Code for the paper "Modeling nascent transcription from chromatin landscape and structure"
Fuente:
Zenodo
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Recurso digital |
| Langue: | anglais |
| Publié: |
Zenodo
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866901765752881152 |
|---|---|
| author | Pielies Avelli, Marc Sigurdsson, Arnor Ollé López, Joaquim Narita, Takeo choudhary, chunaram Krietenstein, Nils Rasmussen, Simon |
| author_facet | Pielies Avelli, Marc Sigurdsson, Arnor Ollé López, Joaquim Narita, Takeo choudhary, chunaram Krietenstein, Nils Rasmussen, Simon |
| contents | <p><strong>Abstract:</strong><br><br>Different cell types and their associated functionalities can emerge from a single genomic sequence when certain regions are expressed while others remain silenced. The study of gene regulation and its potential malfunctioning in different cellular contexts is hence pivotal to understand both development and disease. We present the Chromatin Landscape and Structure to Expression Regressor (CLASTER), an epigenetic-based deep neural network that can integrate different data modalities describing the chromatin landscape and its 3D structure in their raw format. CLASTER effectively translates them into nascent transcription levels measured by EU-seq at a kilobasepair resolution. Our predictions reached a Pearson correlation with targets above r=0.86 at both bin and gene levels, without relying on DNA sequence nor explicitly extracted chromatin features. The model mostly used the information found within 10 kbp of the predicted locus to perform the predictions, even when a wide genomic region of 1 Mbp was available. Explicit modeling of long-range interactions using multi-headed attention and high-resolution chromatin contact maps had little impact on model performance, despite the model correctly identifying elements in these inputs influencing nascent transcription. The trained model then served as a platform to predict the transcriptional impact of simulated epigenetic silencing perturbations. Our results point towards a rather local, integrative and combinatorial paradigm of gene regulation, where changes in the chromatin environment surrounding a gene shape its context-specific transcription. We conclude that the predominant locality and limitations of current machine learning approaches might emerge as a genuine signature of genomic organization, having broad implications for future modeling approaches.<br><br><strong>Github repository:<br></strong><a href="https://github.com/RasmussenLab/CLASTER">https://github.com/RasmussenLab/CLASTER</a></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15102113 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Code for the paper "Modeling nascent transcription from chromatin landscape and structure" Pielies Avelli, Marc Sigurdsson, Arnor Ollé López, Joaquim Narita, Takeo choudhary, chunaram Krietenstein, Nils Rasmussen, Simon Biomedical Research Deep Learning <p><strong>Abstract:</strong><br><br>Different cell types and their associated functionalities can emerge from a single genomic sequence when certain regions are expressed while others remain silenced. The study of gene regulation and its potential malfunctioning in different cellular contexts is hence pivotal to understand both development and disease. We present the Chromatin Landscape and Structure to Expression Regressor (CLASTER), an epigenetic-based deep neural network that can integrate different data modalities describing the chromatin landscape and its 3D structure in their raw format. CLASTER effectively translates them into nascent transcription levels measured by EU-seq at a kilobasepair resolution. Our predictions reached a Pearson correlation with targets above r=0.86 at both bin and gene levels, without relying on DNA sequence nor explicitly extracted chromatin features. The model mostly used the information found within 10 kbp of the predicted locus to perform the predictions, even when a wide genomic region of 1 Mbp was available. Explicit modeling of long-range interactions using multi-headed attention and high-resolution chromatin contact maps had little impact on model performance, despite the model correctly identifying elements in these inputs influencing nascent transcription. The trained model then served as a platform to predict the transcriptional impact of simulated epigenetic silencing perturbations. Our results point towards a rather local, integrative and combinatorial paradigm of gene regulation, where changes in the chromatin environment surrounding a gene shape its context-specific transcription. We conclude that the predominant locality and limitations of current machine learning approaches might emerge as a genuine signature of genomic organization, having broad implications for future modeling approaches.<br><br><strong>Github repository:<br></strong><a href="https://github.com/RasmussenLab/CLASTER">https://github.com/RasmussenLab/CLASTER</a></p> |
| title | Code for the paper "Modeling nascent transcription from chromatin landscape and structure" |
| topic | Biomedical Research Deep Learning |
| url | https://doi.org/10.5281/zenodo.15102113 |