David Charlot, PhD, MSEng

And that 👉 https://lnkd.in/giNXhs-7 is why folks designing and building plasmids or strains should instead use GitLife Biotech's tech to document in full their engineering process!

19

This is fun, a pending Illumina patent (US20240158849A1) that describes a completely new way to do sequencing (surfaced by Nava Whiteford on the ASeq discord). Inventors are Rico Otto and Hayden Black. My interpretation (maybe the inventors will chime in to correct🤪): - Build a chip with pairs of electrodes on it, each pair of electrodes fitted with a circuit [160] that measures very small electrical changes (e.g. current) between the electrodes. - Assemble a long polymer bridge between the two electrodes. - Here's where it gets crazy: coat the bridge in gold 👑 so it's electrically connected at each end to an electrode, and etch the gold off the middle of the bridge (what could do wrong 😳) so there is an exposed detector [113] - Mix up a soup of bases like A [123] that have a conductive tail [133]; each base gets its own version of the tail, and each of the four tails is electrically different e.g. has a different resistance. - Send a polymerase [105] chunking along the DNA strand to be sequenced [150], incorporating bases like [123] to form a complementary strand [140] - Each time a base is incorporated into [140] its conductive tail [133] somehow (😳) flops onto the bridge detector [111] so changes the electrical properties of the bridge which can measured by the detector circuit. Easy peasy, sequencing squeezy! Patents shows some scanning tunneling microscope pictures that may or may not show this working 🤷‍♂️ Why do this? If this works in practice (big if around any sequencing technology) it's pretty cool as it's a single (maybe CMOS) chip with no light source, optical detectors, integration time, nanopore (organic or otherwise). As the investors write, it "is robust, reproducible, sensitive, accurate, works in real time, detects single molecules, and has high throughput." Anyway, nice to see there's some greenfield research going on at Illumina 👏👏👏

368

41 Comments

Al-ien Among Us... I have commented on the challenges of losing one's voice and different ways to overcome this limitation. I will briefly detail how HealthAI is integrated into a silicon (M2 or later) chip Apple product and how to use these tools to speak with your natural voice again. This time via type to speech. So how to regain your natural voice... Banking your voice is the essential step. I will outline how to do this in the Apple ecosystem in the following and illustrate it in the image. Go to Accessibility and find Personal Voice. Open and follow the instructions. By reading the phrases, Apple's AI formulates a voice image for you. After an hour or so, it will appear as a voice option. Next, go to Life Voice in Accessibility, and select your banked voice. At this time, you can write commonly used phrases and save them. Finally, to make the system really useful, make your "Action Button" pop up Live Speech when you press it in. If you do not want to dedicate the Action Button, just clink on the on/off Right button three times. The 3-click or Action Button will pull up a small typing screen and a keyboard. Type what you want to say and hit return. You should hear your voice (the banked one) speaking the words you just typed. If you do this from a lock screen, the voice may sound like Siri...but when your phone, iPad, or Mac is open, it will sound like you. Finally, your mobile devices do not project sound well. A Bluetooth speaker can be very helpful to be heard in noisy or spacious environments. Now, open Live Speech, and really "talk" to friends and family again!!!

26

3 Comments

ISoP Community. As the co-chair of this years communications committee, alongside Eleni Karatza, we have some pretty big updates so please read through this post. First and foremost, ACoP 2024 registration is open. Please see the following link (also found below): https://lnkd.in/eNZ2PAcq Note hotel reservations are open and the cut off date for group rate is October 6th. However, as always, if you plan to attend I would suggest booking sooner than later. You can reserve a room by calling 877-800-4888 or through the Reservation site here: https://lnkd.in/ea95yZQS If you haven't checked out the new ISoP website, it looks great! There is a brand new members only section with various benefits. There is a main home feed which contains content/posts from various "communities". Honestly, it feels/looks like an internal Facebook exclusive for our society (I don't mean this in a negative way). You can update your profile, connect with others, and keep up to date with ISoP events/communications. Here is the link the updated website and members section (you must have an active membership): https://lnkd.in/eDVHwgSZ Right now there is only one main community called "Members Connect Community", which contains all ISoP members and acts as a way to make a broad post to everyone. In the future, we could create ISoP SIG specific groups, alumni groups, local ISoP chapters, and others. Even individual working groups within ISoP (e.g., QSP SIG WGs) could create their own channel. Here is the link to the Member Connect Community channel: https://lnkd.in/eBZWrscu If there are any questions feel free to reach out to me directly or comment below! Happy Father's Day!

36

It was great to return to another season of CDL-Seattle's computational health stream last week. I've seen many incubators, and Creative Destruction Lab is consistently one of the best for the following reasons: 🧠 World-class mentors who have built and exited companies devote four hours every 8 weeks to work with the companies that move on. 🗣 The feedback is direct, helpful, and brutally honest. You can spend months trying to get the kind of feedback from Zoom pitches that you can get in a single day of CDL. 🏭 Streams are focused on specific industries, so there's far less general business advice and more specific feedback from someone who's built a company in your vertical. 💸 It's all equity-free, philanthropically supported, and includes an educational component for UW Foster School of Business students. ⏰ Sessions are ALWAYS on schedule, and the organizing team is amazing. Thanks to Emer Dooley, Amy Lippmann, Dhwani Patel, Cassa Hanon, and Ramzy Huneidi for running such a great session. 🏛 Last, but not least, the program brings together some of the most amazing people from the local entrepreneurial ecosystem looking to pay it forward with young companies. #startups #entrepreneurship #mentorship #education University of Washington CoMotion at University of Washington Buerk Center for Entrepreneurship

72

3 Comments

Team of Physics, Math and CS engineers are solving complex molecular biology problems in AI. Almost no biologists 👏 Chai Discovery team is excited to release Chai-1, a new multi-modal foundation model for molecular structure prediction that performs at the state-of-the-art across a variety of tasks relevant to drug discovery. Chai-1 enables unified prediction of proteins, small molecules, DNA, RNA, covalent modifications, and more. Chai-1 model achieves a 77% success rate on the PoseBusters benchmark (vs. 76% by AlphaFold3), as well as an Cα LDDT of 0.849 on the CASP15 protein monomer structure prediction set (vs. 0.801 by ESM3-98B). #Math #AI #Biology https://lnkd.in/gTJEgVBY

4

This is REVELATORY! Imagine you’re in space, looking at a black hole, a mysterious, invisible giant that gobbles up anything too close. Now, in most cases, black holes come with a close companion, like a star or another black hole, drawn into a tight, deadly embrace by the black hole’s intense gravity. But recently, scientists from MIT and Caltech seemed to have discovered something remarkable. A black hole with two companions! one nearby, which it’s slowly devouring, and another star orbiting from incredibly far away, so far it takes 70,000 years to complete just one orbit! Here’s why this is such a big deal: when black holes form, they usually explode with enough energy to push away anything in the vicinity. But here, that distant star is still hanging around, which suggests this black hole might have formed in a totally different way. Instead of exploding, it likely “gently” collapsed, pulling in on itself and becoming a black hole without the usual violent blast. This type of formation is a new idea in black hole science. This discovery not only changes our understanding of how black holes form but also gives us the first example of a black hole that may have been created in this calm, quiet way. It’s like finding a missing piece in the puzzle of black holes, hinting that the universe might be hiding more of these unusual “quietly formed” black holes. #science

12

1 Comment

Just a friendly reminder about my upcoming presentation at the #chibioprocessing summit on August 19th at 11:00 am. In this session, I'll be sharing insights on how to effectively visualize and optimize small-scale development data for large-scale perfusion processes, ultimately helping us reach our cost of goods and sustainability goals. I'm excited to discuss how combining mechanistic models with comprehensive digital factory models linked to Bayesian Optimization can help us achieve these objectives. Join me for the session titled "Evaluate and Optimize Perfusion Cell Culture in Manufacturing Using Bayesian Optimization Linked to Process Models." #continuousprocessing #processintensification #nextgenerationprocessing #processmodeling #biosolve #sustainability #processmodelevolution #optimization

58

3 Comments

I learned a new word: petavoxel I just came accross an exciting publication in Science by Alexander Shapson-Coe et al. The teams at Harvard University and Google Research, unlocked a new dimension of neural exploration with their "A petavoxel fragment of human cerebral cortex reconstructed at nanoscale resolution." The dataset is so vast, it offers a detailed roadmap of around 57,000 cells and 150 million synapses in just 1 cubic millimeter of brain tissue. To put this in perspective, the world’s largest metropolis, Tokyo, “only” has a population of approximately 40 million people! This 1.4 petabytes of data captures the brain's microstructure in previously unknown detail. https://lnkd.in/e4d8eNcz The implications are profound and uncovering the nuances of brain architecture could revolutionize treatments for conditions like epilepsy, Alzheimer's, and Parkinson's. Also, this is #OpenScience, setting a new bar for neuroscience collaborations and #innovation. Back to #petavoxel : it’s a unit of measurement of tri-dimensional pixels, a whole quadrillion of them! #TheMoreYouKnow #HappyFriday.

8

Here Goyon et al describes a novel immobilized RNase T1 and A cartridges in conjugation  with a 2D-LC-MS analysis for the online nucleotide mapping of mRNAs. 🛎Overview: Goyon et al employed for the first dimension is immobilized RNase T1 and A cartridges and the second dimension was HILIC separation which was hyphenated to MS. 🎯 Summary: With there 2D LCMS approach observed between 5.8–51.5 and 3.5–19.3%, respectively for unique digestion products, this was increased 65.6–85.6 and 69.7–85.0% using the RNase T1 and A. #massspectrometry #massspec #biopharmaceuticals #bioanalytical #biotech #science #scienceandtechnology #research #chemistry #mrna #bioprocessing #chromatography #nucleotides #rnatherapeutics #oligonucleotides #biotech #LCMS https://lnkd.in/ebDuvMf3

20

I just want to be a farmer with kittens, butterflies and animals running around! Why? Spectral leakage. Yup, it sounds innocuous, but it's a bug/condition that occurs in Fourier Neural Operators. Have you ever faced a bug that seems to grow more elusive the deeper you dig into it? I'm knee-deep in that battle after spending all of Sunday on it, and I'm still at it now. AI research is exhausting! The crux of the issue is improper windowing in the Fourier transform, which leads to spectral energy leaking into adjacent frequencies. The result is inaccurate predictions, unstable training, and a nagging sense of unease every time you rerun the model. What's gnarly about this bug is that it's invisible until it's not. No errors, no crashes, just degrading accuracy or predictions that don't quite fit. Debugging it requires an intersection of signal processing intuition, neural network know-how, and a healthy dose of patience. I've been untangling it bit by bit—implementing windowing, validating against known solutions, and questioning every decision made in the code. It’s exhausting, but I guess that’s the nature of chasing spectral ghosts in complex systems. #Kittens #Rainbows #Butterfly #AI

1

2 Comments

Struggling to find qualified histotechnologists for your lab? You’re not alone. I just wrapped up a conversation with a laboratory director from the West Coast, and he shared some real challenges his lab is facing. Like many, he’s dealing with a shortage of histotechnologists. His lab currently relies on travelers, which creates significant issues: 1.) These travelers are expensive. 2.) They often lead to quality problems. There’s a lack of local talent; the pipeline just isn’t there. So, what's the solution? International recruitment. Here’s how it can transform their pathology department. Build Your Own Pipeline: Instead of waiting for new histotechnologist to relocate to the this city you can take control and bring your own. Imagine bringing in 3 to 4 motivated histotechnologists from the Philippines who are ready to contribute to your lab. Quick Turnaround: The process can move fast. As a nonprofit, this lab can get new staff in about six months. That’s efficient and effective. Cost Efficiency: By hiring international candidates, they can eliminate the need for temporary workers, reducing costs and training time. Plus, these new hires can stay for up to six years, providing stability and continuity. In summary, now you know you can utilize International recruitment not just for medical laboratory scientist but histotechnologist as well.

16

8 Comments

A couple of announcements for ISoP Members, 1. Today (August 5th) is the last day for early bird ACoP 2024 conference registration. Please see link below to register! https://lnkd.in/eeYTx_WY 2. ISoP QSP SIG Virtual QSP Week is next week (August 12-15). My own research interests certainly bias me here, but I think this will be the best Virtual QSP Week yet! There are several talks discussing how AI/ML can be leveraged for identifying biomarkers, clustering patient populations to understand treatment response, and the use of generative AI and LLMs in QSP model development and applications. Don't forget to register and add these events to your calendar in advance (instead of trying to find the zoom link day of). The way it works is that you need to click the registration links below for each event, you will get an email, and then you need to click add the event to your calendar for each of the 4 separate webinars. Please see more information on each of webinars below. Agenda and Speakers: Session 1. 12 Aug 2024, Monday, 9 am EDT: Registration Link: https://lnkd.in/er9jeTXM AI-driven exploration of dementia biomarkers Chairs: Suruchi Bakshi, Shaina Short Presenter: Dea Gosishvili, University of Amsterdam Session 2. 13 Aug 2024, Tuesday, 9 am EDT: Registration Link: https://lnkd.in/eaxqPyf5 From molecules to systems: leveraging NEURON for multiscale modeling      Chairs: Suruchi Bakshi, Shaina Short Presenter: Robert McDougal, Yale University   Session 3. 14 Aug 2024, Wednesday 11 am EDT Registration Link: https://lnkd.in/ew2ZqusU Using multi-omics clustering and machine learning to identify key characteristics driving treatment response in SLE virtual patients       Chairs: Prakash Packrisamy, Vincent Hurez Presenter: Renee Myers, Rosa & Co. LLC Application of GenAI in QSP model development       Chairs: Prakash Packrisamy, Vincent Hurez Presenters: Anuraag Saini and Ali Farnoud, Boehringer Ingelheim Session 4. 15 Aug 2024, Thursday11 am EDT Registration Link: https://lnkd.in/ekKGdZht Large Language Model tools for QSP modeling       Chair: Carolyn Cho Presenters: Chris Rackaukas and Emily Nieves, Massachusetts Institute of Technology Link to QSP SIG Website and Virtual QSP Week: https://lnkd.in/e96SdAsh Lastly, if you have not yet checked out the new ISoP Members Community please do so. Trying to build a vibrant environment for the community to engage in conversation is extremely difficult. We are trying to figure out the features of this new application, your help is appreciated throughout this process! Link below: https://lnkd.in/eBZWrscu

5

OMG you would think I would LOVE an announcement that Illumina and NVIDIA were working together but honestly this sounds like this morning's second case of Illumina having to give up a lot to get a little. Deal has two parts: (1) Illumina's "get" is to host a bunch of Nvidia tools for LLMs and data analytics in on the Illumina Connected Analytics platform. Also MONAI for spatial cell imaging workflows though not sure what they have to do with NGS. Anyway, this seems like a nice-to-have, maybe a convenience to customers - but I don't think it opens up any new functionality. Doesn't cost Nvidia anything, and they get to add another logo on their partners slide 🤷‍♂️ (2) Illumina (this is the "give" part) will be "enabling DRAGEN algorithms on NVIDIA GPUs". Not sure why this is good for Illumina, and the PR doesn't explain this benefit at all 🤯 DRAGEN is built on a hardware architecture - FPGA - that has nothing to do with GPU at all, in fact it's kind of the opposite. So Illumina is going to have to make a major investment in porting DRAGEN to Nividia GPU for no stated benefit to Illumina. But the benefit to Nvidia is clear: they get to claim yet another customer for their already vast GPU customer base, and they get to big to displace FPGAs in Illumina instruments. Must be missing something here 🤔🤔🤔 (Don't forget to check out our JMP podcast! https://lnkd.in/gU_qpY3S)

219

29 Comments

Can Polaris become the guiding star in this drug development #rAIvolution? A recent correspondence in Nature Portfolio's Nature Machine Intelligence, led by Cas Wognum of Valence Labs and Recursion, calls for "an industry-led initiative to critically assess machine learning for real-world drug discovery." This collaborative effort is both timely and crucial for our industry's future. Here's a free copy of the paper: https://lnkd.in/eNkQGqUR The authors, representing a consortium of ten leading biotech and pharmaceutical companies, argue that despite exciting innovations, we lack standardized benchmarks and evaluation methods tailored to drug discovery's unique challenges. This gap is delaying ML adoption and potentially misleading us about real-world impact. The fact that competitors are joining forces underscores the importance of this initiative. These include: Johnson & Johnson, Bayer, Novartis, Blueprint Medicines, Merck, Nimbus Therapeutics, Pfizer, AstraZeneca, and Relay Therapeutics. Why does this matter? The challenges we face in implementing ML for drug discovery are multifaceted: • Inconsistent datasets hinder progress • High-stakes decisions require reliable methods • Current benchmarks may not reflect real-world conditions • Interdisciplinary expertise is crucial but often siloed The proposed solution is an open-science, cross-industry initiative focusing on curating representative benchmark datasets, developing rigorous evaluation guidelines, and creating open-source tools to implement best practices. We have a responsibility to bridge the gap between perceived progress and actual impact. This Polaris - Benchmarks for methods that matter effort could become our guiding star in the vast sea of data and methodologies. By pooling our expertise and resources, we can establish a fixed point of reference to guide ML innovation in our field. The question now is: how can we all contribute to this initiative? What unique insights could each of us bring to the table? Our collective expertise can chart a more accurate course for innovation, potentially revolutionizing how we approach drug development and ultimately benefiting patients worldwide. Let's start a conversation about shaping the future of ML in drug discovery. #MachineLearning #DrugDevelopment #Innovation #Biotech #Collaboration Illustration EMxMJ

20

2 Comments

Today FutureHouse released ~2,500 hard bio evals that test lab protocol design, scientific literature RAG, sequence design, figure understanding, table understanding, and more. We benchmarked against >10 independent PhD-level experts. Frontier LLMs do not yet exceed humans. Making this required setting up a large pool of experts in experimental biology - which was a big task to begin with. Next - we designed question that we believe test an LLM reasoning ability, not knowledge, and built questions across the biology accordingly. Finally - to check for contamination or training on evals - we withheld 20%. The work was done by Jon Laurent, Joseph Janizek, Michael McCanna, Michael Hammerling, Michaela Hinks, Siddharth Narayanan, Manvitha Ponnapati, and Samuel G. Rodriques Data: https://lnkd.in/gK2N3nVp Blog: https://lnkd.in/gK3q6ihn Preprint: https://lnkd.in/gdMDk7uQ

283

5 Comments

Sololearn has proven itself to be an irreplacable app for me lately in terms of microlearning. I've been using it a lot to practice coding whenever I'm away from my computer. I mean, I'm literally coding the structural skeleton of a website whenever I'm out and about. Doesn't get much better than that for a simple smartphone mobile app I reckon. A good competitor to Duolingo for language-learning during my downtime. Highly recommended. https://lnkd.in/dbehxMXj #html #webdevelopment #selflearning

9

2 Comments