Abstract
We present a comparison of machine learning methods for the prediction of four quantitative traits in Arabidopsis thaliana. High prediction accuracies were achieved on individuals grown under standardized laboratory conditions from the 1001 Arabidopsis Genomes Project. An existing body of evidence suggests that linear models may be impeded by their inability to make use of non-additive effects to explain phenotypic variation at the population level. The results presented here use a nested cross-validation approach to confirm that some machine learning methods have the ability to statistically outperform linear prediction models, with the optimal model dependent on availability of training data and genetic architecture of the trait in question. Linear models were competitive in their performance as per previous work, though the neural network class of predictors was observed to be the most accurate and robust for traits with high heritability. The extent to which non-linear models exploit interaction effects will require further investigation of the causal pathways that lay behind their predictions. Future work utilizing more traits and larger sample sizes, combined with an improved understanding of their respective genetic architectures, may lead to improvements in prediction accuracy.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 4
Claim · model-written summary
Some machine learning methods statistically outperformed linear prediction models for genomic prediction in Arabidopsis thaliana.
- Taxon
- Arabidopsis thaliana
Arabidopsis thalianae3 - Outcome
- prediction accuraciese0
- Direction
- outperforme1
- Comparator
- linear prediction modelse1
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“High prediction accuracies were achieved on individuals grown under standardized laboratory conditions from the 1001 Arabidopsis Genomes Project”
e1“some machine learning methods have the ability to statistically outperform linear prediction models”
e3“We present a comparison of machine learning methods for the prediction of four quantitative traits in Arabidopsis thaliana”
Claim · model-written summary
The neural network class of predictors was the most accurate and robust for Arabidopsis thaliana traits with high heritability.
- Taxon
- Arabidopsis thalianaArabidopsis thalianae3
- Material
- neural network class of predictorse2
- Outcome
- most accurate and robuste2
- Qualifier
- for traits with high heritabilitye2
- Comparator
- Linear modelse2
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e2“Linear models were competitive in their performance as per previous work, though the neural network class of predictors was observed to be the most accurate and robust for traits with high heritability”
e3“We present a comparison of machine learning methods for the prediction of four quantitative traits in Arabidopsis thaliana”
Claim · model-written summary
Genomic prediction accuracies for Arabidopsis thaliana were high under standardized laboratory conditions.
- Taxon
- Arabidopsis thalianaArabidopsis thalianae3
- Outcome
- prediction accuraciese0
- Value
- Highe0
- Setting
- standardized laboratory conditionse0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“High prediction accuracies were achieved on individuals grown under standardized laboratory conditions from the 1001 Arabidopsis Genomes Project”
e3“We present a comparison of machine learning methods for the prediction of four quantitative traits in Arabidopsis thaliana”
Claim · model-written summary
The optimal prediction model for Arabidopsis thaliana traits depends on training data availability and trait genetic architecture.
- Taxon
- Arabidopsis thalianaArabidopsis thalianae3
- Outcome
- optimal modele1
- Qualifier
- dependent on availability of training data and genetic architecture of the traite1
Not reportedValue
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e1“with the optimal model dependent on availability of training data and genetic architecture of the trait in question”
e3“We present a comparison of machine learning methods for the prediction of four quantitative traits in Arabidopsis thaliana”