Deep Learning Suggests That Gene Expression is Encoded in All Parts of a Co-evolving Interacting Gene Regulatory Structure

Overview

Journal Nat Commun

Specialty Biology

Date 2020 Dec 2

PMID 33262328

Citations 62

Authors

Jan Zrimec

Christoph S Borlin

Filip Buric

Azam Sheikh Muhammad

Rhongzen Chen

Verena Siewers

Vilhelm Verendel

Jens Nielsen

Mats Topel

Aleksej Zelezniak

Affiliations

Soon will be listed here.

Abstract

Understanding the genetic regulatory code governing gene expression is an important challenge in molecular biology. However, how individual coding and non-coding regions of the gene regulatory structure interact and contribute to mRNA expression levels remains unclear. Here we apply deep learning on over 20,000 mRNA datasets to examine the genetic regulatory code controlling mRNA abundance in 7 model organisms ranging from bacteria to Human. In all organisms, we can predict mRNA abundance directly from DNA sequence, with up to 82% of the variation of transcript levels encoded in the gene regulatory structure. By searching for DNA regulatory motifs across the gene regulatory structure, we discover that motif interactions could explain the whole dynamic range of mRNA levels. Co-evolution across coding and non-coding regions suggests that it is not single motifs or regions, but the entire gene regulatory structure and specific combination of regulatory elements that define gene expression levels.

Citing Articles

Precise engineering of gene expression by editing plasticity.

Qiu Y, Liu L, Yan J, Xiang X, Wang S, Luo Y Genome Biol. 2025; 26(1):51.

PMID: 40065399 PMC: 11892124. DOI: 10.1186/s13059-025-03516-7.

Inferring protein from transcript abundances using convolutional neural networks.

Schwehn P, Falter-Braun P BioData Min. 2025; 18(1):18.

PMID: 40016737 PMC: 11866710. DOI: 10.1186/s13040-025-00434-z.

Chromatin enables precise and scalable gene regulation with factors of limited specificity.

Perkins M, Crocker J, Tkacik G Proc Natl Acad Sci U S A. 2025; 122(1):e2411887121.

PMID: 39793086 PMC: 11725945. DOI: 10.1073/pnas.2411887121.

Amino acid sequence encodes protein abundance shaped by protein stability at reduced synthesis cost.

Buric F, Viknander S, Fu X, Lemke O, Carmona O, Zrimec J Protein Sci. 2024; 34(1):e5239.

PMID: 39665261 PMC: 11635393. DOI: 10.1002/pro.5239.

Deep learning approaches for non-coding genetic variant effect prediction: current progress and future prospects.

Wang X, Li F, Zhang Y, Imoto S, Shen H, Li S Brief Bioinform. 2024; 25(5).

PMID: 39276327 PMC: 11401448. DOI: 10.1093/bib/bbae446.

References

Agarwal V, Shendure J . Predicting mRNA Abundance Directly from Genomic Sequence Using Deep Convolutional Neural Networks. Cell Rep. 2020; 31(7):107663. DOI: 10.1016/j.celrep.2020.107663. View

Ludwig M, Bergman C, Patel N, Kreitman M . Evidence for stabilizing selection in a eukaryotic enhancer element. Nature. 2000; 403(6769):564-7. DOI: 10.1038/35000615. View

Trabelsi A, Chaabane M, Ben-Hur A . Comprehensive evaluation of deep learning architectures for prediction of DNA/RNA sequence binding specificities. Bioinformatics. 2019; 35(14):i269-i277. PMC: 6612801. DOI: 10.1093/bioinformatics/btz339. View

Subramanian S, Kumar S . Gene expression intensity shapes evolutionary rates of the proteins encoded by the vertebrate genome. Genetics. 2004; 168(1):373-81. PMC: 1448110. DOI: 10.1534/genetics.104.028944. View

Fu L, Niu B, Zhu Z, Wu S, Li W . CD-HIT: accelerated for clustering the next-generation sequencing data. Bioinformatics. 2012; 28(23):3150-2. PMC: 3516142. DOI: 10.1093/bioinformatics/bts565. View

Li W, Godzik A . Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences. Bioinformatics. 2006; 22(13):1658-9. DOI: 10.1093/bioinformatics/btl158. View

Dvir S, Velten L, Sharon E, Zeevi D, Carey L, Weinberger A . Deciphering the rules by which 5'-UTR sequences affect protein expression in yeast. Proc Natl Acad Sci U S A. 2013; 110(30):E2792-801. PMC: 3725075. DOI: 10.1073/pnas.1222534110. View

Zhou Z, Dang Y, Zhou M, Yuan H, Liu Y . Codon usage biases co-evolve with transcription termination machinery to suppress premature cleavage and polyadenylation. Elife. 2018; 7. PMC: 5869017. DOI: 10.7554/eLife.33569. View

Wittkopp P, Kalay G . Cis-regulatory elements: molecular mechanisms and evolutionary processes underlying divergence. Nat Rev Genet. 2011; 13(1):59-69. DOI: 10.1038/nrg3095. View

10.

Cherry J, Adler C, Ball C, Chervitz S, Dwight S, Hester E . SGD: Saccharomyces Genome Database. Nucleic Acids Res. 1998; 26(1):73-9. PMC: 147204. DOI: 10.1093/nar/26.1.73. View

11.

Mittal P, Brindle J, Stephen J, Plotkin J, Kudla G . Codon usage influences fitness through RNA toxicity. Proc Natl Acad Sci U S A. 2018; 115(34):8639-8644. PMC: 6112741. DOI: 10.1073/pnas.1810022115. View

12.

Cunningham F, Achuthan P, Akanni W, Allen J, Amode M, Armean I . Ensembl 2019. Nucleic Acids Res. 2018; 47(D1):D745-D751. PMC: 6323964. DOI: 10.1093/nar/gky1113. View

13.

Hershberg R, Petrov D . Selection on codon bias. Annu Rev Genet. 2008; 42:287-99. DOI: 10.1146/annurev.genet.42.110807.091442. View

14.

Clement Y, Torbey P, Gilardi-Hebenstreit P, Crollius H . Enhancer-gene maps in the human and zebrafish genomes using evolutionary linkage conservation. Nucleic Acids Res. 2020; 48(5):2357-2371. PMC: 7049698. DOI: 10.1093/nar/gkz1199. View

15.

Cock P, Antao T, Chang J, Chapman B, Cox C, Dalke A . Biopython: freely available Python tools for computational molecular biology and bioinformatics. Bioinformatics. 2009; 25(11):1422-3. PMC: 2682512. DOI: 10.1093/bioinformatics/btp163. View

16.

Li B, Ruotti V, Stewart R, Thomson J, Dewey C . RNA-Seq gene expression estimation with read mapping uncertainty. Bioinformatics. 2009; 26(4):493-500. PMC: 2820677. DOI: 10.1093/bioinformatics/btp692. View

17.

Vanhercke T, Ampe C, Tirry L, Denolf P . Reducing mutational bias in random protein libraries. Anal Biochem. 2005; 339(1):9-14. DOI: 10.1016/j.ab.2004.11.032. View

18.

Katoh K, Standley D . MAFFT multiple sequence alignment software version 7: improvements in performance and usability. Mol Biol Evol. 2013; 30(4):772-80. PMC: 3603318. DOI: 10.1093/molbev/mst010. View

19.

Zelezniak A, Vowinckel J, Capuano F, Messner C, Demichev V, Polowsky N . Machine Learning Predicts the Yeast Metabolome from the Quantitative Proteome of Kinase Knockouts. Cell Syst. 2018; 7(3):269-283.e6. PMC: 6167078. DOI: 10.1016/j.cels.2018.08.001. View

20.

Schneider T, Stormo G, Gold L, Ehrenfeucht A . Information content of binding sites on nucleotide sequences. J Mol Biol. 1986; 188(3):415-31. DOI: 10.1016/0022-2836(86)90165-8. View