Bits In Bio Weekly - October 8th 2024
Updates From and Around the Bits in Bio Community
📢 Highlights
The 2024 Nobel Prize in Physics goes to seminal machine learning Scientists
ProteinAligner brings tri-modal pre-training to protein foundation models
Disgraced He Jianku returns to the lab after prison , backed by Crypto financier
Not yet a member of our super awesome slack community of >7500? Join HERE 🤗
👀 In Case You Missed it ..
Seminal Machine Learning Scientists receive 2024 Noble Prize in Phyiscs
The 2024 Nobel Prize in Physics has been awarded to Geoffrey Hinton and John Hopfield for their pioneering work in artificial intelligence and neural networks. Hinton, known as the "godfather of AI," played a critical role in developing deep learning techniques that have revolutionized machine learning. John Hopfield is recognized for creating the Hopfield network, a foundational model in understanding how neural networks can process and store information. Their contributions have laid the groundwork for major advancements in AI across various fields, including healthcare and autonomous systems, and have become increasingly relevant to biotech as AI pervades the industry.
ProteinAligner: Multi-modal Pre-training for Protein Foundation Models
While protein language models have shown success in learning protein representations, they heavily rely on pretraining with amino acid sequences, neglecting other modalities such as structure and related literature. A new pre-training framework called ProteinAligner was released by UCSD researchers, integrates 3 main modalities: sequences, structures, and literature. This tri-modal learning approach captures more biological insights and can exceed other multi-modality models like ESM on a variety of downstream tasks. ProteinAligner demonstrates higher accuracy, F1 scores, and ROC-AUC results than state-of-the-art models in tasks such as detecting type I anti-CRISPR activities and protein thermostability. Proteinaligner is flexible since it doesn’t require all modalities to be fed as data. The authors plan on incorporating other data modalities like protein-protein interactions. Their code is open-source and hosted on GitHub.
Disgraced CRISPR Scientist He Jiankui Eyes Return to Human Embryo Research
In a dramatic and divisive turn of events seemingly out of a dystopian science fiction novel, the iconoclastic geneticist, He Jiankui is back in the lab. The scientist behind the CRISPR babies scandal, plans to resume his research on human embryos after serving a 3 year prison sentence for unauthorized gene editing. Jiankui's initial work, which led to the birth of genetically modified children in 2018, sparked widespread ethical debates and cries of second wave of eugenics. Now, he alleges that he aims to focus on treating rare diseases using gene editing, though significant ethical and regulatory concerns persist. The scientific community remains divided on whether his return to research should be permitted, given the risks involved and his flaunting the law in his past work and dubious ethical footing of his financial backer, a controversial Crypto financier and alleged fraudster, Ryan Shea.
Judo Therapeutics Launches with $100M to Tackle Kidney Disease
Biotech newcomer, Judo Therapeutics, has launched with $100 million in funding to advance its pipeline of genetic medicines targeting kidney disease. The company's approach focuses on precision medicine to address genetically defined chronic kidney conditions, which represent a significant unmet medical need. The funds will support preclinical development and expand research into potential gene therapies. Investors include ARCH Venture Partners and other biotech investment heavyweights, with the goal of delivering innovative kidney disease treatments leveraging the latest and greatest in wet and dry lab methods.
Eli Lilly Backs Arda Therapeutics in $43M Series A to Pioneer ADCs for Fibrotic Diseases
San Carlos based Arda Therapeutics has raised $43 million in a Series A funding round led by Andreessen Horowitz (a16z) with participation from Eli Lilly, among others. The company aims to expand its work in developing antibody-drug conjugates (ADCs) specifically targeting fibrotic diseases by eliminating pathogenic cells driving disease progression. Arda leverages a proprietary platform that integrates single-cell data with machine learning to identify and eliminate disease-causing cell populations. The funding will be used to accelerate Arda’s preclinical pipeline, and could represent a significant step toward applying ADC technology into the fibrosis space, beyond its current applications in oncology.
BindCraft: one-shot design of functional protein binders
Researchers from EPFL, Zurich University and MIT have developed BindCraft, a tool that uses deep learning to design protein binders targeting protein-protein interactions. The tool leverages AlphaFold2, and aims at reducing the need for extensive experimental screening to make protein design accessible to smaller labs. The BindCraft pipeline claims it allows flexibility in targeting diverse protein structures, achieving success rates of 10-100% across ten challenging targets. The binders exhibit nanomolar to subnanomolar affinities with applications including cell-surface receptors, common allergens, de novo designed proteins, and multi-domain nucleases, such as CRISPR-Cas9. The team made their code available on Github along with binder design protocols. A Google Colab notebook is also available to run BindCraft directly.
City Therapeutics Secures $135M for RNAi-Based Medicine
After the appointment of John Maraganore, former Alnylam CEO and biotech legend, as a strategic advisor, City Therapeutics has announced it has raised $135 million to develop RNAi-based therapies for chronic pain, advancing ion channel modulators with support from investors like Westlake Village BioPartners. The notable addition to the team adds significant expertise in RNAi therapeutics. This funding round will accelerate City’s preclinical research and development, with their focus on ion channel modulators representing a promising new avenue in pain management.
Concentriq: Embeddings and Developer Toolkit for Pathology AI Development
Proscia, a Philadelphia-based software company specializing in AI-enabled pathology, has introduced Concentriq Embeddings for Pathology applications, and a complementary AI Toolkit. Concentriq Embeddings comprises a set of foundation models (DINOv2, PLIP, ConvNext, and CTransPath) that enables “pathology and data science teams to generate high-dimensional numerical representation embeddings from whole slide images.” The AI Toolkit is a collection of open-source resources, including a Python client, tutorials, and helper functions built to facilitate the use of the Concentriq Embeddings platform. Their code is available on Github.
$115M More for Triveni Bioscience’s Immunology and Rare Disease Pipeline
Triveni Biosciences has raised $115 million in a new financing round, less than a year after securing $92 million. Led by Goldman Sachs Alternatives, the funds will be used to advance Triveni’s pipeline, particularly in immunology and rare diseases. The biotech's rapid fundraising follows its formation through a merger of Modify Therapeutics and Amagma Therapeutics. The additional financing will help accelerate both preclinical and clinical development in their disease-targeting programs.
Lundbeck Partners with Charles River for AI-Enabled Drug Discovery
Multinational CRO, Charles River Laboratories, has been recruited into a promising collaboration with Lundbeck Partners to leverage AI-powered drug discovery for neurological diseases. The collaboration will focus on utilizing Charles River's AI capabilities to identify and optimize drug candidates for psychiatric and neurological disorders. Lundbeck hopes to accelerate its drug discovery pipeline through this partnership, with AI playing a critical role in targeting complex diseases like Alzheimer’s. The financial terms remain undisclosed, but this partnership marks another step toward AI-driven innovation in neuro drug discovery, and is noteworthy due to its foundation on a CRO partnership rather than a more traditional pharmaceutical company.
Merck Signs $1.9B Deal with Mestag for Fibroblast Therapies
The 350 year old pharma giant, Merck, has entered into a partnership with Mestag Therapeutics to develop therapies targeting fibroblasts for inflammatory diseases. The deal, valued at up to $1.9 billion, aims to leverage Mestag’s expertise in fibroblast biology to create novel treatments that target inflammation at its cellular roots. Mestag will receive an undisclosed upfront payment along with potential milestone payments tied to the success of the collaboration. This partnership underscores Merck's relentless strategic expansion into immunology and inflammation-focused treatments.
🗓️ Upcoming BiB Events
See our handy dandy Lu.ma event calendar HERE, please RSVP so folks can plan accordingly!
Seattle Fall Biotech Happy Hour – Thursday, October 10th @ Tapster
Thanks to Nermeeta Dhillon, Jag Singh, and Brenda Phansukhumthana for organizing!
San Diego Mixer – Thursday, October 10th @ The Scripps Research Institute
Thank you Robbie Matthews and Nick Edwards for organizing!
San Francisco Builder Showcase – Thursday, October 17th @ FutureHouse
Thank you Beko Jang, Eti Sinha, Shantenu Agarwal, and Nicholas Larus-Stone for organizing!
📰 Top Community Conversations
@Ever curious on how to DIY your lab automation setup? Thomas Richardson digs in!
link to post
🙋 🙏 Community Asks
Feedback: How is the Newsletter doing? We’re trying different formats/content. In case the hyperlink above didn’t get your attention, maybe a bright orange button will!
Volunteer: Want to get involved with Bits in Bio, meet new members across the community, and learn about the ecosystem? We are looking for volunteers to help us create great content and manage the community.
🏢 Job Openings
Notable postings below - over 100 more on our community job board!
Full-Stack Software Engineer at Ark Biotech
ML/Computational Biology Scientist at Kerna Labs
Part-Time Robotics Engineer at Cellular Vehicles
SEO Consultant at Ganymede
Senior Simulation Software Engineer at Ark Biotech
Sr. Marketing Manager at Automata
🙏 Thank you for being a BiB Weekly reader!
We want to deliver what matters most in Bio AI and would love your feedback on how we can do better. Please weigh in as anon here or DM me directly!
— Vince Alessi, BiB Editor in Chief