Applications of Generative AI in Biotech

Exciting progress in AI x Biology you should know about: EvolutionaryScale's ESM3, a new language model, simulates 500 million years of protein evolution. As someone working in AI x Biology, I dove into this right away. (1) This model, trained on an extensive dataset, can generate diverse protein sequences, structures, and functions. ESM3 has already demonstrated its capability by creating esmGFP, a green fluorescent protein analogous to evolving over half a billion years. This achievement underscores ESM3’s potential to revolutionize programmable biology and protein design. (2) ESM3 integrates multimodal reasoning, allowing precise control over protein creation. This opens doors to significant advancements in medicine, biological research, and sustainable energy solutions. The model’s ability to reason across different modalities sets a new benchmark for AI in scientific research. (3) Moreover, EvolutionaryScale’s commitment to open science ensures that ESM3’s models and data are accessible, fostering collaboration and responsible AI development. This transparency is vital for accelerating scientific discoveries and practical applications. (A) I find the quality of ESM3’s work impressive, showcasing a sophisticated understanding of protein biochemistry. Its capacity to generate high-quality, functional proteins far removed from existing variants illustrates its transformative potential. Future research could explore ESM3’s application in developing specific therapeutic proteins or industrial biocatalysts, paving the way for innovative solutions across various fields. (B) However, again with powerful generative AI models, a key area for improvement is optimizing the model’s efficiency to balance complexity and performance, making it more accessible for broader scientific and industrial use. I believe ESM3 stands as a testament to the power of AI in advancing biological research and technology. Its implications are far-reaching, promising a future of accelerated scientific breakthroughs and innovative applications. Paper: https://lnkd.in/gvv8FKPA Blog Post: https://lnkd.in/gQRQKExG #GenAI #Biology #ArtificialIntelligence

My latest: VantAI just announced a deal with Bristol Myers Squibb potentially worth up to $674 million. The goal? To use generative AI to design drugs that use the body's own cellular waste disposal process to fight disease. The key is using a combination of LLMs and the same graph theory algorithms that TikTok uses to send you Travis and Taylor content to design what are called "molecular glues." These glues bind to pathogens in the body, like cancer cells, connecting them to the protein degraders your cell uses to break down stuff it doesn't need anymore. Why AI? Because your body doesn't naturally use this process to fight disease, VantAI CEO Zach Carpenter explained to me. "You can't just discover glues through trial and error." You have to design the molecules that do it, a Herculean task without the last decade's advances in machine learning. Read more.

Accenture's annual Life Sciences CEO Imperatives Research, based on interviews with CEOs of top 40 life sciences companies, reveals key challenges and opportunities in the industry adopting Generative AI 1. Drug Development Challenges: • Average time to market: 10-12 years • Costs exceeding $2.6 billion per drug • 90% failure rate for drug candidates • Stagnant R&D productivity over the past decade 2. Industry Trends: •Increasing complexity in manufacturing and commercialization due to new modalities and personalized treatments •Low growth period for top 20 biopharma companies (4% average revenue CAGR over next 5 years) •High cost of capital driving CFOs to seek profitability enhancements 3. Impact of Intelligent Technologies: • Optimizing clinical trial protocols and resource allocation • Improving forecasting through data analysis • AI-discovered drug candidates progressing through clinical pipelines 4. Executive Focus: • Many C-suite executives focused on individual use cases rather than end-to-end processes • 66% see potential in generative AI but lack implementation plans 5. Key Value-Based Initiatives: • Accelerating time to clinic and market • Maximizing medicine value proposition • Improving medicine accessibility • Creating end-to-end feedback loops for insights sharing 6. Generative AI Impact: • 40% of working hours in Life Sciences to be impacted • 95% of workers want to learn new AI skills, but only 15% of organizations reskilling at scale • Potential to consolidate 100 roles to 70 positions in product development, manufacturing, quality, and supply chain 7. Data Management Challenges: • Typical biopharma companies manage over 100 different applications • Need for effective data infrastructure integrating internal, external, and synthetic data 8. Recommendations: • Implement generative AI-based workflows for cross-functional integration • Focus on end-to-end processes and capabilities • Develop implementation plans for AI adoption • Invest in reskilling workforce for AI competencies • Integrate data infrastructure across the value chain The research emphasizes the potential for AI to transform the biopharma industry while maintaining ethical, environmental, and scientific integrity standards. It highlights the need for companies to adapt to technological advancements, improve data management, and focus on end-to-end processes to stay competitive in a challenging market environment. #biopharma #generativeai #commercialexcellence #manufacturing #supplychain #regulatory #clinicaloperations #datalifecycle #drugdiscovery #translationalscience #marketaccess #patientengagement Source: www.accenture.com Disclaimer: The opinions are mine and not of prospective employer's.

Designing new proteins from scratch. Cut-and-pasting genes and using AI to build the full genome of an organism. Growing semiconductors. Does that sound like the concept of a new sci-fi novel? That was a week in biotech. Let's explore: EvolutionaryScale, founded by ex-Meta researchers, emerged from stealth with $142M in seed funding and a massive large language model for life sciences. The LLM, called ESM3, is a generative AI model that allows interactive prompting to create proteins. It’s like playing with the LEGO Group blocks for protein for extreme industrial conditions or new biological functions. It could transform our ability to program biology like computers. The generative protein space is hot for a reason: it helps us understand how proteins work, lets us make better and faster drugs, and could enable a new generation of industry. It’s also essential to developing new tools for bioremediation and sustainable manufacturing. OK, so that was proteins, the molecular machines and building blocks of life. Now, let’s talk about a word processor for DNA and ChatGPT for genomes, the instruction books that tell every cell what to build and how to work. Patrick Hsu and his team at the Arc Institute introduced Bridge RNAs, molecules that allow you to unzip DNA, add new material, and zip it back up. This precision editing tool improves our ability to edit organisms like cut and paste. In February, Hsu and his team also introduced an AI Genome Foundational Model that could unlock generative organism design, enabling the design of entire genomes from scratch. This could lead to more precise medicines, new organisms designed for a specific purpose, and the ability to design genetic circuits as easily as computer chips (which isn’t straightforward, by the way). Soon, we might be able to design new cells entirely from scratch Also, a team from David Baker’s lab at the University of Washington previewed a paper demonstrating the potential of using protein design for semiconductor growth and generating protein-semiconductor hybrid materials. Do we live in an awesome world or what? Alexandre Zanghellini Arzeda Andrew Hessel Biomatter Vega Shah, PhD

🔬 Revolutionizing Pharma with AI & Gen AI: Roche and Genentech Lead the Way 🚀 The pharmaceutical and biotech industries are undergoing a massive transformation, and Roche and Genentech are at the forefront of this revolution. By strategically integrating Artificial Intelligence (AI) and Generative AI (Gen AI) across their operations, these industry leaders are redefining innovation in drug discovery, manufacturing, diagnostics, and personalized medicine. 💡 What’s happening? Faster Drug Discovery: The "lab in a loop" approach uses AI to predict, test, and refine potential drug candidates, cutting down timelines significantly. AI is even helping design personalized cancer vaccines and combating drug-resistant bacteria! Smarter Manufacturing: AI-driven predictive models are improving manufacturing yields by up to 10% and reducing quality control issues by 50%. Advanced Diagnostics: AI-powered imaging and digital pathology are enhancing cancer detection and diagnostics, with up to 97% accuracy in certain use cases. Personalized Medicine: AI is uncovering key biomarkers, enabling more targeted treatments, and transforming how we approach patient care. 🤝 Key Partnerships Roche and Genentech are teaming up with leading tech innovators like NVIDIA, Recursion Pharmaceuticals, and Genesis Therapeutics to harness cutting-edge AI tools for drug discovery and beyond. 🌍 Global Trends in AI Generative AI is accelerating drug design, reducing costs by up to 50%. AI is optimizing clinical trials, improving patient recruitment, and cutting trial timelines by 70%. AI-driven supply chain tools are enhancing resilience and reducing waste. 📈 Future Impact Roche and Genentech’s AI initiatives promise: ✅ Faster drug discovery and development. ✅ Enhanced precision medicine for better patient outcomes. ✅ Greater operational efficiency across R&D and manufacturing. ⚠️ Challenges Ahead Of course, integrating AI isn’t without risks: data privacy concerns, algorithm bias, and regulatory hurdles require careful navigation. But Roche and Genentech are leading with responsible AI practices, ensuring transparency, fairness, and compliance with evolving global regulations. 🌟 The Takeaway AI and Gen AI aren’t just tools—they’re transformational forces reshaping healthcare. Roche and Genentech are proving that by embracing innovation, the future of medicine can be faster, smarter, and more personalized than ever before. 💬 What are your thoughts on the role of AI in healthcare innovation? Let’s discuss in the comments! #PharmaInnovation #ArtificialIntelligence #GenerativeAI #HealthcareTransformation #Roche #Genentech #AIinHealthcare #DrugDiscovery #DigitalTransformation

Revolutionizing Life Sciences R&D: The Power of Intelligent Automation and GenAI "Life sciences companies are using artificial intelligence (AI) to transform drug discovery by extracting concepts and relationships from data. By 2030, the time required for screening to preclinical testing will be reduced only a few months, and new potential drug candidates would be identified at more affordable prices." - Deloitte: 2023 Global Life Sciences Outlook 🧬 UiPath has released a white paper on the transformative impact of combining intelligent automation with Generative AI (Gen AI) in Life Sciences R&D. Patterns such as personalized message generation, context-driven analysis, and conversational assistant enhancements are paving the way for unprecedented efficiency and responsiveness. The synergy of automation and Gen AI is showcased through various use cases, including Pharmacovigilance processes, patient/donor screening, regulatory submissions, narrative generation, and SOP documentation queries. Key Points: 🔷 Pattern 1: Personalized Message Generation Context gathering for crafting personalized messages. Application in regulatory forms and complex responses. 🔷 Pattern 2: Context-Driven Analysis Automation analyzes data for the next best action. Embedding business context into responses or workflows. 🔷 Pattern 3: Conversational Assistant Enhancement Automation adds context and action to verbal or text queries. Initial stages with tremendous growth potential in verbal query interfaces. 🔷 Use Cases and Impact: 🔹Pharmacovigilance Process (PV): Gen AI-enhanced automation streamlines data analysis and submission processes, making them more intuitive and responsive. 🔹Patient/Donor Screening: Coordinating appointments, guiding through questionnaires, and generating follow-up documents for personalized therapies. 🔹Regulatory Submissions (NDA/BLA): Gen AI expedites the completion of new product submissions, potentially saving 10-20 weeks and generating substantial revenue benefits. 🔹Narrative Ability: Gen AI's ability to generate narratives accelerates data analysis, impacting clinical data summaries and more complex scenarios. 🔹Query SOP Documentation: Gen AI reviews extensive SOP libraries, providing real-time responses to user queries, and enhancing process execution. In 2023, we witnessed a remarkable evolution of the emergence of GenAI. In 2024 we will see the beginning of AI-enabled automation, propelling us into a new era of efficiency and discovery. #IntelligentAutomation #GenAI #LifeSciences #ResearchAndDevelopment #Innovation #uipath 𝗡𝗼𝘁𝗶𝗰𝗲: The views expressed in this post are my own. The perspectives within any of my posts or articles are not those of my employer or the employers of any contributing experts. 𝗟𝗶𝗸𝗲 👍 this post? Click 𝘁𝗵𝗲 𝗯𝗲𝗹𝗹 icon 🔔 for more!

🚀 Quantum AI for Drug Discovery: A Step Closer to Targeting the “Undruggable” In 2015, generative AI in chemistry was in its infancy. Many dismissed it. We went all in. Today, the same is happening with quantum computing. Our latest work—published in Nature Biotechnology in collaboration with the University of Toronto—demonstrates how a hybrid quantum-classical AI model can design small molecules to target KRAS, one of the most notorious oncogenes in cancer. This mutation drives 90% of pancreatic cancers, 40% of colorectal cancers, and 32% of lung cancers. With a training dataset of 1.1 million molecules, we used quantum-enhanced generative AI to produce novel KRAS inhibitors. The results? A 21.5% higher success rate in generating drug-like candidates compared to classical AI models. We’re not claiming speed or cost advantages over GPUs—yet. But we are proving what’s possible. By 2026-2027, quantum as a service (QaaS) from Microsoft, Amazon, and China will be widely available. The future of AI-powered drug discovery is quantum-classical, and we’re ready. Beautiful article by Cami Rosso of Psychology Today Link: https://lnkd.in/d6rKnUrZ 👉 Read the full study: https://lnkd.in/d2x--q4e 👉 Join the conversation—where do you see quantum AI making the biggest impact in biotech? #QuantumComputing #AI #DrugDiscovery #Biotech #InsilicoMedicine

Recent advances in generative biology for biotherapeutic discovery. https://lnkd.in/eEeepysD "Generative biology combines artificial intelligence (AI), advanced life sciences technologies, and automation to revolutionize the process of designing novel biomolecules with prescribed properties, giving drug discoverers the ability to escape the limitations of biology during the design of next-generation protein therapeutics. Significant hurdles remain, namely: (i) the inherently complex nature of drug discovery, (ii) the bewildering number of promising computational and experimental techniques that have emerged in the past several years, and (iii) the limited availability of relevant protein sequence-function data for drug-like molecules. There is a need to focus on computational methods that will be most practically effective for protein drug discovery and on building experimental platforms to generate the data most appropriate for these methods. Here, we discuss recent advances in computational and experimental life sciences that are most crucial for impacting the pace and success of protein drug discovery." Interesting new review by Marissa Mock, Christopher Langmead, Peter Grandsard, Suzanne Edavettal and Alan Russell on the use of generative models for the design therapeutic proteins.