Locally deployed AI agents for CRISPR guide discovery from outbreak reports
- 1NiagaraBio, Inc.
Abstract
Translating outbreak reports into computational work supporting diagnostic development requires biological interpretation, literature review, data retrieval, and specialized analysis. We developed a domain-specific agent harness to coordinate a CRISPR guide-discovery pipeline using locally hosted open-weight models. The agent interprets requests, reviews literature, assembles inputs, and initiates analysis; the pipeline assesses candidate guides for researcher inspection. Evaluation with Gemma 4 31B, Nemotron 3.5 Super VL, and Qwen 3.8 27B on an NVIDIA DGX Spark demonstrated completion of the computational workflow. Disease and pathogen identification were consistent across runs, while gene selection, strain coverage, and candidate yield varied. Nemotron 3.5 Super VL had the shortest reported times to evaluation. Qwen 3.8 27B applied pipeline evaluation criteria more consistently, but required longer evaluation times. The runs demonstrated the utility of smaller language models when coupled with structured bioinformatics workflows. These findings support the feasibility of locally deployed agent coordination for diagnostic research as frontier models add additional restrictions on biological tasks.
Related
- Democratizing Clinical Tumor Whole Genome Sequencing: 18-hour End-to-end Analysis via Trillion-parameter Large Language Models Locally Deployed on Consumer-grade Hardware
- Discovery and Optimization of Imidazothiazole Carboxamides as Novel Anti-Tuberculosis Agents
- Integrated Approach for the Discovery of Antifungal and Antibiofilm Agents From Cerrado Plants
- Distributed AI agents enable comprehensive discovery of biological insights at scale
- From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
BibTeX
@misc{schuler2026locally,
title = {{Locally deployed AI agents for CRISPR guide discovery from outbreak reports}},
author = {T. M. Schuler and G. A. Schuler and A. R. S. Zobel},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.20.760479},
url = {https://www.biorxiv.org/content/10.64898/2026.10.20.760479v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Locally deployed AI agents for CRISPR guide discovery from outbreak reports
AU - T. M. Schuler
AU - G. A. Schuler
AU - A. R. S. Zobel
PY - 2026
DA - 2026/10/20
PB - bioRxiv
DO - 10.64898/2026.10.20.760479
UR - https://www.biorxiv.org/content/10.64898/2026.10.20.760479v1
AB - Translating outbreak reports into computational work supporting diagnostic development requires biological interpretation, literature review, data retrieval, and specialized analysis. We developed a domain-specific agent harness to coordinate a CRISPR guide-discovery pipeline using locally hosted open-weight models. The agent interprets requests, reviews literature, assembles inputs, and initiates analysis; the pipeline assesses candidate guides for researcher inspection. Evaluation with Gemma 4 31B, Nemotron 3.5 Super VL, and Qwen 3.8 27B on an NVIDIA DGX Spark demonstrated completion of the computational workflow. Disease and pathogen identification were consistent across runs, while gene selection, strain coverage, and candidate yield varied. Nemotron 3.5 Super VL had the shortest reported times to evaluation. Qwen 3.8 27B applied pipeline evaluation criteria more consistently, but required longer evaluation times. The runs demonstrated the utility of smaller language models when coupled with structured bioinformatics workflows. These findings support the feasibility of locally deployed agent coordination for diagnostic research as frontier models add additional restrictions on biological tasks.
ER -