DeepLoc: prediction of protein subcellular localization using deep learning

Armenteros, José Juan Almagro; Sønderby, Casper Kaae; Sønderby, Søren Kaae; Nielsen, Henrik; Winther, Ole

doi:10.1093/bioinformatics/btx431

Cited by 882 publications

(650 citation statements)

References 26 publications

Supporting

Mentioning

643

Contrasting

Unclassified

Order By: Relevance

“…The best performing one, DeepLoc (Almagro Armenteros et al, 2017), was selected by testing prediction output of proteins that their localization in the cell was experimentally tested (such as: Dani, Ganot, Priouzeau, Furla, & Sabourault, 2014). DeepLoc prediction algorithm relies only on sequence information and was demonstrated to achieve a good accuracy (Almagro Armenteros et al, 2017). Only proteins that were predicted to be membranal and not soluble and that were ranked with high a hierarchical tree likelihood (>0.5), were taken into consideration.…”

Section: Differential Gene Expression Analysismentioning

confidence: 99%

Symbiotic lifestyle triggers drastic changes in the gene expression of the algal endosymbiont Breviolum minutum (Symbiodiniaceae)

Maor-Landaw

Oppen

McFadden

2019

Ecology and Evolution

View full text Add to dashboard Cite

Coral-dinoflagellate symbiosis underpins the evolutionary success of corals reefs. Successful exchange of molecules between the cnidarian host and the Symbiodiniaceae algae enables the mutualistic partnership. The algae translocate photosynthate to their host in exchange for nutrients and shelter. The photosynthate must traverse multiple membranes, most likely facilitated by transporters. Here, we compared gene expression profiles of cultured, free-living Breviolum minutum with those of the homologous symbionts freshly isolated from the sea anemone Exaiptasia diaphana, a widely used model for coral hosts. Additionally, we assessed expression levels of a list of candidate host transporters of interest in anemones with and without symbionts. Our transcriptome analyses highlight the distinctive nature of the two algal life stages, with many gene expression level changes correlating to the different morphologies, cell cycles, and metabolisms adopted in hospite versus free-living.Morphogenesis-related genes that likely underpin the metamorphosis process observed when symbionts enter a host cell were up-regulated. Conversely, many downregulated genes appear to be indicative of the protective and confined nature of the symbiosome. Our results emphasize the significance of transmembrane transport to the symbiosis, and in particular of ammonium and sugar transport. Further, we pinpoint and characterize candidate transporters-predicted to be localized variously to the algal plasma membrane, the host plasma membrane, and the symbiosome membrane-that likely serve pivotal roles in the interchange of material during symbiosis.Our study provides new insights that expand our understanding of the molecular exchanges that underpin the cnidarian-algal symbiotic relationship. K E Y W O R D S Breviolum minutum, Exaiptasia diaphana, free-living, in hospite, symbiosis, transporters S U PP O RTI N G I N FO R M ATI O N Additional supporting information may be found online in the Supporting Information section. How to cite this article: Maor-Landaw K, van Oppen MJH, McFadden GI. Symbiotic lifestyle triggers drastic changes in the gene expression of the algal endosymbiont Breviolum minutum (Symbiodiniaceae).

show abstract

Section: Differential Gene Expression Analysismentioning

confidence: 99%

Symbiotic lifestyle triggers drastic changes in the gene expression of the algal endosymbiont Breviolum minutum (Symbiodiniaceae)

Maor-Landaw

Oppen

McFadden

2019

Ecology and Evolution

View full text Add to dashboard Cite

show abstract

“…The presence of signal peptides was determined using SignalP predictor (http://www.cbs.dtu.dk/ services/SignalP) (Emanuelsson et al, 1999;Armenteros et al, 2019). DeepLoc-1.0 (http://www.cbs.dtu.dk/services/ DeepLoc-1.0) was used to predict the subcellular localization of the PKS and FAS proteins (Armenteros et al, 2017).…”

Section: Rna Extraction and Sequencingmentioning

confidence: 99%

Transcriptomic investigation into polyketide toxin synthesis in Ostreopsis (Dinophyceae) species

Verma

Kohli

Harwood

et al. 2019

Environmental Microbiology

View full text Add to dashboard Cite

Summary In marine ecosystems, dinoflagellates can become highly abundant and even dominant at times, despite their comparatively slow growth. Their ecological success may be related to their production of complex toxic polyketide compounds. Ostreopsis species produce potent palytoxin‐like compounds (PLTX), which are associated with human skin and eye irritations, and illnesses through the consumption of contaminated seafood. To investigate the genetic basis of PLTX‐like compounds, we sequenced and annotated transcriptomes from two PLTX‐producing Ostreopsis species; O. cf. ovata, O. cf. siamensis, one non‐PLTX producing species, O. rhodesae and compared them to a close phylogenetic relative and non‐PLTX producer, Coolia malayensis. We found no clear differences in the presence or diversity of ketosynthase and ketoreductase transcripts between PLTX producing and non‐producing Ostreopsis and Coolia species, as both groups contained >90 and > 10 phylogenetically diverse ketosynthase and ketoreductase transcripts, respectively. We report for the first‐time type I single‐, multi‐domain polyketide synthases (PKSs) and hybrid non‐ribosomal peptide synthase/PKS transcripts from all species. The long multi‐modular PKSs were insufficient by themselves to synthesize the large complex polyether backbone of PLTX‐like compounds. This implies that numerous PKS domains, including both single and multi‐, work together on the biosynthesis of PLTX‐like and other related polyketide compounds.

show abstract

“…NetSurfP‐1.0 is a tool published in 2009 for prediction of solvent accessibility and secondary structure using a feed‐forward neural network architecture. Since then, deep learning techniques have affected the application of machine learning in biology expanding the ability of prediction tools to produce more accurate results on complex datasets . Here, we present NetSurfP‐2.0, a new extended version of NetSurfP, that uses a deep neural network approach to accurately predict absolute and relative solvent accessibility, secondary structure using both 3‐ and 8‐class definitions, φ and ψ dihedral angles, and structural disorder, of any given protein from its primary sequence only.…”

Section: Introductionmentioning

confidence: 99%

NetSurfP‐2.0: Improved prediction of protein structural features by integrated deep learning

et al. 2019

Self Cite

View full text Add to dashboard Cite

The ability to predict local structural features of a protein from the primary sequence is of paramount importance for unraveling its function in absence of experimental structural information. Two main factors affect the utility of potential prediction tools: their accuracy must enable extraction of reliable structural information on the proteins of interest, and their runtime must be low to keep pace with sequencing data being generated at a constantly increasing speed. Here, we present NetSurfP‐2.0, a novel tool that can predict the most important local structural features with unprecedented accuracy and runtime. NetSurfP‐2.0 is sequence‐based and uses an architecture composed of convolutional and long short‐term memory neural networks trained on solved protein structures. Using a single integrated model, NetSurfP‐2.0 predicts solvent accessibility, secondary structure, structural disorder, and backbone dihedral angles for each residue of the input sequences. We assessed the accuracy of NetSurfP‐2.0 on several independent test datasets and found it to consistently produce state‐of‐the‐art predictions for each of its output features. We observe a correlation of 80% between predictions and experimental data for solvent accessibility, and a precision of 85% on secondary structure 3‐class predictions. In addition to improved accuracy, the processing time has been optimized to allow predicting more than 1000 proteins in less than 2 hours, and complete proteomes in less than 1 day.

show abstract

DeepLoc: prediction of protein subcellular localization using deep learning

Abstract: jjalma@dtu.dk.

Cited by 882 publications

References 26 publications

Symbiotic lifestyle triggers drastic changes in the gene expression of the algal endosymbiont Breviolum minutum (Symbiodiniaceae)

Symbiotic lifestyle triggers drastic changes in the gene expression of the algal endosymbiont Breviolum minutum (Symbiodiniaceae)

Transcriptomic investigation into polyketide toxin synthesis in Ostreopsis (Dinophyceae) species

NetSurfP‐2.0: Improved prediction of protein structural features by integrated deep learning

Contact Info

Product

Resources

About