How to Accelerate Drug Development Using Technology

Want to accelerate your advanced therapy's path to patients AND attract more investment?  💯 From preclinical development to commercial manufacturing, every decision biotech teams make is driven by data. But if that data is fragmented, incomplete, or reliant on paper-based records, it can slow everything down - regulatory approvals, investor confidence, and ultimately, patient access. In the latest article in my Blueprint for Breakthroughs newsletter, I've teamed up with Emmanuel Casasola, Anand Srinivasan, Ph.D., and Joe Higdon, to explore why early adoption of electronic batch records (eBR) is becoming a competitive advantage in biotech. Unfortunately, many companies wait until late-stage clinical trials or commercialization to implement digital systems, but the reality is: ⚠️ Deferring eBR leads to costly rework, slow approvals, and data integrity concerns. ✅ Starting early builds a seamless, scalable foundation that accelerates progress. At BBG Advanced Therapies and BioBridge Global, we designed our digital infrastructure with this in mind, and our customers benefit greatly. By integrating a fully compliant eBR system early in development, our partners gain: 🔹 Regulatory-Ready Data – Structured, traceable records support IND/BLA filings from day one. 🔹 Process Maturity – Batch records evolve with the therapy, ensuring continuity from preclinical to commercial scale. 🔹 Investor Confidence – A well-documented, GMP-aligned process signals operational readiness and reduces perceived risk. The question isn’t whether to adopt eBR, but WHEN. Companies that embrace early data maturity will stand out in an increasingly competitive funding landscape. 📖 Read the full article below. What’s been your experience with digital manufacturing systems? Let’s discuss how biotech teams can future-proof development and move therapies forward faster. #AdvancedTherapies #eBR #DataIntegrity #CellTherapy #GeneTherapy #ManufacturingInnovation #BlueprintForBreakthroughs #CGT #ATMP #ISPE #ISCT #ASCGT #AABB Blood Centers of America | Foundation for the Accreditation of Cellular Therapy | AABB | ISPE | MasterControl

Stacie Calad-Thomson started her talk on the impact of #AI in #drugdevelopment, highlighting that while AI provides frameworks and insights, it's not a silver bullet. AI is a game-changer, significantly expediting the drug discovery process. A journey from traditional drug discovery to AI-driven applications: The Problems: Traditional drug discovery challenges, including a high failure rate, data silos, complexity of biology, and inefficient design-make-test cycles. The process takes a decade and costs $billions. 1- Target Identification: Companies like Recursion use lab #automation and multi-omics (#invivomics, #phenomics, #metabolomics, #proteomics, #transcriptomics, #genomics) data to map biological relationships and run 2 Million experiments weekly. They leverage NVIDIA GPUs and recently secured a $50M investment, and acquired Cyclica & Valence Labs. By integrating AI, bridge the gap between #Biotech and #Techbio. 2- HIT Screening: Open source tools like AlphaFolio have revolutionized drug discovery by predicting 3D protein structures, enabling rapid in silico screening and precise target design. 3- Lead ID: BenevolentAI generative molecular design and active learning facilitate the rapid identification of potent drug candidates, such as #Percipinib, Eli Lilly and Company, for COVID treatments. 4- Lead Optimization: Exscientia combines generative molecular design with active learning for multi-parameter optimization, streamlining drug development. 5- Preclinical: Exscientia's AI-driven platform improves cancer treatment and outcomes. They achieved remarkable results, including a two-year remission for a chemotherapy-intolerant patient at a fraction of CAR-T costs. 6- Clinical Trials: Predicting disease severity and patient stratification for #COVID-19 clinical trials. As CSO at BioSymetrics, Stacie outlined their platform's capabilities, promising phenomics-driven hit discovery in less than a year, with a timeline covering gene-disease drivers, in-vivo modeling, hit identification, and target identification. Stacie contributes to responsible and ethical AI in healthcare as a board The Alliance for Artificial Intelligence in Healthcare (AAIH), collaborating with regulators. AI is undoubtedly transforming drug development, and Stacie's insights shed light on its immense potential. Following her talk, the panel moderated by Anjali Pandey, SVP Sudo Biosciences, Frazier Life Sciences, engaged panelists on a similar topic. Nitin Kumar, CEO, Nuron.IO, Sachin Sontakke, Sr. Dir Gilead Sciences, Preetha Ram, CTO Pier 70 Ventures. The consensus was that AI has and will change healthcare and how patients are cared for.  Since 2019, AI drug discovery start-ups had 352 deals and raised $10B from 600 unique investors. 80% of this $10B was invested in the top 30 companies. The tech-first is the most appealing to investors. The investment gap remains in manufacturing. Big thanks Anurag Mairal, PhD (He/His), Ashutosh Shastry & Pushkar Hingwe

Today, in (quasi-) new technologies: RNA delivery with cell membrane-coated nanoparticles The authors of this new article have taken a significant step forward in nucleic acid drug delivery, particularly for mRNA-based vaccines. Traditional lipid carriers face challenges such as premature release and immunogenicity. In this research, a novel system using chitosan methacrylate-tripolyphosphate (CMATPP) nanoparticles was presented, which can be coated with biological membranes to enhance delivery efficiency. Some interesting findings to be aware of: 1) Controlled release: by coating CMATPP nanoparticles with red blood cell (RBC) membranes, the researchers significantly reduced the initial burst release of siRNA, offering a more controlled and sustained release profile. 2) Biomimetic approach: the use of RBC membranes not only controls release but also preserves key proteins, potentially extending circulation time and reducing immune recognition, a crucial factor for drug delivery systems. 3) Versatility in coating: The authors expanded this concept to include extracellular vesicles and cell-derived nanovesicles, demonstrating the adaptability of their system. Using microfluidic devices and electroporation, they've created hybrid CDN-CMATPP nanoparticles, which retain specific cell markers, hinting at possibilities for personalized medicine. 4) Enhanced stability and performance? The CMATPP nanoparticles, when cross-linked, maintain stability in physiological conditions, and when coated, they exhibit properties like reduced immunogenicity and better payload retention, critical for siRNA delivery. The ability to use different cell sources for membrane coatings opens new avenues for targeted drug delivery, while the use of microfluidics in their fabrication process suggests scalability and the potential for high-throughput production, crucial for clinical applications. Full link to the article here: https://lnkd.in/ebCtnf5N #RNATherapeutics #DrugDelivery #BiomimeticNanoparticles #BiotechInnovation #PersonalizedMedicine

Technological Innovations in Glycosylation Technological innovations in glycosylation research have greatly advanced our understanding and manipulation of glycan structures, opening new possibilities for both basic science and therapeutic applications. One of the most transformative innovations is glycoengineering, in which tools such as CRISPR/Cas9 are used to precisely edit genes involved in glycosylation pathways. This allows for targeted modifications of glycosylation patterns in proteins, enabling the creation of optimized therapeutic proteins with enhanced efficacy and reduced immunogenicity. Another key innovation has been the development of high-throughput glycan profiling platforms. These technologies, including glycan microarrays and advanced mass spectrometry methods, enable rapid and comprehensive analysis of glycan structures. These tools have accelerated research by allowing large-scale screening of glycan-protein interactions, leading to the discovery of new glycan biomarkers and therapeutic targets. Advances in synthetic biology have also contributed to the field, particularly through the development of microbial systems designed to produce human-like glycosylation patterns. These systems provide a more consistent and scalable approach to producing glycosylated biopharmaceuticals, thereby reducing costs and increasing the availability of glycoengineered therapeutics. Additionally, computational approaches, including machine learning and artificial intelligence (AI), are being integrated into glycoscience to predict glycosylation patterns and their biological effects. These techniques pave the way for the design of more effective sugar-based drugs and personalized medicine. Overall, these technological innovations are driving significant advances in glycosylation research, enabling more precise control of sugar structures and expanding the potential for therapeutic development. Reference [1] Mengyuan He et al., Signal Transduction and Targeted Therapy 2024 (https://lnkd.in/e_smSGsu) [2] Haining L et al., Biotechnology Advances 2022 (https://lnkd.in/epGg7hFJ) [3] Leva Bagdonaite et al., Nature Reviews Methods Primers 2022 (https://lnkd.in/eZmDTHHy) #Glycosylation #GlycoEngineering #CRISPR #Glycomics #Glycoproteomics #Biotechnology #AI #MachineLearning #Bioprocessing #Biotherapeutics #BiomedicalInnovation

Conducting clinical trials (#CTs) has become increasingly costly and complex, especially when focusing on novel therapies in areas like #oncology and #rare_diseases. The challenges in running CTs targeting narrower patient groups have led to the exploration of innovative tools such as external control arms (#ECA), virtualization, decentralized clinical trials (#DCTs), and #tokenization for real-world patient follow-up. Key Highlights: - Ethical and Efficient: ECAs eliminate the need for placebo groups, ensuring all participants receive active treatment, addressing ethical concerns. - Accelerated Timelines: By reducing the recruitment of control-arm patients, ECAs can significantly shorten trial durations. - Enhanced Generalizability: Incorporating diverse real-world data enhances the relevance of trial results across varied populations. - Innovative Tools: Integration of virtualization, DCTs, and tokenization technology enriches clinical trial data, enhancing patient-centricity and efficiency. Source: Zou, K. H., Vigna, C., Talwai, A., Jain, R., Galaznik, A., Berger, M. L., & Li, J. Z. (2024). The Next Horizon of Drug Development: External Control Arms and Innovative Tools to Enrich Clinical Trial Data. Therapeutic Innovation & Regulatory Science, 58, 443–455. https://lnkd.in/ektUS9Ri #ClinicalTrials #DrugDevelopment #ExternalControlArms #RealWorldData #Innovation #Healthcare

Traditional drug discovery is slow and costly, often taking over 10 years and $1 billion to develop a new therapy. Existing computational approaches still rely on searching limited molecule libraries instead of designing entirely new candidates. 𝗗𝗶𝗳𝗳𝗦𝗠𝗼𝗹 𝗶𝘀 𝗮 𝗴𝗲𝗻𝗔𝗜 𝗺𝗼𝗱𝗲𝗹 𝘁𝗵𝗮𝘁 𝗱𝗶𝗿𝗲𝗰𝘁𝗹𝘆 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝘀 𝗿𝗲𝗮𝗹𝗶𝘀𝘁𝗶𝗰 𝟯𝗗 𝗱𝗿𝘂𝗴 𝗰𝗮𝗻𝗱𝗶𝗱𝗮𝘁𝗲𝘀 𝗰𝗼𝗻𝗱𝗶𝘁𝗶𝗼𝗻𝗲𝗱 𝗼𝗻 𝗯𝗶𝗼𝗹𝗼𝗴𝗶𝗰𝗮𝗹 𝘁𝗮𝗿𝗴𝗲𝘁 𝘀𝗵𝗮𝗽𝗲𝘀.  1. Outperformed all state-of-the-art shape-conditioned models by achieving a 61.4% success rate in generating molecules with highly similar shapes to ligands  2. Generated entirely new molecular graphs while preserving 3D shapes, ensuring 99.9% novelty compared to known datasets.  3. Improved binding affinities by 13.2% using protein pocket guidance and by 17.7% when combined with shape guidance.  4. Produced molecules for critical targets like CDK6 and neprilysin with higher predicted binding affinities and better ADMET profiles than existing FDA-approved drugs.  5. Ran more than 10× faster than previous protein-conditioned models, generating high-affinity candidates with favorable drug-likeness and synthetic accessibility. The two‐stage architecture balances expressivity and control: 1. Pretraining a dedicated shape encoder (SE) 2. Driving a shape‐conditioned diffusion model (DIFF) with a multilayer GVP‐based graph network (SMP) and shape‐aware scalar/vector fusion (SARL) But, I think unifying or streamlining modules (for instance, replacing separate SARL/BTRL blocks with an attention‐based equivariant layer) could reduce parameter counts and simplify training without sacrificing performance. Also, the inference efficiency (0.46 s per molecule for DiffSMol+p vs. 77.89 s for AR) demonstrates readiness for high‐throughput screening even though it could be a bit more efficient when training. Cool to see fast inference speed though Here's the awesome work: https://lnkd.in/gR8AvWwD Congrats to Ziqi Chen, Bo Peng, Tianhua Zhai, Daniel Adu-Ampratwum & Xia Ning! I post my takes on the latest developments in health AI – 𝗰𝗼𝗻𝗻𝗲𝗰𝘁 𝘄𝗶𝘁𝗵 𝗺𝗲 𝘁𝗼 𝘀𝘁𝗮𝘆 𝘂𝗽𝗱𝗮𝘁𝗲𝗱! Also, check out my health AI blog here: https://lnkd.in/g3nrQFxW

The biopharmaceutical industry faces unprecedented challenges with R&D productivity remaining flat despite rising costs. Current development timelines exceed 10 years, with R&D costs surpassing $2 billion per asset and only 13% of Phase 1 trials reaching launch. This article from McKinsey summarizes that R&D Tech Stack in detail. Value Creation Opportunities Financial Impact • Gen AI tools to unlock $53B annual value across R&D • 30% reduction in R&D IT spending through cloud migration • Cost reduction through AI-powered trial optimization Performance Metrics • Accelerated development timelines • Improved success rates through AI-driven decision making • Enhanced regulatory submission quality Strategic Imperatives Technology Integration • Enterprise-wide AI deployment for measurable ROI • Cloud-based infrastructure for scalability • Automated workflows and real-time analytics • Integrated data management across R&D functions Operational Excellence • Streamlined clinical trial processes • Automated documentation and regulatory submissions • Enhanced data quality and compliance • Reduced manual interventions Implementation Framework consistes of a suggested Four-Layer Architecture • Analytics Layer: AI/ML for insights and decision support • Application Layer: Integrated SaaS platforms • Data Layer: Centralized cloud-based management • Infrastructure Layer: Hybrid cloud foundation Critical Success Factors • Clear scope definition and modernization strategy • Vendor selection for optimal interoperability • Strong business-IT collaboration • Change management and adoption planning Executive Action Items Immediate Priorities • Assess current tech stack maturity • Identify high-value AI use cases • Define modernization roadmap • Select strategic technology partners Strategic Considerations • Choose between platform, best-of-breed, or hybrid approach • Balance standardization with customization needs • Ensure seamless integration across layers • Maintain regulatory compliance Risk Management Key Considerations • Data security and privacy • Vendor lock-in prevention • Legacy system integration • Regulatory compliance Expected Outcomes Short-term Benefits • Accelerated trial timelines • Reduced operational costs • Improved data quality • Enhanced decision-making capability Long-term Value • Sustained R&D productivity gains • Competitive advantage through innovation • Scalable digital infrastructure • Future-ready organization #Healthcare2025 #DigitalTransformation #BioPharma #TechnologyStack #AI #ML #ValueBasedCare #PatientCare #R&D #Innovation #Automation #CloudComputing #DataPlatforms #RemoteMonitoring #Personalization #Genomics #WearableTech #ClinicalEfficiency #WorkforceOptimization #HealthcostReduction #PreventiveCare #DigitalHealth #RoboticsAutomation #PatientExperience #InteroperableSystems #HospitalAtHome #MentalHealth #ChronicCare #UrgentCare Source: www.mckinsey.com Disclaimer: Opinion are mine and not of employer's

This new AI tool can design antibody drugs 100x faster than traditional methods - without trial and error. It’s called Chai-2. And it might quietly change how we discover drugs. Here’s why: Normally, designing an antibody drug takes months of testing in the lab - just to find one molecule that works. But Chai-2, an AI model built by Chai Discovery, skips that entire process. It watched hours of real-world data and learned to generate antibody candidates from scratch - with atomic-level precision. This new AI tool can design antibody drugs 100x faster - and with zero trial-and-error. In early tests on 52 new antigens, it produced viable hits for 50% of them - in just two weeks. That too without any screening or manual lab trials. The team calls it “Photoshop for molecules.” And the analogy makes sense - it lets researchers design antibodies with programmable control, rather than waiting for randomness to deliver results. This matters for two big reasons: ▶ 1. It’s faster and cheaper Fewer experiments means lower R&D costs and faster GTM. Especially powerful for early-stage biotechs running on tight timelines and capital. ▶ 2. It’s not just about antibodies Chai-2 can design miniproteins, explore new formats, and expand the kinds of molecules we can even consider therapeutically. As a funding coach and investor in healthtech, I see a signal here: → Founders who can compress the drug discovery loop - even slightly - will unlock investor confidence faster. Would you bet on a drug designed by AI if it meant saving months (and millions)? #entrepreneurship #healthtech #innovation

🚀 Revolutionizing Drug Discovery with Multi-Modal Integrated Causal AI Agents 💊🔬 The future of precision medicine is here! 🌟 Traditional drug discovery is a slow, expensive, and high-risk process, but AI-powered multi-agent systems are transforming the game. By integrating causal inference, machine learning, and multi-modal data, Multi-Modal Integrated Causal AI Agents (MATMCD) enable faster, more accurate, and personalized drug development. 🧬🔍 🔎 Why Do We Need Causal AI Agents in Drug Discovery? ❌ 90% failure rate in clinical trials due to toxicity, inefficacy, or unforeseen side effects. ⏳ 10-15 years and $2B+ in costs to develop a single drug. 🔗 Fragmented biomedical data across genomics, proteomics, and clinical trials. 🧩 Complex biological systems that traditional statistical models fail to interpret. 💡 How Can Causal AI Agents Solve These Challenges? By leveraging multi-modal data sources (genomic sequences, protein structures, patient data, and chemical libraries), Causal AI Agents enhance hypothesis generation, target validation, and drug optimization. 🤖 Causal Multi-Agent AI System in Drug Discovery 🔹 Data Augmentation Agent (DA-AGENT) – Collects and integrates multi-modal biomedical data. 🔹 Causal Constraint Agent (CC-AGENT) – Constructs causal graphs linking drug interactions & disease mechanisms. 🔹 Predictive Modeling Agent – Forecasts drug efficacy, toxicity risks, and off-target effects. 🔹 Optimization & Personalization Agent – Tailors drug treatments based on biomarker & genetic data. 🔹 Decision Support Agent – Assists researchers by summarizing insights & optimizing experimental designs. ⚡ Key Benefits of Causal AI Agent-Powered Drug Discovery ✅ Higher Precision – AI-driven causal inference & simulations reduce false leads and improve target selection. ✅ Faster Drug Development – Automated molecular screening & clinical trial optimization accelerate time-to-market. ✅ Personalized & Adaptive Therapies – AI-driven precision medicine tailors treatments to individual patients. ✅ Enhanced Data Utilization – AI unlocks hidden patterns across genomics, proteomics, and chemical datasets. 🚀 The Future of Causal AI Agents in Drug Discovery 🔬 Autonomous AI-driven research labs conducting automated experiments. 📊 Real-time adaptive drug development using live clinical & patient data. ⚖️ AI-powered regulatory compliance streamlining FDA approval & safety profiling. #AIAgents #DrugDiscovery #PrecisionMedicine #CausalAI #Healthcare