EvoLSTM: Context-dependent Models of Sequence Evolution Using a Sequence-to-sequence LSTM

Overview

Journal Bioinformatics

Publisher Oxford University Press

Specialty Biology

Date 2020 Jul 14

PMID 32657367

Citations 3

Authors

Dongjoon Lim

Mathieu Blanchette

Affiliations

Soon will be listed here.

Abstract

Motivation: Accurate probabilistic models of sequence evolution are essential for a wide variety of bioinformatics tasks, including sequence alignment and phylogenetic inference. The ability to realistically simulate sequence evolution is also at the core of many benchmarking strategies. Yet, mutational processes have complex context dependencies that remain poorly modeled and understood.

Results: We introduce EvoLSTM, a recurrent neural network-based evolution simulator that captures mutational context dependencies. EvoLSTM uses a sequence-to-sequence long short-term memory model trained to predict mutation probabilities at each position of a given sequence, taking into consideration the 14 flanking nucleotides. EvoLSTM can realistically simulate mammalian and plant DNA sequence evolution and reveals unexpectedly strong long-range context dependencies in mutation probabilities. EvoLSTM brings modern machine-learning approaches to bear on sequence evolution. It will serve as a useful tool to study and simulate complex mutational processes.

Availability And Implementation: Code and dataset are available at https://github.com/DongjoonLim/EvoLSTM.

Supplementary Information: Supplementary data are available at Bioinformatics online.

Citing Articles

Insertions and Deletions: Computational Methods, Evolutionary Dynamics, and Biological Applications.

Redelings B, Holmes I, Lunter G, Pupko T, Anisimova M Mol Biol Evol. 2024; 41(9).

PMID: 39172750 PMC: 11385596. DOI: 10.1093/molbev/msae177.

Context-Dependent Substitution Dynamics in Plastid DNA Across a Wide Range of Taxonomic Groups.

Morton B J Mol Evol. 2022; 90(1):44-55.

PMID: 35037071 DOI: 10.1007/s00239-021-10040-2.

Attention-Based Deep Multiple-Instance Learning for Classifying Circular RNA and Other Long Non-Coding RNA.

Liu Y, Fu Q, Peng X, Zhu C, Liu G, Liu L Genes (Basel). 2021; 12(12).

PMID: 34946967 PMC: 8701965. DOI: 10.3390/genes12122018.

References

Zhang H, Lang Z, Zhu J . Dynamics and function of DNA methylation in plants. Nat Rev Mol Cell Biol. 2018; 19(8):489-506. DOI: 10.1038/s41580-018-0016-z. View

Blanchette M, Kent W, Riemer C, Elnitski L, Smit A, Roskin K . Aligning multiple genomic sequences with the threaded blockset aligner. Genome Res. 2004; 14(4):708-15. PMC: 383317. DOI: 10.1101/gr.1933104. View

Rodrigue N, Lartillot N, Bryant D, Philippe H . Site interdependence attributed to tertiary structure in amino acid sequence evolution. Gene. 2005; 347(2):207-17. DOI: 10.1016/j.gene.2004.12.011. View

Siepel A, Haussler D . Phylogenetic estimation of context-dependent substitution rates by maximum likelihood. Mol Biol Evol. 2003; 21(3):468-88. DOI: 10.1093/molbev/msh039. View

Ranwez V, Harispe S, Delsuc F, Douzery E . MACSE: Multiple Alignment of Coding SEquences accounting for frameshifts and stop codons. PLoS One. 2011; 6(9):e22594. PMC: 3174933. DOI: 10.1371/journal.pone.0022594. View

Delsuc F, Brinkmann H, Philippe H . Phylogenomics and the reconstruction of the tree of life. Nat Rev Genet. 2005; 6(5):361-75. DOI: 10.1038/nrg1603. View

Earl D, Nguyen N, Hickey G, Harris R, Fitzgerald S, Beal K . Alignathon: a competitive assessment of whole-genome alignment methods. Genome Res. 2014; 24(12):2077-89. PMC: 4248324. DOI: 10.1101/gr.174920.114. View

Haudry A, Platts A, Vello E, Hoen D, Leclercq M, Williamson R . An atlas of over 90,000 conserved noncoding sequences provides insight into crucifer regulatory regions. Nat Genet. 2013; 45(8):891-8. DOI: 10.1038/ng.2684. View

Blanchette M, Green E, Miller W, Haussler D . Reconstructing large regions of an ancestral mammalian genome in silico. Genome Res. 2004; 14(12):2412-23. PMC: 534665. DOI: 10.1101/gr.2800104. View

10.

Greff K, Srivastava R, Koutnik J, Steunebrink B, Schmidhuber J . LSTM: A Search Space Odyssey. IEEE Trans Neural Netw Learn Syst. 2016; 28(10):2222-2232. DOI: 10.1109/TNNLS.2016.2582924. View

11.

Ehrlich M, Wang R . 5-Methylcytosine in eukaryotic DNA. Science. 1981; 212(4501):1350-7. DOI: 10.1126/science.6262918. View

12.

Miller W, Rosenbloom K, Hardison R, Hou M, Taylor J, Raney B . 28-way vertebrate alignment and conservation track in the UCSC Genome Browser. Genome Res. 2007; 17(12):1797-808. PMC: 2099589. DOI: 10.1101/gr.6761107. View

13.

Fletcher W, Yang Z . INDELible: a flexible simulator of biological sequence evolution. Mol Biol Evol. 2009; 26(8):1879-88. PMC: 2712615. DOI: 10.1093/molbev/msp098. View

14.

Goldman N, Yang Z . A codon-based model of nucleotide substitution for protein-coding DNA sequences. Mol Biol Evol. 1994; 11(5):725-36. DOI: 10.1093/oxfordjournals.molbev.a040153. View

15.

Arndt P, Hwa T . Identification and measurement of neighbor-dependent nucleotide substitution processes. Bioinformatics. 2005; 21(10):2322-8. DOI: 10.1093/bioinformatics/bti376. View

16.

Beggs M, Eisenach K, Cave M . Mapping of IS6110 insertion sites in two epidemic strains of Mycobacterium tuberculosis. J Clin Microbiol. 2000; 38(8):2923-8. PMC: 87149. DOI: 10.1128/JCM.38.8.2923-2928.2000. View

17.

Kimura M . A simple method for estimating evolutionary rates of base substitutions through comparative studies of nucleotide sequences. J Mol Evol. 1980; 16(2):111-20. DOI: 10.1007/BF01731581. View

18.

Bird A . DNA methylation and the frequency of CpG in animal DNA. Nucleic Acids Res. 1980; 8(7):1499-504. PMC: 324012. DOI: 10.1093/nar/8.7.1499. View

19.

Surralles J, Ramirez M, Marcos R, Natarajan A, Mullenders L . Clusters of transcription-coupled repair in the human genome. Proc Natl Acad Sci U S A. 2002; 99(16):10571-4. PMC: 124978. DOI: 10.1073/pnas.162278199. View

20.

Holmes I . A probabilistic model for the evolution of RNA structure. BMC Bioinformatics. 2004; 5:166. PMC: 534097. DOI: 10.1186/1471-2105-5-166. View