@lipme/ts-biofiledetector NPM

TS-BIOFILEDETECTOR

Overview

A set of function to predict file formats

Formats included:

Fasta (proteic/nucleic)
GFF3 (annotation/alignment)
BED
VCF
TSV, with specific typing of :
- OrthoFinder
- InterProScan
- Nicknames
- Xref (a simple minimalist query/target table with additionnal columns)
- PAF
- Differential Gene Expression Table
BAM
BigWig

Installation

npm i @lipme/ts-biofiledetector

Usage

import { getFileFormat } from "@lipme/ts-biofiledetector";

Output

Fasta

{
  format: "fasta",
  valid: true|false,
  metadata: {
    type: "dna|protein",
    category: "sequence",
    seqids: ['list','of','seqids']
    error?: { 'errorType' : ['list', 'of', 'erroneous', 'lines']}
  }
}

GFF3

{
    format: "gff3",
    valid: true|false,
    metadata: {
    type: "annotation|alignment",
    category: "annotation|alignment",
    seqids: ['list','of','seqids'],
    features: ['list', 'of', 'features'],
    attributes: ['list', 'of', 'attributes'],
    error?: { 'errorType' : ['list', 'of', 'erroneous', 'lines']}
  }
}

{
  format: "bed",
  valid: true|false,
  metadata: {
    type: "bed3|bed4|bed6|bed9|bed12",
    category: "annotation",
    seqids: ['list','of','seqids'],
    columns: "numberOfColumns",
    withBrowser: true|false, //browser line found
    withTrack: true|false, //track line found
    error?: { 'errorType' : ['list', 'of', 'erroneous', 'lines']}
  }
}

{
  format: "vcf",
  valid: true|false,
  metadata: {
    type: "VCFversion",
    category: "polymorphism",
    seqids: ['list','of','seqids'],
    samples: ['list','of','samples'],
    fields: {'INFO', 'and', 'FORMAT', 'metadata'}
    error?: { 'errorType' : ['list', 'of', 'erroneous', 'lines']}
    }
}

{
  format: "tsv",
  valid: true|false,
  metadata: {
    type: "tsvX|orthofinder|interproscan|nicknames|xref|paf|dge",
    category: "table|alignment",
    columns: "numberOfColumns",
    lines: "numberOfLines",
    explicitHeader: true|false, //true if first line stars with '#'
    header:: ['list','of','field','names'],
    error?: { 'errorType' : ['list', 'of', 'erroneous', 'lines']}
    }
}

{
  format: "bam",
  valid: true,
  metadata: {
    type: "alignment",
    category: "alignment",
    seqids: ['list', 'of', 'seqids'], // @SQ lines
    programs: ['list', 'of', 'programs']  //@PG lines
  }
}

BigWig

{
  format: "bigwig",
  valid: true,
  metadata: {
    type: "quantitative",
    category: "quantitative",
    seqids: ['list', 'of', 'seqids'], // @SQ lines
    version: 'bigwigVersion'
  }
}