Vector Space Biosciences and Oracle Develop Language Models to Advance Human Spaceflight

Vector Space Biosciences today announced that it is working with the Oracle Cloud Infrastructure (OCI) team to develop large-scale language modeling (LLM) and visualization applications to help advance space bioscience. These artificial intelligence (AI) models support the research and development of strategies against diseases associated with stressors associated with the protection and repair of the human body during spaceflight. Vector Space Biosciences aims to innovate faster by leveraging OCI’s AI-accelerated GPU clusters, optimized for deep learning and scientific computing, to develop new technologies in drug repurposing, drug design, materials design and precision medicine. Accelerate the development of new applications, including multi-omic innovations. .

For humanity to build a moon base or go to Mars, we need to understand how to protect and repair the human body during spaceflight. Spaceflight involves various stressors on the human body, such as microgravity and radiation in the form of galactic cosmic rays (GCR) and his HZE particles, the high-energy nuclear component of his GCR. These stressors wreak havoc on the human body. Vector Space Biosciences collaborates with technical and scientific collaborators including Oracle, Imperial College of London (ICL), University College London (UCL), University of California, San Diego (UCSD), IFO Rome, McGill University, and others to develop protein, pathway , drug compounds, and context-dependent hidden relationship detection between molecular sequences, leveraging advanced language modeling techniques to enable new hypotheses, insights, interpretations, and discoveries. This includes biological CubeSats launched from Vandenberg Space Force Station first to Low Earth Orbit (LEO) and then to deep space missions for the purpose of conducting biological experiments in microgravity and radiation. includes the design and development of Data are analyzed and interpreted using advanced language modeling and visualization.

Language models represent the cutting edge of AI (artificial intelligence) and ML (machine learning) today. Working with Oracle, Vector Space Biosciences can co-develop more complex, high-performance applications such as:

Correlation Matrix Dataset Builder (CMDB) API: A REST-based API that enables new ways to cluster context-sensitive known and hidden relationships [1, 2] Analyze between proteins, pathways, drug compounds and molecular sequences in real time based on the latest advances in language modeling.
Protein-Protein Interaction Network (PPIN) API: A REST-based API that can be used to generate multi-level graph networks from correlation matrix datasets. Graph networks represent context-dependent known and hidden relationships between proteins, pathways, drug compounds, and molecular sequences.

Language models and their vector representations (embeddings) are used in AI, such as AlphaFold2’s ability to predict how proteins fold based on amino acid sequences, ProteinMPNN’s ability to design entirely new proteins from scratch, and Chroma’s ‘DALL’. It is at the core of recent progress. -E 2 for Biology” and the recent release of OpenAI’s ChatGPT, a groundbreaking language model for human interaction, along with NVIDIA’s extensive work to generate, predict and understand biological data in new ways. BioNeMo, a Scaled Language Model (LLM) feature. Languages exist in many forms, from sequences of DNA/RNA, sequences of amino acids, sequences of nucleotides and molecules, to music, mathematics, software, or chemical notation. Any sequence of symbols, including human language, is a language. .

“Vector Space Biosciences is passionate about developing AI and advanced language modeling to bring significant advances in biotechnology. We are honored to support this pioneering effort,” said Karan Batta, Vice President of Product Management at OCI. . “By combining OCI with his NVIDIA computing power, Vector Space Biosciences is pushing the boundaries of AI and demonstrating its potential to test and develop critical technologies that advance space science.”

The language model will continue to be at the core of additional applications currently being developed by Vector Space Biosciences with the support of OCI. Applications span multiple industries in the life sciences, including biotechnology and drug development, and include the upcoming launch of revenue-generating biological CubeSats. The provenance and security of the correlation matrix dataset is managed through a VXV wallet-friendly API architecture that supports on-chain signed utility token transactions.

Vector Space Biosciences also leverages OCI storage, OCI compute, CPU and networking capabilities to support a data platform capable of generating over 100,000,000,000 different real-time datasets, along with MySQL database services. OCI’s bare metal computing instances powered by NVIDIA Tensor Core GPUs provide biological scientists with an HPC platform for applications that rely heavily on language modeling, machine learning, and data-intensive jobs.

About Vector Space Biosciences, Inc.

Vector Space Biosciences, Inc. (SBIO), parent company of Vectorspace AI (VXV), along with scientific collaborators, will launch a biological CubeSat to generate data on microgravity and radiation. This data will lead to the development of measures against diseases associated with stressors related to the protection and repair of the human body during spaceflight. This includes using a network of scientific data engineering pipelines to build targeted language models that generate real-time datasets that enhance artificial intelligence (AI) operations in space bioscience, biotechnology, and drug development. will be Working with leading scientific laboratories in the fields of human aging, cancer and nutrigenomics, our goal is to generate new hypotheses and Accelerating the process of new discoveries. Developing advanced large and small language modeling technology, our platform can generate over 100,000,000,000 different real-time datasets to accelerate discovery. Innovations in space bioscience will bring products and services to every industry, including financial markets, and, more importantly, new forms of precision medicine for all of humanity. For more information, visit vectorspacebio.science or spacebiodao.com.

trademark

Oracle, Java, and MySQL are registered trademarks of Oracle Corporation.