Neural network facilitated ab initio derivation of linear formula: A case study on formulating the relationship between DNA motifs and gene expression
Liu, C.; Wang, W.
Show abstract
Developing models with high interpretability and even deriving formulas to quantify relationships between biological data is an emerging need. We propose here a framework for ab initio derivation of sequence motifs and linear formula using a new approach based on the interpretable neural network model called contextual regression model. We showed that this linear model could predict gene expression levels using promoter sequences with a performance comparable to deep neural network models. We uncovered a list of 300 motifs with important regulatory roles on gene expression and showed that they also had significant contributions to cell-type specific gene expression in 154 diverse cell types. This work illustrates the possibility of deriving formulas to represent biology laws that may not be easily elucidated. (https://github.com/Wang-lab-UCSD/Motif_Finding_Contextual_Regression)
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- DeepCORE: An interpretable multi-view deep neural network model to detect co-operative regulatory elements 96%
- Gra-CRC-miRTar: The pre-trained nucleotide-to-graph neural networks to identify potential miRNA targets in colorectal cancer 95%
- Dissecting the binding mechanisms of transcription factors to DNA using a statistical thermodynamics framework. 93%
Similar papers in this journal
- Mixing features of transcription factors and genes enables accurate prediction of gene regulation relationships for unknown transcription factors 95%
- A Comprehensive Evaluation of Self Attention for Detecting Regulatory Feature Interactions 94%
- Genomic background sequences systematically outperform synthetic ones in de novo motif discovery for ChIP-seq data 94%
Similar papers in this journal
- Controlled Noise: Evidence of Epigenetic Regulation of Single-Cell Expression Variability 94%
- Integration of multi-source gene interaction networks and omics data with graph attention networks to identify novel disease genes 94%
- ezGeno: An Automatic Model Selection Package for Genomic Data Analysis 94%
Similar papers in this journal
- Assessing deep learning algorithms in cis-regulatory motif finding based on genomic sequencing data 96%
- PTFSpot: Deep co-learning on transcription factors and their binding regions attains impeccable universality in plants 95%
- Enhancing single-cell cellular state inference by incorporating molecular network features 95%
"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.