How AI will change the pharma/biotech industry

What does the electrification of factories back in the 19th century have in common with applying AI to drug discovery today? For one, as our Chief Scientific Officer Markus Gershater points out in his latest piece for Technology Networks, both are new technologies that need time and significant changes to working practices. Realizing the full potential of electrification, for instance, didn't just involve swapping steam engines for electric engines. It meant making fundamental changes to how factories were run—something that took 50 years to take effect. And just like the promise that electric engines held in the 19th century, in drug discovery today the huge number of exceptionally diverse, AI generated targets are an opportunity: They represent a wealth of potential therapeutic programs.   But as Markus warns, their potential could be wasted, unless the rest of the drug discovery process can ramp up to meet the challenge. Read his full piece here: https://lnkd.in/ehc6xNRq #DrugDiscovery #AI 

AI appears to be everywhere in biotech and pharma these days. 🔸 AI inspires hopes of making processes in pharma faster, more efficient, more automated, and cheaper. 🔸 AI also inspires fears of human job loss and employing black-box algorithms in a field that concerns human health. 🔸 Navigating the promise and the risks of AI will be one of the greatest opportunities and challenges in the years to come. ➡️ In her talk, “Artificial Intelligence in Pharma: Between Hype, Hope, and Fear,” Healthonaut Louise von Stechow looks beyond the hype and explores how AI can benefit biotech and pharma. If you’re in Berlin on the 12th of February, sign up for the idalab seminar and join the discussion on AI in biotech and pharma. https://lnkd.in/ejmBJpSs Everyone is welcome, space is limited. Registration is required. https://lnkd.in/eV445VGQ

“It’s not an option not to try.” In a conversation with Asher Mullard in Nature Reviews Drug Discovery, Najat Khan, PhD, Chief R&D Officer and Chief Commercial Officer, addresses the skepticism around AI drug discovery, explaining:  ▪ why she’s committed to using data science and AI to improve the way drugs are discovered and developed; ▪ why she made the career leap from pharma to TechBio;  ▪ the promising indicators she sees for AI drug discovery; ▪ and why AI is the future of the industry. “It's really easy to cross your arms and be the Monday-morning quarterback, versus the person in the arena figuring it out,” Najat says. “We’re applying AI, machine learning and automated workflows to improve how drugs are developed because patients need better solutions.” She chose to join Recursion from J&J, she says, because of the high quality data, the expanding chemistry capabilities, and the strength of the clinical pipeline. “Recursion understands that creating an AI-first drug discovery engine is not just about the volume of data, but also about the quality, reproducibility and labeling of the data so that you can actually use it for machine learning. It’s a critical differentiator.” When it comes to the pervasive skepticism around AI drug discovery, Najat says “it's not an option not to try.” “I see a lot of people waiting to say ‘gotcha’, versus taking a constructive mindset,” she adds. “But we cannot continue to settle for a 10% success rate in drug development. That bar is way too low, the cost is too high, and patients are waiting.” Read more: https://lnkd.in/dtuhy3RE #ai #ml #datascience #drugdiscovery #techbio #pharma #patients #biology #chemistry Nature Portfolio

I love finding food for thought in unexpected places! This article is written by Micha Y. Breakstone 🇮🇱🎗️ from Somite.AI, where they're using AI to create advanced cell-based therapies. Talk about fit for purpose -- so so so much data to crunch through to make even the tiniest of advancements. In the article, Mr. Breakstone writes about a contest where AI participants set out to predict a biological process, but none of the AI models performed better than random guessing. The media commentary about the contest was that AI had failed. But what I love is Mr. Breakstone's perspective, in particular these two points jumped out at me: - What is a "failure" now could be the stepping stone leading to a breakthrough later, so we need to keep pushing forward. - We know that AI requires domain-specific data. However, it's not just enough to give AI access to existing data, we must figure out how to generate more data and more useful data. "The real story isn't about AI's current limitations. It's about the exciting potential that lies ahead as we overcome these initial hurdles." https://lnkd.in/g4H439bR

It's been over a decade since the AI revolution started reshaping drug development. Today, AI is used to discover new biological targets, perform rational drug design, manage clinical trials, identify patient sub-populations, and so much more — all detailed in this comprehensive survey. What sets CytoReason apart in this vast, dynamic space? First and foremost, we're a tech company, not a biotech company. We'll never develop our own drugs. So we'll never compete with our customers. Second, we offer a combination of software, professional services, and a platform of computational disease models, which is constantly enriched with proprietary and public data. And third, we help biopharma executives make data-driven decisions in key R&D junctions, so they ultimately improve the probability of phase 2 success. https://lnkd.in/dkUrnKpx

"The hype will play out in the long term," James Fraser said. "The hard part of drug discovery (is) it's a pretty long business. You can't take the wet lab part out of it yet. Stuff needs to play out in the clinic." Ron Leuty takes an in-depth look at Profluent and how #AI has become a force in drug development (biologics & small molecule). We are seeing this play out in applications to the QB3 mentoring program. It is striking how many new companies are touting that their use of AI/ML provides a competitive advantage. It's almost more remarkable if a drug discovery company is NOT using AI. And it is very hard to judge the longer-term commercial prospects of a new company whose approach relies on AI/ML. Obviously the quality of the data the models are using is paramount. Anyone with thoughts about how to assess these companies, please weigh in! https://lnkd.in/gaVr3CPj

📰 News: 📰 🚀 Unleashing the Power of AI in Drug Discovery 🚀 Let's dive into how artificial intelligence -AI- is revolutionizing the pharmaceutical world! 💊✨ With AI, companies can supercharge the drug discovery process, targeting diseases more precisely while slashing both time and costs. Just imagine a world where groundbreaking medications hit the market faster and more efficiently. Here are some eye-popping numbers to get you excited: 🔍 Traditional drug discovery takes over a decade and costs billions. Only 10-15% of these drugs make it to market. ⚡ AI has the potential to reduce time and costs by up to 50%, according to recent studies. 📈 AI's ability to analyze vast datasets opens up new avenues for personalized medicine and innovative treatments. Large language models -LLMs- and statistical analysis are proving to be game-changers. Take ChemCrow for example, which combines LLMs and statistical modeling to revolutionize chemical discovery. Could your company be the next to benefit from AI? Dive into the conversation! Share your thoughts in the comments below, and don’t forget to follow Bernier Group for more insights on the latest in business culture and digital transformation. 🚀👥 -AIDrugDiscovery -MedicalInnovation -PharmaTech -BernierGroup #AIDriven #Digital #AI #Data #SMB #SME #Strategy #Innovation #Business #ArtificialIntelligence #AnniQ https://lnkd.in/eskYHuAs

Excellent short essay by Nathan Frey and Eric Dai on the value of AI/ML in the #drug #development process emphasizing the decision making process as the one that offers greates value. I prefer to use the term "drug development" as I believe "drug discovery" is selling the opportunity of AI/ML short. Discover is imho not the bottleneck, deciding on which #hits to mature to #leads and eventually clinical candidates is where true value is generated - by reducing #uncertainty in the decision making process. At iuvantium we offer exactly this to our partners: #certainty for immunobiology. With our technology platform we can predict quality and quantity of an immunological response, have the tool box to program immunobiology, and eventually build a digital twin of the immune system to move toward in silico clinical trials and personlized medicine.

🚀 Introducing DrugAgent: Transforming Drug Discovery with AI! 🧬💡 Drug discovery is complex, costly, and often hindered by high failure rates. Enter DrugAgent, a cutting-edge multi-agent AI framework designed to revolutionize the process. Developed by researchers from the University of Southern California, Carnegie Mellon University, and Rensselaer Polytechnic Institute, this tool automates machine learning (ML) pipelines in pharmaceutical research, simplifying workflows and boosting efficiency. 🧠🤖 🔑 Key Highlights: -Automating ML in Drug Discovery: DrugAgent leverages Large Language Models (LLMs) for data acquisition, model selection, and pipeline optimization, making advanced ML accessible to pharmaceutical scientists. -Domain-Specific Excellence: It excels where general-purpose frameworks struggle, addressing challenges like chemical data preprocessing and domain-specific API calls. -Proven Success: In an ADMET prediction case study, DrugAgent achieved an impressive F1 score of 0.92, showcasing its potential to streamline drug screening and reduce late-stage failures. 🌟 How It Works: 1️⃣ LLM Instructor: Identifies domain-specific tasks and builds tools to meet complex needs. 2️⃣ LLM Planner: Systematically explores and refines solutions, ensuring robust ML workflows. 3️⃣ Dynamic Optimization: Adopts and evaluates multiple models (e.g., ChemBERTa, graph neural networks), selecting the best-performing approach—like random forests in ADMET tasks. 💼 Why It Matters: -Lowering Barriers: Simplifies ML integration for non-experts in pharmaceuticals. -Boosting Efficiency: Reduces the time and cost of drug discovery, allowing scientists to focus on strategic innovation. -Higher Success Rates: Improves accuracy in predicting crucial drug properties, minimizing resource-intensive failures. DrugAgent bridges the gap between AI's theoretical capabilities and the specialized needs of pharmaceutical research, pointing to a future where AI drives faster, smarter, and more cost-effective drug development. 🌍💊 #AIinPharma #DrugDiscovery #MachineLearning #PharmaceuticalInnovation #HealthcareAI #DrugAgent #FutureOfMedicine

Last chance to register for Logica’s webinar on AI in drug discovery! See how we’re overcoming industry challenges with human and AI synergy, delivering better leads and candidates faster. https://okt.to/4U5kaJ #AI #ML #webinar #Logica