|
0
|
1 \documentclass[10pt,pdftex]{article}
|
|
|
2 \usepackage{color}
|
|
|
3 \definecolor{gray}{rgb}{0.7,0.7,0.7}
|
|
|
4
|
|
|
5 \setlength{\topmargin}{0.0cm}
|
|
|
6 \setlength{\textheight}{21.5cm}
|
|
|
7 \setlength{\oddsidemargin}{0cm}
|
|
|
8 \setlength{\textwidth}{16.5cm}
|
|
|
9 \setlength{\columnsep}{0.6cm}
|
|
|
10
|
|
|
11 \begin{document}
|
|
|
12
|
|
|
13 \begin{center}
|
|
|
14 \begin{tabular}{|l|l|l|l|l|}
|
|
|
15 \hline
|
|
|
16 \multicolumn{2}{|c|}{\bf Field} & \multicolumn{1}{c|}{\bf Descrption} & \multicolumn{1}{c|}{\bf Type} & \multicolumn{1}{c|}{\bf Value} \\\hline\hline
|
|
|
17 \multicolumn{2}{|l|}{\sf magic} & Magic string & {\tt char[4]} & {\tt BCF\char92 4} \\\hline
|
|
|
18 \multicolumn{2}{|l|}{\sf l\_seqnm} & Length of concatenated sequence names & {\tt int32\_t} & \\\hline
|
|
|
19 \multicolumn{2}{|l|}{\sf seqnm} & Concatenated names, {\tt NULL} padded & {\tt char[{\sf l\_seqnm}]} & \\\hline
|
|
|
20 \multicolumn{2}{|l|}{\sf l\_smpl} & Length of concatenated sample names & {\tt int32\_t} & \\\hline
|
|
|
21 \multicolumn{2}{|l|}{\sf smpl} & Concatenated sample names & {\tt char[{\sf l\_smpl}]} & \\\hline
|
|
|
22 \multicolumn{2}{|l|}{\sf l\_meta} & Length of the meta text (double-hash lines)& {\tt int32\_t} & \\\hline
|
|
|
23 \multicolumn{2}{|l|}{\sf meta} & Meta text, {\tt NULL} terminated & {\tt char[{\sf l\_meta}]} & \\\hline
|
|
|
24 \multicolumn{5}{|c|}{\it \color{gray}{List of records until the end of the file}}\\\cline{2-5}
|
|
|
25 & {\sf seq\_id} & Reference sequence ID & {\tt int32\_t} & \\\cline{2-5}
|
|
|
26 & {\sf pos} & Position & {\tt int32\_t} & \\\cline{2-5}
|
|
|
27 & {\sf qual} & Variant quality & {\tt float} & \\\cline{2-5}
|
|
|
28 & {\sf l\_str} & Length of {\sf str} & {\tt int32\_t} & \\\cline{2-5}
|
|
|
29 & {\sf str} & {\tt ID+REF+ALT+FILTER+INFO+FORMAT}, {\tt NULL} padded & {\tt char[{\sf l\_str}]} &\\\cline{2-5}
|
|
|
30 & \multicolumn{4}{c|}{Blocks of data; \#blocks and formats defined by {\tt FORMAT} (table below)}\\
|
|
|
31 \hline
|
|
|
32 \end{tabular}
|
|
|
33 \end{center}
|
|
|
34
|
|
|
35 \begin{center}
|
|
|
36 \begin{tabular}{clp{9cm}}
|
|
|
37 \hline
|
|
|
38 \multicolumn{1}{l}{\bf Field} & \multicolumn{1}{l}{\bf Type} & \multicolumn{1}{l}{\bf Description} \\\hline
|
|
|
39 {\tt DP} & {\tt uint16\_t[n]} & Read depth \\
|
|
|
40 {\tt GL} & {\tt float[n*G]} & Log10 likelihood of data; $G=\frac{A(A+1)}{2}$, $A=\#\{alleles\}$\\
|
|
|
41 {\tt GT} & {\tt uint8\_t[n]} & {\tt missing\char60\char60 7 | phased\char60\char60 6 | allele1\char60\char60 3 | allele2} \\
|
|
|
42 {\tt \_GT} & {\tt uint8\_t+uint8\_t[n*P]} & {Generic GT; the first int equals the max ploidy $P$. If the highest bit is set,
|
|
|
43 the allele is not present (e.g. due to different ploidy between samples).} \\
|
|
|
44 {\tt GQ} & {\tt uint8\_t[n]} & {Genotype quality}\\
|
|
|
45 {\tt HQ} & {\tt uint8\_t[n*2]} & {Haplotype quality}\\
|
|
|
46 {\tt \_HQ} & {\tt uint8\_t+uint8\_t[n*P]} & {Generic HQ}\\
|
|
|
47 {\tt IBD} & {\tt uint32\_t[n*2]} & {IBD}\\
|
|
|
48 {\tt \_IBD} & {\tt uint8\_t+uint32\_t[n*P]} & {Generic IBD}\\
|
|
|
49 {\tt PL} & {\tt uint8\_t[n*G]} & {Phred-scaled likelihood of data}\\
|
|
|
50 {\tt PS} & {\tt uint32\_t[n]} & {Phase set}\\
|
|
|
51 %{\tt SP} & {\tt uint8\_t[n]} & {Strand bias P-value (bcftools only)}\\
|
|
|
52 \emph{Integer} & {\tt int32\_t[n*X]} & {Fix-sized custom Integer; $X$ defined in the header}\\
|
|
|
53 \emph{Numeric} & {\tt double[n*X]} & {Fix-sized custom Numeric}\\
|
|
|
54 \emph{String} & {\tt uint32\_t+char*} & {\tt NULL} padded concat. strings (int equals to the length) \\
|
|
|
55 \hline
|
|
|
56 \end{tabular}
|
|
|
57 \end{center}
|
|
|
58
|
|
|
59 \begin{itemize}
|
|
|
60 \item A BCF file is in the {\tt BGZF} format.
|
|
|
61 \item All multi-byte numbers are little-endian.
|
|
|
62 \item In a string, a missing value `.' is an empty C string ``{\tt
|
|
|
63 \char92 0}'' (not ``{\tt .\char92 0}'')
|
|
|
64 \item For {\tt GL} and {\tt PL}, likelihoods of genotypes appear in the
|
|
|
65 order of alleles in {\tt REF} and then {\tt ALT}. For example, if {\tt
|
|
|
66 REF=C}, {\tt ALT=T,A}, likelihoods appear in the order of {\tt
|
|
|
67 CC,CT,TT,CA,TA,AA} (NB: the ordering is different from the one in the original
|
|
|
68 BCF proposal).
|
|
|
69 \item Predefined {\tt FORMAT} fields can be missing from VCF headers, but custom {\tt FORMAT} fields
|
|
|
70 are required to be explicitly defined in the headers.
|
|
|
71 \item A {\tt FORMAT} field with its name starting with `{\tt \_}' is specific to BCF only.
|
|
|
72 It gives an alternative binary representation of the corresponding VCF field, in case
|
|
|
73 the default representation is unable to keep the genotype information,
|
|
|
74 for example, when the ploidy is not 2 or there are more than 8 alleles.
|
|
|
75 \end{itemize}
|
|
|
76
|
|
|
77 \end{document}
|
