SEND: a controversy in nonclinical research

Another thought-provoking article on Virtual Control Groups. Marc Ellison continues to provide excellent thought leadership on the urgent issues facing the SEND community. Thanks Marc! #VirtualControlGroups #SEND #SENDIG #InSilico #NonClinical #PreClinical

🧪 Transforming Toxicology with QSAR Modeling! Discover how Quantitative Structure-Activity Relationship (QSAR) models are reshaping chemical risk assessment by integrating with Adverse Outcome Pathways (AOPs). This comprehensive approach predicts chemical bioactivity towards specific targets linked to toxicity, minimizing the need for traditional animal testing. 🚫🐭 Learn how cutting-edge machine learning techniques are boosting predictive accuracy for liver, kidney, and neurological toxicities, and paving the way for safer chemical development. From data curation to real-world applications, explore the future of computational toxicology! Read the full blog to dive into methodologies, results, and practical applications -> https://lnkd.in/gSCqB9EF At Medvolt, we harness the power of generative AI, alongside other large language models (LLMs) and deep learning technologies, through our innovative platform 𝐌𝐞𝐝𝐆𝐫𝐚𝐩𝐡. 𝐅𝐞𝐞𝐥 𝐟𝐫𝐞𝐞 𝐭𝐨 𝐜𝐨𝐧𝐭𝐚𝐜𝐭 𝐮𝐬 𝐢𝐟 𝐲𝐨𝐮 𝐡𝐚𝐯𝐞 𝐚𝐧𝐲 𝐢𝐧𝐪𝐮𝐢𝐫𝐢𝐞𝐬 𝐨𝐫 𝐫𝐞𝐪𝐮𝐢𝐫𝐞 𝐚 𝐝𝐞𝐦𝐨𝐧𝐬𝐭𝐫𝐚𝐭𝐢𝐨𝐧. Visit our website: https://www.medvolt.ai or reach out to us via email: [email protected] #QSAR #Toxicology #AOP #MachineLearning #ChemicalSafety #RiskAssessment #ComputationalToxicology #InnovationInScience

Explore the future of toxicology in the "Tox Hack: Unleashing the Power of AI and Machine Learning" symposium, led by Claire Neilan and Peyton M.. Learn how AI and machine learning are reshaping toxicology assessments, accelerating drug discovery, and improving safety through innovative data-driven approaches. Don't miss the opportunity to dive into real-world applications of AI in toxicology! Link for registration to the Annual meeting: https://lnkd.in/ek5UQRza

Consider joining RTI International on September 11th, 2024 for a webinar on the use of AI and other new approach methodologies to overcome some of the toughest problems in toxicology, drug development, and biomedical research. To learn more about this webinar, “How to Characterize and Validate AI and In Vitro NAMs for Toxicity Testing”, please visit: https://lnkd.in/g9JKa2NG To register, please visit: https://lnkd.in/ghZe-uTW #Webinar #Toxicology #AI #STEM #Research #Biomedicine #Pharmacology

🚀 The Rapid Growth of AI in Predictive Toxicology 🧬 The AI in Predictive Toxicology market is experiencing remarkable growth, expanding from $0.38 billion in 2023 to an anticipated $1.41 billion by 2028, driven by a strong CAGR of 30.3%. This surge is attributed to increasing regulatory pressures, rising concerns over chemical safety, and the growing demand for more ethical and cost-effective toxicity screening methods. The future looks promising with emerging trends such as explainable AI, personalized toxicity assessments, and the regulatory acceptance of AI-based predictions. Innovations like 3D cell culture models, federated learning, and generative models are set to revolutionize the field. Moreover, strategic collaborations and acquisitions are playing a crucial role in advancing AI-driven drug discovery. Partnerships like SyntheticGestalt and Enamine, along with Clarivate's acquisition of Bioinfogate, highlight the industry's commitment to innovation. As this dynamic market evolves, it's exciting to see how AI will continue to enhance the efficiency and ethics of drug discovery. Stay tuned for more developments! https://lnkd.in/gq2H3Jb3 #ArtificialIntelligence #PredictiveToxicology #DrugDiscovery #Innovation

👉🏼 Comparing answers of artificial intelligence systems and clinical toxicologists to questions about poisoning: Can their answers be distinguished? 🤓 Santiago Nogué-Xarau 👇🏻 https://lnkd.in/e-hKWFNF 🔍 Focus on data insights: - 📊 240 AI answers were evaluated by experts, revealing that a small percentage were attributed to toxicologists. - 🤖 ChatGPT demonstrated the highest perceived quality and level of knowledge among the AI systems tested. - 💬 Text quality ratings indicated that AI-generated responses, particularly from ChatGPT, often resembled professional writing in toxicology. 💡 Main outcomes and implications: - 🧪 AI systems, especially ChatGPT, can produce convincing text on complex topics like toxicology, complicating the differentiation between AI and human experts. - 🔍 The findings suggest a need for careful assessment of AI responses in clinical contexts, as they may be mistaken for expert opinion. 📚 Field significance: - 📈 The study highlights the potential of AI in providing credible information but also raises concerns about reliance on AI in critical fields such as healthcare. - 🔗 Future research could explore the implications of AI in toxicology further and the importance of integrating AI output with human expertise for optimal patient care. 🗄️: [#AI #Toxicology #ClinicalPractice #TextQuality #ExpertEvaluation #Healthcare]

I am excited to share that our paper "Advancing predictive toxicology: overcoming hurdles and shaping the future" has been published in Digital Discovery #RSCDigital . This article was a project I contributed to during my time at Ignota Labs, a company that continues to be a pioneer in this space. All too often we hear about the power of #AI in drug discovery, but predictive models don't come without their challenges, something we discuss in detail in this perspective article. If you are interested in AI drug discovery, then following Ignota Labs as they continue to build transformative technology to save distressed pharmaceuticals is an absolute must!!! My thanks to all my fellow authors for their fantastic work getting this article out there. Link: https://lnkd.in/d4MMZ5q8

Thrilled to see this article being featured and to have worked alongside the amazing team at Ignota Labs on it. This work discusses the difficulty in addressing safety issues within drug discovery, whilst highlighting how in silico tools can be used to turn safety issues around. I encourage anyone curious about how AI, cheminformatics and bioinformatics can be used to tackle toxicity within drug discovery to read the article using the link below. #DigitalDiscovery #drugsafety #cheminformatics #AI

Great Article from Ignota Labs ! Read about SOTA in tox and mechanistic modelling and hypothesis generation — the next stage of ML for real world toxicity prediction!

Imagine exploring the potential of leveraging visual data to enhance and expedite toxicology studies. Specifically, I wonder if scientists routinely save and archive the following types of data, amongst others, during their toxicology research: 1. Microscopy images 2. High-content screening (HCS) data 3. Histopathology slides 4. Other visual data Can AWS Rekognition or other image recognition models be trained on these visual datasets to predict toxicological outcomes and potentially reduce the time required for toxicology assessments? Could using these visual data to train AI models provide a reliable probability for supporting or refuting toxicology hypotheses, thereby speeding up the toxicology testing process? Specific to DeepTox, the null hypothesis would be as follows: "Null Hypothesis (H₀): DeepTox does not significantly reduce the time required to conduct toxicology studies compared to traditional methods." If the null hypothesis is rejected, the alternative hypothesis would be accepted, which can be stated as: "Alternative Hypothesis (H₁): DeepTox significantly reduces the time required to conduct toxicology studies compared to traditional methods." #Toxicology #AI #MachineLearning #DataScience #Biotech #Pharma #Microscopy #HighContentScreening #Histopathology #DeepLearning #Innovation #Research #AWSRekognition #DrugDevelopment