From code to natural language: MErlin - a multiomics toolkit for bacterial epigenomics delivered as Claude agent skill.
- 1University of Florence
Abstract
Interpreting a bacterial methylome is a multi-omics problem. It requires integrating modified-base calls with genome annotation, motif inventories, methyltransferase genotypes, transcript abundance, replichore position and, increasingly, chromosome conformation. These data types are commonly generated in incompatible formats, use inconsistent sequence and gene identifiers, and originate from different analytical workflows. The relevant algorithms are available, but assembling them into a coherent and statistically defensible analysis remains a substantial data-integration and interface problem. We present MErlin (Methylation-driven Expression & Regulation Linkage in Interacting Nuclear-domains), a multi-omics toolkit comprising seventeen composable modules, from basecalled modBAM files to ranked gene-level evidence and a self-contained HTML report. MErlin is distributed both as a conventional Python package and as an agent skill: a structured, version-controlled layer of procedural knowledge that enables a compatible large language model (LLM) assistant to select and operate the audited package without generating a new analysis implementation for each request. This design treats natural language as an interface to fixed analytical operations rather than as a substitute for tested scientific software. The skill encodes module-selection rules, mandatory preflight checks, questions that require human input, design-to-inference constraints, and interpretation guidance. We describe MErlin's architecture and statistics, validate it against a synthetic dataset with planted ground truth, and illustrate the conversational interface on a real methylome-transcriptome comparison in Pseudoalteromonas haloplanktis TAC125. MErlin is open source and available at https://github.com/IacopoPasseri/MErlin
Related
- Heritable variation in root bacterial microbiomes alters natural selection on host plants
- The global evolutionary dynamics of natural capsule switching in a human-restricted bacterial pathogen
- A natural depsipeptide antibiotic binds the E-site of the bacterial ribosome
- Word-Class and Construction-Like Structure Emerges in Neural Successor Representations Trained on Natural Language
- ScProteoAgent enables natural-language-driven single-cell proteomics analysis and interpretation
BibTeX
@misc{passeri2026from,
title = {{From code to natural language: MErlin - a multiomics toolkit for bacterial epigenomics delivered as Claude agent skill.}},
author = {I. Passeri and S. Pety and M. Giovannini and M. Fondi and A. Mengoni and E. Perrin},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.02.748773},
url = {https://www.biorxiv.org/content/10.64898/2026.09.02.748773v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - From code to natural language: MErlin - a multiomics toolkit for bacterial epigenomics delivered as Claude agent skill.
AU - I. Passeri
AU - S. Pety
AU - M. Giovannini
AU - M. Fondi
AU - A. Mengoni
AU - E. Perrin
PY - 2026
DA - 2026/09/02
PB - bioRxiv
DO - 10.64898/2026.09.02.748773
UR - https://www.biorxiv.org/content/10.64898/2026.09.02.748773v1
AB - Interpreting a bacterial methylome is a multi-omics problem. It requires integrating modified-base calls with genome annotation, motif inventories, methyltransferase genotypes, transcript abundance, replichore position and, increasingly, chromosome conformation. These data types are commonly generated in incompatible formats, use inconsistent sequence and gene identifiers, and originate from different analytical workflows. The relevant algorithms are available, but assembling them into a coherent and statistically defensible analysis remains a substantial data-integration and interface problem. We present MErlin (Methylation-driven Expression & Regulation Linkage in Interacting Nuclear-domains), a multi-omics toolkit comprising seventeen composable modules, from basecalled modBAM files to ranked gene-level evidence and a self-contained HTML report. MErlin is distributed both as a conventional Python package and as an agent skill: a structured, version-controlled layer of procedural knowledge that enables a compatible large language model (LLM) assistant to select and operate the audited package without generating a new analysis implementation for each request. This design treats natural language as an interface to fixed analytical operations rather than as a substitute for tested scientific software. The skill encodes module-selection rules, mandatory preflight checks, questions that require human input, design-to-inference constraints, and interpretation guidance. We describe MErlin's architecture and statistics, validate it against a synthetic dataset with planted ground truth, and illustrate the conversational interface on a real methylome-transcriptome comparison in Pseudoalteromonas haloplanktis TAC125. MErlin is open source and available at https://github.com/IacopoPasseri/MErlin
ER -