Aadyot Bhatnagar, an ML Scientist at Profluent Bio, discusses groundbreaking advancements in CRISPR technology, particularly the development of OpenCRISPR-1, an AI-generated protein. He explores the fascinating parallels between gene editing and software coding, highlighting how AI is revolutionizing protein design and gene editing practices. The conversation also dives into the interdisciplinary challenges faced in biotech, emphasizing the crucial collaboration between scientists and engineers. Bhatnagar shares insights on how AI is shaping the future of genetics.
Read more
AI Summary
AI Chapters
Episode notes
auto_awesome
Podcast summary created with Snipd AI
Quick takeaways
CRISPR technology enables precise gene editing akin to modifying computer code, significantly advancing treatments for genetic disorders and agriculture.
Profluent Bio's release of OpenCRISPR-1 as an open-source protein exemplifies a commitment to democratizing gene editing access and fostering collaboration.
Deep dives
Precision Gene Editing with CRISPR
CRISPR technology is revolutionizing biotechnology by allowing precise edits to genes, similar to editing computer code. This method enables researchers to modify DNA to address genetic disorders, enhance agricultural crops, and create new medical treatments. The Nobel Prize in Chemistry 2020 recognized its development, highlighting the significant advancements it presents in genetic science. As a testament to its impact, recent innovations like OpenCRISPR-1, an AI-generated protein, push the boundaries of what CRISPR can achieve in gene editing.
AI's Role in Protein Design
Artificial intelligence is effectively utilized to design proteins, as demonstrated by Profluent Bio's approach to protein generation through sequence-based modeling. This method parallels natural language processing, where proteins are understood as sequences of amino acids, enabling the creation of new CRISPR proteins highly distinct from those found in nature. By leveraging generative models like Progen2, researchers have been able to fine-tune and curate datasets specifically for CRISPR applications, leading to the discovery of superior protein candidates for gene editing. This intersection of AI and biology signifies a transformative shift toward more efficient protein engineering.
Open Source Protein Editing
Profluent Bio's decision to open-source OpenCRISPR-1 reflects a commitment to democratizing access to gene editing technologies. This initiative addresses the high costs associated with existing CRISPR therapies, which can reach millions of dollars, by making critical resources available for ethical use in research. The aim is to foster widespread research collaboration and ultimately lower costs for future medical treatments. Such transparency in the scientific community can catalyze breakthroughs in treating genetic diseases that currently lack affordable therapies.
Challenges in AI-Driven Gene Editing
The integration of machine learning into gene editing presents unique challenges, particularly regarding the complexity of biological systems and the need for extensive datasets. Selecting the optimal protein candidates from vast generated libraries poses hurdles in terms of maximizing experimental success while meeting biological criteria. Additionally, maintaining rigorous standards for model training and testing is essential to ensure reliable outputs, given the critical nature of gene editing. By utilizing property prediction models and minimizing experimental cycles, researchers aim to streamline workflows and enhance the efficiency of discovering viable therapeutic solutions.
CRISPR is a powerful tool in biotechnology that allows scientists to precisely edit genes, much like editing lines of code in a computer program. Just as developers can remove or alter specific parts of a code to fix bugs or enhance functionality, CRISPR enables researchers to modify DNA to correct genetic disorders, improve crops, or develop new treatments. The development of CRISPR-based editing was recognized by the Nobel Prize in Chemistry in 2020 awarded to Emmanuelle Charpentier and Jennifer Doudna.
Profluent Bio is an AI-first protein design company that recently developed OpenCRISPR-1, which is an AI-generated, CRISPR-like protein that does not occur in nature. Importantly, the company also released the protein and nucleic acid sequences for OpenCRISPR-1.
Aadyot Bhatnagar is an ML Scientist at Profluent Bio and previously worked at Salesforce. He joins the podcast with Sean Falconer to talk about OpenCRISPR-1 and how it was made.
Sean’s been an academic, startup founder, and Googler. He has published works covering a wide range of topics from information visualization to quantum computing. Currently, Sean is Head of Marketing and Developer Relations at Skyflow and host of the podcast Partially Redacted, a podcast about privacy and security engineering. You can connect with Sean on Twitter @seanfalconer.