CEMIG: Prediction of the cis-regulatory motif using the De Bruijn graph from ATAC-seq
Wang, Y.; Li, Y.; Wang, C.; Ma, Q.; Liu, B.
Show abstract
AbstractsSequence motif discovery algorithms identify novel DNA patterns with significant biological roles, such as transcription factor (TF) binding site motifs. Chromatin accessibility data, accumulated through assay for transposase-accessible chromatin with sequencing (ATAC-seq), has enriched resources for motif discovery. However, computational efforts in ATAC-seq data analysis mainly target TF binding activity footprinting rather than motif prediction. Here, we introduce CEMIG, an algorithm predicting and characterizing TF binding sites, leveraging the De Bruijn and Hamming distance graph models. Evaluation of 129 ATAC-seq datasets from the Cistrome Data Browser suggests that CEMIG outperforms three widely used methods using four metrics. It is noteworthy that CEMIG is employed to predict cell-type-specific and shared TF motifs in GM12878 and K562 cells, facilitating comprehensive gene expression and functional genomics analysis.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- BIT: Bayesian Identification of Transcriptional Regulators from Epigenomics-Based Query Region Sets 96%
- Stripenn detects architectural stripes from chromatin conformation data using computer vision 96%
- Massively parallel reporter perturbation assay uncovers temporal regulatory architecture during neural differentiation 96%
"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.