QTG-Finder: A Machine-Learning Based Algorithm To Prioritize Causal Genes of Quantitative Trait Loci in Arabidopsis and Rice

Lin, Fan; Fan, Jue; Rhee, Seung Y.

doi:10.1534/g3.119.400319

Cited by 31 publications

(37 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 4-fold cross-validation results showed that the accuracy, precision, recall, and F1-Measure of the CNN model were all >73%. Compared with the recall of 64% and 79% in Arabidopsis thaliana and Oryza sativa, respectively 53 , the prediction performance of our model was good. Although the recall in Oryza sativa was higher than in our study, the genes were only prioritized in the QTL regions, while we prioritized genes in the whole genome.…”

Section: Discussionmentioning

confidence: 81%

A gene prioritization method based on a swine multi-omics knowledgebase and a deep learning model

Tang

et al. 2020

Commun Biol

View full text Add to dashboard Cite

The analyses of multi-omics data have revealed candidate genes for objective traits. However, they are integrated poorly, especially in non-model organisms, and they pose a great challenge for prioritizing candidate genes for follow-up experimental verification. Here, we present a general convolutional neural network model that integrates multi-omics information to prioritize the candidate genes of objective traits. By applying this model to Sus scrofa, which is a non-model organism, but one of the most important livestock animals, the model precision was 72.9%, recall 73.5%, and F1-Measure 73.4%, demonstrating a good prediction performance compared with previous studies in Arabidopsis thaliana and Oryza sativa. Additionally, to facilitate the use of the model, we present ISwine (http://iswine.iomics.pro/), which is an online comprehensive knowledgebase in which we incorporated almost all the published swine multi-omics data. Overall, the results suggest that the deep learning strategy will greatly facilitate analyses of multi-omics integration in the future.

show abstract

Section: Discussionmentioning

confidence: 81%

A gene prioritization method based on a swine multi-omics knowledgebase and a deep learning model

Tang

et al. 2020

Commun Biol

View full text Add to dashboard Cite

show abstract

“…To prioritize candidate genes underlying QTLs, a computational approach based on algorithms would be very helpful. In a study, researchers developed QTG-Finder, a machine learning based algorithm to prioritize candidate genes by ranking them within QTL region [58]. These studies are useful to narrow down candidate genes and such algorithms should be implemented in studies aiming to predict causal QTLs and genes for traits of interest.…”

Section: Discussionmentioning

confidence: 99%

Genotyping by Sequencing Revealed QTL Hotspots for Trichome-Based Plant Defense in Gossypium hirsutum

Ahmed

Nazir

Pan

et al. 2020

Genes

View full text Add to dashboard Cite

Cotton possesses certain physical features, including leaf and stem trichomes that help plants deter damage caused by insect pests, and to some extent, from abiotic factors as well. Among those features, trichomes (pubescence) hold a special place as a first line of defense and a managemental tool against sucking insect pests of cotton. Different insect pests of cotton (whiteflies, aphids, jassids, and boll weevil) severely damage the yield and quality of the crop. Likewise, whiteflies, aphids, jassids, and other insect pests are considered as potential carriers for cotton leaf curl viruses and other diseases. Genotyping by sequencing (GBS) study was conducted to understand and explore the genomic regions governing hairy (Pubescence) leaves and stem phenotypes. A total of 224 individuals developed from an intraspecific cross (densely haired cotton (Liaoyang duomao mian) × hairless cotton (Zong 128)) and characterized phenotypically for leaf and stem pubescence in different environments. Here we identify and report significant QTLs (quantitative trait loci) associated with leaf and stem pubescence, and the response of plant under pest (aphid) infestation. Further, we identified putative genes colocalized on chromosome A06 governing mechanism for trichome development and host–pest interaction. Our study provides a comprehensive insight into genetic architecture that can be employed to improve molecular marker-assisted breeding programs aimed at developing biotic (insect pests) resilient cotton cultivars.

show abstract

“…The methods for cross-validation, external validation and feature importance analysis were the same as previously described (Lin et al 2019). The causal genes used for external validation were not used for training the QTG-Finder models.…”

Section: Methodsmentioning

confidence: 99%

QTG-Finder2: a generalized machine-learning algorithm for prioritizing QTL causal genes in plants

Lin

Lazarus

Rhee

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Linkage mapping has been widely used to identify quantitative trait loci (QTL) in many plants and usually requires a time-consuming and labor-intensive fine mapping process to find the causal gene underlying the QTL. Previously, we described QTG-Finder, a machine-learning algorithm to rationally prioritize candidate causal genes in QTLs. While it showed good performance, QTG-Finder could only be used in Arabidopsis and rice because of the limited number of known causal genes in other species. Here we tested the feasibility of enabling QTG-Finder to work on species that have few or no known causal genes by using orthologs of known causal genes as training set. The model trained with orthologs could recall about 64% of Arabidopsis and 83% of rice causal genes when the top 20% ranked genes were considered, which is similar to the performance of models trained with known causal genes. We further extended the algorithm to include polymorphisms in conserved non-coding sequences and gene presence/absence variation as additional features. Using this algorithm, QTG-Finder2, we trained and cross-validated Sorghum bicolor and Setaria viridis models. The S. bicolor model was validated by causal genes curated from the literature and could recall 70% of causal genes when the top 20% ranked genes were considered. In addition, we applied the S. viridis model and public transcriptome data to prioritize a plant height QTL and identified 13 candidate genes. QTL-Finder2 can accelerate the discovery of causal genes in any plant species and facilitate agricultural trait improvement.

show abstract

QTG-Finder: A Machine-Learning Based Algorithm To Prioritize Causal Genes of Quantitative Trait Loci in Arabidopsis and Rice

Cited by 31 publications

References 68 publications

A gene prioritization method based on a swine multi-omics knowledgebase and a deep learning model

A gene prioritization method based on a swine multi-omics knowledgebase and a deep learning model

Genotyping by Sequencing Revealed QTL Hotspots for Trichome-Based Plant Defense in Gossypium hirsutum

QTG-Finder2: a generalized machine-learning algorithm for prioritizing QTL causal genes in plants

Contact Info

Product

Resources

About