ChatGEM: An Agentic Architecture Enabling Interactive Simulation of Genome-Scale Metabolic Models
Chowdhury, N.; George, A.; Purohit, S.; Contolesi, A.; Bredeweg, E. L.; Czajka, J.; Stratton, K. G.; Gao, Y.; Stephenson, M.; Elmore, J. R.; Scott, A.; Leach, D. T.; Jerger, A.; Lemmon, T.; Piehowski, P.; Tate, K.; Fulcher, J. M.; Beliaev, A.; Burnum-Johnson, K.; Rigor, P.; Bardhan, J.
Show abstract
Genome-scale metabolic models (GEMs) are powerful tools for predicting cellular phenotypes and guiding microbial strain engineering, yet broad adoption remains challenging due to the computational expertise required. To overcome that, we present ChatGEM, an agentic platform that enables interactive GEM simulation through natural language. Built on the multi-agent ADEPT framework, ChatGEM integrates COBRApy within a retrieval-augmented generation (RAG) architecture that coordinates code generation and execution through specialized agents. Benchmarking across three tasks of increasing complexity showed that RAG-enabled code generation improved the mean overall performance score from 2.63 to 4.20 while reducing the execution time significantly starting from routine to complex tasks. Application of ChatGEM using an enzyme-constrained GEM (ecGEM) for four engineered Pseudomonas putida KT2440 strains identified the constitutive strain as the optimal chassis for succinate overproduction using a succinate leakage index - a prediction observed experimentally. Therefore, ChatGEM democratizes metabolic modeling by enabling researchers without computational expertise to perform sophisticated GEM-based analyses through natural language, and, hence, accelerating scientific discovery.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Reconstructor: A COBRApy compatible tool for automated genome-scale metabolic network reconstruction with parsimonious flux-based gap-filling 93%
- DeepES: Deep learning-based enzyme screening to identify orphan enzyme genes 93%
- Predicting the subcellular location of prokaryotic proteins with DeepLocPro 92%
Similar papers in this journal
- A computational toolbox to investigate the metabolic potential and resource allocation in fission yeast 94%
- Minimization of proteome reallocation explains metabolic transition in hierarchical utilization of carbon sources 94%
- Gempipe: a tool for drafting, curating and analyzing pan and multi-strain genome-scale metabolic models. 93%
Similar papers in this journal
- Guiding the Refinement of Biochemical Knowledgebases with Ensembles of Metabolic Networks and Machine Learning 95%
- APOLLO: A genome-scale metabolic reconstruction resource of 247,092 diverse human microbes spanning multiple continents, age groups, and body sites 91%
- Deciphering the Signaling Network Landscape of Breast Cancer Improves Drug Sensitivity Prediction 90%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.