Leveraging human-trained neural networks for cross-species chromatin regulation annotations
Abstract
Analogous to the Encyclopedia of DNA Elements (ENCODE) project, the Functional Annotation of ANimal Genomes (FAANG) consortium has produced chromatin annotations for domesticated animals, albeit in smaller amounts. Although acquiring experimental data is more accessible and affordable for many species, human and mouse organisms will remain the reference. Classical methods based on sequence conservation can be used to infer missing annotations, but are inappropriate for non-conserved sequences. While regulatory sequences share low to moderate conservation, they have retained their regulatory function during the evolution process. Here, we take advantage of three neural networks (DeepBind, DeepSEA, and Enformer) trained with human and mouse ENCODE data to infer chromatin annotations (transcription factors binding, chromatin accessibility, and histone marks) in cattle, pig, chicken, and European seabass. For this purpose, we comprehensively assessed the quality of predictions using experimental data from FAANG, through AUC-ROC and AUC-PR metrics. Our results showed low variability between tissues and similar performances for various annotations in mammals and chicken, with AUC-PR ranging from 0.663 ± 0.010 (chicken) to 0.765 ± 0.009 (pig) for the best predicted experiment, H3K4me3 (all tissues grouped), but lower (0.238 ± 0.005) in fish. Further analyses focused on pigs highlighted (i) accurate predictions even for non-conserved sequences, and (ii) variable predictions depending on genomic feature annotations. Our results advocate the widespread use of human-trained neural networks as a first step in cross-species genome annotation before training species-specific models.
Related
- TIME FOR COFFEE coordinates phase separation and chromatin regulation for salt tolerance
- Microtubule-dependent regulation of chromatin dynamics by the Smc5/6 complex
- Hierarchical chromatin polyvalency governs robust gene regulation and organogenesis
- NAD Metabolism Drives CTCF-Cohesin Chromatin Regulation in EBV-Transformed B-Cells
- Integration of ATAC- and RNA-sequencing identifies chromatin and transcriptomic signatures in classical and non-classical zebrafish osteoblasts and indicates mechanisms of entpd5a regulation
BibTeX
@article{maillard2026leveraging,
title = {{Leveraging human-trained neural networks for cross-species chromatin regulation annotations}},
author = {Noémien Maillard and Julie Demars and Raphaël Mourad},
journal = {G3},
year = {2026},
month = sep,
doi = {10.1093/g3journal/jkag230},
url = {https://hal.inrae.fr/hal-05744249v2},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Leveraging human-trained neural networks for cross-species chromatin regulation annotations
AU - Noémien Maillard
AU - Julie Demars
AU - Raphaël Mourad
PY - 2026
DA - 2026/09/02
JO - G3
DO - 10.1093/g3journal/jkag230
UR - https://hal.inrae.fr/hal-05744249v2
AB - Analogous to the Encyclopedia of DNA Elements (ENCODE) project, the Functional Annotation of ANimal Genomes (FAANG) consortium has produced chromatin annotations for domesticated animals, albeit in smaller amounts. Although acquiring experimental data is more accessible and affordable for many species, human and mouse organisms will remain the reference. Classical methods based on sequence conservation can be used to infer missing annotations, but are inappropriate for non-conserved sequences. While regulatory sequences share low to moderate conservation, they have retained their regulatory function during the evolution process. Here, we take advantage of three neural networks (DeepBind, DeepSEA, and Enformer) trained with human and mouse ENCODE data to infer chromatin annotations (transcription factors binding, chromatin accessibility, and histone marks) in cattle, pig, chicken, and European seabass. For this purpose, we comprehensively assessed the quality of predictions using experimental data from FAANG, through AUC-ROC and AUC-PR metrics. Our results showed low variability between tissues and similar performances for various annotations in mammals and chicken, with AUC-PR ranging from 0.663 ± 0.010 (chicken) to 0.765 ± 0.009 (pig) for the best predicted experiment, H3K4me3 (all tissues grouped), but lower (0.238 ± 0.005) in fish. Further analyses focused on pigs highlighted (i) accurate predictions even for non-conserved sequences, and (ii) variable predictions depending on genomic feature annotations. Our results advocate the widespread use of human-trained neural networks as a first step in cross-species genome annotation before training species-specific models.
SN - 2160-1836
ER -