{"id":98,"date":"2026-11-04T11:31:57","date_gmt":"2026-11-04T11:31:57","guid":{"rendered":"https:\/\/blog.swalifebiotech.com\/?p=98"},"modified":"2026-11-04T11:33:29","modified_gmt":"2026-11-04T11:33:29","slug":"evidence-provenance-in-rd-intelligence-dashboards-why-traceability-matters-more-than-ai-generated-insights","status":"publish","type":"post","link":"https:\/\/blog.swalifebiotech.com\/?p=98","title":{"rendered":"Evidence Provenance in R&amp;D Intelligence Dashboards: Why Traceability Matters More Than AI-Generated Insights"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\"><em>By Dr. Pravin D. Badhe | Founder &amp; CEO, Swalife Biotech<\/em><\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Introduction: A Dashboard Is Not Evidence<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Artificial intelligence is changing how pharmaceutical and biotechnology researchers discover information, interpret scientific literature, identify biological targets and prioritise development opportunities.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Modern research intelligence dashboards can bring together thousands of publications, molecular interactions, biological pathways, clinical studies and regulatory documents.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Within minutes, researchers can receive a structured overview of a disease, potential therapeutic targets, candidate molecules and research opportunities.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">But an important question remains:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Can we trace every scientific conclusion displayed on the dashboard back to its original evidence?<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">An AI-generated statement may appear convincing. However, without identifying its source, experimental context, analytical method and limitations, it may not be reliable enough to guide an R&amp;D decision.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">This is why evidence provenance should be a foundational requirement of AI-enabled research intelligence.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">1. What Is Evidence Provenance?<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Evidence provenance describes the origin, history, processing and interpretation of scientific information.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">It helps researchers understand not only <em>what<\/em> information is presented, but also <em>where it came from and how it was produced<\/em>.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">For example, imagine an R&amp;D dashboard displaying the statement:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><em>&#8220;A plant-derived molecule may influence a biological pathway associated with cancer progression.&#8221;<\/em><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Before using this information to guide research, scientists should be able to answer:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Which scientific publication supports the association?<\/li>\n\n\n\n<li>Was the evidence generated in a computational, cell-based, animal or human study?<\/li>\n\n\n\n<li>Which compound, concentration, biological model and outcome were investigated?<\/li>\n\n\n\n<li>Was the mechanism directly demonstrated or inferred?<\/li>\n\n\n\n<li>Have independent studies reproduced the findings?<\/li>\n\n\n\n<li>Was the conclusion generated by an AI system or verified by a scientific reviewer?<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">These questions distinguish scientific evidence from an unsupported interpretation.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The World Wide Web Consortium&#8217;s PROV framework provides a structured approach to recording the entities, activities and agents involved in producing information.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">For pharmaceutical R&amp;D, provenance should extend beyond citations to include the experimental and computational processes underlying scientific conclusions.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">2. Why Conventional AI Dashboards Can Be Misleading<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">AI-powered research tools can help summarise complex scientific information, but their outputs require critical evaluation.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">A. A Citation Does Not Automatically Support a Claim<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">A research dashboard may display a scientific reference beside a conclusion.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">However, the reference might report a different biological system, experimental condition or outcome.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Researchers must verify that the cited evidence genuinely supports the displayed statement.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">B. Computational Predictions Are Not Experimental Findings<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Machine learning, molecular docking, network pharmacology and other computational techniques can help generate research hypotheses.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">However, predicted molecular interactions should not be presented as experimentally validated biological activity.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Similarly, a predicted binding affinity should not be confused with a measured binding value.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">C. Evidence From Different Research Stages Is Not Interchangeable<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">An effect observed in cultured cells cannot automatically be interpreted as a therapeutic benefit in humans.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Animal findings, clinical observations, systematic reviews and regulatory conclusions each answer different scientific questions.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Combining them without identifying their differences may create a misleading impression of certainty.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">D. Scientific Evidence Changes<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Research findings evolve as new studies become available.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">A dashboard prepared using older literature may overlook more recent contradictory findings, methodological limitations or changes in regulatory understanding.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Consequently, evidence provenance also requires version history and an identifiable date of assessment.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">3. Evidence Provenance and the FAIR Data Principles<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The FAIR Guiding Principles, introduced in 2016, provide an important foundation for scientific data management.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">FAIR represents four characteristics:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Findable:<\/strong> Research information and supporting data should be discoverable through suitable identifiers and metadata.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Accessible:<\/strong> Researchers should understand how to retrieve the relevant information, including when access restrictions apply.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Interoperable:<\/strong> Data should use consistent representations and terminology so that information from different systems can be integrated.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Reusable:<\/strong> Scientific information should contain sufficient context, provenance and documentation to support appropriate reuse.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">For an R&amp;D intelligence dashboard, these principles can inform the design of evidence repositories, research workflows and scientific reporting systems.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">FAIR compliance alone does not establish scientific validity. Nevertheless, FAIR-aligned documentation can make evidence easier to examine, compare and reuse.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">4. What Should an Evidence-Traceable R&amp;D Dashboard Contain?<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">I believe a scientifically responsible R&amp;D intelligence dashboard should provide at least six essential layers of information.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Layer 1: Source Identification<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Every significant scientific claim should be connected to an identifiable source.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Relevant metadata may include publication title, authors, publication year, DOI, database identifier or regulatory document reference.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Layer 2: Experimental Context<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Researchers should know whether the underlying evidence originates from computational modelling, laboratory experiments, animal studies, clinical investigations or other sources.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Where relevant, the dashboard should record the experimental model, method, concentration, dose and measured endpoints.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Layer 3: Evidence Classification<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Research findings should be categorised according to the type of evidence supporting them.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">A computational hypothesis should remain clearly distinguishable from an experimentally demonstrated finding.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Layer 4: Interpretation and Limitations<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Dashboards should identify uncertainty, contradictory observations, methodological weaknesses and gaps requiring further research.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Layer 5: AI Processing History<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">When AI systems are used to extract or interpret scientific information, the workflow should document the model or software version, processing date, relevant analytical settings and any transformations applied.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Layer 6: Human Scientific Review<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Expert reviewers should evaluate whether the information is accurately extracted, appropriately interpreted and suitable for its intended research use.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>A dashboard becomes more useful for decision-making when its conclusions can be independently examined\u2014not simply when it contains more information.<\/strong><\/p>\n\n\n\n<h2 class=\"wp-block-heading\">5. Evidence Provenance in Natural-Product Drug Discovery<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Natural-product research presents a particularly important application of evidence provenance.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Medicinal plants contain chemically diverse constituents, and the properties of an extract may depend on its botanical source, extraction process, composition and experimental conditions.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Consider a hypothetical research project investigating green tea-derived compounds for potential chemopreventive applications.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">A research intelligence dashboard might include information about:<\/p>\n\n\n\n<ol start=\"1\" class=\"wp-block-list\">\n<li>The botanical source and extraction procedure.<\/li>\n\n\n\n<li>Identified constituents and their chemical structures.<\/li>\n\n\n\n<li>Published biological activity associated with individual compounds.<\/li>\n\n\n\n<li>Potential targets and pathways suggested by computational analysis.<\/li>\n\n\n\n<li>Available preclinical and clinical evidence.<\/li>\n\n\n\n<li>Formulation-related information and limitations.<\/li>\n\n\n\n<li>Safety, regulatory and translational considerations.<\/li>\n<\/ol>\n\n\n\n<p class=\"wp-block-paragraph\">Importantly, these findings must remain connected to their original research context.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">For example, biological activity reported for a purified compound should not automatically be attributed to a crude extract or a finished formulation.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Likewise, evidence of activity in an experimental cancer model should not be interpreted as established clinical cancer prevention.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">An evidence-traceable system helps preserve these distinctions.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">6. Connecting Evidence Provenance With AI-Assisted Drug Discovery<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The potential value of AI in drug discovery extends beyond accelerating literature searches.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">AI may assist researchers with identifying relevant publications, recognising relationships between molecular structures and biological targets, comparing evidence, generating hypotheses and preparing structured research reports.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">However, these capabilities should operate within clearly defined scientific boundaries.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">In January 2025, the U.S. Food and Drug Administration issued draft guidance proposing a risk-based credibility assessment framework for AI models used to generate information supporting regulatory decisions about drug and biological product safety, effectiveness or quality.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The framework emphasises evaluating AI credibility within a specific <em>context of use<\/em>.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Although that draft guidance is not a universal standard for every research dashboard, the underlying principle is relevant: an AI output must be assessed in relation to the decision it is intended to support.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">An exploratory research hypothesis and a regulatory submission require different levels of assurance.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">7. From Research Intelligence to Product Development Decisions<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">A well-designed research intelligence dashboard should support practical questions throughout the product-development process.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">For example:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Research planning:<\/strong> Which scientific questions remain unanswered?<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Target identification:<\/strong> What evidence supports the association between a molecule and a biological target?<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Candidate prioritisation:<\/strong> What experimental evidence and development constraints should influence candidate selection?<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Formulation development:<\/strong> Are there solubility, stability, bioavailability or safety concerns that require investigation?<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Translational research:<\/strong> What additional studies would be necessary before advancing a candidate?<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Regulatory planning:<\/strong> What evidence may be required to support the intended product category and proposed claims?<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">These decisions should not rely solely on a dashboard&#8217;s graphical presentation.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">They require transparent supporting information, expert interpretation and, where necessary, experimental validation.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">8. Our Approach at Swalife Biotech: Product Development &amp; Medical Intelligence<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">At Swalife Biotech, our research direction involves integrating scientific evidence, AI-assisted analysis and structured product-development intelligence.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Through our <strong>Product Development &amp; Medical Intelligence (PDMI)<\/strong> initiative, we are working towards research workflows that connect information across multiple stages of pharmaceutical and botanical product development.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Our approach emphasises:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Traceable scientific evidence and source verification.<\/li>\n\n\n\n<li>Structured target and pathway research.<\/li>\n\n\n\n<li>Molecular and formulation intelligence.<\/li>\n\n\n\n<li>Clear distinctions between predictions and validated findings.<\/li>\n\n\n\n<li>Scientific review before information is used to support development decisions.<\/li>\n\n\n\n<li>Translation of research findings into practical development questions.<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">For natural-product research, this approach is particularly relevant to botanical formulations, nutraceutical development, precision chemoprevention research and the investigation of plant-derived small molecules.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">We see evidence provenance as an important design requirement for these workflows, rather than claiming that every component has already undergone independent validation.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Our objective is to support researchers and development teams in moving from fragmented scientific information towards more transparent, evidence-informed decisions.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">9. A Practical Checklist for R&amp;D Teams<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Before relying on an AI-generated research intelligence report, consider the following:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Can the original evidence supporting each important conclusion be retrieved?<\/li>\n\n\n\n<li>Are computational predictions clearly identified?<\/li>\n\n\n\n<li>Are preclinical and clinical findings distinguished?<\/li>\n\n\n\n<li>Are conflicting studies and limitations documented?<\/li>\n\n\n\n<li>Are source dates, versions and processing methods recorded?<\/li>\n\n\n\n<li>Has a qualified scientific reviewer assessed the interpretation?<\/li>\n\n\n\n<li>Is the information appropriate for the intended R&amp;D decision?<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">If a dashboard cannot answer these questions, its output should be treated as preliminary research intelligence rather than a validated scientific conclusion.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Conclusion: The Future of Research Intelligence Must Be Traceable<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">The future of pharmaceutical R&amp;D will not be determined simply by how quickly AI systems generate reports or how attractively information is presented.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The more important question is whether researchers can evaluate, verify and appropriately use the information they receive.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>AI can help us process scientific information faster. Evidence provenance helps us understand whether that information deserves our confidence.<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\">As AI-enabled research platforms evolve, traceability, scientific accountability, human review and appropriate validation should become central to their design.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">For research-driven biotechnology companies, these principles are essential to building more credible and useful product-development intelligence.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h3 class=\"wp-block-heading\">Explore Swalife Research Intelligence<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Swalife Biotech is developing AI-supported research and product-development intelligence approaches for botanical, nutraceutical and pharmaceutical R&amp;D.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Explore our research platforms and scientific capabilities:<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Predictive Intelligence:<\/strong> <a href=\"https:\/\/predictiveintelligence.swalifebiotech.com\/\">https:\/\/predictiveintelligence.swalifebiotech.com\/<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Research Intelligence:<\/strong> <a href=\"https:\/\/swalifeintelligence.swalifebiotech.com\/\">https:\/\/swalifeintelligence.swalifebiotech.com\/<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Swalife Healthcare Consultancy:<\/strong> <a href=\"https:\/\/www.swalifehealthcare.com\/\">https:\/\/www.swalifehealthcare.com\/<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Swalife Biotech:<\/strong> <a href=\"https:\/\/www.swalifebiotech.com\/\">https:\/\/www.swalifebiotech.com\/<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><em>This article is intended for scientific education and research discussion. Computational predictions and preliminary research findings should not be interpreted as established clinical efficacy, safety or regulatory approval.<\/em><\/p>\n\n\n\n<h3 class=\"wp-block-heading\">References<\/h3>\n\n\n\n<ol start=\"1\" class=\"wp-block-list\">\n<li>Wilkinson MD, et al. (2016). The FAIR Guiding Principles for Scientific Data Management and Stewardship. <em>Scientific Data<\/em>, 3, 160018. <a href=\"https:\/\/doi.org\/10.1038\/sdata.2016.18\">https:\/\/doi.org\/10.1038\/sdata.2016.18<\/a><\/li>\n\n\n\n<li>World Wide Web Consortium (2013). PROV-Overview: An Overview of the PROV Family of Documents. <a href=\"https:\/\/www.w3.org\/TR\/prov-overview\/\">https:\/\/www.w3.org\/TR\/prov-overview\/<\/a><\/li>\n\n\n\n<li>U.S. Food and Drug Administration (2025). Considerations for the Use of Artificial Intelligence to Support Regulatory Decision-Making for Drug and Biological Products. Draft Guidance. <a href=\"https:\/\/www.fda.gov\/regulatory-information\/search-fda-guidance-documents\/considerations-use-artificial-intelligence-support-regulatory-decision-making-drug-and-biological\">https:\/\/www.fda.gov\/regulatory-information\/search-fda-guidance-documents\/considerations-use-artificial-intelligence-support-regulatory-decision-making-drug-and-biological<\/a><\/li>\n\n\n\n<li>U.S. Food and Drug Administration. Quality Essentials: Inspectional Coverage of QMS and Data Integrity. <a href=\"https:\/\/www.fda.gov\/media\/179075\/download\">https:\/\/www.fda.gov\/media\/179075\/download<\/a><\/li>\n<\/ol>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>By Dr. Pravin D. Badhe | Founder &amp; CEO, Swalife Biotech Introduction: A Dashboard Is Not Evidence Artificial intelligence is [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":99,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[2,9,6],"tags":[13,14,12],"class_list":["post-98","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-in-drug-discovery","category-ai-in-drug-discovery-clinical-insights-pdmi-platform-skincare-science","category-pdmi-platform","tag-ai","tag-drugdiscovery","tag-swalifebiotech"],"_links":{"self":[{"href":"https:\/\/blog.swalifebiotech.com\/index.php?rest_route=\/wp\/v2\/posts\/98","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.swalifebiotech.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.swalifebiotech.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.swalifebiotech.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.swalifebiotech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=98"}],"version-history":[{"count":2,"href":"https:\/\/blog.swalifebiotech.com\/index.php?rest_route=\/wp\/v2\/posts\/98\/revisions"}],"predecessor-version":[{"id":101,"href":"https:\/\/blog.swalifebiotech.com\/index.php?rest_route=\/wp\/v2\/posts\/98\/revisions\/101"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blog.swalifebiotech.com\/index.php?rest_route=\/wp\/v2\/media\/99"}],"wp:attachment":[{"href":"https:\/\/blog.swalifebiotech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=98"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.swalifebiotech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=98"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.swalifebiotech.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=98"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}