San Diego-based Nanome, a startup that allows scientists to understand 3D molecular structures in virtual reality, has announced the launch of MARA, a generative AI copilot. MARA serves as an assistant for chemists working in biopharma research and development, providing critical insights and executing routine cheminformatics tasks.
MARA, available through a ChatGPT-like web interface, uses large language models and access to real-time internal data and molecular simulation systems to provide meaningful answers to scientific queries in a conversational tone. It can retrieve data from various sources, perform data analysis and simulations, and provide clear answers alongside system observability.
Keita Funakawa, co-founder of Nanome, explains, “Over time, MARA will be integrated into Nanome’s XR (AR/VR Platform) with various modalities such as voice, eye tracking, gestures/hand tracking, and text-based input.”
Enhanced Research Capabilities with MARA
MARA’s capabilities range from exploring, preparing, and rectifying molecular file formats to performing complex multi-step processes across diverse tools and databases. It empowers chemists by providing them with the expertise of data scientists and enabling them to explore new theories and ideas, thereby accelerating the research process.
MARA’s platform also allows organizations to wire in custom molecular simulation tools, databases, electronic lab notebooks, and more, in an easy and secure way. It supports on-premise with open-source language models such as Llama v2, as well as integration with cloud foundation model providers like OpenAI’s GPT models.
“The MARA Platform enables organizations to wire in custom molecular simulation tools, databases, electronic lab notebooks, and more in an easy and secure way… Clear visibility into the reasoning and tools also instills scientific confidence in not just the outcome of the answers but also how the MARA responds,” said Funakawa.
Positive Reception and Future Plans
While Nanome did not disclose the number of organizations currently using MARA, leading pharmaceutical companies have started utilizing the AI copilot. The reception from chemists and biologists during testing has been overwhelmingly positive, with one former director of medicinal chemistry stating that MARA could save chemists weeks of time and open new abilities for SAR analysis.
Currently, Nanome is focused on optimizing the MARA experience for biopharma R&D. However, the company has plans to bring the assistant to its VR platform and expand its capabilities to work with genetics data, clinical data, material science data, and data from other scientific disciplines. Funakawa emphasizes the importance of transparency, accountability, and aligning the AI with user needs to gain trust and widespread adoption.
