_description":"National University of Singapore (NUS) researchers have demonstrated that deep learning allows them to observe the dynamics of single molecules...","og_url":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/","og_site_name":"NUS Faculty of Science","article_publisher":"https:\/\/www.facebook.com\/NUSFacultyofScience\/","article_published_time":"2024-02-07T16:00:37+00:00","article_modified_time":"2024-02-22T14:22:04+00:00","og_image":[{"width":667,"height":537,"url":"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218.jpg","type":"image\/jpeg"}],"author":"SOH Kok Hoe","twitter_card":"summary_large_image","twitter_misc":{"Written by":"SOH Kok Hoe","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#article","isPartOf":{"@id":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/"},"author":{"name":"SOH Kok Hoe","@id":"https:\/\/www.science.nus.edu.sg\/#\/schema\/person\/7d763fa59b757623726b1c72282de82b"},"headline":"Deep learning for real-time molecular imaging","datePublished":"2024-02-07T16:00:37+00:00","dateModified":"2024-02-22T14:22:04+00:00","mainEntityOfPage":{"@id":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/"},"wordCount":658,"commentCount":0,"publisher":{"@id":"https:\/\/www.science.nus.edu.sg\/#organization"},"image":{"@id":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#primaryimage"},"thumbnailUrl":"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218.jpg","articleSection":["Data science","Research News"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/","url":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/","name":"Deep learning for real-time molecular imaging - NUS Faculty of Science","isPartOf":{"@id":"https:\/\/www.science.nus.edu.sg\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#primaryimage"},"image":{"@id":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#primaryimage"},"thumbnailUrl":"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218.jpg","datePublished":"2024-02-07T16:00:37+00:00","dateModified":"2024-02-22T14:22:04+00:00","breadcrumb":{"@id":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#primaryimage","url":"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218.jpg","contentUrl":"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2024\/01\/359._TW_DBS_20231218.jpg","width":667,"height":537},{"@type":"BreadcrumbList","@id":"https:\/\/www.science.nus.edu.sg\/blog\/2024\/02\/deep-learning-for-real-time-molecular-imaging\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.science.nus.edu.sg\/"},{"@type":"ListItem","position":2,"name":"Deep learning for real-time molecular imaging"}]},{"@type":"WebSite","@id":"https:\/\/www.science.nus.edu.sg\/#website","url":"https:\/\/www.science.nus.edu.sg\/","name":"NUS Faculty of Science","description":"Leading in Science Education, Research and Innovation to Transform Our Future","publisher":{"@id":"https:\/\/www.science.nus.edu.sg\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.science.nus.edu.sg\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.science.nus.edu.sg\/#organization","name":"NUS Faculty of Science","url":"https:\/\/www.science.nus.edu.sg\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.science.nus.edu.sg\/#\/schema\/logo\/image\/","url":"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2022\/06\/fos-logo-768x190-1.png","contentUrl":"https:\/\/www.science.nus.edu.sg\/wp-content\/uploads\/2022\/06\/fos-logo-768x190-1.png","width":768,"height":190,"caption":"NUS Faculty of Science"},"image":{"@id":"https:\/\/www.science.nus.edu.sg\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/NUSFacultyofScience\/","https:\/\/www.instagram.com\/nus.fos\/?hl=en"]},{"@type":"Person","@id":"https:\/\/www.science.nus.edu.sg\/#\/schema\/person\/7d763fa59b757623726b1c72282de82b","name":"SOH Kok Hoe","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.science.nus.edu.sg\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/9b9160c6f1e2f411cd00f9372bf78344?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/9b9160c6f1e2f411cd00f9372bf78344?s=96&d=mm&r=g","caption":"SOH Kok Hoe"},"url":"https:\/\/www.science.nus.edu.sg\/blog\/author\/scisohkh\/"}]}},"_links":{"self":[{"href":"https:\/\/www.science.nus.edu.sg\/wp-json\/wp\/v2\/posts\/60216"}],"collection":[{"href":"https:\/\/www.science.nus.edu.sg\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.science.nus.edu.sg\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.science.nus.edu.sg\/wp-json\/wp\/v2\/users\/16"}],"replies":[{"embeddable":true,"href":"https:\/\/www.science.nus.edu.sg\/wp-json\/wp\/v2\/comments?post=60216"}],"version-history":[{"count":6,"href":"https:\/\/www.science.nus.edu.sg\/wp-json\/wp\/v2\/posts\/60216\/revisions"}],"predecessor-version":[{"id":61085,"href":"https:\/\/www.science.nus.edu.sg\/wp-json\/wp\/v2\/posts\/60216\/revisions\/61085"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.science.nus.edu.sg\/wp-json\/wp\/v2\/media\/59393"}],"wp:attachment":[{"href":"https:\/\/www.science.nus.edu.sg\/wp-json\/wp\/v2\/media?parent=60216"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.science.nus.edu.sg\/wp-json\/wp\/v2\/categories?post=60216"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.science.nus.edu.sg\/wp-json\/wp\/v2\/tags?post=60216"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}