In the first of a new series, we ask: #WhyAI? At Deep Genomics, we are pioneering new AI science alongside biological science. But what are some key challenges facing biotech and pharmaceutical industries that foundation models can help solve? While the current climate for biopharma innovation is seemingly ideal, productivity remains low. @The National Institutes of Health in the United States highlighted that of 16 leading pharma companies, R&D spending increased at a compound annual growth rate of 6% between 2001-2020. This led to an average R&D expenditure per company of $6.7 billion - and nearly half had negative productivity as a result. Standard AI has not yet lived up to the promise of increased productivity, but AI foundation models, such as BigRNA, offer a new approach. BigRNA can uniquely discover - at speed - a wide range of new targets and RNA therapeutic opportunities that otherwise would take too much money and workforce power to find. Want to learn more about BigRNA and “Why AI”? Learn more on the Deep Genomics website: https://lnkd.in/gP4apMmb #BigRNA #techbio #biotech #aipharma
Deep Genomics’ Post
More Relevant Posts
-
🤖 Exciting strides in AI are revolutionizing drug discovery, propelling us towards faster, more efficient development of life-saving medications. With vast data sets and complex molecular interactions, AI algorithms are adept at predicting drug-target interactions, identifying promising compounds, and optimizing molecular structures. By harnessing machine learning and deep learning techniques, researchers can navigate the intricate landscape of biological systems with unprecedented precision, accelerating the discovery process from years to mere months. ☘ 🤖AI & ML in Biotechnology 🤖 ☘ "Artificial Intelligence in Drug Discovery" by Nathan Brown is an insightful exploration into the intersection of artificial intelligence (AI) and pharmaceutical research. Brown delves into the transformative potential of AI in accelerating the drug discovery process, offering a comprehensive overview of cutting-edge techniques and applications. Through clear and accessible language, he elucidates complex concepts, making this book accessible to both experts and newcomers in the field. Comment your mail below for the full version.. #MachineLearning #ToxicityPrediction #PharmaceuticalResearch #BiotechAI #MLinBiotech #AIinBiotech #DSforBiotech #BiotechDataScience #Bioinformatics #BiotechAnalytics #AIHealthcare #MLMedicine #BiotechInnovation #DSBiotech #PrecisionMedicine #BioAI #MLResearch #AIinDrugDiscovery #BiotechTech #DataDrivenBiotech #AIHealth #BioML #BiotechInsights #MLforHealthcare #AIinGenomics #BiotechStartups #DSinHealthcare #BiotechTrends #MLBiotechApplications #AIinBiomedical #BiotechInnovations #DataScienceBio #AIinLifeSciences #Datascience
To view or add a comment, sign in
-
🔬 Bioinformatics and Systems Biology Researcher | 💻 Molecular Docking & Dynamics | 🧬 Onco Omics | 📊 Big Data Analyst | 🎯 Precision Oncology | 🤖 AI & ML Enthusiast | 🐍 Python Programmer
🚀 **Revolutionizing Drug Discovery with Generative AI** 🧬 The future of pharmaceuticals is here, and it's powered by #GenerativeAI! 🤖✨ By leveraging cutting-edge AI, we're transforming drug discovery into a faster, more efficient process. 🔬 **What's Changing?** Generative AI can design novel drug molecules from scratch, predict their properties, and evaluate their potential—all at lightning speed. This means less time in the lab and more time bringing life-saving treatments to market. ⏱️💊 🌟 **Why It Matters?** AI-driven models analyze vast datasets to uncover hidden patterns, enabling researchers to explore a broader chemical space and discover new drug candidates like never before. The synergy between AI and human expertise promises groundbreaking therapies developed at an unprecedented pace. 🌐💡 future of healthcare with #ai and #innovation! 🌍💼 #drugdiscovery #bioinformatics #cadd #bigdata #generativeai #deeplearning #molecularmodeling #structurebiology #alphafold3 #healthcarerevolution #biotech #pharma #techInnovation #futureofmedicine
Drug Discovery with Generative AI #bioinformatics #ai #drugdiscovery #generativeai #nvidia
https://www.youtube.com/
To view or add a comment, sign in
-
The incredible promise and current limitations of leveraging AI for drug discovery Google DeepMind’s AlphaFold stunned the world by predicting protein structures with unprecedented accuracy. Leveraging this, Recursion Pharma made a massive leap forward by calculating potential bindings for 36 billion compounds to over 15,000 AlphaFold-predicted human proteins. Their announcement prompted great excitement about AI accelerating drug discovery. However, crucial new analysis by Stanford University researchers Masha Karelina et al. published in eLife Sciences Publications, Ltd. (https://lnkd.in/exkCFsZt) and echoed in Nature Portfolio’s #Nature (https://lnkd.in/e2ZH2xJC) suggests AlphaFold's prowess at structural prediction does not yet reliably translate into identifying high-quality leads for drug binding. Carrie Arnold writes that the reasons likely involve small inaccuracies in computationally-predicted structures versus experimental ones, and an inability to fully account for subtle protein shape changes when ligands bind. Realizing the full potential of AlphaFold for drug discovery will require extensive validation efforts across academia and industry to translate structural insights into actionable small molecule leads. This highlights that while the future is tremendously bright for innovations at the intersection of computation and drug development, patience and collective effort across sectors are needed to fulfill the promise. AlphaFold massively expands our lens for unraveling biology's mysteries. But we must temper expectations and rigorously assess current limitations, while forging broad collaborations focused on transparency and data sharing. There is no doubt the road ahead remains long - but it is also breathtakingly exciting. Onward and upward! #AlphaFold #biotech #Innovation #AI Illustration EMxID
To view or add a comment, sign in
-
Leveraging Knowledge Graph Embeddings for Breakthroughs in Drug Repurposing Exciting developments are underway in the realm of drug discovery! 🌟 Our team is at the forefront, utilizing Knowledge Graph Embeddings (KGE) to drive innovation in drug repurposing. By embedding complex biomedical information into lower-dimensional spaces, we are uncovering hidden relationships between drugs, diseases, and biological pathways. The power of KGE lies in its ability to synthesize vast amounts of data, including genetic information, protein interactions, and pharmacological properties. This approach not only accelerates the identification of new therapeutic uses for existing drugs but also significantly cuts down the cost and time involved in bringing treatments to patients in need. As we integrate AI with bioinformatics, the potential for patient-specific therapy and personalized medicine grows. Our mission to transform patient outcomes continues, and the promise of KGE in revolutionizing healthcare is more tangible than ever. Join the conversation and explore how artificial intelligence and machine learning are paving the way for smarter, faster, and more effective drug repurposing strategies. #DrugDiscovery #DrugRepurposing #KnowledgeGraphs #AIinHealthcare #MachineLearning #PersonalizedMedicine #Bioinformatics
To view or add a comment, sign in
-
AI and Drug Discovery, a very hot topic! 🔥 The more I navigate on LinkedIn, the more I read insightful discussions about the role of AI in drug discovery. There are so many diverse viewpoints that really challenge my understanding of AI’s role in this field. 📚 Before releasing my article next week, which will delve into this topic, I would like to share with you several posts/articles that I found very insightful: 1. Niven R. Narain (found in the post by Erin Blank): “AI Isn’t the Magic Bullet to Simplify Drug Discovery” (https://lnkd.in/emBDrXwf) 2. Alister Campbell: “Discussion on how AI is revolutionizing drug discovery by cutting development time and costs” (https://lnkd.in/eY5aw_Yq) 3. Charlie Harris: “AlphaFold3: A foundation model for biology (?)” (https://lnkd.in/eD4scYSF) 4. Nils Weskamp: “Explaining AI is a process, not an algorithm” (https://lnkd.in/emw-RPxU) 5. Andrii Buvailo, Ph.D. Buvailo: “Pioneering the Largest Foundation Model to Transform RNA Research: An Interview with Brendan Frey” (https://lnkd.in/e5ZnNGSW) Enjoy your read and please share your feedback in the comments. I would love to hear from you! What do you think about the role of AI in drug discovery? 🤔💬 #MachineLearning #AI #DrugDiscovery #Biotech #Alphafold #ExplainableAI #Innovation (Illustrative picture credit goes to https://lnkd.in/eksxcNst)
To view or add a comment, sign in
-
🧬 Exploring Targeted Protein Degradation (TPD) and the Role of AI 🧬 Targeted Protein Degradation (TPD) has emerged as a game-changer in drug development, offering a precise mechanism to remove disease-causing proteins. But how can we maximize its potential? 🎯 This is where Artificial Intelligence steps in. AI brings a data-driven approach to the table, sifting through vast amounts of information to uncover novel and promising small molecules, even for challenging targets. 🌱 Kantify, a pioneer in AI-powered drug discovery, is excited to share our insights at the upcoming 6th Targeted Protein Degradation Summit from October 30 to November 2, 2023. 🗓️ Our Chief Technology Officer, Nik Subramanian, will delve into building a pipeline using AI and the promising results we've achieved. Stay tuned for more updates on these insightful sessions as we harness the power of AI to revolutionize drug discovery and transformational science. 🚀 #TargetedProteinDegradation #AIinDrugDiscovery #KantifyAtTPD
To view or add a comment, sign in
-
Really nice summary of real progress and some future challenges in computational drug discovery!
The Gordon conference on computer-aided drug design (CADD) is widely considered to be the premier scientific conference in the field. With the high level of hype surrounding the application of #ai and #ml to drug discovery, attending this meeting was a humbling reminder of the challenges that remain in using computers to bring new medicines to humans. Here are my key takeaways: ⭐ AI/ML is here to stay. Researchers in the field - ranging from academic labs to behemoths such as Google - are developing new AI technologies to address problems ranging from structure determination to hit discovery, automated synthesis and experimentation, and property optimization. HOWEVER, optimizing the learning loop between experimental data generation and model creation remains a significant challenge. Simply stated, we are not necessarily generating the right data and/or enough of it. ⭐ DESPITE the tremendous progress the industry has seen w.r.t the development of AI-based methods, much of the real world application of computational methods to drug discovery is still rooted in traditional biophysics-based approaches. This disconnect speaks to both the cultural and technological hurdles that still exist. We are not there yet. ⭐ As we go after harder problems, i.e. tackling the "undruggable", interrogating protein dynamics is KEY. Many talks emphasized the importance of dynamics based approaches (MD, induced fit, etc) to inform molecular design strategies. Proteins are not static entities and can no longer be treated as such. ⭐ Alternative therapeutic modalities (degraders, peptides, antibodies, RNA, etc) are gaining in application, yet technologies for addressing these still lag behind small molecules by years (if not decades). We need to become less small-molecule focused and develop technologies that can be impactful across multiple modalities. ⭐ADMET remains a huge unsolved problem. We need more and better data, and we need to SHARE it. #drugdiscovery #computeraideddesign #biotech #pharma
To view or add a comment, sign in
-
Thanks for this useful summary!
The Gordon conference on computer-aided drug design (CADD) is widely considered to be the premier scientific conference in the field. With the high level of hype surrounding the application of #ai and #ml to drug discovery, attending this meeting was a humbling reminder of the challenges that remain in using computers to bring new medicines to humans. Here are my key takeaways: ⭐ AI/ML is here to stay. Researchers in the field - ranging from academic labs to behemoths such as Google - are developing new AI technologies to address problems ranging from structure determination to hit discovery, automated synthesis and experimentation, and property optimization. HOWEVER, optimizing the learning loop between experimental data generation and model creation remains a significant challenge. Simply stated, we are not necessarily generating the right data and/or enough of it. ⭐ DESPITE the tremendous progress the industry has seen w.r.t the development of AI-based methods, much of the real world application of computational methods to drug discovery is still rooted in traditional biophysics-based approaches. This disconnect speaks to both the cultural and technological hurdles that still exist. We are not there yet. ⭐ As we go after harder problems, i.e. tackling the "undruggable", interrogating protein dynamics is KEY. Many talks emphasized the importance of dynamics based approaches (MD, induced fit, etc) to inform molecular design strategies. Proteins are not static entities and can no longer be treated as such. ⭐ Alternative therapeutic modalities (degraders, peptides, antibodies, RNA, etc) are gaining in application, yet technologies for addressing these still lag behind small molecules by years (if not decades). We need to become less small-molecule focused and develop technologies that can be impactful across multiple modalities. ⭐ADMET remains a huge unsolved problem. We need more and better data, and we need to SHARE it. #drugdiscovery #computeraideddesign #biotech #pharma
To view or add a comment, sign in
-
The Gordon conference on computer-aided drug design (CADD) is widely considered to be the premier scientific conference in the field. With the high level of hype surrounding the application of #ai and #ml to drug discovery, attending this meeting was a humbling reminder of the challenges that remain in using computers to bring new medicines to humans. Here are my key takeaways: ⭐ AI/ML is here to stay. Researchers in the field - ranging from academic labs to behemoths such as Google - are developing new AI technologies to address problems ranging from structure determination to hit discovery, automated synthesis and experimentation, and property optimization. HOWEVER, optimizing the learning loop between experimental data generation and model creation remains a significant challenge. Simply stated, we are not necessarily generating the right data and/or enough of it. ⭐ DESPITE the tremendous progress the industry has seen w.r.t the development of AI-based methods, much of the real world application of computational methods to drug discovery is still rooted in traditional biophysics-based approaches. This disconnect speaks to both the cultural and technological hurdles that still exist. We are not there yet. ⭐ As we go after harder problems, i.e. tackling the "undruggable", interrogating protein dynamics is KEY. Many talks emphasized the importance of dynamics based approaches (MD, induced fit, etc) to inform molecular design strategies. Proteins are not static entities and can no longer be treated as such. ⭐ Alternative therapeutic modalities (degraders, peptides, antibodies, RNA, etc) are gaining in application, yet technologies for addressing these still lag behind small molecules by years (if not decades). We need to become less small-molecule focused and develop technologies that can be impactful across multiple modalities. ⭐ADMET remains a huge unsolved problem. We need more and better data, and we need to SHARE it. #drugdiscovery #computeraideddesign #biotech #pharma
To view or add a comment, sign in
22,997 followers
Project Leader - Oligonucleotide Therapeutics - at Evotec
2w🙂