Joel Dudley

Single Transcript Unit Surrogate Reporter (STU-SR) systems to enhance the selection of genome-edited plants https://lnkd.in/eevaDBt5

7

1 Comment

Will PacBio's new chemistry SPRQ renewed interest in clinical long-reads? Pacific Biosciences, the makers of the Revio long-read sequencer, announced last week that they were launching a new sequencing chemistry that would improve sequencing yield by 30% while also reducing the cost of a whole genome (20x) to less than $500. In my initial reading of their press release, I missed the 20x part and got really excited about PacBio finally having a price competitive genome because a long-read based whole genome is truly impactful in clinical genetics. This is because long-reads allow us to give patients more complete answers, but it's also because if you have long-reads you can eliminate all of the crazy expensive ancillary tests you need to use to gap fill a short-read 'whole genome.' These include things like: MLPA - for variants in repetitive regions or pseudogenes Arrays - for getting at larger structural variants that are missed by short-reads Methylation profiling - to pick up non-sequence based epigenetic variation But you might be wondering how a 30% increase in yield brings the $1,000 Revio genome down to $500. It's because they're now saying that a Revio whole genome only requires 20x coverage. Why does a Revio genome now only require 20x coverage? Mostly because it helps them hit their $500-a-genome number. In this week's premium issue of Omic․ly ($5/month), I review PacBio's SPRQ chemistry and explain, with data, why 30x genomes are the clinical standard. But if using facts to combat troubling press releases about 'the cost of a genome' aren't your thing, the free issue has: 1) A USB drive? Nah, an epigenetic drive! 2) A not-so-deep dive into Single Cell and Spatial Transcriptomics 3) Linus Pauling molecularly characterized the first Mendelian Disease: Sickle Cell Anemia Catch it here: https://buff.ly/3YRaYwz

27

2 Comments

By leveraging AI with vast genetic databases, we are not only quickening the pace of identifying potential drug targets but also enhancing the accuracy of clinical diagnostics and predictive modeling. Recently, I had the privilege of discussing the profound impact AI is having on pharmaceutical R&D with Kim Branson, GSK's SVP Global Head of Artificial Intelligence and Machine Learning. Listen on Raising Health: https://lnkd.in/g6QUm2-A

41

5 Comments

If you are here at #JPM2025 or tuning in through the webcast and want to learn more - send me a message. We’re excited to share how our platform is transforming the #regulatorylifecyle, infusing AI thoughtfully throughout traditional processes to drive efficiency. #biotechshowcase #AIinHealth #regulatoryoperations #medicalwriting

14

Focus your data science team on biological insights and trial optimizations rather than data cleanup. The 640,000,000 relationships within Qiagen’s Biomedical KB-AI have been generated using AI + NLP tools for cutting-edge connections, including 6.4M gene-causal, 1.9M disease-causal, and 1.1M drug-causal relationships. KB-AI can help drive drug discovery and repurposing explorations, letting you identify new targets and indications with genetic evidence found across scientific literature, and establish potential biomarkers for clinical development. In addition to leveraging the latest publications, KB-AI also mines patents, grants, and prepublication arXiv sources, empowering competitive landscape analyses by target, drug, and indication, and streamlining scientific due diligence for M&A.

9

Interested in seeing what Rocky Balboa, Jeff Spicoli, AI and machine learning have in common, check out this Timmerman Report article on east Coast vs West Coast AI culture clash. We are fortunate to have a network of experienced AI & machine learning professionals available for consulting assignment. Let us know if we can be of help.

1

AI Proteins, a biotechnology company that uses computational de novo protein design to create therapeutic miniproteins, announced last week an agreement with Bristol Myers Squibb (BMS) to discover and develop novel miniprotein-based therapeutics using AI Proteins’ discovery platform. The deal could be worth up to $400M plus royalties on net sales. Miniproteins comprise: a peptide that folds into a highly stable structure, optional disulfide bonds, canonical amino acids without post translational modifications, entirely novel composition of matter designed to be non-immunogenic, and more. Notably, the company says, “because drug-like properties are designed into the miniproteins from the start, every molecule with optimized activity is ready to begin pre-clinical studies.” AI in drug discovery is one of the most active areas of biotech deal-making right now. There has been a steady stream of deals the last two years, but just within the last few months:

2

I was on a very interesting panel about the democratization of science, about communicating science to the people, about synthetic biology, and all sorts of cool, interrelated concepts. It was also filmed at a really neat studio space at Concordia University. If you have any interest in these topics, go watch the video now! #scicomm #syntheticbiology #synbio #sciencejournalism #trust #biology #sciencemuseum #scienceeducation https://lnkd.in/eQDmcduh

8

1 Comment

This article is inspired by comments from Tony Czarnik and Stefan Ivanov regarding my previous blog post at https://lnkd.in/gFPhXfKW. To clarify, I am writing from the perspective of an AI believer or practitioner, acknowledging the critical viewpoint that claims "AI has shown little in terms of actual achievements in drug discovery." However, I believe it is not sufficient to simply agree with this stance without further elaboration. My focus here is on higher-level concepts rather than practical examples. Here are three key takeaways: 1. Need for Comprehensive Data Collection The current drug discovery process often lacks systematic documentation and relies heavily on subjective reporting, which hampers the ability to draw robust conclusions. Scientists, particularly chemists and biologists, should prioritize automating the collection of extensive data and metadata to create a rich database for analysis. 2. Integration of Mathematical and Data-Driven Approaches Two primary strategies for improving drug discovery are mathematical modeling and data-driven methods. While traditional scientific practices lean toward mathematical modeling for deeper understanding, advancements in AI highlight the effectiveness of data-driven approaches in addressing existing challenges and providing new insights into complex biological processes. 3. Transformative Role of AI AI technology plays a crucial role in drug discovery by enabling scientists to embrace data-driven methodologies that enhance problem-solving capabilities and deepen understanding of biological systems. Combining both mathematical models and data-driven techniques can lead to a more robust framework for innovation in the pharmaceutical industry.

17

21 Comments

👉🏼 ChatGPT-based meta-analysis for evaluating the temporal and spatial characteristics of deoxynivalenol contamination in Chinese wheat 🤓 Chuanzhi Jiang 👇🏻 https://lnkd.in/eDfshqdT 🔍 Focus on data insights: - 📊 Utilized a ChatGPT-assisted methodology for enhanced data screening and extraction, achieving a 20.5-fold increase in efficiency compared to manual operations. - 🌍 Conducted meta-subgroup analysis revealing significant spatiotemporal heterogeneity in deoxynivalenol

1

The risk of cardiovascular mortality increased especially when Klotho < 660.9 pg/ml, and the risk of all-cause mortality was further increased when Klotho < 568.8 pg/ml. Monitoring Klotho concentrations when below 700 pg/ml are necessary for preventing premature death in patients with CKD. #klotho

1

Negar Janani, Ph.D., Yaning Liu, Troy Butler, Erin Austin and co-authors publish "A novel application of data-consistent inversion to overcome spurious inference in genome-wide association studies" in the journal "Genetic Epidemiology". DOI: 10.1002/gepi.22563 In this article, the authors, Negar Janani, Ph.D., Kendra Young, Gregory Kinney, MPH PhD, Matt Strand, John E. Hokanson, Yaning Liu, Troy Butler, and Erin Austin, propose an assumption-free model built upon data-consistent inversion (DCI), which is a recently developed measure-theoretic framework utilized for uncertainty quantification. This proposed DCI-derived model builds a nonparametric distribution on model inputs that propagates to the distribution of observed data without the required normality assumption of residuals in the regression model. This characteristic enables the proposed DCI-derived model to cover all genetic variants without emphasizing on additivity of the classic-GWAS model. Through simulations and a replication GWAS with data from the COPDGene, the authors demonstrate the ability of this model to control the Type-I error rate at least as well as the classic-GWAS (additive linear model) approach while having similar or greater power to discover variants in different genetic modes of transmission. Find the article at: https://lnkd.in/g9w8s7Kr

18

It's all LLM training all the time now, nothing else matters 😳 "The Tahoe-100M data set is the world's largest atlas of single-cell transcriptomic data, mapping how drugs impact patient cells at scale. It comprises 100 million cells and 60,000 experiments, mapping 1,200 drug treatments across 50 different tumor models. It is larger than all public single-cell datasets combined, and 50x larger than all publicly available, drug-perturbed single-cell data put together." "The NVIDIA team will contribute machine learning and data engineering expertise to TRAIN MODELS on this data and package for use."

118

4 Comments

Thank you, Eric Topol, MD Topol, for your continued insights on this important class of drugs, which might be able to lower the incidence of obesity and, in turn, lower the incidence of chronic disease. While single and double agonists are effective in weight loss, their effectiveness tends to plateau over time, possibly due to a tolerance or resistance effect. GLP-1R agonists can effectively reduce body weight in obese patients to levels not previously achieved with anti-obesity therapies (Knerr PJ et al., Mol Metab. 2022 Sep;63:101533), the weight-lowering effect of rationally-designed, next-generation single molecule GLP-1/GIP/Gcg tritagonists is superior to that of semaglutide, tirzepatide, and other chemically and pharmacokinetically matched dual agonists. https://lnkd.in/g7qc8-bA

1

To use innovative science to do transformative good: that's what we're doing at Clene Nanomedicine, Inc.

37

3 Comments

This January, researchers and industry leaders will convene for Cambridge Healthtech Institute's Models for de novo Design conference, January 14-15 in San Diego https://lnkd.in/e7NychW3. De novo protein structure prediction methods endeavor to predict tertiary structures from sequences based on general principles around protein folding dynamics and conformational features. This unique event will feature progress in this emerging area, advancing computational models for antibody and mini-protein design, automated model generation, binding prediction and interaction models. Additionally, attendees will receive project updates on de novo designs in the clinic. In attending the forum, you will gain an understanding of the following: • Advances in in silico Antibody Structure and Dynamics Prediction • Benchmarking Studies to Validate AI Models • Deep Learning for Protein Therapeutics Optimization • Cutting-Edge Tools and Approaches for Protein Design • Integrating Functional Protein Design into Language Models At the BioLogic Summit, you will hear updates on de novo design from Prescient Design, Profluent, University of Washington, Stanford University, Xaira Therapeutics, AstraZeneca, Amgen, and many more. These sessions will provide valuable perspectives on how computational innovations, particularly those driven by AI, are making significant strides in the biotech and biopharma space, potentially leading to more rapid and cost-effective drug development. We hope to see you this January in San Diego. #antibodies #antibody #aI #ml #biotechnology #biotherapeutic #biopharmaceuticals #drugdiscovery #pharmaceutical #protein engineering

12

We support clinical researchers on a daily basis, and we know that high-quality data is essential to the success of their work - especially when collaborating across multiple research sites. However, harmonizing data collection methods and ensuring consistent quality can present significant challenges. We enjoyed having this discussion about this topic with our CSO Rym Ben Othman and Joann Diray Arce, PhD where we bring the importance of selecting compatible, scalable data platforms that can support diverse workflows across research locations, Best practices for maintaining data consistency, standardization, and integrity throughout the research lifecycle, Techniques for achieving near real-time data updates while upholding rigorous standards of participant privacy and data protection...

4

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

Today, we’re announcing a major milestone at Recursion: REC-1245 – a potentially first-in-class RBM39 degrader – has received FDA IND clearance for a Phase 1/2 clinical trial for the treatment of biomarker-enriched solid tumors and lymphoma. This is our first program to reach clinical studies derived from our AI-enabled Maps of Biology. REC-1245 represents the incredible breakthroughs made possible by our Maps, which use machine learning to explore predicted biological and chemical relationships to identify new targets. We’ll be advancing REC-1245 for the treatment of biomarker enriched solid tumors and lymphoma, and estimate that the initially addressable population for this potential therapeutic will be >100,000 patients in the US and EU5.   How did we get to REC-1245? It all started with CDK12. CDK12 is a well-validated and promising cancer target but one that has long been considered difficult to drug due to its high structural similarity to CDK13 which, if antagonized, causes significant tox. This is where our unique AI-enabled phenotypic approach comes in. By comparing morphological signatures induced by individually knocking out every human gene, we uncovered that RNA Binding Protein 39 (RBM39) seemed to have the same biological function as CDK12. We also used our AI-enabled map to find starting point molecules that inhibited RBM39, allowing us to mimic CDK12 inhibition while mitigating the toxicities associated with pan-CDK inhibitors. The preclinical data supports that RBM39 degradation induces splicing defects which downregulate DNA Damage Response (DDR) networks and cell cycle checkpoints. By leveraging our proprietary dataset, models, compute, and industrialized workflows, we’re not only driving new discoveries, but rapidly increasing the pace of discovery. We progressed REC-1245 from hit to preclinical candidate in under 18 months, more than twice the speed of industry average, and we expect the Phase 1/2 trial to initiate in Q4 2024. Very proud of this team and excited for the many new medicines to come in our future! Learn more:  https://lnkd.in/gTifXatG #techbio #ai #ml #drugdiscovery #target #cancer #cdk12 #rbm39 #automation

414

7 Comments