CACTUS

RESOURCE

Abstract

CACTUS is an innovative LLM‐based agent that combines the cognitive capabilities of large language models with domain‐specific tools. By integrating cheminformatics tools, CACTUS assists researchers in tasks such as molecular property prediction, similarity searching, and drug‐likeness assessment.
Developers:
Kumar, Neeraj [1] McNaughton, Andrew [1] Knutson, Carter [1] Varikoti, Rohith [1] Kruel, Agustin [1]
  1. Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Release Date:
2024-06-03
Project Type:
Open Source, Publicly Available Repository
Software Type:
Scientific
Licenses:
BSD 2-clause "Simplified" License
Sponsoring Org.:
Code ID:
127871
Site Accession Number:
Battelle IPID 33073-E
Research Org.:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Country of Origin:
United States

RESOURCE

Citation Formats

Kumar, Neeraj, McNaughton, Andrew, Knutson, Carter, Varikoti, Rohith, and Kruel, Agustin. CACTUS. Computer Software. https://github.com/pnnl/cactus. USDOE. 03 Jun. 2024. Web. doi:10.11578/dc.20240603.2.
Kumar, Neeraj, McNaughton, Andrew, Knutson, Carter, Varikoti, Rohith, & Kruel, Agustin. (2024, June 03). CACTUS. [Computer software]. https://github.com/pnnl/cactus. https://doi.org/10.11578/dc.20240603.2.
Kumar, Neeraj, McNaughton, Andrew, Knutson, Carter, Varikoti, Rohith, and Kruel, Agustin. "CACTUS." Computer software. June 03, 2024. https://github.com/pnnl/cactus. https://doi.org/10.11578/dc.20240603.2.
@misc{ doecode_127871,
title = {CACTUS},
author = {Kumar, Neeraj and McNaughton, Andrew and Knutson, Carter and Varikoti, Rohith and Kruel, Agustin},
abstractNote = {CACTUS is an innovative LLM‐based agent that combines the cognitive capabilities of large language models with domain‐specific tools. By integrating cheminformatics tools, CACTUS assists researchers in tasks such as molecular property prediction, similarity searching, and drug‐likeness assessment.},
doi = {10.11578/dc.20240603.2},
url = {https://doi.org/10.11578/dc.20240603.2},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20240603.2}},
year = {2024},
month = {jun}
}