Large language models complement established workflows for mechanistic model construction and refinement in systems biology

This archive contains the run records, models, results, and figure scripts of the paper “Large language models complement established workflows for mechanistic model construction and refinement in systems biology” (Dorešić et al., 2026, bioRxiv). Octomod, the workflow that produced these results, is on GitHub: https://github.com/ICB-DCM/Octomod. This archive holds what the runs produced and what the figures were made from. For the CTD and PBMC applications (Results 1 and 3) every number and every figure of the paper can be traced to a run record and re-made from here without the workflow. For the macrophage and sphingolipid applications (Results 2 and 4) it holds the run records, inputs, and models, and the figure scripts with their inputs. The material of the two agent-only analyses is in agent_only_analyses/. README.md in the archive describes the contents, the setup, and how to re-make the figures and tables.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-12
DOI
https://doi.org/10.5281/zenodo.24147166
Primary Topic
Gene Regulatory Network Analysis
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Large language models complement established workflows for mechanistic model construction and refinement in systems biology

Paul Jonas Jost, Manuel Huth, Simon Merkt, Dilan Pathirana et al.
Zenodo (CERN European Organization for Nuclear Research)
Gene Regulatory Network Analysis
preprint

Large language models complement established workflows for mechanistic model construction and refinement in systems biology

Paul Jonas Jost, Manuel Huth, Simon Merkt, Dilan Pathirana, Jan Hasenauer, Domagoj Dorešić, Lea Seep, Y. Liu, Christoph Thiele, Vincent Wieland, Carolina Alvarez-Garavito, Paula Rocio Moore Dillems
preprint en

Abstract

This archive contains the run records, models, results, and figure scripts of the paper “Large language models complement established workflows for mechanistic model construction and refinement in systems biology” (Dorešić et al., 2026, bioRxiv). Octomod, the workflow that produced these results, is on GitHub: https://github.com/ICB-DCM/Octomod. This archive holds what the runs produced and what the figures were made from. For the CTD and PBMC applications (Results 1 and 3) every number and every figure of the paper can be traced to a run record and re-made from here without the workflow. For the macrophage and sphingolipid applications (Results 2 and 4) it holds the run records, inputs, and models, and the figure scripts with their inputs. The material of the two agent-only analyses is in agent_only_analyses/. README.md in the archive describes the contents, the setup, and how to re-make the figures and tables.

Zenodo (CERN European Organization for Nuclear Research)
University of Bonn (DE), European Molecular Biology Laboratory (DE), European Molecular Biology Laboratory (DE)
Gene Regulatory Network Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon