EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Coala: a standard-based framework for converting CWL-described command-line tools into agentic toolsets

Qiang Hu iD, Qianqian Zhu, Hong Zhang, Tao Liu iD, Song Liu iD

Bioinformatics · 2026

DOI: 10.1093/bioinformatics/btag641 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Qiang Hu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics and Bioinformatics, Roswell Park Comprehensive Cancer Center, Buffalo, NY 14203, United States. Hauptthemen laut MEDLINE: Software, Computational Biology. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Summary Large Language Models (LLM) can orchestrate computational analyses through agentic systems, but scaling their toolsets remains a barrier because tool definitions are often hard coded into agent implementation. We developed Command-line LLM-agent Adapter (Coala), a standard-based framework that bridges the Model Context Protocol (MCP) and the Common Workflow Language (CWL). Coala turns CWL tool descriptions into MCP-compatible, LLM-accessible schemas, treating tool definitions as data rather than code. Tools are then executed in containerized environments through a generic MCP server, which separates the agent’s reasoning from tool execution. This framework improves reproducibility, reduces ongoing maintenance burden, and enables interactive access to local command-line tools through natural-language queries. Availability and implementation Coala is available at https://coala.info and is openly developed on GitHub: https://github.com/coala-info/coala.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SoftwareComputational BiologyLarge Language ModelsWorkflow

Autor:innen und Institutionen

  • Department of Biostatistics and Bioinformatics, Roswell Park Comprehensive Cancer Center, Buffalo, NY 14203, United States.

ORCID-Profile: Qiang Hu, Tao Liu, Song Liu

Zitieren

APA

Hu, Q., Zhu, Q., Zhang, H., Liu, T., & Liu, S. (2026). Coala: a standard-based framework for converting CWL-described command-line tools into agentic toolsets. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag641

Vancouver

Hu Q, Zhu Q, Zhang H, Liu T, Liu S. Coala: a standard-based framework for converting CWL-described command-line tools into agentic toolsets. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag641

BibTeX
@article{Hu2026,
  author = {Hu, Qiang and Zhu, Qianqian and Zhang, Hong and Liu, Tao and Liu, Song},
  title = {Coala: a standard-based framework for converting CWL-described command-line tools into agentic toolsets},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag641}
}
Kostenlos starten →