Ivan Dimov

InduPro raised an $85M series A (https://lnkd.in/gnPMq2pP). Exciting to see protein sequencing + AI enabling the discovery of new protein-led cancer treatments. "Our MInt platform leverages deep learning analysis of proprietary protein microenvironment and membrane proteomic data to define the architecture of the cell surface proteome across different target classes and indications. This allows us to identify novel targets and co-target pairs for selective tumor targeting (bispecifc ADCs and TCEs) or immunological synapse modulation (bi/multispecific mAbs)."

10

Techbio Unicorn Owkin Unveils AI-Driven Oncology and Immunology Pipeline : 4 early-stage de novo drug discovery programs and 1 patent-protected in-licensed drug asset ! 🤖𝐀𝐈-𝐏𝐨𝐰𝐞𝐫𝐞𝐝 𝐏𝐢𝐩𝐞𝐥𝐢𝐧𝐞 Owkin's pipeline leverages several internal AI engines and multimodal patient data from 61 research centers. With a team of 110 data scientists, Owkin uses spatial multiomics data via MOSAIC, the world's largest dataset in oncology, to understand the tumor microenvironment. This expertise positions Owkin to tackle challenges in precision medicine. 🧬𝐀𝐈 𝐄𝐧𝐠𝐢𝐧𝐞𝐬 𝐒𝐞𝐥𝐞𝐜𝐭 𝐎𝐊𝐍𝟒𝟑𝟗𝟓 𝐟𝐨𝐫 𝐢𝐧𝐥𝐢𝐜𝐞𝐧𝐬𝐢𝐧𝐠 Owkin's biomarker engine created detailed EP2/EP4 signatures using multimodal patient data, identifying actionable biomarkers. The AI drug positioning engine screened over 30 cancer indications for OKN4395, identifying the most promising therapeutic combinations for clinical trial 👩‍⚕️𝐂𝐥𝐢𝐧𝐢𝐜𝐚𝐥 𝐓𝐫𝐢𝐚𝐥 𝐎𝐩𝐭𝐢𝐦𝐢𝐳𝐚𝐭𝐢𝐨𝐧 𝐟𝐨𝐫 𝐎𝐊𝐍𝟒𝟑𝟗𝟓 Owkin plans to use its clinical trial optimization solutions to bring OKN4395 to the patients most likely to benefit from this innovative therapeutic. By utilizing its unique AI-driven pipeline, Owkin aims to enhance precision medicine in oncology and immunology.success.

72

5 Comments

Why has NanoTemper's Prometheus become the new gold standard for biophysical characterization of biologics like ADCs? Because data is getting more and more important. Who has the best data, willl win the game. Will have a competitive advantage. Best data -> best #AI model. Best understanding. Biophysics is key. To know what to do. nanoDSF & DLS deliver. Our Prometheus Panta delivers. It gets you high quality data of your biologics. Enables you to get the most value from your sample. Dr. Anja Pomowski from Antikor says: "Prometheus Panta resolved an issue with an ADC candidate not performing as expected in animal studies, outperforming all other devices we had used to evaluate the stability of this candidate." Have a look at the data attached. Have a look at the precision. It is for the trendy ADCs. What do you think when you look at it? #biotechnology #entrepreneurship #startup ————————— I am Philipp - founder, CEO & business angel. My bootstrapped company NanoTemper is a global leader for biophysical tools for biotech. Like my content? Click my name + follow + 🔔

86

13 Comments

Investment, therapeutic viability, and next-gen. technologies... That's what the cell therapy field needs. I had the pleasure of sitting down with Jason C. Foster of Ori Biotech recently on their podcast to talk all things cell therapy, the enabling technologies that support this modality, and the need for more investment. What did we touch on (and link to full podcast below)? Investors needing to see a return when investing in cell therapies. Need to bring manufacturing costs down to expand access. Next-gen. tools to create better, more robust therapies. Purpose-built therapies require purpose-built tools! Our consulting practice, how we help our clients, and how we view the field of advanced therapies. We take a differentiated approach to tracking, following, and mapping key trends across advanced therapies to bring novel, business-impacting insights to our clients. Want to discuss any of the above? Where the field of cell therapies are going? What it means for your own development pipeline? Reach out and let me know what you think in the comments! #celltherapy #venturecapital #consulting https://lnkd.in/g7SH9FAU

51

3 Comments

Tempus AI stock on a tear ($7B market cap today!) gives me an idea for a fun deal 💡🤪 I've long been intrigued about the potential value of GRAIL's phenotype+genotype+methylome database - no way to know really but could be worth far more than Galleri (which seems to have very little value as GRAL market cap << cash). So, what if Tempus bought Grail? What would it get, and what would it cost? We can assume from this week's big Grail layoff that it now operates free and clear of EU restrictions, so I would think pretty much anyone except Illumina could buy it and do with what they wanted (yay capitalism!) The amazing thing buying Grail is that it has $1B in cash but has a market cap of just $500M. So you could offer a 30% premium and still come out of the deal with $350M profit and a fantastic database that could add a couple of billion to Tempus market cap. Tempus could sell Grail data to its pharma customers, restart development of the MRD and DAC tests just halted (Tempus rents its MRD test from Personalis), and save an massive amount of money by pausing Galleri sales - could be restarted in the (unlikely) event Galleri gets FDA approval and CMS reimbursement. Alas there is a fly in the ointment of this whacky plan! There's a clawback clause that requires that if Grail is bought in the 15 month period after the spinout, a bunch of the cash has to get back to Illumina. I think it is: $clawback = $500M x (15 - months-since-spin)/15. So, doesn't work out to buy Grail right now as Illumina would get $500M back and we think we need $650M to buy. But (yay algebra! can you tell I'm on a long flight today? 🤣) if Tempus waits 5 months then Illumina only gets back $350M leaving $650 in bank 👏 So, my unsolicited advice is for Tempus AI is buy Grail in December 2024 and it won't cost you a dime and you'll have an amazing data asset and your own MRD test 🤣🤣🤣

90

11 Comments

🔬 Cell Painting Data Analysis Pipeline in HCS Pipeline 🔬 Today, we're demonstrating how you can analyze your Cell Painting data using the same pipeline we employ internally in the HCS Pipeline platform. With this fully customizable, modular solution, you can simplify and accelerate complex data analysis workflows without needing deep coding expertise. Let’s take a look at the components of the pipeline: 🚀 Step-by-Step Pipeline 🚀 1️⃣ Data Quality Control (QC): Automatically clean your dataset by removing outliers, handling missing values, and applying thresholds for NaNs and zeros. This ensures you're working with high-quality data from the outset. 2️⃣ Feature Reduction: Simplify your dataset by removing highly correlated and non-informative features, keeping only the most important and biologically relevant data to streamline the analysis. 3️⃣ Multiple Levels of Normalization: Apply different normalization methods, including z-score, MAD robustization, and spherizing the data, to remove batch effects and prepare the dataset for accurate downstream analysis. 4️⃣ Aggregation: Aggregate your data across different metadata levels, such as plates or experimental conditions, for seamless comparison and analysis. 5️⃣ UMAP Dimensionality Reduction: Reduce thousands of features to 2D space with UMAP to uncover hidden patterns and similarities between samples. 6️⃣ Interactive Plots: Generate Interactive Distance Matrices and Scatter Plots of UMAP Transformations to visualize relationships and gain insights into your data in just a few clicks. 🔍 Recreate This Pipeline with HCS Pipeline With HCS Pipeline, you can build and customize this analysis pipeline to suit your own research needs. The modular platform makes it easy for anyone to set up powerful workflows without requiring a data scientist. 💬 How are you currently analyzing your Cell Painting data? Let us know in the comments! --- #HCS #CellPainting #DataAnalysis #ResearchTech #Bioinformatics #HCSData #PipelineAutomation

7

1 Comment

Congrats Morteza Mahmoudi and Shahed Behzadi, Ph.D. on this publication! So excited to see your paper advancing the understanding of the protein corona that forms on lipid nanoparticles, and how that can be leveraged in so many areas. Always love diving into all of your research details in complex figures like this https://lnkd.in/gUMJYKEg.

10

2 Comments

A while ago, we posted this beautiful picture of a 3D cell-culture Lego set -- of course AI generated. There is a lot to unpack in this picture: InSphero 's 3D cell culture technology and Lego, though vastly different in their application and complexity, share intriguing parallels that can be drawn to highlight the innovative nature of your biotech solutions. 1. Modularity and Customization: Just as Lego bricks can be assembled in countless ways to create beautiful structures, InSphero’s 3D cell culture technology is inherently modular. This allows researchers to customize and build complex tissue models that closely mimic human biology, catering to specific research needs and experimental designs. 2. Precision and Standardization: Lego's design is renowned for its precision and intercompatibility, a trait mirrored in InSphero’s technology. Your 3D cell-based assays offer consistent, reproducible results, much like how Lego bricks reliably fit together. This standardization is crucial in scientific research where reproducibility is key. 3. Innovation and Complexity: Lego has evolved from simple building blocks to intricate sets that can replicate complex real-world objects. Similarly, InSphero has advanced the field of tissue engineering by moving beyond traditional 2D cell cultures to 3D models that more accurately represent human tissues, allowing for more complex and insightful research. 4. Educational Value: Lego is well-known for its educational benefits, teaching creativity, and problem-solving. In a parallel sense, InSphero’s technology educates the scientific community, offering deeper insights into human biology and disease, fostering innovation in drug discovery and safety testing. 5. Scalability: Just as Lego sets can be scaled from small models to large, intricate constructions, InSphero’s technology is scalable. It allows for applications ranging from small-scale academic research to large-scale, fully automated pharmaceutical drug testing, demonstrating versatility in various research environments. Having been a Lego fan all my life, it's great to take inspiration from such a great company. Let me know what you think! #3Dcellculture #MPS #OrganOnChips #Scalability #Reproducibility

383

32 Comments

This recent announcement of an open-source model (fine tuned Llama 3.1 70B - a model that can technically run on your desktop 😳) outperforming proprietary giants like Claude 3.5 Sonnet and GPT-4o marks a significant milestone in AI development. As someone working closely with these technologies, I've observed several key trends worthy of note: 1️⃣ Enterprise Adoption and Open Source Models The rise of powerful open-source models presents both opportunities and challenges for enterprises. While these models offer increased flexibility and potential cost savings, they also require significant in-house expertise to implement and maintain effectively. My experience suggests that companies are increasingly weighing the trade-offs between proprietary and open-source solutions, with factors like data privacy, customization needs, and long-term strategic goals playing crucial roles in decision-making. However, the eco system is developing at unprecedented speed and ease-of-use is improving daily, making open source increasingly appealing. 2️⃣ The Shifting Focus in Model Development We're witnessing an interesting shift in the AI model landscape. While the race for ever-larger models continues at the frontier, there's growing interest in smaller, more efficient models. These compact powerhouses are becoming viable options for a wide range of use cases, offering a balance of performance and resource efficiency that's particularly attractive for specific enterprise applications. 3️⃣ Democratization Through Reduction Techniques Techniques like distillation and quantization are putting state-of-the-art performance within reach of a broader audience. These methods allow for the creation of smaller, faster models that retain much of the capability of their larger counterparts. I've seen firsthand how this is enabling companies of all sizes to leverage advanced AI capabilities, potentially leveling the playing field in certain sectors. 4️⃣ The Future of Model Deployment The resource requirements for running cutting-edge AI models remain substantial, but they're evolving rapidly. As optimization techniques improve and hardware becomes more specialized, we're likely to see more companies bringing AI operations in-house. This shift could have profound implications for data security, customization, and the overall AI strategy of enterprises. Looking ahead, I anticipate a more diverse AI ecosystem where large frontier models coexist with highly optimized, task-specific models. For those where confidentiality and privacy is key, the days of endless API-requests may soon (already?) be over, and the cost of AI may rapidly approach the electricity cost of your server. (Note the singular.) What are your thoughts on these trends? How is your organization navigating to face the rapid technology changes we're facing? #ArtificialIntelligence #MachineLearning #EnterpriseAI #OpenSourceAI

1

Wow - 2 ex-Meta employees launch EvolutionaryScale landing $142m to advance AI in biology. EvolutionaryScale has introduced ESM3, a cutting-edge language model for biology that predicts protein sequences, structures, and functions. This model can simulate millions of years of evolution, generating new proteins with potential applications in medicine, research, and sustainability. ESM3 represents a significant advancement in AI's ability to design and engineer biological systems. There will be comparisons with AlphaFold3, intrigued where this goes... https://lnkd.in/dhtQDtsA #AIinDrugDiscovery #genomics #proteomics

3

1 Comment

I am excited to announce that one of Access Discovery Bio’s first clients is Cache DNA based out of San Carlos, CA. Cache has an exciting new technology that allows for the “Caching” of DNA and RNA, allowing them to be stored at ambient room temperature. Caching can be done on a small scale with various tubes or can be completely integrated into existing automated technologies that handle plates for working at scale. This is a profound development in my eyes after decades of both working in biorepositories and shipping frozen samples all over the world. I have personally witnessed sample evaporation and loss despite long term cold storage. I’ve seen the dramatic rise in costs not only to create and maintain freezer farms but also to safely ship frozen samples which can often dip into the thousands for a single shipment. I have personally been on call and had to travel into a lab at 2am to recover samples in a failed freezer or during a power outage. I have also worked in the lab having to use various techniques to properly freeze or thaw samples to work with them. For many reasons, I see this as a transformational technology. Who doesn’t like to save massive amounts of money? Everyone does of course and this comes with the added benefits of reducing carbon footprints and helping the environment. Michael Becich and his team at Cache are a great group of scientists who have created something truly beneficial to basic science. Cache is presently offering free demo kits to select customers while supplies last. Given my network is made up almost entirely of people using or storing samples for research, please help me in giving this great start up a signal boost and please reach out directly to me with interest in either demo kits or more information. #biobanking #DNA #RNA #technology #biospecimens https://lnkd.in/eK9q9JQk

28

Exciting! Technologies that continue to push the boundaries...

3

AI and Cultivated Meat, a review This paper is incredibly useful and a must read. Good job New Harvest and Alberta Machine Intelligence Institute (Amii)

5

Risk v. Return Investment Profile: ImmunoPrecise Antibodies Ltd.(NASDAQ: IPA $0.625) CFP has had the opportunity to review Carl Kestens' Fair Value Analysis of ImmunoPrecise(attached below). CFP would encourage all of you to review it as well. CFP's key takeaways and comments are: 1. ImmunoPrecise has a Market Cap of approximately $18 million USD, which is extremely cheap relative to any market evaluation technique you use. 2. IPA has several potential growth drivers that have yet to deliver value to the company. 3. We agree that many investors have given up(lost patience) on the prospects of any of these potential events will actually be achieved. Expectations of Investors have not been met by the Company to date. Herein may lie the opportunity moving forward... 4. IPA has finally addressed its non-existent Capital Markets Strategy with an experienced, and seasoned group out of New York City over the last couple of weeks. 5. The NYC Group is also addressing the Company's Communication, Media, and Investor Relations Strategy. The new messaging(which should have always been in place) is under promise, and over deliver(exceed expectations) go forward. CFP has already seen improvement in the messaging to "simplify" the story to prospective investors. 6. The investment risk/return profile today looks very compelling. It reminds me of some old investment advice: "buy when everyone is selling and sell when everyone is buying." Disclaimer: This is posted for information purposes only. Please consult your investment professional for investment advice. Capital Find Partners owns shares in ImmunoPrecise. IPA (ImmunoPrecise Antibodies) BioStrand (a subsidiary of IPA) InterSystems Quantum Media Group, LLC #LENSai #Biotech #ai #HYFTs #HYFTTechnology #drugdiscovery #healthcare #pharma #personalizedmedicine #omics #AIDrugDiscovery #systemthinking #bioinformatics #antibodies #machinelearning #multiomics #LLMs #datascience #computationalbiology #nlp #ontologies #semantics #knowledgegraphs #lifesciences #bigdata #informationinformationdilemma #patternrecognition #insilico #molecularbiologists #aminoacids #dna #rna #HYFTpatterns

12

3 Comments

AI-enabled #mRNA sequence design. From the paper, "We demonstrate that our AI-generated mRNAs exhibited 8.2-fold and 15.9-fold increases in firefly luciferase expression compared to benchmark mRNAs in two different cell types. Additionally, Our AI-designed COVID-19 mRNA vaccine elicited a 4-fold increase in anti-COVID antibody titer in mice relative to BNT162b2. Furthermore, GEMORNA’s versatility extends to circular mRNA design." https://lnkd.in/eFNyszJn

146

1 Comment

In this episode of cc: Life Science, recorded at #BIO2024 in San Diego, I had the pleasure of speaking with Martin Brenner, the CEO and CSO of iBio. Our focus was the challenges and innovations in developing antibody-based therapeutics, particularly through their epitope engineering platform. Martin shared his insights into the current landscape and future directions of antibody therapies, touching on key aspects such as target selection, engineering challenges, and the role of AI in optimizing therapeutic antibodies. Antibodies have revolutionized therapeutic approaches over the past two decades, with numerous successful drugs already approved. However, as Martin pointed out, we've now picked much of the low-hanging fruit. The target space is becoming increasingly complex, with most approved antibodies focusing on a small set of targets. For instance, about 40% of all approved antibodies target PD-1. While anyone can now develop a PD-1 antibody, the real challenge lies in identifying and effectively targeting novel, more complex antigens. Another significant challenge Martin highlighted is improving the safety and therapeutic window of antibodies. Highly potent antibodies, particularly in oncology, can cause severe side effects. Enhancing the safety profile while maintaining efficacy is a critical area of ongoing research. Surprisingly, it turns out that the best-binding antibody isn't always the most effective therapeutic. I find iBio's approach particularly interesting both in terms of finding better candidates and uncovering new biology in the process. Listen to the full episode to learn more and please subscribe to my Substack if you find this content valuable. https://lnkd.in/egaCjqgs #biotechnology #lifesciences #antibodytherapeutics #storytelling #healthcare 👋 Hi, I’m Chris 🎙️ Founder and host of Life Science Marketing Radio. 👉🏻 Your deepest insights are your best branding. 💌Learn more at https://lnkd.in/eDj2XGSy

2

🌟 Unlocking the Fountain of Youth: Meet the Startup Transforming Aging! 🌟 Age may be inevitable, but what if we could combat its effects? Imagine using antibiotics to prevent aging – sounds futuristic, right? Not for Felix Wong and his team at Integrated Biosciences. With $17M in funding, they're pioneering AI-driven drug development to tackle age-related diseases head-on. 🔬 Powered by cutting-edge research, this startup is pushing boundaries in the fight against aging. Led by the brilliant Wong and backed by a seasoned team, they're not just talking about change – they're making it happen. 💡 Optogenetics, high-throughput screening, and innovative drug programs – Integrated Biosciences is not holding back. Their work is not just groundbreaking; it's shaping the future of healthcare. Ready to defy aging? Join the movement led by this trailblazing startup. Who knows, they might just hold the key to a healthier, more vibrant future. Let's embrace the possibilities of tomorrow together. #AgingRevolution #BioInnovation

3

Here at Cellorama, we believe that getting closer to reality in your organoid, spheroid, and organ-on-chip models will increase success in drug discovery and cancer studies. That's why we created a simple & fast method: 💫 Visualize multiple proteins within your delicate 3D models - no disruption needed! 💫 Investigate cell-to-cell interactions that mimic real-world conditions, leading to more accurate results! 💫 Co-culture & explore various cells in tailored microenvironments, opening doors to groundbreaking discoveries! The secret? Just CellO-IF3 and your primary/secondary antibodies! That's all you need for your next groundbreaking research. Ready to unlock the true potential of your research? See more images and learn more: www.celloramatech.com Video: Liver spheroid and surrounding cells in hydrogel. Albumin (red), Na-K ATase (green), DNA (blue). (Credit: Gamze Demirel)    #organoids #spheroids #organonachip #cellresearch #celllabeling #scientificinnovation #liver #microscopy #fluoresence #confocal #presiciononcology #personalizedmedicine #3Dcellculture #hepatocyte #hydrogel

31

1 Comment