219 lines
7.2 KiB
Plaintext
219 lines
7.2 KiB
Plaintext
A Proposed Standard File Format for Chromatograms
|
||
(Version 2, Revision 0)
|
||
|
||
Simon Dear
|
||
(sd@mrc-lmb.cam.ac.uk)
|
||
Medical Research Council
|
||
Laboratory of Molecular Biology
|
||
18 November 1992
|
||
|
||
|
||
|
||
|
||
0. Introduction
|
||
|
||
We seek to establish a standard chromatogram file format that will be
|
||
supported by all sequencing machine manufacturers and software
|
||
developers. Our software supports data in this format. We will
|
||
encourage other software developers to do the same, and equipment
|
||
manufacturers to provide either files in the format, or conversion
|
||
software to produce them.
|
||
|
||
|
||
1. The Header Record
|
||
|
||
The file begins with a 128 byte header record that describes the
|
||
location and size of the chromatogram data in the file. Nothing is
|
||
implied about the order in which the components (samples, sequence and
|
||
comments) appear. The version field is a character string
|
||
respresenting the version and revision of the SCF format. The current
|
||
value of this field is "2.00"
|
||
|
||
/*
|
||
** Type definition for the Header structure
|
||
*/
|
||
#define SCF_MAGIC (((((long)'.'<<8)+(long)'s'<<8)+(long)'c'<<8)+(long)'f')
|
||
typedef struct {
|
||
long magic_number;
|
||
long sample; /* Number of elements in Samples matrix */
|
||
long samples_offset; /* Byte offset from start of file */
|
||
long bases; /* Number of bases in Bases matrix */
|
||
long bases_left_clip; /* Number of bases in left clip (vector)*/
|
||
long bases_right_clip; /* Number of bases in right clip (unreliable) */
|
||
long bases_offset; /* Byte offset from start of file */
|
||
long comments_size; /* Number of bytes in Comment section */
|
||
long comments_offset; /* Byte offset from start of file */
|
||
char version[4]; /* "version.revision" */
|
||
long sample_size; /* Size of samples in bytes 1=8bits, 2=16bits*/
|
||
long code_set; /* code set used */
|
||
long spare[20]; /* Unused */
|
||
} Header;
|
||
|
||
NOTE: Features new to version 2
|
||
|
||
For versions of SCF files 2.0 or greater (Header.version >= "2.00"),
|
||
the version number, precision of data, the uncertain code set are
|
||
specified in the header. Otherwise, the precision is assumed to be 1
|
||
byte, and the code set to be the default code set.
|
||
|
||
The following uncertainty code sets are recognised. People wishing to
|
||
use others with the SCF format should register them with the author of
|
||
this document.
|
||
|
||
0 {A,C,G,T,-} (default)
|
||
1 Staden
|
||
2 IUPAC (NC-IUB)
|
||
3 Pharmacia A.L.F. (NC-IUB)
|
||
4 {A,C,G,T,N} (ABI 373A)
|
||
5 IBI/Pustell
|
||
6 DNA*
|
||
7 DNASIS
|
||
8 IG/PC-Gene
|
||
9 MicroGenie
|
||
|
||
|
||
2. The Sample Points.
|
||
|
||
The trace information is stored at byte offset Header.samples_offset
|
||
from the start of the file. For each sample point there are values for
|
||
each of the four bases. Header.sample_size holds the precision of the
|
||
sample values. The precision must be one of "1" (unsigned byte) and
|
||
"2" (unsigned short). The sample points need not be normalised to any
|
||
particular value, though it is assumed that they represent positive
|
||
values. This is, they are of unsigned type.
|
||
|
||
/*
|
||
** Type definition for the Sample data
|
||
*/
|
||
|
||
typedef struct {
|
||
unsigned char sample_A; /* Sample for A trace */
|
||
unsigned char sample_C; /* Sample for C trace */
|
||
unsigned char sample_G; /* Sample for G trace */
|
||
unsigned char sample_T; /* Sample for T trace */
|
||
} Samples1;
|
||
typedef struct {
|
||
unsigned short sample_A; /* Sample for A trace */
|
||
unsigned short sample_C; /* Sample for C trace */
|
||
unsigned short sample_G; /* Sample for G trace */
|
||
unsigned short sample_T; /* Sample for T trace */
|
||
} Samples2;
|
||
|
||
NOTE: Features new to version 2
|
||
The samples are no longer restricted to 8 bit values.
|
||
|
||
|
||
3. Sequence Information.
|
||
|
||
Information relating to the base interpretation of the trace is stored
|
||
at byte offset Header.bases_offset from the start of the file. Stored
|
||
for each base are: its character representation and a number (an index
|
||
into the Samples data structure) indicating its position within the
|
||
trace. The relative probabilities of each of the 4 bases occuring at
|
||
the point where the base is called can be stored in prob_A, prob_C,
|
||
prob_G and prob_T.
|
||
|
||
The Amersham FilmReader uses Bases.spare[0] to store the confidence
|
||
level of the base. The value ranges from 0 (low confidence) to 8
|
||
(high), and 9 indicating the base has been manually edited.
|
||
|
||
/*
|
||
** Type definition for the sequence data
|
||
*/
|
||
typedef unsigned char byte;
|
||
typedef struct {
|
||
long peak_index; /* Index into Samples matrix for base position */
|
||
byte prob_A; /* Probability of it being an A */
|
||
byte prob_C; /* Probability of it being an C */
|
||
byte prob_G; /* Probability of it being an G */
|
||
byte prob_T; /* Probability of it being an T */
|
||
char base; /* Called base character */
|
||
byte spare[3]; /* Spare */
|
||
} Base;
|
||
|
||
|
||
|
||
4. Comments.
|
||
|
||
Comments are stored at offset Header.comments_offset from the start of
|
||
the file. Lines in this section are of the format:
|
||
|
||
<Field-ID>=<Value>
|
||
|
||
<Field-ID> can be any string, though several have special meaning and
|
||
their use is encouraged.
|
||
|
||
ID Field Example
|
||
---- ------------------------ ----------------
|
||
MACH Sequencing machine model MACH=Pharmacia A.L.F.
|
||
TPSW Trace processing software version TPSW=A.L.F. Analysis Program, Version=1.67
|
||
BCSW Base calling software version BCSW=A.L.F. Analysis Program, Version=1.67
|
||
DATF Data source format DATF=AM_Version=2.0
|
||
DATN Data source name DATN=a10c.alf
|
||
CONV Format conversion software CONV=makeSCF v2.0
|
||
|
||
Other fields might include:
|
||
|
||
ID Field Example
|
||
---- ------------------------ ----------------
|
||
OPER Operator OPER=sd
|
||
STRT Time run started STRT=Aug 05 1991 12:25:01
|
||
STOP Time run stopped STOP=Aug 05 1991 16:26:25
|
||
PROC Time processed PROC=Aug 05 1991 18:50:13
|
||
EDIT Time edited EDIT=Aug 05 1991 19:06:18
|
||
NAME Sample name NAME=a21b1.s1
|
||
SIGN Average signal strength SIGN=A=56,C=66,G=13,T=18
|
||
SPAC Average base spacing SPAC=12.04
|
||
SCAL Factor used in scaling traces SCAL=0.5
|
||
|
||
|
||
/*
|
||
** Type definition for the comments
|
||
*/
|
||
typedef char Comments; /* Zero terminated list of \n separated entries */
|
||
|
||
Appendix: Byte ordering and integer representation
|
||
|
||
"Forward byte and reverse bit" ordering will be used for all integer
|
||
values. This is the same as used in the MC680x0 and SPARC processors,
|
||
but the reverse of the byte ordering used on the VAX and Intel 80x86
|
||
processors.
|
||
|
||
|
||
Off+0 Off+1
|
||
+-------+-------+
|
||
Short | MSB | LSB |
|
||
+-------+-------+
|
||
|
||
Off+0 Off+1 Off+2 Off+3
|
||
+-------+-------+-------+-------+
|
||
Long | MSB | ... | ... | LSB |
|
||
+-------+-------+-------+-------+
|
||
|
||
|
||
|
||
To read integers on systems with any byte order use something like this:
|
||
|
||
short read_short(FILE *fp)
|
||
{
|
||
unsigned char buf[sizeof(short)];
|
||
|
||
fread(buf, sizeof(buf), 1, fp);
|
||
return (short)
|
||
(((unsigned short)buf[1]) +
|
||
((unsigned short)buf[0]<<8));
|
||
}
|
||
|
||
long read_long(FILE *fp)
|
||
{
|
||
unsigned char buf[sizeof(long)];
|
||
|
||
fread(buf, sizeof(buf), 1, fp);
|
||
return (long)
|
||
(((unsigned long)buf[3]) +
|
||
((unsigned long)buf[2]<<8) +
|
||
((unsigned long)buf[1]<<16) +
|
||
((unsigned long)buf[0]<<24));
|
||
}
|
||
|