Latest Innovations in Gene Editing and Drug Discovery

Probably one of the most important articles in biotech AI this year...🧬👇 A new Nature Biomedical Engineering paper describes CRISPR-GPT, a large language model–driven, multi-agent system for automating CRISPR gene-editing workflows (link in the comments). ⚙️ The system coordinates multiple specialized AI agents to do these things: - Select appropriate CRISPR systems, design guide RNAs, and choose delivery methods. - Generate experimental protocols and assay plans. - Analyze results from wet-lab experiments and adapt subsequent steps. I can't stress enough the potential significance of this work, which IMO lies in the integration of computational reasoning with experimental execution, enabling “closed-loop” cycles where experiment design, execution, and analysis are connected and automated. The authors tested their agentic CRISPR-GPT system in real experiments, e.g., these: 🧬 Knockout of four genes in a human lung adenocarcinoma cell line. In the multigene knockout experiment targeting four genes (TGFβR1, SNAI1, BAX, BCL2L1) in A549 lung adenocarcinoma cells, the AI-generated protocol achieved consistently ~80% editing efficiency across all targets, as measured by NGS analysis 🧬 Activation of two genes in a human melanoma cell line. In the epigenetic activation experiments in a human melanoma cell line, the reported efficiencies were approximately 56.5% for NCR3LG1 and 90.2% for CEACAM1, based on flow cytometry comparing gRNA-edited groups versus negative controls. With this kind of agentic AI tools, it could become possible to explore larger experimental spaces more systematically and at greater speed. This really clicks with my vision of what the key role of AI systems is in drug discovery and biotech research: tying pieces together and allowing for holistic discovery vs classical reductionism (such as "target-ligand"-centric DD workflows). We outlined our ideas about this with Oleg Kucheriavyi earlier this year, in our industry report "Beyond Legacy Tools: Defining Modern AI Drug Discovery for 2025 and Beyond." The report is published with BioPharmaTrend.com, check it out via the link in the comments 📑 👇. Looking forward, systems like CRISPR-GPT could evolve into general-purpose lab intelligence, able to handle multi-modal data, integrate with robotics, and support continuous, iterative discovery. The space is worth watching. If you are following AI drug discovery and other deep tech trends, subscribe to Where Tech Meets Bio, a leading Substack newsletter in this niche (link in comments). Image from the article (citation in comments)

What’s going on with CRISPR & Gene Editing? And not just one or two companies. The entire field is heating up - scientifically, clinically, commercially... 🧬 CASGEVY (Vertex Pharmaceuticals + CRISPR Therapeutics) became the first-ever approved CRISPR therapy - now authorized in the US, UK, EU, Saudi Arabia, and Canada. While approvals largely occurred across late 2023 and early 2024, they’ve set the foundation for 2025’s commercial push. 🧬 Beam Therapeutics posted new data this June from its BEACON trial (base editing for sickle cell). 🧬 Prime Medicine, Inc. released early human data in May for CGD. 🧬 Verve Therapeutics shared updated data on its in vivo base editing program - and was acquired by Eli Lilly and Company this month to accelerate gene editing in cardiometabolic disease. 🧬 Ensoma secured FDA clearance for its first in vivo IND - a major moment for non-viral delivery. 🧬 Metagenomi presented platform advances in May at ASGCT 2025. 🧬 Chroma Medicine (now nChroma Bio) and Caribou Biosciences are progressing steadily - from preclinical epigenetic editing to clinical-stage oncology programs CB-010 and CB-011. ...From ex vivo to in vivo, AAV to LNP, episomal to chromosomal - Gene editing is maturing fast. ✅ Manufacturing now defines competitive edge ✅ Talent bottlenecks at the translational interface ✅ Proof of efficacy beyond sickle cell ✅ Targeted capital from Lilly (Verve acquisition), Gates Foundation (Tessera Therapeutics investment) - and SoftBank (early backer of ElevateBio & Synthego Corporation) But momentum isn’t without turbulence: 🔻 Pfizer dropped its approved AAV therapy Beqvez in Feb 2025. 🔻 Intellia Therapeutics, Inc. cut staff in Jan - and is now focused on leveraging its Waltham facility for late-stage programs. 🔻 Mammoth Biosciences reprioritized in May. 🔻 Even Scribe Therapeutics hasn’t regained its early licensing pace. 🔻 CMC hiring remains a challenge across pre-commercial gene editing companies. Because the hard part in 2025 isn’t editing the gene. It’s delivering it - predictably, safely, and at scale. So who’s actually building the full-stack gene editing engine? 🧬 Beam Therapeutics + ElevateBio - base editing + industrial vector manufacturing 🧬 Intellia Therapeutics, Inc. - leveraging its state-of-the-art Waltham site for internal supply 🧬 Verve Therapeutics - now Lilly-backed, pushing in vivo delivery boundaries 🧬 ReCode Therapeutics, Aera Therapeutics, iECURE, inc. - next-gen LNP & AAV delivery players 🧬 Tessera - backed by the Gates Foundation, pushing RNA-based editing 🧬 Chroma, Metagenomi, Caribou - engineering durability, precision & manufacturing compatibility - CRISPR isn’t just a breakthrough anymore. - It’s a business model test. Who’s solving the delivery, durability, and dose puzzle? 👇 Let’s hear it - who do you think is leading this next phase? #CRISPR #GeneEditing #Biotech #CGT #Manufacturing #CMC #BaseEditing

🚀 AI meets CRISPR: a new era of genome editing is here. We’re excited to announce the publication of our review, “Harnessing artificial intelligence to advance CRISPR-based genome editing technologies” in Nature Portfolio Reviews Genetics! In this work, we and many thought-leaders explore how AI-driven methods—from deep learning to language models—are powering the next generation of genome editing: optimizing guide RNAs, engineering novel enzymes, and ultimately accelerating therapeutics and functional biology. 🔬 Highlights: AI-powered design and prediction tools for CRISPR/Cas systems (nuclease, base, prime editing) Virtual cell/organ models to guide target selection and outcome prediction Roadmap for integrating AI into editing pipelines—from tool discovery to clinical translation 📘 Full paper → https://lnkd.in/eMJU6UdJ Free-access link: https://rdcu.be/eQycP Proud to contribute to this intersection of computational biology, machine learning, and gene therapy — the future of precision medicine is being built today. Shoutout to all the co-authors for their valuable contributions! Particularly my friend and colleague Bowen Li for his leadership!

American researchers have unveiled STITCHR in Nature, a novel gene-editing tool that enables the precise insertion of entire therapeutic genes into specific genomic locations without introducing unwanted mutations. Unlike traditional CRISPR systems, which typically correct single mutations and often face targeting limitations, STITCHR offers a "one-and-done" solution by inserting full genes. It may be a game-changing approach for treating diseases caused by a wide range of mutations, such as cystic fibrosis. STITCHR, short for Specific Target-Primed Insertion Through Targeted CRISPR Homing of Retroelements, harnesses enzymes derived from retrotransposons, genetic elements also known as "jumping genes", to guide gene integration with high specificity. Notably, the system can be delivered entirely in RNA form, simplifying logistics compared to approaches that require both RNA and DNA components. This advancement marks a major step forward in gene therapy, offering a promising strategy to treat diverse genetic disorders by replacing faulty genes in their entirety.

UC San Diego + Yale University may have just rewritten the gene editing playbook. CRISPR changed medicine forever - but it comes with baggage. Off-target edits. Genomic damage. Risk that scales with use. Now UC San Diego and Yale researchers have unveiled a new system that could be safer: → Targets small nuclear RNAs instead of DNA directly → Makes precise, temporary changes with fewer unintended effects → Can edit pre-mRNA and long non-coding RNAs linked to neurodegenerative and cardiovascular diseases → Early data shows no off-target activity compared with state-of-the-art CRISPR Why it matters: This isn’t a CRISPR replacement - it’s another arrow in the quiver for precision medicine. By working upstream of DNA, it could enable treatments tuned to individual diseases without permanent genomic scars. If it holds up, this could open a new era of personalized therapies - safer, smarter, and more adaptable than what came before. Who wins first: Biotechs that learn how to translate RNA editing into scalable therapeutics.

🟥 Dual and Multiplex CRISPR Systems for Simultaneous Regulation and Editing of Genes CRISPR technology has moved beyond single gene targeting, paving the way for dual and multiplex CRISPR systems capable of simultaneous regulation and editing of multiple genes. These advances are essential for studying complex genetic networks, polygenic diseases, and synthetic biology applications, making gene editing more efficient, scalable, and precise. By allowing coordinated activation, repression, or modification of multiple genetic elements, these systems open up new possibilities for precision medicine, functional genomics, and cellular engineering. A key innovation in this field is the development of dual-function CRISPR systems, where catalytically inactive Cas9 (dCas9) is fused to different effector domains to activate one gene while silencing another in the same system. For example, dCas9-VP64 promotes gene activation, while dCas9-KRAB represses gene expression. Similarly, dCas9-p300 (a histone acetyltransferase) enhances transcriptional accessibility of chromatin, while dCas9-DNMT3A (a methyltransferase) promotes gene silencing through DNA methylation. These dual-function approaches are particularly beneficial for cancer research, as oncogenes can be silenced while tumor suppressor genes can be reactivated, creating more effective therapeutic strategies. In addition to dual-function applications, multiplexed CRISPR systems allow for the simultaneous targeting of multiple genes in a single experiment. One of the most promising strategies involves Cas12a (Cpf1), which can process multiple guide RNAs (gRNAs) independently, thus streamlining the editing of multiple disease-associated genes. In addition, polycistronic gRNA arrays enable coordinated control of gene networks involved in polygenic diseases such as diabetes, neurodegenerative diseases, and autoimmune diseases. These multiplexed approaches enhance our ability to correct multiple mutations simultaneously, making them extremely valuable for future gene therapy applications. Dual and multiplexed CRISPR systems are becoming more precise, efficient, and scalable with continued advances in AI-optimized gRNA design, improved Cas enzyme variants, and advanced delivery methods. These innovations are expected to revolutionize synthetic biology, regenerative medicine, and personalized gene therapy, enabling complex genetic modifications with greater accuracy and reduced off-target effects. As these technologies mature, they will unlock the full potential of CRISPR for multi-gene regulation, whole genome editing, and complex disease treatment. References [1] Nicholas McCarty et al., Nature Communications 2020 (https://lnkd.in/e8XzQAzG) [2] Amalie Brokso et al., Molecular Therapy 2025 (https://lnkd.in/eqcbi24g) #GeneEditing #MultiplexCRISPR #GenomeEngineering #GeneticTherapy #AIinBiotech #BiomedicalInnovation #BiotechBreakthroughs #CSTEAMBiotech

The lab of David Baker keeps pushing the AI frontier in biology. The newest advance: A team of 21 scientists describing how they made enzymes from scratch using AI models that perform some fairly complicated chemical feats. There is vast potential for where this technology goes from here. It could allow scientists to design enzymes in new ways — from building better gene editors to new proteases to a library of plastic-degrading enzymes. “The bigger picture is we can now use deep learning, ML diffusion methods, to make really active enzymes,” Baker told me, adding his lab is now working on making nucleases, or enzymes that cut nucleic acids, and thinking about base editors, another type of gene editing. For my latest at Endpoints News, I talked with Baker and three of the leading researchers on this Science paper: Anna Lauko, Sam Pellock, and Kiera Sumida:

This is incredible: A baby just became the first person in the world to receive personalized gene-editing treatment. KJ Muldoon was cured of a rare genetic disorder that kills 50% of infants within their first week. Here's the full story (& how this could change everything): 1. The deadly genetic disorder that should have killed him KJ was born with CPS1 deficiency… A condition affecting 1 in 1.3 million babies. Without the CPS1 enzyme, toxic ammonia builds up in the blood, causing severe brain damage or death. Doctors initially offered "comfort care," expecting KJ wouldn't survive. 2. The revolutionary custom gene therapy approach Instead of accepting this fate, a team at Children's Hospital of Philadelphia created a personalized CRISPR gene therapy. This wasn't an off-the-shelf treatment… It was custom-designed to fix KJ's specific genetic mutation. 3. Unprecedented speed in gene therapy development The most impressive part of all this? The entire treatment was developed in just 7 months. Typically, gene therapies take 1-2 years to produce. The team streamlined the process by focusing solely on KJ's unique mutation rather than trying to create a treatment for all CPS1 cases. 4. The cutting-edge delivery mechanism behind the treatment The therapy used lipid nanoparticles (tiny fat bubbles) to deliver billions of microscopic gene editors directly to KJ's liver. These editors contained mRNA with precise instructions. Essentially a "GPS signal" guiding them to the exact location in his genome. 5. Remarkable transformation in the baby's health KJ received three infusions between February & April 2025. The results? He's now thriving. He: • Is developing normally • Requires less medication • Can eat more protein-rich foods (previously restricted) Outcomes that would have been impossible before. 6. Implications for millions with rare genetic diseases This is more than just one baby's miracle cure. It proves personalized gene therapy is possible for ultra-rare conditions affecting just one person. Globally, 350 million people suffer from rare diseases. Most are genetic & have no treatments. 7. How this solves a fundamental healthcare business problem The breakthrough addresses a fundamental healthcare problem: Pharmaceutical companies have little incentive to develop treatments for diseases affecting just a handful of people worldwide. This approach could create a repeatable framework, where only the mutation-specific instructions need changing. 8. Major challenges that still need to be overcome There are however challenges that still remain: • Cost (gene therapies often run into millions per patient) • Delivery (current methods work well for liver but not other organs) • Regulatory pathways (how do you approve a treatment used by just one person?) But the template now exists. This is what real medical innovation looks like. If you enjoyed this... Follow me for more content like this.

In a historic leap for science and medicine, researchers at the Broad Institute in the US have successfully edited human brain cells using an advanced CRISPR method called prime editing. This technology allows scientists to rewrite DNA sequences with remarkable precision, correcting harmful mutations in neurons without cutting the DNA or triggering immune responses. Unlike traditional CRISPR, which snips DNA and can cause unintended damage, prime editing acts like a molecular word processor. It swaps individual DNA bases with surgical accuracy, making it a safer tool for the brain's delicate environment. The breakthrough was tested on lab-grown neural organoids that mimic human brain development, showing strong potential for treating conditions like Alzheimer’s, Parkinson’s, and Huntington’s disease. These disorders often arise from single gene mutations, and now for the first time, researchers have a method to fix those faulty genes directly in brain cells. Although challenges remain, especially in delivering these tools across the blood-brain barrier, scientists are already making progress using nanoparticles and engineered viral vectors. Ethical debates about editing the human brain continue, but this achievement brings hope to millions. If proven safe in humans, this technology could become a game-changing therapy for once untreatable neurological diseases. CRISPR is no longer just about the future. It’s changing lives now. #CRISPRMedicine #BrainHealthRevolution #GeneEditingBreakthrough #NeuroScienceFuture