Revolutionizing Therapeutics: The Launch of Trillion Gene Atlas Aimed at AI-Driven Medicine
Basecamp Research, an innovative AI lab focused on biological design, has recently unveiled its ambitious project: the Trillion Gene Atlas. This groundbreaking initiative aims to revolutionize the realm of medicine by vastly expanding the genomic data available for AI-driven therapeutic design. By collecting genetic information from over 100 million species across thousands of locations, the Atlas will enhance our understanding of evolutionary genetic diversity by a factor of 100. The project is powered by state-of-the-art technology from partner organizations like Anthropic, Ultima Genomics, PacBio, and the advanced computing infrastructure provided by NVIDIA.
Unveiled at prestigious events such as SXSW in Austin and the NVIDIA GTC conference in San Jose, the Trillion Gene Atlas seeks to overcome the limitations of current biological AI models which primarily rely on a narrow slice of known life on Earth. Glen Gowers, the co-founder and CEO of Basecamp Research, expressed that the Atlas significantly broadens the genetic universe beyond traditional public databases, establishing a novel framework for programmable therapeutic design.
Furthermore, the Trillion Gene Atlas aligns with similar ambitions seen in large-scale projects like the Human Genome Project. It taps into a growing network of global biodiversity partners to achieve its goal of essentially providing AI systems with the diverse training data necessary to learn from evolution for on-demand medicine design.
One of the critical challenges in AI drug development is the availability of diverse biological data. With current foundational models primarily sourced from public repositories that are limited in scale, Basecamp Research’s EDEN foundation models circumvent this barrier by relying on BaseData™, a proprietary genomic database boasting over ten times the volume of all public resources put together. The ADEN models demonstrate how larger, more diverse data sets can unlock new laws of scaling, allowing AI to effectively design therapeutics for various diseases and treatment types. Through these advancements, EDEN has become a pioneering model, achieving success in generating therapeutics from mere disease prompts.
The Trillion Gene Atlas is taking this methodology a step further by incorporating even more genomic data into what has been dubbed the 'internet of biology.' Phil Lorenz, Chief Technology Officer at Basecamp Research, emphasizes that simply building larger models isn't a solution; it requires high-quality, well-contextualized data for effective outcomes.
Over the past six years, the collaborative efforts of Basecamp Research have encompassed a substantial network of scientific partners hailing from 31 countries. This collaboration focuses on creating scalable evolutionary genomics pipelines specifically designed for AI training. The partnerships enhance not only the capacity for high-quality genomic data collection but also promote local capacity building while ensuring equitable Access and Benefit-Sharing agreements.
The cutting-edge sequencing involved in the Trillion Gene Atlas is made possible by the advances in ultra-high-throughput sequencing from Ultima Genomics and PacBio, which can deliver high accuracy long reads necessary for powering advanced AI algorithms. Gilad Almogy, founder and CEO of Ultima Genomics, indicated that the UG200 Series sequencers contribute significantly to generating the expansive datasets required for this ambitious project. Similarly, PacBio’s HiFi sequencing ensures that the complete genomic context is maintained, allowing for exceptional detail in complex biological samples.
Through its collaboration with NVIDIA, processing high-volume genetic data – termed petabase – will be greatly accelerated. The innovative use of technology aims to compress tasks that traditionally would require more than two decades into under two years, further bolstering the efficiency of data analysis and therapeutic design.
In addition to the technical components, the collaborative effort brings in Anthropic’s capabilities, merging advanced AI reasoning with Basecamp's therapeutic design framework. This partnership aims to leverage Claude, an advanced reasoning AI, to help transform complex clinical data into actionable therapeutic insights.
The Trillion Gene Atlas is not just a scientific endeavor but a monumental step towards reshaping the future of drug design. By increasing the evolutionary data available to AI systems, Basecamp Research is keen on expediting therapeutic development processes, particularly in emerging fields such as gene therapy and combatting antibiotic resistance. Ultimately, this initiative is poised to turn vast datasets into tangible medical advancements, marking a new chapter in the integration of AI and biology for improved healthcare outcomes.
Unveiled at prestigious events such as SXSW in Austin and the NVIDIA GTC conference in San Jose, the Trillion Gene Atlas seeks to overcome the limitations of current biological AI models which primarily rely on a narrow slice of known life on Earth. Glen Gowers, the co-founder and CEO of Basecamp Research, expressed that the Atlas significantly broadens the genetic universe beyond traditional public databases, establishing a novel framework for programmable therapeutic design.
Furthermore, the Trillion Gene Atlas aligns with similar ambitions seen in large-scale projects like the Human Genome Project. It taps into a growing network of global biodiversity partners to achieve its goal of essentially providing AI systems with the diverse training data necessary to learn from evolution for on-demand medicine design.
One of the critical challenges in AI drug development is the availability of diverse biological data. With current foundational models primarily sourced from public repositories that are limited in scale, Basecamp Research’s EDEN foundation models circumvent this barrier by relying on BaseData™, a proprietary genomic database boasting over ten times the volume of all public resources put together. The ADEN models demonstrate how larger, more diverse data sets can unlock new laws of scaling, allowing AI to effectively design therapeutics for various diseases and treatment types. Through these advancements, EDEN has become a pioneering model, achieving success in generating therapeutics from mere disease prompts.
The Trillion Gene Atlas is taking this methodology a step further by incorporating even more genomic data into what has been dubbed the 'internet of biology.' Phil Lorenz, Chief Technology Officer at Basecamp Research, emphasizes that simply building larger models isn't a solution; it requires high-quality, well-contextualized data for effective outcomes.
Over the past six years, the collaborative efforts of Basecamp Research have encompassed a substantial network of scientific partners hailing from 31 countries. This collaboration focuses on creating scalable evolutionary genomics pipelines specifically designed for AI training. The partnerships enhance not only the capacity for high-quality genomic data collection but also promote local capacity building while ensuring equitable Access and Benefit-Sharing agreements.
The cutting-edge sequencing involved in the Trillion Gene Atlas is made possible by the advances in ultra-high-throughput sequencing from Ultima Genomics and PacBio, which can deliver high accuracy long reads necessary for powering advanced AI algorithms. Gilad Almogy, founder and CEO of Ultima Genomics, indicated that the UG200 Series sequencers contribute significantly to generating the expansive datasets required for this ambitious project. Similarly, PacBio’s HiFi sequencing ensures that the complete genomic context is maintained, allowing for exceptional detail in complex biological samples.
Through its collaboration with NVIDIA, processing high-volume genetic data – termed petabase – will be greatly accelerated. The innovative use of technology aims to compress tasks that traditionally would require more than two decades into under two years, further bolstering the efficiency of data analysis and therapeutic design.
In addition to the technical components, the collaborative effort brings in Anthropic’s capabilities, merging advanced AI reasoning with Basecamp's therapeutic design framework. This partnership aims to leverage Claude, an advanced reasoning AI, to help transform complex clinical data into actionable therapeutic insights.
The Trillion Gene Atlas is not just a scientific endeavor but a monumental step towards reshaping the future of drug design. By increasing the evolutionary data available to AI systems, Basecamp Research is keen on expediting therapeutic development processes, particularly in emerging fields such as gene therapy and combatting antibiotic resistance. Ultimately, this initiative is poised to turn vast datasets into tangible medical advancements, marking a new chapter in the integration of AI and biology for improved healthcare outcomes.
Topics Health）
【About Using Articles】
You can freely use the title and article content by linking to the page where the article is posted.
※ Images cannot be used.
【About Links】
Links are free to use.