Shiva Amiri

Ankit Gupta, the head of AI and Senior Director of Machine Learning Research for Ginkgo Bioworks, Inc. sits down with Amar Drawid, Ph.D. to discuss bioengineering beyond healthcare, how the company is using generative AI and large language models to accelerate bioengineering, it expects this to revolutionize the field. #bioengineering #biosecurity #generativeAI #machinelearning models #biotechnology https://lnkd.in/gv6axJE5

17

This is just incredible. Neal Ghosh's demonstration of how #VentureIQ takes deeply technical and complicated content across a range of industrial use cases and ages/stages through an AI-generated conversational podcast (a la #notebookLM) is really mind-blowing. Check out his post, below, and if you haven't seen VentureIQ, yet, let's get you set up to learn more. You can visit VentureIQ.ai or DM any of us over here to book a demo!

2

🧩 One thing we've noticed with #VentureIQ technology is how well it can distill and communicate complex technical material 🧩 Whether it's a #deeptech venture, a novel #AI application, or even a patent submission, we can quickly distill the business and strategic implications for investors...and sometimes even the founders/PIs themselves! 🤯 Based on our work so far, the tech can handle a wide array of research areas and technological sectors -- anything from blockchain algorithms to vaccine development. It handles the nuance of the field, the specific terminology, and extracts the key concepts which matter for venture-building. 🤓 To demonstrate, I took a patent I helped write with Eric Laber on reinforcement learning. I ran it through #Ventureiq to build a commercial assessment (key differentiators, target markets). Then for fun I had #NotebookLM make a podcast out of it. I've uploaded the result it here (DM me if you'd like the actual report): https://lnkd.in/eiTejsny This is more than just automation or streamlining operations - it's about unlocking clarity and insight when it was previously unattainable, and the ability to do it over and over again no matter the sector or vertical. Interested in more info? DM me so we can chat.

11

2 Comments

CRISPR and AI are redefining gene editing. Profluent and Stanford University are leading the charge with their latest breakthrough - AI-designed CRISPR models. No more time-consuming search for organisms. No more slow, resource-draining methods. Welcome to the era of AI-driven CRISPR research. AI models, steeped in protein and genomic sequences, can decode genetic patterns with ease. They create CRISPR designs that surpass traditional tools, offering precise edits and significantly reduced side effects. Meet OpenCRISPR-1. An AI-designed, error-minimizing, gene-editing powerhouse. Better yet, it's open-source. Now everyone can explore this technology, free of charge. The future of precision medicine is here. https://lnkd.in/dxt7vJBg #genomesequencing #biomarkers #aiindrugdiscovery

6

Are mini proteins the new antibodies? Mini proteins are highly stable, easy to manufacture, and very quick to design thanks to recent AI methods. Unlike mAbs, there is a large body of structural data to train machine learning models on to generate de novo mini protein binders. Of course, there are many apparent drawbacks to using mini proteins. Short half-lives can be tackled by fusing to Fc domains. Although it's not clear what the advantage over antibodies are here. The most promising approach seems to be designing binders to sites that antibodies don't recognize, e.g. intracellular targets where antibodies are too large to pass the cell membrane. Another common concern appears to be immunogenicity, I'll quote David Baker here: "The immunogenicity of designed proteins are lower than you'd expect. There have been clinical trials now of our designed cytokine mimic, and it elicited very little antibodies, and all the antiviral proteins have been in many animal system and there's no sign of any neutralizing antibody response." In unique cases such as radiopharmaceuticals (Aktis Oncology comes to mind), mini proteins' small size is a benefit, where having filtration through the kidney is quite useful. ------- David Baker's talk "The Coming of Age of De Novo Protein Design" and the Nature News feature "AI has dreamt up a blizzard of new proteins. Do any of them actually work?" shed some light onto this question as well. I wanted to highlight the multiple published protocols that generate experimentally validated, nanomolar binders to diverse targets available on Tamarind Bio below. BindCraft(Pacesa et. al.): https://lnkd.in/gXZwZxYX Automated pipeline using AlphaFold to generate binders with 10-100% experimental success rate for challenging targets such as cellular receptors, allergens, de novo designed proteins, and CRISPR-Cas9. Paper: https://lnkd.in/gS4wWZeE RFdiffusion Binder Design Pipeline(Bennet, Watson, Juergens et. al.): https://lnkd.in/erjPwnYY Combined scoring using AlphaFold and ProteinMPNN with RFdiffusion for experimentally validated high affinity binders. Paper: https://lnkd.in/gWEBsvxw

593

27 Comments

Today, we are excited to announce new investments from NVIDIA, along with Greycroft and 7wireVentures, who contributed a combined total of an additional $17 million to our Series A extension, bringing the total investment in Hippocratic AI to $137 million. Our ongoing technical collaboration with NVIDIA to develop super low-latency "Empathy Inference" paved the way for the NVentures investment - one of their first non-biotech healthcare company investments. Empathy inference will help patients to naturally build an even deeper emotional connection with Hippocratic’s voice-enabled AI agents—a vital component of the patient-provider experience. The first close of our Series A round was co-led by Premji Invest - US and General Catalyst with participation from SV Angel and Memorial Hermann Health System as well as existing investors Andreessen Horowitz (a16z Bio + Health), Cincinnati Children's, WellSpan Health, and Universal Health Services (UHS) at a $500 million valuation. Read more in our press release and the news coverage (in comment).

146

4 Comments

Loved bringing together a group of research-centric, product-minded technologists building the future of AI tonight in the 🅱️🍎, incl. product / eng leadership @ NVIDIA, Pinecone, Datadog; founding eng @ Abnormal Security, Modal, Counsel Health; applied AI @ OpenAI, Anthropic; research eng @ Meta (FAIR), Harvey, Google DeepMind; founders @ Sapien and some of NYC's greatest stealth AI co's ☄ We covered a lot of ground over 4 hours - some of the recurring themes in our conversations: - Agents:🕴Model inference is getting so much faster, which will unlock AI agents' potential. That said, agents should be trained to handle very narrow tasks, reliably, first vs. an open-ended approach many startups are attempting today - Robotics: 🤖 While the science is not there yet, the robotics market and its impact will be much bigger than LLM. The introduction of humanoids will fundamentally change how we live. That said, the U.S. is in a vulnerable position due to lack of supply chain independence, compared to rivals like China - Value creation: ✨ AI personalization is overrated as consumers mostly care about status (i.e., ‘whatever is the best’) vs. what's tailored to them. Delivering great UX is still hugely undervalued, for both enterprise and consumer use cases. Cost and reliability remain enterprise buyers' front-and-center priorities. AI can preserve endangered rare languages by documenting and creating digital archives / databases cc: our amazing sponsor Arc (Brendan Bettencourt, Erika Bricky, Eric Lo), Visible Ventures

136

5 Comments

Big healthcare AI news yesterday as Tempus AI received the first-ever CPT code for an algorithm-only analysis of previously-sequenced, laboratory developed test transcriptomic data. TLDR: AI molecular phenotyping has a new business model. The PurISTSM test uses RNA profiling to identify molecular subtypes in patients with advanced pancreatic ductal adenocarcinoma, which may inform first-line therapy selection and management. While I'm skeptical that payer balance sheets are going to solve the "who pays for healthcare AI" problem, the reimbursement pipes for clinical AI are maturing. I am surprised to see more progress for usage-based vs. performance-based models given the many challenges with FFS economics. It will be interesting to see how payers assess the "medical necessity" and therefore reimbursability of clinical AI as these models come to market. https://t.co/eLe18SmihV

420

9 Comments

There appears to be a "Superstar Effect" in healthcare and biomedical AI research right now. A small percentage of publications are truly novel methods contributions that introduce new capabilities or behaviors; whereas a majority of contemporary research publications are focused on implementation science to assess the real-world utility and performance of new methods. This dynamic seems different from prior eras, when the translational infrastructure for implementing novel AI methods was largely unavailable. While methods research often captures more attention and accolades, both types of research are critical – novel methods without implementation science lacks translatability; implementation science without novel methods lacks novelty. If our goal is to invent and deploy transformative AI methods in real-world healthcare and life sciences contexts, we ought to continue encouraging and rewarding stellar implementation science work alongside breakthrough methods development.

90

3 Comments

The fantastic BioGlyph product and the team of Fernando Garces, McClain Kressman, and Avi Peltz will enable Dotmatics Luma customers to create, enumerate, and assess of a whole host of antibody formats within a beautiful visual interface. This is a key part of the Lab-in-a-Loop concept: 1) computational simulation and ML models inform the selection of molecules, 2) those molecules are made via experiments in the wet lab, 3) results data from the wet lab are used to adapt ML models and optimize the overall process. Dotmatics Luma is at the center of this cycle, enabling scientists to orchestrate every piece while collecting all data in an open and harmonized way so it can accelerate decision-making for critical areas of research. Multispecific Antibodies (MsAbs) is one of the fastest growing of those areas. I'm very excited to see what our customers will achieve with this! https://lnkd.in/e9JpFna8

11

1 Comment

LLM Roadblocks to Discovery I'm encouraged by the great response to my latest series of posts (50k+ views) and have combined them in this white paper. Sections are: Emerging Science The Nature of Human Language Modeling Abstract Concepts Biomimetic Data Selection for Drug Discovery Leveraging Neuroscience for RWR in Biomimetic Digital Twin Ecosystems Language is a Tool of Intelligence, NOT its Source

2

LLM Roadblocks to Discovery I'm encouraged by the great response to my latest series of posts (50k+ views) and have combined them in this white paper. Sections are: Emerging Science The Nature of Human Language Modeling Abstract Concepts Biomimetic Data Selection for Drug Discovery Leveraging Neuroscience for RWR in Biomimetic Digital Twin Ecosystems Language is a Tool of Intelligence, NOT its Source

1

Dyno Therapeutics uses machine learning guided engineering of large molecular libraries to build new AAVs with: - 100x greater brain transduction - 10x improved liver detargeting - comparable production Inspired by their work, Hannah Han L. replicated a historic paper by Ogden et al, which took a look at all single-codon mutants of the AAV2 cap gene across 735 positions. She reproduced some of the key scientific results and had fun thinking about the same biological questions the Dyno team was confronted with years ago: 1/ How do mutations effect viral production? 2/ How do mutations effect biodistribution? 3/ How can we use machine learning to generate new, optimal designs? Along the way she digs into the guts of interesting visualizations and shows how to use Latch Plots — a Python-based scientific plotting framework - to answer these concrete questions.

87

4 Comments

Just a few months ago, we were training on a curated set of genetic research papers from arXiv. These LLMs have been invaluable for our internal research, empowering scientists to understand how different traits and SNP interact for a particular health objective. However, keeping pace with this ever-evolving field presents two key challenges: The data deluge: arXiv churns out thousands of new papers daily, making it impossible to constantly retrain our LLMs with the latest findings. The model release frenzy: New LLM architectures and fine-tuned models appear on platforms like Hugging Face at a dizzying rate. How can we leverage these advancements without starting from scratch every time? How do you solve this problem?: model merging! Imagine this: hundreds of specialized models, some focusing on the exact dataset we need, are readily available on Hugging Face. What if we could combine the strengths of these pre-trained models with our own, leveraging tools like "mergekit"? This powerful tool allows anyone to merge a million-dollar trained model with a specialized one on a regular 16GB CPU machine using sharding. The entire process can take as little as 30 minutes! This opens up a world of possibilities: Reduced Training Costs: Say goodbye to expensive, time-consuming retraining! Merging pre-trained models allows us to incorporate the latest advancements efficiently. Faster Innovation: By leveraging existing models, we can focus on fine-tuning and customization, accelerating our research and development cycles. Democratization of AI: Mergekit empowers researchers of all levels to tap into the power of advanced LLMs without needing access to massive compute resources. The future of LLM development is collaborative and efficient. By embracing model merging, we can unlock the full potential of this technology and accelerate scientific progress! #AI #LLMs #MachineLearning #Research

25

3 Comments

New startup launches out of stealth to offer total RNA sequencing and free Gen AI-driven data analysis copilot. Based in California and Texas, Biostate AI , the scalable biodata foundry startup has raised more than $4 million to advance its total RNA sequencing uses its patent-pending Barcode-Integrated Reverse Transcription (BIRT) technology to affordably, scalably, and comprehensively analyze all types of RNA. In contrast, traditional gene expression profiling using RNA sequencing (RNAseq) typically only captures information from messenger RNA, which accounts for less than 10% of all known RNA species. Biologically important classes of non-coding RNA include long non-coding RNAs (lncRNAs), micro RNAs (miRNAs), circular RNAs (circRNAs), and enhancer RNAs (eRNAs). Biostate AI has filed 9 pending patents on its technologies, and collaborates with a number of industry partners on new technology development, including Twist Bioscience. Biostate AI also recently exclusively in-licensed further intellectual property (IP) from the California Institute of Technology (Caltech) to expand the range of biomolecules analyzed. Subscribe to Where Tech Meets Bio (Substack Newsletter) for our weekly roundup of news in tech+bio space going out every Sunday. #biotech #startup #genAI #biopharmatrend Image credit: Biostate AI

71

12 Comments

This is the most circulated article yesterday, and rightfully so... The first straight shot by SSI Lab from Ilya Sutskever, Daniel Gross, and Daniel Levy Safety and reliability are essentially the biggest bottleneck for widespread adoption of AI… and we see so many bright startups working on trust and reliability products to solve this It will touch every company to come Question is - how will the budding trust and reliability startups work with SSI? Link Ventures #venturecapital #artificialintelligence #generativeai

19

2 Comments

Here is an idea for a new AI startup that can have significant upside potential with rapid scale: Tackling enterprise code merge and Git management problems. This has been a major challenge and I still see this issue persist. We need a fully AI managed CI/CD. Current tools are still old school. I will take 2% equity for the idea and to mentor the team/startup into a winning proposition (funding, product, market access) 😇 My back of the envelope math says this is a $5billion TAM. Yup TAM. There will be 45million human developers and probably an equal number of AI agents coding and merging code by 2030. This issue requires a ground-up rethinking and redesign. As development teams grow, codebases scale, and branching strategies become complex, the challenge of managing code merges becomes increasingly gnarly. Large teams often encounter difficult merge conflicts, review bottlenecks, and inconsistent processes. This is compounded by the need to integrate with CI/CD pipelines, automated tests, and quality checks, which can slow down development and cause significant disruptions. Also, picture an AI that learns the structure of your codebase, tracks developer patterns, and autonomously predicts where conflicts might arise, offering instant solutions before they become roadblocks as well. It could intelligently handle branching strategies, propose code changes to prevent conflicts, and streamline pull request reviews with context-aware recommendations. An AI-powered solution could optimize and automate much of this process, detecting potential conflicts early, suggesting resolutions, and streamlining reviews. With the right approach, this startup could significantly improve developer efficiency, reduce downtime, and accelerate the release cycles for large-scale enterprise teams. #startup #idea #AI

7

In the medical field, AI assists in detecting issues like irregular heart rhythms and identifying skin cancer. However, is AI’s involvement in our genome necessary? Profluent, a protein-design company established in 2022 in Berkeley, California, believes it is. #AICreated #AlterHumanDNA #GeneEditingTools #Scitke

1

In a world full of LLMs Google DeepMind quietly releases a new version of AlphaFold, a model that predicts structure and interactions of all life’s molecules (proteins, DNA, RNA, ligands) with unprecedented accuracy. For the interactions of proteins with other molecule types we see at least a 50% improvement compared with existing prediction methods. https://lnkd.in/dJkNghUY

41