Usage and Limitations

AutoML Assistant leverages a Large Language Model (LLM) to provide guidance, suggest features, and generate Python code artifacts (including models, scripts, and notebooks). All outputs, including code and model results, should be thoroughly reviewed, validated, and interpreted by a qualified scientist or data professional before being used for critical scientific findings, clinical decisions, or deployment. DNAnexus makes no warranty as to the accuracy, completeness, or usefulness of any information or output generated by the Assistant.

Experimental Tool: This tool is intended to accelerate initial data exploration and model prototyping. It is not a substitute for standard, rigorous machine learning and statistical practices. Because this tool is experimental, this tool shall not be used for clinical diagnosis or to guide therapeutic care.

Data Responsibility: Users are solely responsible for the selection, security, and quality of the input data (Apollo Cohorts) used with the AutoML Assistant. The model's performance and output quality are directly dependent on the input data.

For a detailed breakdown of these limitations, please refer to the Comprehensive Disclaimer Appendix at the end of this section.