2019
DOI: 10.26508/lsa.201900429
|View full text |Cite
|
Sign up to set email alerts
|

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 lay… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

4
639
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
7
1
1

Relationship

0
9

Authors

Journals

citations
Cited by 721 publications
(643 citation statements)
references
References 38 publications
4
639
0
Order By: Relevance
“…We predicted the chloroplast transit peptide (cTP) of VC1 using TargetP online (version 2.0) 19 . An E. coli codon-optimized version of VC1 coding for an N-terminal His-tag and lacking the predicted cTP-coding region ( Supplementary File 7 ) was synthesized (GenScript) and cloned into expression vector pET22b(+) using restriction sites NdeI and HindIII.…”
Section: Methodsmentioning
confidence: 99%
“…We predicted the chloroplast transit peptide (cTP) of VC1 using TargetP online (version 2.0) 19 . An E. coli codon-optimized version of VC1 coding for an N-terminal His-tag and lacking the predicted cTP-coding region ( Supplementary File 7 ) was synthesized (GenScript) and cloned into expression vector pET22b(+) using restriction sites NdeI and HindIII.…”
Section: Methodsmentioning
confidence: 99%
“…Similarities between PAC domain sequences have been calculated using either Blast2seq (https://blast.ncbi.nlm.nih.gov/Blast.cgi) or needle (http://www.bioinformatics.nl/cgi-bin/ emboss/needle). The sub-cellular localization of proteins has been predicted with TargetP-2.0 ( [45], http://www.cbs.dtu.dk/services/TargetP/) and the presence of β-sheets and/or α-helices using SABLE ( [46], http://sable.cchmc.org/) and NetSurfP ( [47], http://www.cbs.dtu.dk/services/NetSurfP/). The selected PAC domains starting at the Gly amino acid located three amino acids upstream of Cys 1 and ending at Cys 6 have been aligned using PROMALS3D ( [48], http://prodata.swmed.edu/ promals3d/promals3d.php) to take into account the prediction of α-sheets.…”
Section: Comparisons and Alignment Of Pac Domainsmentioning
confidence: 99%
“…FPP-derived Table 1. N-terminal sequences are omitted according to prediction by TargetP-2.0 [21] (http://www.cbs.dtu.dk/services/TargetP). Highly conserved regions are highlighted in gray.…”
Section: Trans-prenyltransferasesmentioning
confidence: 99%