CITATION.cff

# YAML 1.2
---
authors:
  -
    family-names: Vlasova
    given-names: Anna
  -
    family-names: "Hermoso Pulido"
    given-names: Toni
    orcid: "https://orcid.org/0000-0003-2016-6465"
  -
    family-names: Camara
    given-names: Francisco
    orcid: "https://orcid.org/0000-0002-1971-5466 "
  -
    family-names: Ponomarenko
    given-names: Julia
    orcid: "https://orcid.org/0000-0002-1477-9444"
  -
    family-names: "Guigó"
    given-names: Roderic
    orcid: "https://orcid.org/0000-0002-5738-4477"
cff-version: "1.2.0"
doi: "10.5281/zenodo.5526102"
keywords:
  - "functional annotation"
  - containerization
  - pipeline
  - reproducibility
license: GPL-3.0+
message: "If you use this software, please cite it using these metadata."
repository-code: "https://github.com/guigolab/FA-nf"
title: "FA-nf: A Functional Annotation Pipeline for Proteins from Non-Model Organisms Implemented in Nextflow"
preferred-citation:
  type: article
  authors:
    - family-names: Vlasova
      given-names: Anna
    - family-names: "Hermoso Pulido"
      given-names: Toni
      orcid: "https://orcid.org/0000-0003-2016-6465"
    - family-names: Camara
      given-names: Francisco
      orcid: "https://orcid.org/0000-0002-1971-5466 "
    - family-names: Ponomarenko
      given-names: Julia
      orcid: "https://orcid.org/0000-0002-1477-9444"
    - family-names: "Guigó"
      given-names: Roderic
      orcid: "https://orcid.org/0000-0002-5738-4477"
  doi: "10.3390/genes12101645"
  journal: "Genes"
  title: "FA-nf: A Functional Annotation Pipeline for Proteins from Non-Model Organisms Implemented in Nextflow"
  abstract: "Functional annotation allows adding biologically relevant information to predicted features in genomic sequences, and it is, therefore, an important procedure of any de novo genome sequencing project. It is also useful for proofreading and improving gene structural annotation. Here, we introduce FA-nf, a pipeline implemented in Nextflow, a versatile computational workflow management engine. The pipeline integrates different annotation approaches, such as NCBI BLAST+, DIAMOND, InterProScan, and KEGG. It starts from a protein sequence FASTA file and, optionally, a structural annotation file in GFF format, and produces several files, such as GO assignments, output summaries of the abovementioned programs and final annotation reports. The pipeline can be broken easily into smaller processes for the purpose of parallelization and easily deployed in a Linux computational environment, thanks to software containerization, thus helping to ensure full reproducibility."
  year: 2021
  volume: 12
  number: 10
  issn: 2073-4425
...