Association·arcadia
Comparison of deep learning MLP to linear regression on simulated data
Association comparing performance (Pearson's r) between MLP deep learning and linear regression models on synthetic genotype-phenotype datasets with varying epistatic variance.
Confidence
90%
active
Evidence Quote
“MLP deep learning models outperform ridge regression on simulated data with epistatic variance, assessed via Pearson correlation.”
Relationship
Multilayer perceptron (MLP) deep learning model outperforms linear regression
Arguments
Connections (7)
Deep learning capture of epistatic variance in genotype-phenotype mappingInferenceChain
Non-additive interactions like epistasis drive phenotypic variationAssociation
Data regimes and deep learning benefits in genotype-phenotype mappingInferenceChain
Data regimes and genetic architecture constrain deep learning benefitsInferenceChain
Reasoning on deep learning benchmarking in genotype–phenotype mappingInferenceChain
Deep learning architecture and theoretical foundationsInferenceChain
Reasoning on deep learning and genotype-phenotype predictionInferenceChain
Evidence
“Evidence that the learning rate of the deep learning MLP model was optimized using Optuna, improving performance.”
(2024). When do deep learning models outperform linear regression?
“Simulated data and analysis scripts made publicly available on Zenodo for reproducibility of genotype-phenotype mapping results.”
Synthesis for current paper
“Compiled empirical results from various deep learning benchmarking studies showing heterogeneity in model performance across datasets and genetic architectures.”
Synthesis for current paper