The Sanger FASTQ file format for sequences with quality scores, and the Solexa/Illumina FASTQ variants

Abstract

FASTQ has emerged as a common file format for sharing sequencing read data combining both the sequence and an associated per base quality score, despite lacking any formal definition to date, and existing in at least three incompatible variants. This article defines the FASTQ format, covering the original Sanger standard, the Solexa/Illumina variants and conversion between them, based on publicly available information such as the MAQ documentation and conventions recently agreed by the Open Bioinformatics Foundation projects Biopython, BioPerl, BioRuby, BioJava and EMBOSS. Being an open access publication, it is hoped that this description, with the example files provided as Supplementary Data, will serve in future as a reference for this important file format.

Figure 1.

Visual representation of the mapping between PHRED and Solexa quality scores. Vertical layout represents the probability of error on a log scale, therefore the PHRED points are equally spaced (black circles on left), while the Solexa points are not (white circles on right). Solid black lines are reciprocal mappings between scores, and grey arrows are lossy mappings. Near the top of the figure, the black lines are almost horizontal because the two scores are almost equal. The straightforward mapping of higher scores is omitted due to space.