ToxPipe: integrating AI into toxicoinformatics
6 affiliations
- 1Predictive Toxicology Branch (PTB), National Institute of Environmental Health Science (NIEHS), National Institutes of Health (NIH), Durham, NC, United States
- 2Axle Informatics, North Bethesda, MD, United States
- 3Dynanet Corporation, Elkridge, MD, United States
- 4Office of Data Science (ODS), NIEHS, NIH, Durham, NC, United States
- 522nd Century Technologies, McLean, VA, United States
- 6GAP Solutions, Herndon, VA, United States
Abstract
ToxPipe is a modular, fully open-source software stack designed to accelerate toxicological data analysis and decision-making by integrating large language model (LLM) capabilities with workflow, monitoring, and user-interface services. ToxPipe leverages existing open-source technologies like LibreChat, LiteLLM, and Langflow to provide centralized and streamlined access to different LLMs for end users and developers and logging and auditing of LLM use for organizations. ToxPipe also allows for open-source/local model support. While the ToxPipe ecosystem also supports advanced AI functions such as MCP server integration, RAG and literature search, and agent creation, we did not observe clear benefits using these configurations relative to the GPT-5.5 baseline assertion coverage scores. ToxPipe is available as a series of Docker containers for rapid and reproducible deployment.
Related
- Hybrid risk scores integrating polygenic and clinical variables for endometriosis prediction
- The importance of integrating evolutionary–developmental perspectives into One Health approaches
- Personalizing Inhaled Therapy in COPD and Asthma: Integrating Drug, Device, and Patient Factors
- Editorial: Innovating public mental health: integrating digital therapeutics for comprehensive mood disorder management
- Integrating emergency medical services and hospital surge capacity for mass-gathering preparedness: a structured narrative review
BibTeX
@article{combs2026toxpipe,
title = {{ToxPipe: integrating AI into toxicoinformatics}},
author = {Parker K. Combs and Parker K. Combs and Trey O. Saddler and Trey O. Saddler and Amlan Talukder and Amlan Talukder and Jonathon F. Fleming and Jonathon F. Fleming and Jeremy N. Erickson and David M. Reif and Charles P. Schmitt and Scott S. Auerbach},
journal = {Frontiers in Toxicology},
year = {2026},
month = oct,
doi = {10.3389/ftox.2026.1907845},
url = {https://doi.org/10.3389/ftox.2026.1907845},
note = {CC BY},
}
RIS
TY - JOUR
TI - ToxPipe: integrating AI into toxicoinformatics
AU - Parker K. Combs
AU - Parker K. Combs
AU - Trey O. Saddler
AU - Trey O. Saddler
AU - Amlan Talukder
AU - Amlan Talukder
AU - Jonathon F. Fleming
AU - Jonathon F. Fleming
AU - Jeremy N. Erickson
AU - David M. Reif
AU - Charles P. Schmitt
AU - Scott S. Auerbach
PY - 2026
DA - 2026/10/23
JO - Frontiers in Toxicology
DO - 10.3389/ftox.2026.1907845
UR - https://doi.org/10.3389/ftox.2026.1907845
AB - ToxPipe is a modular, fully open-source software stack designed to accelerate toxicological data analysis and decision-making by integrating large language model (LLM) capabilities with workflow, monitoring, and user-interface services. ToxPipe leverages existing open-source technologies like LibreChat, LiteLLM, and Langflow to provide centralized and streamlined access to different LLMs for end users and developers and logging and auditing of LLM use for organizations. ToxPipe also allows for open-source/local model support. While the ToxPipe ecosystem also supports advanced AI functions such as MCP server integration, RAG and literature search, and agent creation, we did not observe clear benefits using these configurations relative to the GPT-5.5 baseline assertion coverage scores. ToxPipe is available as a series of Docker containers for rapid and reproducible deployment.
SN - 2673-3080
ER -