Inferring protein from transcript abundances using convolutional neural networks

Background Although transcript abundance is often used as a proxy for protein abundance, it is an unreliable predictor. As proteins execute biological functions and their expression levels influence phenotypic outcomes, we developed a convolutional neural network (CNN) to predict protein abundances...

Full description

Saved in:
Bibliographic Details
Published in:BioData mining Vol. 18; no. 1; pp. 18 - 15
Main Authors: Schwehn, Patrick Maximilian, Falter-Braun, Pascal
Format: Journal Article
Language:English
Published: London BioMed Central 27.02.2025
BioMed Central Ltd
Springer Nature B.V
BMC
Subjects:
Abundance
Algorithms
Amino acid sequence
Amino acids
Analysis
Arabidopsis thaliana
Artificial intelligence
Artificial neural networks
Bioinformatics
Biomedical and Life Sciences
Computational Biology/Bioinformatics
Computer Appl. in Life Sciences
Convolutional neural networks
Data Mining and Knowledge Discovery
Datasets
Experiments
Explainable AI
Genes
Genetic aspects
Identification and classification
Life Sciences
Machine learning
Methods
Neural networks
Ontology
Predictions
Protein-to-mRNA ratio
Proteins
Proteomics
Regression analysis
Regulatory sequences
Synthesis
Translational regulation
Germany
Explainable AI
Regression analysis
Protein-to-mRNA ratio
Translational regulation
Convolutional neural networks
ISSN:1756-0381, 1756-0381
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Background Although transcript abundance is often used as a proxy for protein abundance, it is an unreliable predictor. As proteins execute biological functions and their expression levels influence phenotypic outcomes, we developed a convolutional neural network (CNN) to predict protein abundances from mRNA abundances, protein sequence, and mRNA sequence in Homo sapiens (H. sapiens) and the reference plant Arabidopsis thaliana (A. thaliana) . Results After hyperparameter optimization and initial data exploration, we implemented distinct training modules for value-based and sequence-based data. By analyzing the learned weights, we revealed common and organism-specific sequence features that influence protein-to-mRNA ratios (PTRs), including known and putative sequence motifs. Adding condition-specific protein interaction information identified genes correlated with many PTRs but did not improve predictions, likely due to insufficient data. The integrated model predicted protein abundance on unseen genes with a coefficient of determination (r 2 ) of 0.30 in H. sapiens and 0.32 in A. thaliana. Conclusions For H. sapiens, our model improves prediction performance by nearly 50% compared to previous sequence-based approaches, and for A. thaliana it represents the first model of its kind. The model’s learned motifs recapitulate known regulatory elements, supporting its utility in systems-level and hypothesis-driven research approaches related to protein regulation.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1756-0381
1756-0381
DOI:10.1186/s13040-025-00434-z