Detecting sequence signals in targeting peptides using deep learning (2024)

Armenteros, J. J. A., Salvatore, M., Emanuelsson, O., Winther, O., Von Heijne, G., Elofsson, A. (2019). Detecting sequence signals in targeting peptides using deep learning. Life Science Alliance, 2(5), Article 201900429. https://doi.org/10.26508/lsa.201900429

Armenteros, Jose Juan Almagro ; Salvatore, Marco ; Emanuelsson, Olof et al. / Detecting sequence signals in targeting peptides using deep learning. In: Life Science Alliance. 2019 ; Vol. 2, No. 5.

@article{909568c1cf73473597b9c066b6b4cee0,

title = "Detecting sequence signals in targeting peptides using deep learning",

abstract = "In bioinformatics, machine learning methods have been used to predict features embedded in the sequences. In contrast to what is generally assumed, machine learning approaches can also provide new insights into the underlying biology. Here, we demonstrate this by presenting TargetP 2.0, a novel state-of-the-art method to identify N-terminal sorting signals, which direct proteins to the secretory pathway, mitochondria, and chloroplasts or other plastids. By examining the strongest signals from the attention layer in the network, we find that the second residue in the protein, that is, the one following the initial methionine, has a strong influence on the classification. We observe that two-thirds of chloroplast and thylakoid transit peptides have an alanine in position 2, compared with 20% in other plant proteins. We also note that in fungi and single-celled eukaryotes, less than 30% of the targeting peptides have an amino acid that allows the removal of the N-terminal methionine compared with 60% for the proteins without targeting peptide. The importance of this feature for predictions has not been highlighted before.",

author = "Armenteros, {Jose Juan Almagro} and Marco Salvatore and Olof Emanuelsson and Ole Winther and {Von Heijne}, Gunnar and Arne Elofsson and Henrik Nielsen",

year = "2019",

month = jan,

day = "1",

doi = "10.26508/lsa.201900429",

language = "English",

volume = "2",

journal = "Life Science Alliance",

issn = "2575-1077",

publisher = "Life Science Alliance",

number = "5",

}

Armenteros, JJA, Salvatore, M, Emanuelsson, O, Winther, O, Von Heijne, G, Elofsson, A 2019, 'Detecting sequence signals in targeting peptides using deep learning', Life Science Alliance, vol. 2, no. 5, 201900429. https://doi.org/10.26508/lsa.201900429

Detecting sequence signals in targeting peptides using deep learning. / Armenteros, Jose Juan Almagro; Salvatore, Marco; Emanuelsson, Olof et al.
In: Life Science Alliance, Vol. 2, No. 5, 201900429, 01.01.2019.

Research output: Contribution to journal › Journal article › Research › peer-review

TY - JOUR

T1 - Detecting sequence signals in targeting peptides using deep learning

AU - Armenteros, Jose Juan Almagro

AU - Salvatore, Marco

AU - Emanuelsson, Olof

AU - Winther, Ole

AU - Von Heijne, Gunnar

AU - Elofsson, Arne

AU - Nielsen, Henrik

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In bioinformatics, machine learning methods have been used to predict features embedded in the sequences. In contrast to what is generally assumed, machine learning approaches can also provide new insights into the underlying biology. Here, we demonstrate this by presenting TargetP 2.0, a novel state-of-the-art method to identify N-terminal sorting signals, which direct proteins to the secretory pathway, mitochondria, and chloroplasts or other plastids. By examining the strongest signals from the attention layer in the network, we find that the second residue in the protein, that is, the one following the initial methionine, has a strong influence on the classification. We observe that two-thirds of chloroplast and thylakoid transit peptides have an alanine in position 2, compared with 20% in other plant proteins. We also note that in fungi and single-celled eukaryotes, less than 30% of the targeting peptides have an amino acid that allows the removal of the N-terminal methionine compared with 60% for the proteins without targeting peptide. The importance of this feature for predictions has not been highlighted before.

AB - In bioinformatics, machine learning methods have been used to predict features embedded in the sequences. In contrast to what is generally assumed, machine learning approaches can also provide new insights into the underlying biology. Here, we demonstrate this by presenting TargetP 2.0, a novel state-of-the-art method to identify N-terminal sorting signals, which direct proteins to the secretory pathway, mitochondria, and chloroplasts or other plastids. By examining the strongest signals from the attention layer in the network, we find that the second residue in the protein, that is, the one following the initial methionine, has a strong influence on the classification. We observe that two-thirds of chloroplast and thylakoid transit peptides have an alanine in position 2, compared with 20% in other plant proteins. We also note that in fungi and single-celled eukaryotes, less than 30% of the targeting peptides have an amino acid that allows the removal of the N-terminal methionine compared with 60% for the proteins without targeting peptide. The importance of this feature for predictions has not been highlighted before.

U2 - 10.26508/lsa.201900429

DO - 10.26508/lsa.201900429

M3 - Journal article

C2 - 31570514

AN - SCOPUS:85072779066

SN - 2575-1077

VL - 2

JO - Life Science Alliance

JF - Life Science Alliance

IS - 5

M1 - 201900429

ER -

Armenteros JJA, Salvatore M, Emanuelsson O, Winther O, Von Heijne G, Elofsson A et al. Detecting sequence signals in targeting peptides using deep learning. Life Science Alliance. 2019 Jan 1;2(5):201900429. doi: 10.26508/lsa.201900429