{"Package":"deepredeff","Title":"Deep Learning Prediction of Effectors","Version":"0.1.1","Authors@R":"\nperson(given = \"Ruth\",\nfamily = \"Kristianingsih\",\nrole = c(\"aut\", \"cre\", \"cph\"),\nemail = \"ruth.kristianingsih30@gmail.com\",\ncomment = c(ORCID = \"0000-0003-1873-6203\"))","Description":"A tool that contains trained deep learning models\nfor predicting effector proteins. 'deepredeff' has been trained to\nidentify effector proteins using a set of known experimentally\nvalidated effectors from either bacteria, fungi, or oomycetes.\nDocumentation is available via several vignettes, and the paper by\nKristianingsih and MacLean (2020) .","License":"MIT + file LICENSE","URL":"https://github.com/ruthkr/deepredeff/","BugReports":"https://github.com/ruthkr/deepredeff/issues/","Depends":"R (>= 2.10)","Imports":"Biostrings, dplyr, ggplot2, ggthemes, keras, magrittr, purrr,\nreticulate, rlang, seqinr, tensorflow","Suggests":"covr, kableExtra, knitr, rmarkdown, stringr, testthat","VignetteBuilder":"knitr","biocViews":"","Config/reticulate":"list( packages = list( list(package = \"tensorflow\",\nversion = \"2.0.0\", pip = FALSE) ) )","Encoding":"UTF-8","RoxygenNote":"7.1.1","NeedsCompilation":"no","Packaged":"2021-07-16 09:12:16 UTC; kristiar","Author":"Ruth Kristianingsih [aut, cre, cph]\n()","Maintainer":"Ruth Kristianingsih ","Repository":"CRAN","Date/Publication":"2021-07-16 09:30:02 UTC","repoType":"cran","tarballUrl":"ftp://cran.r-project.org/pub/R/src/contrib/deepredeff_0.1.1.tar.gz","jsonAuthors":[{"name":"Ruth Kristianingsih","email":"ruth.kristianingsih30@gmail.com","maintainer":true}],"readme":"\n\n\n# deepredeff

\n\n\n\n[![CRAN_Status_Badge](https://www.r-pkg.org/badges/version/deepredeff)](https://cran.r-project.org/package=deepredeff)\n[![lifecycle](https://img.shields.io/badge/lifecycle-stable-brightgreen.svg)](https://lifecycle.r-lib.org/articles/stages.html#stable)\n[![R build\nstatus](https://github.com/ruthkr/deepredeff/workflows/R-CMD-check/badge.svg)](https://github.com/ruthkr/deepredeff/actions)\n[![Codecov test\ncoverage](https://codecov.io/gh/ruthkr/deepredeff/branch/master/graph/badge.svg)](https://codecov.io/gh/ruthkr/deepredeff?branch=master)\n[![pkgdown\nstatus](https://github.com/ruthkr/deepredeff/workflows/pkgdown/badge.svg)](https://ruthkr.github.io/deepredeff/)\n[![tensorflow\nversion](https://img.shields.io/badge/tensorflow-v2.0.0-orange)](https://www.tensorflow.org/)\n[![python\nversion](https://img.shields.io/badge/python-v3.6-blue)](https://www.python.org/)\n[![doi](https://img.shields.io/badge/DOI-10.1101%2F2020.07.08.193250-blue)](https://www.biorxiv.org/content/10.1101/2020.07.08.193250v1)\n\n\n**deepredeff** is a package to predict effector protein given amino acid\nsequences. This tool can be used to predict effectors from three\ndifferent taxa, which are oomycete, fungi, and bacteria.\n\n## Installation\n\nYou can install the released version of `deepredeff` from\n[CRAN](https://CRAN.R-project.org) with:\n\n``` r\ninstall.packages(\"deepredeff\")\n```\n\nAnd the development version from [GitHub](https://github.com/) with:\n\n``` r\n# install.packages(\"devtools\")\ndevtools::install_github(\"ruthkr/deepredeff\")\n```\n\nThe `deepredeff` package uses TensorFlow. If you already have TensorFlow\n2.0.0 or later in your system, then you can specify the environment\nwhere TensorFlow is installed using `reticulate::use_condaenv()`.\nOtherwise, you can install TensorFlow, by using the\n`install_tensorflow()` function as follows:\n\n``` r\nlibrary(deepredeff)\ninstall_tensorflow()\n```\n\n**Note that this only needs to be run once**, the first time you use\n`deepredeff`.\n\n## Documentation\n\nTo use `deepredeff`, you can read the documentation on the following\ntopics:\n\n1. [Getting\n started](https://ruthkr.github.io/deepredeff/articles/overview.html)\n2. [Effector prediction with various different input formats and\n models](https://ruthkr.github.io/deepredeff/articles/predict.html)\n\n## Quick start\n\nThis is a basic example which shows you how to predict effector\nsequences if you have a FASTA file:\n\n``` r\n# Load the package\nlibrary(deepredeff)\n\n# Define the fasta path from the sample data\nbacteria_fasta_path <- system.file(\n \"extdata/example\", \"bacteria_sample.fasta\", \n package = \"deepredeff\"\n)\n\n# Predict the effector candidate using bacteria model\npred_result <- predict_effector(\n input = bacteria_fasta_path,\n taxon = \"bacteria\"\n)\n#> Loaded models successfully!\n#> Model used for taxon bacteria: ensemble_weighted.\n```\n\n``` r\n# View results\npred_result\n```\n\n| name | sequence | s_score | prediction |\n|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------|----------:|:-------------|\n| tr⎮A0A0N8SZV2⎮A0A0N8SZV2_PSESY Type III secretion system effector HopAI1 OS=Pseudomonas syringae pv. syringae OX=321 GN=ALO45_04155 PE=4 SV=1 | MPINRPAFNLKLNTAIAQPTLKKDA | 0.9483424 | effector |\n| tr⎮A5CLR7⎮A5CLR7_CLAM3 Pat-1 protein OS=Clavibacter michiganensis subsp. michiganensis (strain NCPPB 382) OX=443906 GN=pat-1 PE=4 SV=1 | MQFMSRINRILFVAVVSLLSVLGCC | 0.0798178 | non-effector |\n| sp⎮B2SU53⎮PTHX1_XANOP TAL effector protein PthXo1 OS=Xanthomonas oryzae pv. oryzae (strain PXO99A) OX=360094 GN=pthXo1 PE=1 SV=2 | MDPIRSRTPSPARELLPGPQPDRVQ | 0.9943361 | effector |\n| tr⎮C0SPN9⎮C0SPN9_RALSL Uncharacterized protein RSc2139 OS=Ralstonia solanacearum OX=305 GN=RSc2139 PE=4 SV=1 | MSIGRSKSVAGASASHALASGENGS | 0.8418444 | effector |\n| tr⎮D2Z000⎮D2Z000_RALSL Type III effector protein OS=Ralstonia solanacearum OX=305 GN=rip61 PE=4 SV=1 | MPPPIRNARTTPPSFDPSAAGDDLR | 0.9953785 | effector |\n| tr⎮Q8XX20⎮Q8XX20_RALSO Putative multicopper oxidase, type 3 signal peptide protein OS=Ralstonia solanacearum (strain GMI1000) OX=267608 GN=RSc2298 PE=4 SV=1 | MSHMTFNTWKAGLWRLAAAAVLSLL | 0.0645516 | non-effector |\n| tr⎮Q87UH8⎮Q87UH8_PSESM Taurine ABC transporter, periplasmic taurine-binding protein OS=Pseudomonas syringae pv. tomato (strain ATCC BAA-871 / DC3000) OX=223283 GN=tauA PE=4 SV=1 | MKLHFSLRLLTALSLTGATFLAQAA | 0.0492858 | non-effector |\n| tr⎮Q4ZTI0⎮Q4ZTI0_PSEU2 Amino acid ABC transporter substrate-binding protein, PAAT family OS=Pseudomonas syringae pv. syringae (strain B728a) OX=205918 GN=Psyr_2503 PE=4 SV=1 | MHRGPSFVKACAFVLSASFMLANTV | 0.3061618 | non-effector |\n| tr⎮Q4ZR15⎮Q4ZR15_PSEU2 Sensor protein OS=Pseudomonas syringae pv. syringae (strain B728a) OX=205918 GN=Psyr_3375 PE=4 SV=1 | MRRQPSLTLRSTLAFALVAMLTVSG | 0.0722144 | non-effector |\n| tr⎮D4I1R4⎮D4I1R4_ERWAC Outer-membrane lipoprotein LolB OS=Erwinia amylovora (strain CFBP1430) OX=665029 GN=lolB PE=3 SV=1 | MLSSNRRLLRLLPLASLLLTACGLH | 0.0489914 | non-effector |\n\nAfter getting the prediction results, you can plot the probability\ndistribution of the results as follows:\n\n``` r\nplot(pred_result)\n```\n\n

\n\nMore examples with different input formats are available on functions\ndocumentations and vignettes, please refer to the\n[documentation](https://ruthkr.github.io/deepredeff/).","jobInfo":{"package":"deepredeff","version":"0.1.1","parsingStatus":"success","parserVersion":1,"parsedAt":"2021-07-16T12:30:18+0000"}}

Description

Usage

Arguments

Value