Predicting gene expression responses to environment inArabidopsis thalianausing natural variation in DNA sequence DOI Creative Commons

Margarita Takou,

Emily S. Bellis, Jesse R. Lasky

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Апрель 28, 2024

Abstract The evolution of gene expression responses are a critical component adaptation to variable environments. Predicting how DNA sequence influences is challenging because the genotype phenotype map not well resolved for cis regulatory elements, transcription factor binding, interactions, and epigenetic features, mention these factors respond environment. We tested if flexible machine learning models could learn some underlying cis- map. this approach using cold-responsive transcriptome profiles in 5 diverse Arabidopsis thaliana accessions. first evidence that regulation plays role environmental response, finding 14 15 motifs were significantly enriched within up- down-stream regions differentially regulated genes (DEGs). next applied convolutional neural networks (CNNs), which de novo sequences predict response found CNNs predicted differential with moderate accuracy, predictions hindered by biological complexity large potential code. Overall, DEGs between specific environments can be based on variation sequences, although more information needs incorporated better may required.

Язык: Английский

Predicting gene expression responses to environment inArabidopsis thalianausing natural variation in DNA sequence DOI Creative Commons

Margarita Takou,

Emily S. Bellis, Jesse R. Lasky

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Апрель 28, 2024

Abstract The evolution of gene expression responses are a critical component adaptation to variable environments. Predicting how DNA sequence influences is challenging because the genotype phenotype map not well resolved for cis regulatory elements, transcription factor binding, interactions, and epigenetic features, mention these factors respond environment. We tested if flexible machine learning models could learn some underlying cis- map. this approach using cold-responsive transcriptome profiles in 5 diverse Arabidopsis thaliana accessions. first evidence that regulation plays role environmental response, finding 14 15 motifs were significantly enriched within up- down-stream regions differentially regulated genes (DEGs). next applied convolutional neural networks (CNNs), which de novo sequences predict response found CNNs predicted differential with moderate accuracy, predictions hindered by biological complexity large potential code. Overall, DEGs between specific environments can be based on variation sequences, although more information needs incorporated better may required.

Язык: Английский

Процитировано

0