Skip to main content Skip to main navigation


NP-BERT: A Two-Staged BERT Based Nucleosome Positioning Prediction Architecture For Multiple Species

Ahtisham Abbasi; Areeb Agha; Sheraz Ahmed; Andreas Dengel
In: BIOSTEC 2023 - 16th International Joint Conference on Biomedical Engineering Systems and Technologies - Final Program and Book of Abstracts. International Conference on Bioinformatics Models, Methods and Algorithms (BIOINFORMATICS-2023), located at BIOSTEC 2023, February 16-18, Lisbon, Portugal, Pages 175-187, SCITEPRESS, 2/2023.


Nucleosomes are complexes of histone and DNA base pairs in which DNA is wrapped around histone proteins to achieve compactness. Nucleosome positioning is associated with various biological processes such as DNA replication, gene regulation, DNA repair, and its dysregulation can lead to various diseases such as sepsis, and tumor. Since nucleosome positioning can be determined only to a limited extent in wet lab experiments, vari- ous artificial intelligence-based methods have been proposed to identify nucleosome positioning. Existing pre- dictors/tools do not provide consistent performance, especially when evaluated on 12 publicly available bench- mark datasets. Given such limitation, this study proposes a nucleosome positioning predictor, namely NP- BERT. NP-BERT is extensively evaluated in different settings on 12 publicly available datasets from 4 differ- ent species. Evaluation results reveal that NP-BERT achieves significant performance on all datasets, and beats state-of-the-art methods on 8/12 datasets, and achieves equivalent performance on 2 datasets.