CITATION.cff

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: >-
  Drug resistance prediction for Mycobacterium tuberculosis
  with reference graphs
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Michael
    name-particle: B
    family-names: Hall
    email: michael.hall2@unimelb.edu.au
    affiliation: University of Melbourne
    orcid: 'https://orcid.org/0000-0003-3683-6208'
  - given-names: Leandro
    family-names: Lima
    affiliation: EMBL-EBI
    orcid: 'https://orcid.org/0000-0001-8976-2762'
  - given-names: Lachlan
    name-particle: J.M
    family-names: Coin
    orcid: 'https://orcid.org/0000-0002-4300-455X'
    affiliation: University of Melbourne
  - given-names: Zamin
    family-names: Iqbal
    affiliation: EMBL-EBI
    orcid: 'https://orcid.org/0000-0001-8466-7547'
identifiers:
  - type: doi
    value: 10.1101/2023.05.04.539481
    description: The bioRxiv deposit of the accompanying paper
repository-code: 'https://github.com/mbhall88/drprg/'
url: 'https://mbh.sh/drprg/'
abstract: >-
  The dominant paradigm for analysing genetic variation
  relies on a central idea: all genomes in a species can be
  described as minor differences from a single reference
  genome. However, this approach can be problematic or
  inadequate for bacteria, where there can be significant
  sequence divergence within a species.


  Reference graphs are an emerging solution to the reference
  bias issues implicit in the “single-reference” model. Such
  a graph represents variation at multiple scales within a
  population – e.g., nucleotide- and locus-level.


  The genetic causes of drug resistance in bacteria have
  proven comparatively easy to decode compared with studies
  of human diseases. For example, it is possible to predict
  resistance to numerous anti-tuberculosis drugs by simply
  testing for the presence of a list of single nucleotide
  polymorphisms and insertion/deletions, commonly referred
  to as a catalogue.


  We developed DrPRG (Drug resistance Prediction with
  Reference Graphs) using the bacterial reference graph
  method Pandora. First, we outline the construction of a
  Mycobacterium tuberculosis drug resistance reference
  graph, a process that can be replicated for other species.
  The graph is built from a global dataset of isolates with
  varying drug susceptibility profiles, thus capturing
  common and rare resistance- and susceptible-associated
  haplotypes. We benchmark DrPRG against the existing
  graph-based tool Mykrobe and the pileup-based approach of
  TBProfiler using 44,709 and 138 publicly available
  Illumina and Nanopore datasets with associated phenotypes.
  We find DrPRG has significantly improved sensitivity and
  specificity for some drugs compared to these tools, with
  no significant decreases. It uses significantly less
  computational memory than both tools, and provides
  significantly faster runtimes, except when runtime is
  compared to Mykrobe on Illumina data.


  We discover and discuss novel insights into
  resistance-conferring variation for M. tuberculosis -
  including deletion of genes katG and pncA – and suggest
  mutations that may warrant reclassification as associated
  with resistance.
keywords:
  - bioinformatics
  - genome graphs
  - antimicrobial resistance
  - resistance prediction
  - software
license: MIT
version: 0.1.1
date-released: '2023-04-06'