File: sequence_from.c

package info (click to toggle)
garlic 1.4-1
  • links: PTS
  • area: main
  • in suites: sarge
  • size: 4,192 kB
  • ctags: 1,368
  • sloc: ansic: 49,603; makefile: 1,079
file content (228 lines) | stat: -rw-r--r-- 6,315 bytes parent folder | download | duplicates (5)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
/* Copyright (C) 2000-2002 Damir Zucic */

/*=============================================================================

				sequence_from.c

Purpose:
	Copy the sequence  from the specified macromolecular complex to
	the sequence buffer. Only the sequence for selected range(s) is
	copied.  A residue is treated as selected  if the first atom of
	this residue is selected.  For proteins,  this is typically  N.
	The original  residue  sequence  indices are copyed.  Insertion
	codes are, however, ignored,  so it is possible  that some res.
	serial indices appear more than once in the buffer.

Input:
	(1) Pointer to MolComplexS structure, with macromol. complexes.
	(2) The number of macromolecular complexes.
	(3) Pointer to RuntimeS structure.
	(4) Pointer to the string which contains  the macromol. complex
	    identifier.

Output:
	(1) Sequence from the specified complex  copied to the sequence
	    buffer.
	(2) Return value.

Return value:
	(1) Positive (command) code on success.
	(2) Negative (error) code on failure.

========includes:============================================================*/

#include <stdio.h>

#include <string.h>

#include <X11/Xlib.h>
#include <X11/Xutil.h>
#include <X11/Xos.h>
#include <X11/Xatom.h>

#include "defines.h"
#include "commands.h"
#include "typedefs.h"

/*======function prototypes:=================================================*/

char		*ExtractToken_ (char *, int, char *, char *);
void		InitHyphob_ (RuntimeS *);

/*======copy sequence from complex to sequence buffer:=======================*/

int SequenceFrom_ (MolComplexS *mol_complexSP, int mol_complexesN,
		   RuntimeS *runtimeSP, char *stringP)
{
int			max_length;
char			*remainderP;
char			tokenA[SHORTSTRINGSIZE];
int			complexID;
int			mol_complexI;
static MolComplexS	*curr_mol_complexSP;
int			job_doneF = 0;
size_t			residue1I, residues1N;
ResidueS		*curr_residueSP;
AtomS			*first_atomSP;
AtomS			*last_atomSP;
AtomS			*curr_atomSP;
size_t			offset;
char			*sourceP, *destP;
size_t			residue2I = 0;
int			bondsN, bondI;
TrueBondS		*curr_bondSP;
int			disulfideF;
int			*curr_disulfideFP;

/* The maximal residue name length: */
max_length = RESNAMESIZE - 1;

/* At least one macromolecular complex should be available: */
if (mol_complexesN == 0)
	{
	strcpy (runtimeSP->messageA, "No structure loaded!");
	runtimeSP->message_length = strlen (runtimeSP->messageA);
	return -1;
	}

/* Take the first token; it should be present: */
remainderP = ExtractToken_ (tokenA, SHORTSTRINGSIZE, stringP, " \t\n");
if (!remainderP)
	{
	strcpy (runtimeSP->messageA, "Complex identifier missing!");
	runtimeSP->message_length = strlen (runtimeSP->messageA);
	return -2;
	}

/* Extract the macromolecular complex identifier: */
if (sscanf (tokenA, "%d", &complexID) != 1)
	{
	strcpy (runtimeSP->messageA, "Bad macromolecular complex identifier!");
	runtimeSP->message_length = strlen (runtimeSP->messageA);
	return -3;
	}

/* Check is the requested complex available at all: */
for (mol_complexI = 0; mol_complexI < mol_complexesN; mol_complexI++)
	{
	/** Prepare the pointer to the current macromolecular complex: **/
	curr_mol_complexSP = mol_complexSP + mol_complexI;

	/* Check the number of atoms;  for bad */
	/* and discarded complexes it is zero: */
	if (curr_mol_complexSP->atomsN == 0) continue;

	/* If macromol. complex is recognized, set the catch flag to one: */
	if (curr_mol_complexSP->mol_complexID == complexID)
		{
		job_doneF = 1;
		break;
		}
	}

/* If the requested complex is not available, return negative value: */
if (job_doneF == 0)
	{
	strcpy (runtimeSP->messageA,
		"The requested complex is not available!");
	runtimeSP->message_length = strlen (runtimeSP->messageA);
	return -4;
	}

/* Copy the sequence: */
residues1N = curr_mol_complexSP->residuesN;
for (residue1I = 0; residue1I < residues1N; residue1I++)
	{
	/* Pointer to the current residue: */
	curr_residueSP = curr_mol_complexSP->residueSP + residue1I;

	/* Pointer to the first atom: */
	first_atomSP = curr_mol_complexSP->atomSP +
		       curr_residueSP->residue_startI;

	/* Pointer to the last atom: */
	last_atomSP = curr_mol_complexSP->atomSP +
		      curr_residueSP->residue_endI;

	/* If this atom is not selected, do not copy the residue name: */
	if (first_atomSP->selectedF == 0) continue;

	/* Pointer to the residue name associated with this atom: */
	sourceP = first_atomSP->raw_atomS.pure_residue_nameA;

	/* Prepare and check the position in seq. */
	/* buffer where this name will be copied: */
	offset = max_length * residue2I;
	if (offset > runtimeSP->sequence_buffer_size - 10 * max_length)
		{
		strcpy (runtimeSP->messageA, "Sequence too long!");
		runtimeSP->message_length = strlen (runtimeSP->messageA);
		return -5;
		}

	/* Copy the residue name: */
	destP = runtimeSP->sequenceP + offset;
	strncpy (destP, sourceP, max_length);

	/* Copy the residue serial index: */
	*(runtimeSP->serialIP + residue2I) =
				first_atomSP->raw_atomS.residue_sequenceI;

	/* Now it is time to set disulfide flag for the current residue. */

	/* Pointer to disulfide flag for the current residue: */
	curr_disulfideFP = runtimeSP->disulfideFP + residue2I;

	/* Reset disulfide flag: */
	*curr_disulfideFP = 0;

	/* Reset the flag: */
	disulfideF = 0;

	/* Check is this residue involved in disulfide bond: */
	for (curr_atomSP = first_atomSP;
	     curr_atomSP <= last_atomSP;
	     curr_atomSP++)
		{
		/* The number of bonds: */
		bondsN = curr_atomSP->bondsN;

		/* Check is disulfide bond present: */
		for (bondI = 0; bondI < bondsN; bondI++)
			{
			/* Pointer to the current bond: */
			curr_bondSP = curr_atomSP->true_bondSA + bondI;

			/* If this bond is disulfide */
			/* bond, set flag and break: */
			if (curr_bondSP->bond_typeI == 2)
				{
				disulfideF = 1;
				break;
				}
			}

		/* If at least one disulfide bond is found, break from loop: */
		if (disulfideF != 0) break;
		}

	/* Update disulfide flag: */
	if (disulfideF) *curr_disulfideFP = 1;

	/* Update the output residue index: */
	residue2I++;
	}

/* Set the number of residues: */
runtimeSP->residuesN = residue2I;

/* Initialize hydrophobicity values: */
InitHyphob_ (runtimeSP);

/* Return positive value on success: */
return 1;
}

/*===========================================================================*/