« back to all changes in this revision
Viewing changes to sequin/sequin3.c
- browse files at revision 8
- compare with another revision
- download diff
- download tarball
- view history from revision 8
- Committer: Bazaar Package Importer
- Author(s): Barry deFreese
- Date: 2006-07-19 23:28:07 UTC
- mfrom: (1.1.5 upstream)
- Revision ID: james.westby@ubuntu.com-20060719232807-et3cdmcjgmnyleyx
Tags: 6.1.20060507-3ubuntu1
Re-merge with Debian
- files added:
- algo/blast/api/blast_message_api.c
- files removed:
- debian/libvibrant6.install
- files modified:
- VERSION
added
removed
sequin/sequin3.c
29
29
*
30
30
* Version Creation Date: 1/22/95
31
31
*
32
* $Revision: 6.629 $
32
* $Revision: 6.678 $
33
33
*
34
34
* File Description:
35
35
*
71
71
#include <saledit.h>
72
72
#include <alignmgr2.h>
73
73
#include <suggslp.h>
74
#include <asn2gnbi.h>
75
76
static void ConvertBadInfProc (SeqFeatPtr sfp, Pointer userdata)
77
78
{
79
GBQualPtr gbq;
80
size_t len;
81
CharPtr ptr, str;
82
83
if (sfp == NULL) return;
84
for (gbq = sfp->qual; gbq != NULL; gbq = gbq->next) {
85
if (StringICmp (gbq->qual, "inference") != 0) continue;
86
if (ValidateInferenceQualifier (gbq->val, FALSE) != VALID_INFERENCE) {
87
if (StringNICmp (gbq->val, "similar to ", 11) == 0) {
88
ptr = StringChr (gbq->val, ':');
89
if (ptr != NULL) {
90
ptr++;
91
if (StringDoesHaveText (ptr)) {
92
len = StringLen ("similar to ") + StringLen (ptr);
93
str = MemNew (len + 5);
94
if (str != NULL) {
95
StringCpy (str, "similar to ");
96
StringCat (str, ptr);
97
gbq->val = MemFree (gbq->val);
98
gbq->val = StringSave (str);
99
MemFree (str);
100
}
101
}
102
}
103
}
104
gbq->qual = MemFree (gbq->qual);
105
gbq->qual = StringSave ("note");
106
}
107
}
108
}
109
110
static void ConvertBadInferenceToNote (IteM i)
111
112
{
113
BaseFormPtr bfp;
114
SeqEntryPtr sep;
115
116
#ifdef WIN_MAC
117
bfp = currentFormDataPtr;
118
#else
119
bfp = GetObjectExtra (i);
120
#endif
121
if (bfp == NULL) return;
122
123
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
124
125
VisitFeaturesInSep (sep, NULL, ConvertBadInfProc);
126
127
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
128
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
129
Update ();
130
}
74
131
75
132
typedef struct {
76
133
Int2 level;
453
510
if (digits + 1 + len > 16) {
454
511
prefix += digits + 1 + len - 16;
455
512
}
513
456
514
for (sep = pbssp->seq_set, segment = 1; sep != NULL; sep = sep->next, segment++) {
457
515
DoFixPartLocus (sep, prefix, segment, digits);
458
516
}
517
459
518
if (sbsp == NULL) return;
460
519
tsip = NULL;
461
520
for (sip = sbsp->id; sip != NULL; sip = sip->next) {
471
530
tsip->name = MemFree (tsip->name);
472
531
sprintf (str, "SEG_%sS", prefix);
473
532
tsip->name = StringSave (str);
533
SeqMgrReplaceInBioseqIndex (sbsp);
474
534
}
475
535
476
536
static void ForceLocusFixup (IteM i)
528
588
while (sdp != NULL) {
529
589
nextsdp = sdp->next;
530
590
empty = FALSE;
531
if (sdp->choice == Seq_descr_genbank && sdp->data.ptrvalue != NULL) {
591
if (sdp->choice == Seq_descr_genbank && sdp->data.ptrvalue == NULL) {
592
empty = TRUE;
593
} else if (sdp->choice == Seq_descr_genbank && sdp->data.ptrvalue != NULL) {
532
594
gbp = (GBBlockPtr) sdp->data.ptrvalue;
533
595
gbp->source = MemFree (gbp->source); /* remove within Sequin */
534
596
gbp->origin = MemFree (gbp->origin);
711
773
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
712
774
if (sep == NULL) return;
713
775
714
AssignCDSmRNAfeatureIDs (sep);
776
AssignFeatureIDs (sep);
777
778
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
779
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
780
ObjMgrDeSelect (0, 0, 0, 0, NULL);
781
Update ();
782
}
783
784
static void ReassignFeatIDs (IteM i)
785
786
{
787
MsgAnswer ans;
788
BaseFormPtr bfp;
789
SeqEntryPtr sep;
790
791
#ifdef WIN_MAC
792
bfp = currentFormDataPtr;
793
#else
794
bfp = GetObjectExtra (i);
795
#endif
796
if (bfp == NULL) return;
797
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
798
if (sep == NULL) return;
799
800
ans = Message (MSG_OKC, "Are you sure you want to reassign feature identifiers?");
801
if (ans == ANS_CANCEL) return;
802
803
ReassignFeatureIDs (sep);
715
804
716
805
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
717
806
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
738
827
ans = Message (MSG_YN, "Are you sure you want to remove feature IDs and links?");
739
828
if (ans == ANS_NO) return;
740
829
741
ClearCDSmRNAfeatureIDs (sep);
830
ClearFeatureIDs (sep);
742
831
743
832
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
744
833
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
841
930
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
842
931
if (sep == NULL) return;
843
932
844
AssignCDSmRNAfeatureIDs (sep);
933
AssignFeatureIDs (sep);
845
934
846
935
ssp = ObjMgrGetSelected ();
847
936
if (ssp == NULL) {
2961
3050
Message (MSG_OK, "Some manual desktop manipulations remain");
2962
3051
}
2963
3052
3053
3054
static void CollectBioseqsForConversion (BioseqPtr bsp, Pointer userdata)
3055
{
3056
ValNodePtr PNTR list;
3057
3058
if (bsp == NULL || bsp->repr != Seq_repr_raw || ISA_aa (bsp->mol)) return;
3059
if (userdata == NULL)
3060
{
3061
return;
3062
}
3063
list = (ValNodePtr PNTR) userdata;
3064
3065
ValNodeAddPointer (list, 0, bsp);
3066
}
3067
3068
static ValNodePtr GetAnnotListForBspList (ValNodePtr bsp_list)
3069
{
3070
BioseqPtr bsp;
3071
SeqAnnotPtr sanp;
3072
ValNodePtr complete_annot_list = NULL, align_annot_list;
3073
ValNodePtr annot_vnp, vnp, bsp_vnp;
3074
Boolean found;
3075
3076
for (bsp_vnp = bsp_list; bsp_vnp != NULL; bsp_vnp = bsp_vnp->next)
3077
{
3078
bsp = (BioseqPtr)(bsp_vnp->data.ptrvalue);
3079
align_annot_list = FindAlignSeqAnnotsForBioseq (bsp);
3080
for (annot_vnp = align_annot_list; annot_vnp != NULL; annot_vnp = annot_vnp->next)
3081
{
3082
sanp = (SeqAnnotPtr) annot_vnp->data.ptrvalue;
3083
if (sanp->type == 2 && sanp->data != NULL)
3084
{
3085
for (vnp = complete_annot_list, found = FALSE;
3086
vnp != NULL && !found;
3087
vnp = vnp->next)
3088
{
3089
if (vnp->data.ptrvalue == sanp)
3090
{
3091
found = TRUE;
3092
}
3093
}
3094
if (!found)
3095
{
3096
ValNodeAddPointer (&complete_annot_list, 0, sanp);
3097
}
3098
}
3099
}
3100
align_annot_list = ValNodeFree (align_annot_list);
3101
}
3102
return complete_annot_list;
3103
}
3104
3105
3106
static void
3107
CleanupAlignmentsAfterConversion
3108
(ValNodePtr adjusted_bsp_list,
3109
Uint2 entityID)
3110
{
3111
ValNodePtr align_annot_list, annot_vnp;
3112
SeqAnnotPtr sanp;
3113
3114
align_annot_list = GetAnnotListForBspList (adjusted_bsp_list);
3115
for (annot_vnp = align_annot_list;
3116
annot_vnp != NULL;
3117
annot_vnp = annot_vnp->next)
3118
{
3119
sanp = annot_vnp->data.ptrvalue;
3120
if (sanp != NULL && sanp->type == 2)
3121
{
3122
ConsolidateSegmentsOverKnownLengthGaps (sanp->data);
3123
FixOneAlignmentOverGaps (sanp->data, entityID);
3124
}
3125
}
3126
align_annot_list = ValNodeFree (align_annot_list);
3127
DeleteMarkedObjects (entityID, 0, NULL);
3128
3129
}
3130
3131
static void CorrectAlignmentsAfterNToGapConversion (SeqEntryPtr sep, Uint2 entityID)
3132
{
3133
ValNodePtr adjusted_bsp_list = NULL;
3134
3135
VisitBioseqsInSep (sep, &adjusted_bsp_list, CollectBioseqsForConversion);
3136
CleanupAlignmentsAfterConversion (adjusted_bsp_list, entityID);
3137
adjusted_bsp_list = ValNodeFree (adjusted_bsp_list);
3138
}
3139
3140
static void ConvertNsToGapsWithSizeList (Uint2 entityID, Int4Ptr gap_sizes, Boolean adjust_cds)
3141
{
3142
ValNodePtr adjusted_bsp_list = NULL;
3143
SeqEntryPtr sep;
3144
3145
sep = GetTopSeqEntryForEntityID (entityID);
3146
if (sep == NULL) return;
3147
VisitBioseqsInSep (sep, &adjusted_bsp_list, CollectBioseqsForConversion);
3148
3149
if (adjust_cds)
3150
{
3151
/* remove the gap locations from the coding regions first */
3152
VisitBioseqsInSep (sep, gap_sizes, PrepareCodingRegionLocationsForDeltaConversionCallback);
3153
}
3154
3155
VisitBioseqsInSep (sep, gap_sizes, ConvertNsToGaps);
3156
CleanupAlignmentsAfterConversion (adjusted_bsp_list, entityID);
3157
adjusted_bsp_list = ValNodeFree (adjusted_bsp_list);
3158
ObjMgrSetDirtyFlag (entityID, TRUE);
3159
ObjMgrSendMsg (OM_MSG_UPDATE, entityID, 0, 0);
3160
}
3161
3162
2964
3163
static void RawSeqToDeltaSeq (IteM i)
2965
3164
2966
3165
{
2967
3166
BaseFormPtr bfp;
2968
SeqEntryPtr sep;
2969
3167
2970
3168
#ifdef WIN_MAC
2971
3169
bfp = currentFormDataPtr;
2973
3171
bfp = GetObjectExtra (i);
2974
3172
#endif
2975
3173
if (bfp == NULL) return;
2976
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
2977
if (sep == NULL) return;
2978
VisitBioseqsInSep (sep, NULL, ConvertNsToGaps);
2979
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
2980
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
3174
ConvertNsToGapsWithSizeList (bfp->input_entityID, NULL, FALSE);
2981
3175
}
2982
3176
2983
3177
static void RawSeqToDeltaSeqUnknownLengthGaps (IteM i)
2984
3178
2985
3179
{
2986
3180
BaseFormPtr bfp;
2987
SeqEntryPtr sep;
2988
3181
Int4 gap_sizes[2];
2989
3182
2990
3183
#ifdef WIN_MAC
2993
3186
bfp = GetObjectExtra (i);
2994
3187
#endif
2995
3188
if (bfp == NULL) return;
2996
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
2997
if (sep == NULL) return;
2998
3189
gap_sizes [0] = 100;
2999
3190
gap_sizes [1] = -1;
3000
VisitBioseqsInSep (sep, gap_sizes, ConvertNsToGaps);
3001
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
3002
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
3191
ConvertNsToGapsWithSizeList (bfp->input_entityID, gap_sizes, FALSE);
3003
3192
}
3004
3193
3005
3194
static void RawSeqToDeltaSeqUnknown100LengthGaps (IteM i)
3006
3195
3007
3196
{
3008
3197
BaseFormPtr bfp;
3009
SeqEntryPtr sep;
3010
3198
Int4 gap_sizes[2];
3011
3199
3012
3200
#ifdef WIN_MAC
3015
3203
bfp = GetObjectExtra (i);
3016
3204
#endif
3017
3205
if (bfp == NULL) return;
3018
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
3019
if (sep == NULL) return;
3020
3206
gap_sizes [0] = -1;
3021
3207
gap_sizes [1] = 0;
3022
VisitBioseqsInSep (sep, gap_sizes, ConvertNsToGaps);
3023
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
3024
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
3208
ConvertNsToGapsWithSizeList (bfp->input_entityID, gap_sizes, FALSE);
3025
3209
}
3026
3210
3027
3211
#if 0
3333
3517
3334
3518
3335
3519
Hide (gcp->form);
3336
if (GetStatus (gcp->adjust_CDS_locations))
3337
{
3338
/* remove the gap locations from the coding regions first */
3339
VisitBioseqsInSep (sep, gap_sizes, PrepareCodingRegionLocationsForDeltaConversionCallback);
3340
/* then change the gap locations into delta gaps */
3341
VisitBioseqsInSep (sep, gap_sizes, ConvertNsToGaps);
3342
}
3343
ObjMgrSetDirtyFlag (gcp->input_entityID, TRUE);
3344
ObjMgrSendMsg (OM_MSG_UPDATE, gcp->input_entityID, 0, 0);
3520
ConvertNsToGapsWithSizeList (gcp->input_entityID, gap_sizes, GetStatus (gcp->adjust_CDS_locations));
3521
3345
3522
Remove (gcp->form);
3346
3523
}
3347
3524
3376
3553
{
3377
3554
msg = CreateListMessage ("Sequence",
3378
3555
raw_in_aln->next == NULL
3379
? " is in an alignment. Do you want to continue?"
3380
: " are in alignments. Do you want to continue?",
3556
? " is in an alignment. The alignment will be automatically adjusted after conversion. Do you want to continue?"
3557
: " are in alignments. The alignment will be automatically adjusted after conversion. Do you want to continue?",
3381
3558
raw_in_aln);
3382
3559
raw_in_aln = ValNodeFreeData (raw_in_aln);
3383
3560
ans = Message (MSG_YN, msg);
3548
3725
3549
3726
} DeltaConversionData, PNTR DeltaConversionPtr;
3550
3727
3728
3729
static SeqAlignPtr
3730
AdjustOneAlignmentForOneBioseqBasedOnGapLocations
3731
(SeqAlignPtr salp_to_adjust,
3732
BioseqPtr bsp,
3733
ValNodePtr gaps,
3734
SeqAlignPtr gap_salp)
3735
{
3736
Int4 aln_index;
3737
SeqIdPtr sip;
3738
ValNodePtr gap_vnp;
3739
GapLocInfoPtr glip;
3740
SeqLocPtr slp;
3741
Int4 gap_start;
3742
Int4 cumulative_offset = 0;
3743
DenseSegPtr dsp;
3744
3745
if (salp_to_adjust == NULL || salp_to_adjust->segtype != SAS_DENSEG
3746
|| bsp == NULL || gaps == NULL)
3747
{
3748
return salp_to_adjust;
3749
}
3750
3751
dsp = (DenseSegPtr) salp_to_adjust->segs;
3752
if (dsp == NULL) {
3753
return salp_to_adjust;
3754
}
3755
sip = bsp->id;
3756
aln_index = 0;
3757
while (sip != NULL && aln_index == 0)
3758
{
3759
aln_index = SeqIdOrderInBioseqIdList (sip, dsp->ids);
3760
if (aln_index == 0)
3761
{
3762
sip = sip->next;
3763
}
3764
}
3765
if (aln_index == 0) {
3766
/* bioseq not in alignment */
3767
return salp_to_adjust;
3768
}
3769
3770
for (gap_vnp = gaps; gap_vnp != NULL; gap_vnp = gap_vnp->next)
3771
{
3772
glip = (GapLocInfoPtr) gap_vnp->data.ptrvalue;
3773
if (glip == NULL || glip->replace)
3774
{
3775
continue;
3776
}
3777
gap_start = glip->start_pos;
3778
if (gap_salp != NULL)
3779
{
3780
gap_start = AlnMgr2MapSeqAlignToBioseq(gap_salp, gap_start, aln_index);
3781
}
3782
if (gap_start < 1)
3783
{
3784
continue;
3785
}
3786
gap_start += cumulative_offset;
3787
if (gap_start > bsp->length)
3788
{
3789
continue;
3790
}
3791
slp = SeqLocIntNew (gap_start, gap_start + glip->length - 1, Seq_strand_plus, sip);
3792
salp_to_adjust = SeqAlignInsertByLoc (slp, salp_to_adjust);
3793
cumulative_offset += glip->length;
3794
}
3795
3796
return salp_to_adjust;
3797
}
3798
3799
3800
static void ShiftAlignmentForGapLocations (SeqAnnotPtr sanp, ValNodePtr gaps)
3801
{
3802
SeqAlignPtr salp;
3803
DenseSegPtr dsp;
3804
Int4 alignment_position = 0, k;
3805
Int4 cumulative_offset = 0;
3806
BoolPtr shift_this_row;
3807
Int4 seg_num = 0, shift_seg;
3808
ValNodePtr gap_vnp;
3809
GapLocInfoPtr glip;
3810
3811
if (sanp == NULL || sanp->data == NULL || sanp->type != 2 || gaps == NULL)
3812
{
3813
return;
3814
}
3815
3816
salp = (SeqAlignPtr) sanp->data;
3817
if (salp->segtype != SAS_DENSEG || salp->segs == NULL)
3818
{
3819
return;
3820
}
3821
3822
dsp = (DenseSegPtr) salp->segs;
3823
3824
shift_this_row = (BoolPtr) MemNew (sizeof (Boolean) * dsp->dim);
3825
3826
for (gap_vnp = gaps; gap_vnp != NULL; gap_vnp = gap_vnp->next)
3827
{
3828
glip = (GapLocInfoPtr) gap_vnp->data.ptrvalue;
3829
if (glip == NULL || glip->replace)
3830
{
3831
continue;
3832
}
3833
while (seg_num < dsp->numseg
3834
&& alignment_position + dsp->lens [seg_num] < glip->start_pos + cumulative_offset)
3835
3836
{
3837
alignment_position += dsp->lens [seg_num];
3838
seg_num++;
3839
}
3840
3841
if (seg_num < dsp->numseg)
3842
{
3843
dsp->lens [seg_num] += glip->length;
3844
for (k = 0; k < dsp->dim; k++)
3845
{
3846
if (dsp->starts [seg_num * dsp->dim + k] == -1)
3847
{
3848
shift_this_row[k] = FALSE;
3849
}
3850
else
3851
{
3852
shift_this_row[k] = TRUE;
3853
}
3854
}
3855
3856
/* shift the rows for which a gap was inserted */
3857
for (k = 0; k < dsp->dim; k++)
3858
{
3859
if (!shift_this_row[k])
3860
{
3861
continue;
3862
}
3863
/* shift start for minus strand rows for seg_num only */
3864
if (dsp->strands != NULL
3865
&& dsp->strands [seg_num * dsp->dim + k] == Seq_strand_minus
3866
&& dsp->starts [seg_num * dsp->dim + k] != -1)
3867
{
3868
dsp->starts [seg_num * dsp->dim + k] -= glip->length;
3869
}
3870
/* shift starts for rows after seg_num */
3871
for (shift_seg = seg_num + 1;
3872
shift_seg < dsp->numseg;
3873
shift_seg++)
3874
{
3875
if (dsp->starts [shift_seg * dsp->dim + k] != -1)
3876
{
3877
if (dsp->strands == NULL
3878
|| dsp->strands [shift_seg * dsp->dim + k] != Seq_strand_minus)
3879
{
3880
dsp->starts [shift_seg * dsp->dim + k] += glip->length;
3881
}
3882
else
3883
{
3884
dsp->starts [shift_seg * dsp->dim + k] -= glip->length;
3885
}
3886
}
3887
}
3888
}
3889
}
3890
cumulative_offset += glip->length;
3891
}
3892
shift_this_row = MemFree (shift_this_row);
3893
}
3894
3895
static void
3896
AdjustAlignmentsBasedOnGapLocations
3897
(ValNodePtr adjusted_bsp_list,
3898
ValNodePtr gaps,
3899
SeqAlignPtr salp,
3900
Uint2 entityID)
3901
{
3902
ValNodePtr align_annot_list, annot_vnp, bsp_vnp;
3903
SeqAnnotPtr sanp, adjustment_sanp = NULL;
3904
BioseqPtr bsp;
3905
Int4 cumulative_offset = 0;
3906
3907
for (bsp_vnp = adjusted_bsp_list; bsp_vnp != NULL; bsp_vnp = bsp_vnp->next)
3908
{
3909
bsp = (BioseqPtr)(bsp_vnp->data.ptrvalue);
3910
align_annot_list = FindAlignSeqAnnotsForBioseq (bsp);
3911
for (annot_vnp = align_annot_list;
3912
annot_vnp != NULL;
3913
annot_vnp = annot_vnp->next)
3914
{
3915
sanp = annot_vnp->data.ptrvalue;
3916
if (sanp != NULL && sanp->type == 2)
3917
{
3918
if (sanp->data == salp)
3919
{
3920
adjustment_sanp = sanp;
3921
}
3922
else
3923
{
3924
sanp->data = AdjustOneAlignmentForOneBioseqBasedOnGapLocations
3925
(sanp->data, bsp, gaps, salp);
3926
}
3927
}
3928
}
3929
align_annot_list = ValNodeFree (align_annot_list);
3930
}
3931
3932
if (adjustment_sanp != NULL)
3933
{
3934
ShiftAlignmentForGapLocations (adjustment_sanp, gaps);
3935
}
3936
3937
CleanupAlignmentsAfterConversion (adjusted_bsp_list, entityID);
3938
}
3939
3940
3551
3941
static void
3552
3942
ConvertRawBioseqToDelta
3553
3943
(BioseqPtr bsp,
3695
4085
sep = GetTopSeqEntryForEntityID (bsp->idx.entityID);
3696
4086
3697
4087
VisitFeaturesInSep (sep, bsp, AdjustCDSLocationsForGapsCallback);
4088
3698
4089
}
3699
4090
4091
typedef struct converttodelta
4092
{
4093
ValNodePtr location_list;
4094
ValNodePtr affected_bioseq_list;
4095
SeqAlignPtr salp;
4096
} ConvertToDeltaData, PNTR ConvertToDeltaPtr;
4097
3700
4098
static void ConvertBioseqToDeltaWithSequenceGapList (BioseqPtr bsp, Pointer userdata)
3701
4099
{
3702
ConvertRawBioseqToDelta (bsp, userdata, NULL, -1);
4100
ConvertToDeltaPtr ctdp;
4101
4102
if (bsp == NULL || bsp->id == NULL
4103
|| bsp->repr != Seq_repr_raw || ISA_aa (bsp->mol)
4104
|| userdata == NULL)
4105
{
4106
return;
4107
}
4108
ctdp = (ConvertToDeltaPtr) userdata;
4109
if (ctdp->location_list == NULL)
4110
{
4111
return;
4112
}
4113
ValNodeAddPointer (&(ctdp->affected_bioseq_list), 0, bsp);
4114
ConvertRawBioseqToDelta (bsp, ctdp->location_list, NULL, -1);
3703
4115
}
3704
4116
3705
4117
static void ConvertBioseqToDeltaWithAlignmentGapList (BioseqPtr bsp, Pointer userdata)
3706
4118
{
3707
Int4 aln_row = -1;
3708
SeqIdPtr sip, sip_next;
3709
SeqAlignPtr salp;
3710
3711
if (bsp == NULL || bsp->id == NULL || userdata == NULL)
3712
{
3713
return;
3714
}
3715
salp = FindAlignmentsForBioseq (bsp);
4119
Int4 aln_row = -1;
4120
SeqIdPtr sip, sip_next;
4121
SeqAlignPtr salp;
4122
ConvertToDeltaPtr ctdp;
4123
ValNodePtr annot_list;
4124
SeqAnnotPtr sanp;
4125
4126
if (bsp == NULL || bsp->id == NULL
4127
|| bsp->repr != Seq_repr_raw || ISA_aa (bsp->mol)
4128
|| userdata == NULL)
4129
{
4130
return;
4131
}
4132
ctdp = (ConvertToDeltaPtr) userdata;
4133
if (ctdp->location_list == NULL)
4134
{
4135
return;
4136
}
4137
4138
annot_list = FindAlignSeqAnnotsForBioseq (bsp);
4139
if (annot_list == NULL || annot_list->data.ptrvalue == NULL)
4140
{
4141
return;
4142
}
4143
sanp = (SeqAnnotPtr) annot_list->data.ptrvalue;
4144
if (sanp->type != 2 || sanp->data == NULL)
4145
{
4146
return;
4147
}
3716
4148
3717
if (salp == NULL)
3718
{
3719
return;
3720
}
4149
salp = sanp->data;
4150
ctdp->salp = salp;
4151
4152
/* Make sure alignment is indexed.
4153
*/
4154
AlnMgr2IndexSeqAlignEx(salp, FALSE);
3721
4155
3722
4156
sip = bsp->id;
3723
4157
3730
4164
sip = sip_next;
3731
4165
}
3732
4166
3733
ConvertRawBioseqToDelta (bsp, userdata, salp, aln_row);
4167
ValNodeAddPointer (&(ctdp->affected_bioseq_list), 0, bsp);
4168
ConvertRawBioseqToDelta (bsp, ctdp->location_list, salp, aln_row);
3734
4169
}
3735
4170
3736
4171
static int LIBCALLBACK SortGapLocations (VoidPtr ptr1, VoidPtr ptr2)
3848
4283
static void DoConvertRawToDeltaWithGapLocations (ButtoN b)
3849
4284
{
3850
4285
DeltaConversionPtr dcp;
3851
ValNodePtr location_list;
3852
4286
SeqEntryPtr sep;
4287
ConvertToDeltaData ctdd;
3853
4288
3854
4289
dcp = (DeltaConversionPtr) GetObjectExtra (b);
3855
4290
if (dcp == NULL)
3863
4298
return;
3864
4299
}
3865
4300
3866
location_list = DialogToPointer (dcp->gap_locations);
3867
if (location_list == NULL)
4301
ctdd.location_list = DialogToPointer (dcp->gap_locations);
4302
if (ctdd.location_list == NULL)
3868
4303
{
3869
4304
Message (MSG_ERROR, "Must supply valid gap locations!");
3870
4305
return;
3871
4306
}
4307
ctdd.affected_bioseq_list = NULL;
4308
ctdd.salp = NULL;
3872
4309
3873
4310
Hide (dcp->form);
3874
4311
WatchCursor ();
3875
4312
Update ();
3876
4313
if (dcp->coord_grp == NULL || GetValue (dcp->coord_grp) == 1)
3877
4314
{
3878
VisitBioseqsInSep (sep, location_list, ConvertBioseqToDeltaWithSequenceGapList);
4315
VisitBioseqsInSep (sep, &ctdd, ConvertBioseqToDeltaWithSequenceGapList);
3879
4316
}
3880
4317
else
3881
4318
{
3882
VisitBioseqsInSep (sep, location_list, ConvertBioseqToDeltaWithAlignmentGapList);
4319
VisitBioseqsInSep (sep, &ctdd, ConvertBioseqToDeltaWithAlignmentGapList);
3883
4320
}
3884
location_list = ValNodeFreeData (location_list);
4321
4322
AdjustAlignmentsBasedOnGapLocations (ctdd.affected_bioseq_list,
4323
ctdd.location_list, ctdd.salp,
4324
dcp->input_entityID);
4325
4326
ctdd.affected_bioseq_list = ValNodeFree (ctdd.affected_bioseq_list);
4327
ctdd.location_list = ValNodeFreeData (ctdd.location_list);
3885
4328
3886
4329
if (GetStatus (dcp->adjust_CDS_locations))
3887
4330
{
3888
4331
VisitFeaturesInSep (sep, NULL, AdjustCDSLocationsForGapsCallback);
3889
4332
}
3890
4333
4334
3891
4335
ObjMgrSetDirtyFlag (dcp->input_entityID, TRUE);
3892
4336
ObjMgrSendMsg (OM_MSG_UPDATE, dcp->input_entityID, 0, 0);
3893
4337
Remove (dcp->form);
4735
5179
fsp = DialogToPointer (fgp->filter_grp);
4736
5180
4737
5181
sep = GetTopSeqEntryForEntityID (fgp->input_entityID);
4738
if (sep == NULL) return;
5182
if (sep == NULL) return FALSE;
4739
5183
fgp->single_interval = GetStatus (fgp->single_interval_btn);
4740
5184
if (GetStatus (fgp->selected_features_only_btn))
4741
5185
{
4955
5399
ChangeGeneFeatureSelection (fgp);
4956
5400
}
4957
5401
4958
typedef struct genetocdsform
4959
{
4960
FEATURE_FORM_BLOCK
4961
4962
PopuP gene_qual_popup;
4963
PopuP gene_qual_popup2;
4964
PopuP gene_qual_popup3;
4965
GrouP qual_caps_grp;
4966
TexT append_text;
4967
ButtoN remove_qual_btn1;
4968
ButtoN remove_qual_btn2;
4969
ButtoN remove_qual_btn3;
4970
ButtoN accept_btn;
4971
4972
Int4 gene_qual_choice;
4973
Int4 gene_qual_choice2;
4974
Int4 gene_qual_choice3;
4975
CharPtr append_string;
4976
Int4 caps_choice;
4977
Boolean remove_gene_qual1;
4978
Boolean remove_gene_qual2;
4979
Boolean remove_gene_qual3;
4980
SeqEntryPtr sep;
4981
FILE *log_fp;
4982
Boolean data_in_log;
4983
4984
} GeneToCDSFormData, PNTR GeneToCDSFormPtr;
4985
4986
static CharPtr GetQualStringForQualChoice (GeneRefPtr grp, SeqFeatPtr sfp, Int4 choice)
4987
{
4988
CharPtr str = NULL;
4989
switch (choice)
4990
{
4991
case 2:
4992
str = grp->locus;
4993
break;
4994
case 3:
4995
str = grp->desc;
4996
break;
4997
case 4:
4998
str = sfp->comment;
4999
break;
5000
}
5001
return str;
5002
}
5003
5004
static Int4 GetGeneQualChoice (GeneToCDSFormPtr gcfp, SeqFeatPtr sfp, GeneRefPtr grp)
5005
{
5006
if (gcfp == NULL) return 0;
5007
5008
if (gcfp->gene_qual_choice != 1
5009
&& StringHasNoText (GetQualStringForQualChoice (grp, sfp, gcfp->gene_qual_choice)))
5010
{
5011
if (gcfp->gene_qual_choice2 != 1
5012
&& StringHasNoText (GetQualStringForQualChoice (grp, sfp, gcfp->gene_qual_choice2)))
5013
{
5014
return gcfp->gene_qual_choice3;
5015
}
5016
else
5017
{
5018
return gcfp->gene_qual_choice2;
5019
}
5020
}
5021
else
5022
{
5023
return gcfp->gene_qual_choice;
5024
}
5025
}
5026
5027
static void LogGeneToCDSNoProtein (GeneToCDSFormPtr gcfp, CharPtr gene_label, SeqIdPtr sip)
5028
{
5029
Char id [41];
5030
5031
if (gcfp == NULL || gcfp->log_fp == NULL || sip == NULL) return;
5032
5033
id [0] = '\0';
5034
SeqIdWrite (SeqIdFindBest (sip, 0), id, PRINTID_FASTA_LONG, sizeof (id) - 1);
5035
5036
if (StringHasNoText (gene_label))
5037
{
5038
fprintf (gcfp->log_fp, "No protein added for unlabeled gene on sequence %s\n", id);
5039
}
5040
else
5041
{
5042
fprintf (gcfp->log_fp, "No protein added for %s on sequence %s\n", gene_label, id);
5043
}
5044
gcfp->data_in_log = TRUE;
5045
}
5046
5047
static void GeneToCDSCallback (SeqFeatPtr sfp, Pointer userdata)
5048
5049
{
5050
SeqFeatPtr cds;
5051
GeneRefPtr grp;
5052
SeqMgrFeatContext context;
5053
Int2 genCode;
5054
CdRegionPtr crp;
5055
ByteStorePtr bs;
5056
BioseqPtr bsp;
5057
SeqEntryPtr psep, nsep, old, topsep;
5058
MolInfoPtr mip;
5059
ProtRefPtr prp;
5060
Char ch;
5061
ValNodePtr descr;
5062
Int2 i;
5063
Boolean partial5, partial3;
5064
CharPtr prot;
5065
CharPtr ptr;
5066
ValNodePtr vnp;
5067
CharPtr protName = NULL;
5068
GeneToCDSFormPtr gcfp;
5069
Int4 prot_len;
5070
CharPtr cp;
5071
Int4 gene_qual_choice;
5072
CharPtr qual_val = NULL;
5073
5074
if (sfp == NULL || sfp->data.choice != SEQFEAT_GENE || userdata == NULL)
5075
return;
5076
5077
gcfp = (GeneToCDSFormPtr) userdata;
5078
5079
CheckSeqLocForPartial (sfp->location, &partial5, &partial3);
5080
5081
cds = SeqMgrGetOverlappingCDS (sfp->location, &context);
5082
if (cds != NULL)
5083
{
5084
return;
5085
}
5086
5087
if (SeqMgrGetDesiredFeature (sfp->idx.entityID, NULL,
5088
0, 0, sfp, &context) == NULL) return;
5089
5090
grp = (GeneRefPtr) sfp->data.value.ptrvalue;
5091
5092
/* use the controls to determine the protein name */
5093
prot_len = 0;
5094
5095
gene_qual_choice = GetGeneQualChoice (gcfp, sfp, grp);
5096
qual_val = GetQualStringForQualChoice (grp, sfp, gene_qual_choice);
5097
5098
5099
if (gene_qual_choice == 1)
5100
{
5101
if (StringHasNoText (gcfp->append_string))
5102
{
5103
LogGeneToCDSNoProtein (gcfp, context.label, SeqLocId (sfp->location));
5104
return;
5105
}
5106
}
5107
else
5108
{
5109
if (StringHasNoText (qual_val))
5110
{
5111
LogGeneToCDSNoProtein (gcfp, context.label, SeqLocId (sfp->location));
5112
return;
5113
}
5114
prot_len += StringLen (qual_val);
5115
}
5116
5117
if (!StringHasNoText (gcfp->append_string))
5118
{
5119
if (prot_len > 0)
5120
{
5121
prot_len ++;
5122
}
5123
prot_len += StringLen (gcfp->append_string);
5124
}
5125
if (prot_len == 0)
5126
{
5127
LogGeneToCDSNoProtein (gcfp, context.label, SeqLocId (sfp->location));
5128
return;
5129
}
5130
5131
/* add one to length for terminating null */
5132
prot_len ++;
5133
protName = (CharPtr) MemNew (prot_len * sizeof (Char));
5134
if (protName == NULL) return;
5135
5136
if (gene_qual_choice != 1 && !StringHasNoText (qual_val))
5137
{
5138
StringCpy (protName, qual_val);
5139
/* apply capitalization */
5140
switch (gcfp->caps_choice)
5141
{
5142
case 1:
5143
/* do nothing, leave capitalization as is */
5144
break;
5145
case 2:
5146
/* capitalize first letter */
5147
protName [0] = toupper (protName[0]);
5148
break;
5149
case 3:
5150
/* capitalize all letters */
5151
for (cp = protName; *cp != 0; cp++)
5152
{
5153
*cp = toupper (*cp);
5154
}
5155
break;
5156
}
5157
if (!StringHasNoText (gcfp->append_string))
5158
{
5159
StringCat (protName, " ");
5160
}
5161
}
5162
if (!StringHasNoText (gcfp->append_string))
5163
{
5164
StringCat (protName, gcfp->append_string);
5165
}
5166
5167
if ((gcfp->gene_qual_choice == gene_qual_choice && gcfp->remove_gene_qual1)
5168
|| (gcfp->gene_qual_choice2 == gene_qual_choice && gcfp->remove_gene_qual2)
5169
|| (gcfp->gene_qual_choice3 == gene_qual_choice && gcfp->remove_gene_qual3))
5170
{
5171
switch (gene_qual_choice)
5172
{
5173
case 1:
5174
/* do nothing - not using a gene qualifier */
5175
break;
5176
case 2:
5177
grp->locus = MemFree (grp->locus);
5178
break;
5179
case 3:
5180
grp->desc = MemFree (grp->desc);
5181
break;
5182
case 4:
5183
sfp->comment= MemFree (sfp->comment);
5184
break;
5185
}
5186
}
5187
5188
cds = SeqFeatNew ();
5189
if (cds == NULL) return;
5190
cds->data.choice = SEQFEAT_CDREGION;
5191
5192
genCode = SeqEntryToGeneticCode (gcfp->sep, NULL, NULL, 0);
5193
crp = CreateNewCdRgn (1, FALSE, genCode);
5194
if (crp == NULL) {
5195
return;
5196
}
5197
5198
cds->data.value.ptrvalue = (Pointer) crp;
5199
cds->location = SeqLocFree (cds->location);
5200
cds->location = AsnIoMemCopy ((Pointer) sfp->location,
5201
(AsnReadFunc) SeqLocAsnRead,
5202
(AsnWriteFunc) SeqLocAsnWrite);
5203
cds->partial = sfp->partial;
5204
cds->next = sfp->next;
5205
sfp->next = cds;
5206
5207
bs = ProteinFromCdRegionEx (cds, TRUE, FALSE);
5208
if (bs != NULL) {
5209
prot = BSMerge (bs, NULL);
5210
bs = BSFree (bs);
5211
if (prot != NULL) {
5212
ptr = prot;
5213
ch = *ptr;
5214
while (ch != '\0') {
5215
*ptr = TO_UPPER (ch);
5216
ptr++;
5217
ch = *ptr;
5218
}
5219
i = (Int2) StringLen (prot);
5220
if (i > 0 && prot [i - 1] == '*') {
5221
prot [i - 1] = '\0';
5222
}
5223
bs = BSNew (1000);
5224
if (bs != NULL) {
5225
ptr = prot;
5226
BSWrite (bs, (VoidPtr) ptr, (Int4) StringLen (ptr));
5227
}
5228
}
5229
}
5230
bsp = BioseqNew ();
5231
if (bsp == NULL) return;
5232
bsp->repr = Seq_repr_raw;
5233
bsp->mol = Seq_mol_aa;
5234
bsp->seq_data_type = Seq_code_ncbieaa;
5235
bsp->seq_data = bs;
5236
bsp->length = BSLen (bs);
5237
bs = NULL;
5238
old = SeqEntrySetScope (NULL);
5239
bsp->id = MakeNewProteinSeqId (cds->location, NULL);
5240
SeqMgrAddToBioseqIndex (bsp);
5241
SeqEntrySetScope (old);
5242
psep = SeqEntryNew ();
5243
if (psep != NULL) {
5244
psep->choice = 1;
5245
psep->data.ptrvalue = (Pointer) bsp;
5246
SeqMgrSeqEntry (SM_BIOSEQ, (Pointer) bsp, psep);
5247
mip = MolInfoNew ();
5248
if (mip != NULL) {
5249
mip->biomol = 8;
5250
mip->tech = 8;
5251
if (partial5 && partial3) {
5252
mip->completeness = 5;
5253
} else if (partial5) {
5254
mip->completeness = 3;
5255
} else if (partial3) {
5256
mip->completeness = 4;
5257
}
5258
vnp = CreateNewDescriptor (psep, Seq_descr_molinfo);
5259
if (vnp != NULL) {
5260
vnp->data.ptrvalue = (Pointer) mip;
5261
}
5262
}
5263
descr = ExtractBioSourceAndPubs (gcfp->sep);
5264
if (IS_Bioseq_set (gcfp->sep))
5265
{
5266
topsep = gcfp->sep;
5267
}
5268
else
5269
{
5270
topsep = GetBestTopParentForData (gcfp->input_entityID, gcfp->sep->data.ptrvalue);
5271
}
5272
AddSeqEntryToSeqEntry (topsep, psep, TRUE);
5273
nsep = FindNucSeqEntry (gcfp->sep);
5274
ReplaceBioSourceAndPubs (gcfp->sep, descr);
5275
SetSeqFeatProduct (cds, bsp);
5276
prp = CreateNewProtRef (protName, NULL, NULL, NULL);
5277
MemFree (protName);
5278
sfp = CreateNewFeature (psep, NULL, SEQFEAT_PROT, NULL);
5279
if (sfp != NULL) {
5280
sfp->data.value.ptrvalue = (Pointer) prp;
5281
}
5282
}
5283
}
5284
5285
static void GeneToCDSBioseqCallback (BioseqPtr bsp, Pointer userdata)
5286
5287
{
5288
GeneToCDSFormPtr gcfp;
5289
5290
if (bsp == NULL || userdata == NULL) return;
5291
gcfp = (GeneToCDSFormPtr) userdata;
5292
gcfp->sep = SeqMgrGetSeqEntryForData (bsp);
5293
VisitFeaturesOnBsp (bsp, (Pointer) gcfp, GeneToCDSCallback);
5294
}
5295
5296
static void GeneToCdsAccept (ButtoN b)
5297
{
5298
GeneToCDSFormPtr gcfp;
5299
Char path [PATH_MAX];
5300
5301
gcfp = (GeneToCDSFormPtr) GetObjectExtra (b);
5302
if (gcfp == NULL) return;
5303
TmpNam (path);
5304
gcfp->log_fp = FileOpen (path, "wb");
5305
if (gcfp->log_fp == NULL) return;
5306
5307
Hide (gcfp->form);
5308
WatchCursor ();
5309
Update ();
5310
5311
gcfp->sep = GetTopSeqEntryForEntityID (gcfp->input_entityID);
5312
if (gcfp->sep == NULL) return;
5313
5314
gcfp->gene_qual_choice = GetValue (gcfp->gene_qual_popup);
5315
gcfp->gene_qual_choice2 = GetValue (gcfp->gene_qual_popup2);
5316
gcfp->gene_qual_choice3 = GetValue (gcfp->gene_qual_popup3);
5317
gcfp->append_string = SaveStringFromText (gcfp->append_text);
5318
gcfp->caps_choice = GetValue (gcfp->qual_caps_grp);
5319
gcfp->remove_gene_qual1 = GetStatus (gcfp->remove_qual_btn1);
5320
gcfp->remove_gene_qual2 = GetStatus (gcfp->remove_qual_btn2);
5321
gcfp->remove_gene_qual3 = GetStatus (gcfp->remove_qual_btn3);
5322
5323
VisitBioseqsInSep (gcfp->sep, (Pointer) gcfp, GeneToCDSBioseqCallback);
5324
5325
ArrowCursor ();
5326
Update ();
5327
Remove (gcfp->form);
5328
FileClose (gcfp->log_fp);
5329
if (gcfp->data_in_log)
5330
{
5331
LaunchGeneralTextViewer (path, "Genes without Proteins");
5332
}
5333
FileRemove (path);
5334
5335
ObjMgrSetDirtyFlag (gcfp->input_entityID, TRUE);
5336
ObjMgrSendMsg (OM_MSG_UPDATE, gcfp->input_entityID, 0, 0);
5337
}
5338
5339
static void CleanupGeneToCDSPage (GraphiC g, VoidPtr data)
5340
{
5341
GeneToCDSFormPtr gcfp;
5342
5343
gcfp = (GeneToCDSFormPtr) data;
5344
if (gcfp != NULL)
5345
{
5346
gcfp->append_string = MemFree (gcfp->append_string);
5347
MemFree (gcfp);
5348
}
5349
}
5350
5351
5352
static void EnableGeneToCdsControls (GeneToCDSFormPtr gcfp)
5353
{
5354
CharPtr cp;
5355
5356
if (gcfp == NULL) return;
5357
5358
if (GetValue (gcfp->gene_qual_popup) == 1)
5359
{
5360
Disable (gcfp->remove_qual_btn1);
5361
SetStatus (gcfp->remove_qual_btn1, FALSE);
5362
Disable (gcfp->qual_caps_grp);
5363
SetValue (gcfp->gene_qual_popup2, 1);
5364
Disable (gcfp->remove_qual_btn2);
5365
SetStatus (gcfp->remove_qual_btn2, FALSE);
5366
Disable (gcfp->gene_qual_popup2);
5367
SetValue (gcfp->gene_qual_popup3, 1);
5368
Disable (gcfp->gene_qual_popup3);
5369
Disable (gcfp->remove_qual_btn3);
5370
SetStatus (gcfp->remove_qual_btn3, FALSE);
5371
cp = SaveStringFromText (gcfp->append_text);
5372
if (StringHasNoText (cp))
5373
{
5374
Disable (gcfp->accept_btn);
5375
}
5376
else
5377
{
5378
Enable (gcfp->accept_btn);
5379
}
5380
MemFree (cp);
5381
}
5382
else
5383
{
5384
Enable (gcfp->remove_qual_btn1);
5385
Enable (gcfp->qual_caps_grp);
5386
Enable (gcfp->gene_qual_popup2);
5387
Enable (gcfp->accept_btn);
5388
if (GetValue (gcfp->gene_qual_popup2) == 1)
5389
{
5390
Disable (gcfp->remove_qual_btn2);
5391
SetStatus (gcfp->remove_qual_btn2, FALSE);
5392
SetValue (gcfp->gene_qual_popup3, 1);
5393
Disable (gcfp->gene_qual_popup3);
5394
Disable (gcfp->remove_qual_btn3);
5395
SetStatus (gcfp->remove_qual_btn3, FALSE);
5396
}
5397
else
5398
{
5399
Enable (gcfp->gene_qual_popup3);
5400
Enable (gcfp->remove_qual_btn2);
5401
if (GetValue (gcfp->gene_qual_popup3) == 1)
5402
{
5403
Disable (gcfp->remove_qual_btn3);
5404
SetStatus (gcfp->remove_qual_btn3, FALSE);
5405
}
5406
else
5407
{
5408
Enable (gcfp->remove_qual_btn3);
5409
}
5410
}
5411
}
5412
}
5413
5414
static void EnableGeneToCdsControlsPopup (PopuP p)
5415
{
5416
GeneToCDSFormPtr gcfp;
5417
5418
gcfp = (GeneToCDSFormPtr) GetObjectExtra (p);
5419
EnableGeneToCdsControls (gcfp);
5420
}
5421
5422
static void EnableGeneToCdsControlsText (TexT t)
5423
{
5424
GeneToCDSFormPtr gcfp;
5425
5426
gcfp = (GeneToCDSFormPtr) GetObjectExtra (t);
5427
EnableGeneToCdsControls (gcfp);
5428
}
5429
5430
static void GeneToCds (IteM i)
5431
5432
{
5433
BaseFormPtr bfp;
5434
GeneToCDSFormPtr gcfp;
5435
WindoW w;
5436
GrouP h, g, k, m, c;
5437
5438
#ifdef WIN_MAC
5439
bfp = currentFormDataPtr;
5440
#else
5441
bfp = GetObjectExtra (i);
5442
#endif
5443
if (bfp == NULL) {
5444
Message (MSG_ERROR, "GeneToCDS error");
5445
return;
5446
}
5447
5448
gcfp = (GeneToCDSFormPtr) MemNew (sizeof (GeneToCDSFormData));
5449
if (gcfp == NULL) return;
5450
gcfp->input_entityID = bfp->input_entityID;
5451
gcfp->input_itemID = bfp->input_itemID;
5452
gcfp->input_itemtype = bfp->input_itemtype;
5453
5454
w = FixedWindow (-50, -33, -10, -10, "Gene to CDS", StdCloseWindowProc);
5455
SetObjectExtra (w, gcfp, CleanupGeneToCDSPage);
5456
gcfp->form = (ForM) w;
5457
5458
h = HiddenGroup (w, -1, 0, NULL);
5459
SetGroupSpacing (h, 10, 10);
5460
5461
g = HiddenGroup (h, 0, 6, NULL);
5462
5463
k = NormalGroup (g, 3, 0, "Select gene qualifier to use in protein name", NULL, NULL);
5464
StaticPrompt (k, "1st Choice", 0, 0, programFont, 'c');
5465
gcfp->gene_qual_popup = PopupList (k, TRUE, EnableGeneToCdsControlsPopup);
5466
SetObjectExtra (gcfp->gene_qual_popup, gcfp, NULL);
5467
PopupItem (gcfp->gene_qual_popup, "None");
5468
PopupItem (gcfp->gene_qual_popup, "locus");
5469
PopupItem (gcfp->gene_qual_popup, "description");
5470
PopupItem (gcfp->gene_qual_popup, "comment");
5471
SetValue (gcfp->gene_qual_popup, 1);
5472
gcfp->remove_qual_btn1 = CheckBox (k, "Remove if used", NULL);
5473
StaticPrompt (k, "2nd Choice", 0, 0, programFont, 'c');
5474
gcfp->gene_qual_popup2 = PopupList (k, TRUE, EnableGeneToCdsControlsPopup);
5475
SetObjectExtra (gcfp->gene_qual_popup2, gcfp, NULL);
5476
PopupItem (gcfp->gene_qual_popup2, "None");
5477
PopupItem (gcfp->gene_qual_popup2, "locus");
5478
PopupItem (gcfp->gene_qual_popup2, "description");
5479
PopupItem (gcfp->gene_qual_popup2, "comment");
5480
SetValue (gcfp->gene_qual_popup2, 1);
5481
gcfp->remove_qual_btn2 = CheckBox (k, "Remove if used", NULL);
5482
StaticPrompt (k, "3rd Choice", 0, 0, programFont, 'c');
5483
gcfp->gene_qual_popup3 = PopupList (k, TRUE, EnableGeneToCdsControlsPopup);
5484
SetObjectExtra (gcfp->gene_qual_popup3, gcfp, NULL);
5485
PopupItem (gcfp->gene_qual_popup3, "None");
5486
PopupItem (gcfp->gene_qual_popup3, "locus");
5487
PopupItem (gcfp->gene_qual_popup3, "description");
5488
PopupItem (gcfp->gene_qual_popup3, "comment");
5489
SetValue (gcfp->gene_qual_popup3, 1);
5490
gcfp->remove_qual_btn3 = CheckBox (k, "Remove if used", NULL);
5491
5492
gcfp->qual_caps_grp = NormalGroup (g, 3, 0,
5493
"Capitalization for gene qualifier in protein name", NULL, NULL);
5494
RadioButton (gcfp->qual_caps_grp, "As is");
5495
RadioButton (gcfp->qual_caps_grp, "Capitalize first initial");
5496
RadioButton (gcfp->qual_caps_grp, "Capitalize all");
5497
SetValue (gcfp->qual_caps_grp, 1);
5498
5499
m = HiddenGroup (g, 0, 2, NULL);
5500
StaticPrompt (m, "Append text to protein name", 0, 0, programFont, 'c');
5501
gcfp->append_text = DialogText (m, "", 14, EnableGeneToCdsControlsText);
5502
SetObjectExtra (gcfp->append_text, gcfp, NULL);
5503
5504
c = HiddenGroup (g, 4, 0, NULL);
5505
gcfp->accept_btn = PushButton (c, "Accept", GeneToCdsAccept);
5506
SetObjectExtra (gcfp->accept_btn, gcfp, NULL);
5507
EnableGeneToCdsControls (gcfp);
5508
5509
PushButton (c, "Cancel", StdCancelButtonProc);
5510
5511
5512
AlignObjects (ALIGN_CENTER, (HANDLE) k, (HANDLE) gcfp->qual_caps_grp,
5513
(HANDLE) m, (HANDLE) c, NULL);
5514
5515
RealizeWindow (w);
5516
Show (w);
5517
Update ();
5518
5519
}
5520
5402
5521
5403
typedef struct featuretocdsform
5522
5404
{
6368
6250
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
6369
6251
}
6370
6252
6253
static void ForcePackageFeatureCallback (SeqEntryPtr sep, Pointer mydata, Int4 index, Int2 indent)
6254
6255
{
6256
BaseFormPtr bfp;
6257
BioseqPtr bsp = NULL;
6258
BioseqSetPtr bssp = NULL;
6259
SeqAnnotPtr firstsap;
6260
SeqAnnotPtr nextsap;
6261
SeqFeatPtr nextsfp;
6262
Pointer PNTR prevsap;
6263
Pointer PNTR prevsfp;
6264
SeqAnnotPtr sap;
6265
SeqFeatPtr sfp;
6266
BioseqPtr target;
6267
6268
if (sep == NULL || sep->data.ptrvalue == NULL) return;
6269
bfp = (BaseFormPtr) mydata;
6270
if (bfp == NULL) return;
6271
if (IS_Bioseq (sep)) {
6272
bsp = (BioseqPtr) sep->data.ptrvalue;
6273
sap = bsp->annot;
6274
prevsap = (Pointer PNTR) &(bsp->annot);
6275
} else if (IS_Bioseq_set (sep)) {
6276
bssp = (BioseqSetPtr) sep->data.ptrvalue;
6277
sap = bssp->annot;
6278
prevsap = (Pointer PNTR) &(bssp->annot);
6279
} else return;
6280
firstsap = sap;
6281
while (sap != NULL) {
6282
nextsap = sap->next;
6283
if (sap->type == 1) {
6284
sfp = (SeqFeatPtr) sap->data;
6285
prevsfp = (Pointer PNTR) &(sap->data);
6286
while (sfp != NULL) {
6287
nextsfp = sfp->next;
6288
target = GetBioseqGivenSeqLoc (sfp->location, bfp->input_entityID);
6289
if (target != bsp || sap != firstsap) {
6290
*(prevsfp) = sfp->next;
6291
sfp->next = NULL;
6292
AddFeatureToBioseq (sfp, target);
6293
} else {
6294
prevsfp = (Pointer PNTR) &(sfp->next);
6295
}
6296
sfp = nextsfp;
6297
}
6298
}
6299
if (sap->data == NULL) {
6300
*(prevsap) = sap->next;
6301
sap->next = NULL;
6302
SeqAnnotFree (sap);
6303
} else {
6304
prevsap = (Pointer PNTR) &(sap->next);
6305
}
6306
sap = nextsap;
6307
}
6308
}
6309
6310
static void ForceRepackage (IteM i)
6311
6312
{
6313
BaseFormPtr bfp;
6314
SeqEntryPtr sep;
6315
6316
#ifdef WIN_MAC
6317
bfp = currentFormDataPtr;
6318
#else
6319
bfp = GetObjectExtra (i);
6320
#endif
6321
if (bfp == NULL) return;
6322
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
6323
if (sep == NULL) return;
6324
WatchCursor ();
6325
Update ();
6326
SeqEntryExplore (sep, bfp, ForcePackageFeatureCallback);
6327
ArrowCursor ();
6328
Update ();
6329
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
6330
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
6331
}
6332
6371
6333
static BioseqSetPtr GetParentNPS (BioseqPtr bsp)
6372
6334
{
6373
6335
BioseqSetPtr bssp;
7287
7249
}
7288
7250
}
7289
7251
7290
/*---------------------------------------------------------------------*/
7291
/* */
7292
/* ConvertCDS_FeatureCallback () -- Called once for each CDS feature */
7293
/* on a Bioseq. This function does */
7294
/* the actual CDS deleting. */
7295
/* */
7296
/*---------------------------------------------------------------------*/
7297
7298
static Boolean LIBCALLBACK ConvertCDS_FeatureCallback (SeqFeatPtr sfp,
7299
SeqMgrFeatContextPtr fcontext)
7252
extern void ConvertCDSToMiscFeat (SeqFeatPtr sfp)
7300
7253
{
7301
7254
CdRegionPtr cdrp;
7302
7255
GBQualPtr gbqual;
7309
7262
ProtRefPtr prp;
7310
7263
ValNodePtr vnp;
7311
7264
7312
/* skip CDSs without products */
7313
if (sfp == NULL || sfp->product == NULL) return TRUE;
7314
7315
/* If no internal stop codons, then done */
7316
7317
if (FALSE == HasInternalStops(sfp))
7318
return TRUE;
7319
7265
if (sfp == NULL || sfp->data.choice != SEQFEAT_CDREGION)
7266
{
7267
return;
7268
}
7269
7320
7270
/* Get the CD region part of the feature, and */
7321
7271
/* the associated protein bioseq. */
7322
7272
7323
7273
cdrp = (CdRegionPtr) sfp->data.value.ptrvalue;
7324
7274
protBsp = BioseqFindFromSeqLoc (sfp->product);
7325
7275
7326
if (protBsp == NULL) return TRUE;
7276
if (protBsp == NULL) return;
7327
7277
7328
7278
/* Convert the CDS feature to a misc_feat */
7329
7279
7331
7281
sfp->data.value.ptrvalue = NULL;
7332
7282
7333
7283
ifp = ImpFeatNew ();
7334
if (NULL == ifp)
7335
return FALSE;
7284
if (NULL == ifp) return;
7336
7285
ifp->key = StringSave ("misc_feature");
7337
7286
7338
7287
sfp->data.choice = SEQFEAT_IMP;
7342
7291
/* Add a name key to the misc_feature */
7343
7292
7344
7293
protSfp = SeqMgrGetBestProteinFeature (protBsp, &protContext);
7345
prp = (ProtRefPtr) protSfp->data.value.ptrvalue;
7294
if (protSfp != NULL)
7295
{
7296
prp = (ProtRefPtr) protSfp->data.value.ptrvalue;
7346
7297
7347
if (prp != NULL) {
7348
vnp = prp->name;
7349
if (NULL != vnp)
7298
if (prp != NULL)
7299
{
7300
vnp = prp->name;
7301
if (NULL != vnp)
7350
7302
{
7351
protName = (CharPtr) vnp->data.ptrvalue;
7352
if (NULL != protName) {
7353
noteStr = (CharPtr) MemNew (StringLen (protName) + 12);
7354
sprintf (noteStr, "similar to %s", protName);
7355
}
7303
protName = (CharPtr) vnp->data.ptrvalue;
7304
if (NULL != protName)
7305
{
7306
noteStr = (CharPtr) MemNew (StringLen (protName) + 12);
7307
sprintf (noteStr, "similar to %s", protName);
7308
gbqual = GBQualNew ();
7309
if (gbqual != NULL)
7310
{
7311
gbqual->qual = StringSave ("note");
7312
gbqual->val = noteStr;
7313
gbqual->next = sfp->qual;
7314
sfp->qual = gbqual;
7315
}
7316
else
7317
{
7318
noteStr = MemFree (noteStr);
7319
}
7320
}
7356
7321
}
7322
}
7357
7323
}
7358
7324
7359
gbqual = GBQualNew ();
7360
if (gbqual == NULL)
7361
return FALSE;
7362
7363
gbqual->qual = StringSave ("note");
7364
gbqual->val = noteStr;
7365
gbqual->next = sfp->qual;
7366
sfp->qual = gbqual;
7367
7368
7325
/* Delete the protein Bioseq that */
7369
7326
/* the CDS points to. */
7370
7327
7372
7329
7373
7330
/* set the subtype to zero so that it will be reindexed */
7374
7331
sfp->idx.subtype = 0;
7332
}
7333
7334
/*---------------------------------------------------------------------*/
7335
/* */
7336
/* ConvertCDS_FeatureCallback () -- Called once for each CDS feature */
7337
/* on a Bioseq. This function does */
7338
/* the actual CDS deleting. */
7339
/* */
7340
/*---------------------------------------------------------------------*/
7341
7342
static Boolean LIBCALLBACK ConvertCDS_FeatureCallback (SeqFeatPtr sfp,
7343
SeqMgrFeatContextPtr fcontext)
7344
{
7345
7346
/* skip CDSs without products */
7347
if (sfp == NULL || sfp->product == NULL) return TRUE;
7348
7349
/* If no internal stop codons, then done */
7350
7351
if (FALSE == HasInternalStops(sfp))
7352
return TRUE;
7353
7354
ConvertCDSToMiscFeat (sfp);
7375
7355
7376
7356
/* Return TRUE to continue on to the next CDS feature */
7377
7357
7445
7425
7446
7426
DeleteMarkedObjects (bfp->input_entityID, 0, NULL);
7447
7427
SeqMgrLinkSeqEntry (sep, parenttype, parentptr);
7428
7429
if (ANS_YES == Message (MSG_YN, "Renormalize Nuc-Prot sets?"))
7430
{
7431
RenormalizeNucProtSets (sep, TRUE);
7432
}
7433
7434
7448
7435
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
7449
7436
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
7450
7437
ArrowCursor ();
8458
8445
Boolean overshot = FALSE;
8459
8446
SeqFeatPtr prevCdsSfp = NULL;
8460
8447
SeqFeatXrefPtr prevXref = NULL;
8461
SeqMgrFeatContext rbsContext;
8448
SeqMgrFeatContext rbsContext, geneContext;
8462
8449
GeneRefPtr rbsGrp;
8463
8450
Int4 rbsLeft;
8464
8451
Int4 rbsRight;
8487
8474
/* Loop through all RBS features */
8488
8475
8489
8476
while (NULL != rbsSfp)
8490
{
8491
8492
/* If the feature has an existing gene xref */
8493
/* then we need to delete it. */
8494
8495
xref = rbsSfp->xref;
8496
while (xref != NULL && xref->data.choice != SEQFEAT_GENE)
8497
{
8498
prevXref = xref;
8499
xref = xref->next;
8500
}
8501
8502
if (xref != NULL)
8503
{
8504
rbsGrp = (GeneRefPtr) xref->data.value.ptrvalue;
8505
rbsGrp = GeneRefFree (rbsGrp);
8506
if (prevXref != NULL)
8507
prevXref->next = xref->next;
8508
else
8509
rbsSfp->xref = xref->next;
8510
SeqFeatXrefFree (xref);
8511
xref = NULL;
8512
}
8513
8514
/* Search for a 'downstream' gene xref */
8515
8516
if (overshot)
8517
overshot = FALSE;
8518
else
8519
{
8520
prevCdsSfp = cdsSfp;
8521
cdsSfp = SeqMgrGetNextFeature (bsp, cdsSfp, 0, FEATDEF_CDS,
8522
&cdsContext);
8523
}
8524
8525
rbsSlp = rbsSfp->location;
8526
strand = SeqLocStrand (rbsSlp);
8527
8528
if (strand == Seq_strand_plus)
8529
{
8530
/* If the gene starts at or 'after' the */
8531
/* RBS, then the RBS probably belongs to */
8532
/* it, so make that gene a xref for the */
8533
/* RBS feature. */
8477
{
8478
/* If the feature has an existing gene xref */
8479
/* then we need to delete it. */
8480
8481
xref = rbsSfp->xref;
8482
while (xref != NULL && xref->data.choice != SEQFEAT_GENE)
8483
{
8484
prevXref = xref;
8485
xref = xref->next;
8486
}
8487
8488
if (xref != NULL)
8489
{
8490
if (prevXref != NULL)
8491
prevXref->next = xref->next;
8492
else
8493
rbsSfp->xref = xref->next;
8494
xref->next = NULL;
8495
SeqFeatXrefFree (xref);
8496
xref = NULL;
8497
}
8498
8499
/* Search for a 'downstream' gene xref */
8500
8501
if (overshot)
8502
overshot = FALSE;
8503
else
8504
{
8505
prevCdsSfp = cdsSfp;
8506
cdsSfp = SeqMgrGetNextFeature (bsp, cdsSfp, 0, FEATDEF_CDS,
8507
&cdsContext);
8508
}
8509
8510
rbsSlp = rbsSfp->location;
8511
strand = SeqLocStrand (rbsSlp);
8512
8513
if (strand == Seq_strand_plus)
8514
{
8515
/* If the gene starts at or 'after' the */
8516
/* RBS, then the RBS probably belongs to */
8517
/* it, so make that gene a xref for the */
8518
/* RBS feature. */
8534
8519
8535
found = FALSE;
8536
while ((cdsSfp != NULL) && (!found))
8520
found = FALSE;
8521
while ((cdsSfp != NULL) && (!found))
8537
8522
{
8538
8523
cdsSlp = cdsSfp->location;
8539
8524
cdsLeft = GetOffsetInBioseq (cdsSlp, bsp,
8541
8526
rbsLeft = GetOffsetInBioseq (rbsSlp , bsp,
8542
8527
SEQLOC_LEFT_END);
8543
8528
if (rbsLeft <= cdsLeft)
8544
{
8545
found = TRUE;
8546
geneSfp = SeqMgrGetOverlappingGene (cdsSlp, NULL);
8547
if (geneSfp != NULL) {
8548
geneGrp = (GeneRefPtr) geneSfp->data.value.ptrvalue;
8549
rbsGrp = CopyGeneRef (geneGrp);
8550
if (rbsGrp != NULL)
8551
{
8552
xref = SeqFeatXrefNew ();
8553
xref->data.choice = SEQFEAT_GENE;
8554
xref->data.value.ptrvalue = rbsGrp;
8555
xref->next = rbsSfp->xref;
8556
rbsSfp->xref = xref;
8557
}
8558
}
8559
}
8529
{
8530
found = TRUE;
8531
geneSfp = SeqMgrGetOverlappingGene (cdsSlp, &geneContext);
8532
if (geneSfp != NULL) {
8533
geneGrp = (GeneRefPtr) geneSfp->data.value.ptrvalue;
8534
rbsGrp = CopyGeneRef (geneGrp);
8535
if (rbsGrp != NULL)
8536
{
8537
xref = SeqFeatXrefNew ();
8538
xref->data.choice = SEQFEAT_GENE;
8539
xref->data.value.ptrvalue = rbsGrp;
8540
xref->next = rbsSfp->xref;
8541
rbsSfp->xref = xref;
8542
}
8543
8544
/* enlarge gene to cover RBS */
8545
if (geneContext.left > rbsContext.left)
8546
{
8547
ExtendSeqLocToPosition (geneSfp->location, TRUE, rbsContext.left);
8548
}
8549
8550
}
8551
}
8560
8552
else
8561
{
8562
if (overshot)
8563
overshot = FALSE;
8564
else
8565
{
8566
prevCdsSfp = cdsSfp;
8567
cdsSfp = SeqMgrGetNextFeature (bsp, cdsSfp, 0,
8568
FEATDEF_CDS,
8569
&cdsContext);
8570
}
8571
}
8553
{
8554
if (overshot)
8555
overshot = FALSE;
8556
else
8557
{
8558
prevCdsSfp = cdsSfp;
8559
cdsSfp = SeqMgrGetNextFeature (bsp, cdsSfp, 0,
8560
FEATDEF_CDS,
8561
&cdsContext);
8562
}
8563
}
8572
8564
}
8573
}
8574
else if (strand == Seq_strand_minus)
8575
{
8576
found = FALSE;
8577
while ((cdsSfp != NULL) && (!found))
8578
{
8579
cdsSlp = cdsSfp->location;
8580
cdsRight = GetOffsetInBioseq (cdsSlp, bsp,
8581
SEQLOC_RIGHT_END);
8582
rbsRight = GetOffsetInBioseq (rbsSlp , bsp,
8583
SEQLOC_RIGHT_END);
8584
if (cdsRight > rbsRight)
8585
{
8586
found = TRUE;
8587
if (prevCdsSfp != NULL)
8588
{
8589
overshot = TRUE;
8590
geneSfp = SeqMgrGetOverlappingGene (prevCdsSfp->location,
8591
NULL);
8592
if (geneSfp != NULL) {
8593
geneGrp = (GeneRefPtr) geneSfp->data.value.ptrvalue;
8594
rbsGrp = CopyGeneRef (geneGrp);
8595
if (rbsGrp != NULL)
8596
{
8597
xref = SeqFeatXrefNew ();
8598
xref->data.choice = SEQFEAT_GENE;
8599
xref->data.value.ptrvalue = rbsGrp;
8600
xref->next = rbsSfp->xref;
8601
rbsSfp->xref = xref;
8602
}
8603
}
8565
}
8566
else if (strand == Seq_strand_minus)
8567
{
8568
found = FALSE;
8569
while ((cdsSfp != NULL) && (!found))
8570
{
8571
cdsSlp = cdsSfp->location;
8572
cdsRight = GetOffsetInBioseq (cdsSlp, bsp,
8573
SEQLOC_RIGHT_END);
8574
rbsRight = GetOffsetInBioseq (rbsSlp , bsp,
8575
SEQLOC_RIGHT_END);
8576
if (cdsRight > rbsRight)
8577
{
8578
found = TRUE;
8579
if (prevCdsSfp != NULL)
8580
{
8581
overshot = TRUE;
8582
geneSfp = SeqMgrGetOverlappingGene (prevCdsSfp->location,
8583
NULL);
8584
if (geneSfp != NULL) {
8585
geneGrp = (GeneRefPtr) geneSfp->data.value.ptrvalue;
8586
rbsGrp = CopyGeneRef (geneGrp);
8587
if (rbsGrp != NULL)
8588
{
8589
xref = SeqFeatXrefNew ();
8590
xref->data.choice = SEQFEAT_GENE;
8591
xref->data.value.ptrvalue = rbsGrp;
8592
xref->next = rbsSfp->xref;
8593
rbsSfp->xref = xref;
8594
}
8595
8596
/* enlarge gene to cover RBS */
8597
if (geneContext.right < rbsContext.right)
8598
{
8599
ExtendSeqLocToPosition (geneSfp->location, TRUE, rbsContext.right);
8600
}
8601
8602
}
8604
8603
8605
}
8606
}
8607
else
8608
{
8609
if (overshot)
8610
overshot = FALSE;
8611
else
8612
{
8613
prevCdsSfp = cdsSfp;
8614
cdsSfp = SeqMgrGetNextFeature (bsp, cdsSfp, 0,
8615
FEATDEF_CDS,
8616
&cdsContext);
8617
}
8618
}
8604
}
8605
}
8606
else
8607
{
8608
if (overshot)
8609
overshot = FALSE;
8610
else
8611
{
8612
prevCdsSfp = cdsSfp;
8613
cdsSfp = SeqMgrGetNextFeature (bsp, cdsSfp, 0,
8614
FEATDEF_CDS,
8615
&cdsContext);
8616
}
8617
}
8619
8618
8620
}
8621
}
8619
}
8620
}
8622
8621
8623
rbsSfp = SeqMgrGetNextFeature (bsp, rbsSfp, 0, FEATDEF_RBS, &rbsContext);
8624
}
8622
rbsSfp = SeqMgrGetNextFeature (bsp, rbsSfp, 0, FEATDEF_RBS, &rbsContext);
8623
}
8625
8624
8626
8625
/* Force an update and redraw */
8627
8626
8939
8938
mibp->strand_values = NULL;
8940
8939
}
8941
8940
8941
8942
typedef struct sequenceconstraint
8943
{
8944
Boolean nucs_ok;
8945
Boolean prots_ok;
8946
8947
Int4 other_constraint_type;
8948
StringConstraintPtr string_constraint;
8949
ChoiceConstraintPtr source_constraint;
8950
ValNodePtr feature_list;
8951
8952
} SequenceConstraintData, PNTR SequenceConstraintPtr;
8953
8954
8955
static SequenceConstraintPtr SequenceConstraintFree (SequenceConstraintPtr scp)
8956
{
8957
if (scp != NULL)
8958
{
8959
scp->string_constraint = StringConstraintFree (scp->string_constraint);
8960
scp->source_constraint = ChoiceConstraintFree (scp->source_constraint);
8961
scp->feature_list = ValNodeFree (scp->feature_list);
8962
scp = MemFree (scp);
8963
}
8964
return scp;
8965
}
8966
8967
8968
typedef struct sequenceconstraintdlg
8969
{
8970
DIALOG_MESSAGE_BLOCK
8971
GrouP seq_type_constraint;
8972
GrouP other_constraint_type;
8973
DialoG source_constraint;
8974
DialoG feature_list;
8975
DialoG feature_string_constraint;
8976
DialoG id_string_constraint;
8977
8978
} SequenceConstraintDlgData, PNTR SequenceConstraintDlgPtr;
8979
8980
8981
enum sequenceconstraintothertype
8982
{
8983
SEQ_CONSTRAINT_ANY = 0,
8984
SEQ_CONSTRAINT_SOURCE,
8985
SEQ_CONSTRAINT_FEATURE_TEXT,
8986
SEQ_CONSTRAINT_ID
8987
};
8988
8989
8990
static void ChangeSequenceConstraintType (GrouP g)
8991
{
8992
SequenceConstraintDlgPtr scdp;
8993
Int4 other_constraint_type;
8994
8995
scdp = (SequenceConstraintDlgPtr) GetObjectExtra (g);
8996
if (scdp == NULL)
8997
{
8998
return;
8999
}
9000
other_constraint_type = (GetValue (scdp->other_constraint_type) - 1) / 2;
9001
Disable (scdp->source_constraint);
9002
Disable (scdp->feature_string_constraint);
9003
Disable (scdp->id_string_constraint);
9004
if (other_constraint_type == SEQ_CONSTRAINT_SOURCE)
9005
{
9006
Enable (scdp->source_constraint);
9007
}
9008
else if (other_constraint_type == SEQ_CONSTRAINT_FEATURE_TEXT)
9009
{
9010
Enable (scdp->feature_string_constraint);
9011
}
9012
else if (other_constraint_type == SEQ_CONSTRAINT_ID)
9013
{
9014
Enable (scdp->id_string_constraint);
9015
}
9016
}
9017
9018
static void ResetSequenceConstraintDialog (DialoG d)
9019
{
9020
SequenceConstraintDlgPtr scdp;
9021
9022
scdp = (SequenceConstraintDlgPtr) GetObjectExtra (d);
9023
if (scdp == NULL)
9024
{
9025
return;
9026
}
9027
9028
SetValue (scdp->seq_type_constraint, 1);
9029
SetValue (scdp->other_constraint_type, SEQ_CONSTRAINT_ANY + 1);
9030
ChangeSequenceConstraintType (scdp->other_constraint_type);
9031
}
9032
9033
static void SequenceConstraintToDialog (DialoG d, Pointer data)
9034
{
9035
SequenceConstraintPtr scp;
9036
SequenceConstraintDlgPtr scdp;
9037
9038
scdp = (SequenceConstraintDlgPtr) GetObjectExtra (d);
9039
if (scdp == NULL)
9040
{
9041
return;
9042
}
9043
9044
scp = (SequenceConstraintPtr) data;
9045
9046
if (scp == NULL)
9047
{
9048
ResetSequenceConstraintDialog (d);
9049
}
9050
else
9051
{
9052
if (scp->nucs_ok && scp->prots_ok)
9053
{
9054
SetValue (scdp->seq_type_constraint, 1);
9055
}
9056
else if (scp->nucs_ok)
9057
{
9058
SetValue (scdp->seq_type_constraint, 2);
9059
}
9060
else
9061
{
9062
SetValue (scdp->seq_type_constraint, 3);
9063
}
9064
SetValue (scdp->other_constraint_type, scp->other_constraint_type + 1);
9065
switch (scp->other_constraint_type)
9066
{
9067
case SEQ_CONSTRAINT_SOURCE:
9068
PointerToDialog (scdp->source_constraint, scp->source_constraint);
9069
break;
9070
case SEQ_CONSTRAINT_FEATURE_TEXT:
9071
PointerToDialog (scdp->feature_string_constraint, scp->string_constraint);
9072
PointerToDialog (scdp->feature_list, scp->feature_list);
9073
break;
9074
case SEQ_CONSTRAINT_ID:
9075
PointerToDialog (scdp->id_string_constraint, scp->string_constraint);
9076
break;
9077
}
9078
ChangeSequenceConstraintType (scdp->other_constraint_type);
9079
}
9080
}
9081
9082
9083
static Pointer DialogToSequenceConstraint (DialoG d)
9084
{
9085
SequenceConstraintPtr scp;
9086
SequenceConstraintDlgPtr scdp;
9087
9088
scdp = (SequenceConstraintDlgPtr) GetObjectExtra (d);
9089
if (scdp == NULL)
9090
{
9091
return;
9092
}
9093
9094
scp = (SequenceConstraintPtr) MemNew (sizeof (SequenceConstraintData));
9095
if (scp != NULL)
9096
{
9097
switch (GetValue (scdp->seq_type_constraint))
9098
{
9099
case 1:
9100
scp->nucs_ok = TRUE;
9101
scp->prots_ok = TRUE;
9102
break;
9103
case 2:
9104
scp->nucs_ok = TRUE;
9105
break;
9106
case 3:
9107
scp->prots_ok = TRUE;
9108
break;
9109
}
9110
9111
scp->other_constraint_type = (GetValue (scdp->other_constraint_type) - 1)/2;
9112
switch (scp->other_constraint_type)
9113
{
9114
case SEQ_CONSTRAINT_SOURCE:
9115
scp->source_constraint = DialogToPointer (scdp->source_constraint);
9116
break;
9117
case SEQ_CONSTRAINT_FEATURE_TEXT:
9118
scp->string_constraint = DialogToPointer (scdp->feature_string_constraint);
9119
scp->feature_list = DialogToPointer (scdp->feature_list);
9120
break;
9121
case SEQ_CONSTRAINT_ID:
9122
scp->string_constraint = DialogToPointer (scdp->id_string_constraint);
9123
break;
9124
}
9125
}
9126
return scp;
9127
}
9128
9129
9130
static void SequenceConstraintMessage (DialoG d, Int2 mssg)
9131
9132
{
9133
SequenceConstraintDlgPtr scdp;
9134
9135
scdp = (SequenceConstraintDlgPtr) GetObjectExtra (d);
9136
if (scdp != NULL) {
9137
switch (mssg) {
9138
case VIB_MSG_INIT :
9139
ResetSequenceConstraintDialog (d);
9140
break;
9141
case VIB_MSG_ENTER :
9142
Select (scdp->other_constraint_type);
9143
break;
9144
default :
9145
break;
9146
}
9147
}
9148
}
9149
9150
static ValNodePtr TestSequenceConstraintDialog (DialoG d)
9151
9152
{
9153
return NULL;
9154
}
9155
9156
9157
static DialoG SequenceConstraintDialog (GrouP g)
9158
{
9159
SequenceConstraintDlgPtr dlg;
9160
GrouP p, k;
9161
9162
dlg = (SequenceConstraintDlgPtr) MemNew (sizeof (SequenceConstraintDlgData));
9163
if (dlg == NULL) return NULL;
9164
9165
p = HiddenGroup (g, -1, 0, NULL);
9166
SetObjectExtra (p, dlg, StdCleanupExtraProc);
9167
SetGroupSpacing (p, 10, 10);
9168
9169
dlg->dialog = (DialoG) p;
9170
dlg->todialog = SequenceConstraintToDialog;
9171
dlg->fromdialog = DialogToSequenceConstraint;
9172
dlg->dialogmessage = SequenceConstraintMessage;
9173
dlg->testdialog = TestSequenceConstraintDialog;
9174
9175
dlg->seq_type_constraint = HiddenGroup (p, 4, 0, NULL);
9176
RadioButton (dlg->seq_type_constraint, "All Sequences");
9177
RadioButton (dlg->seq_type_constraint, "Nucleotides");
9178
RadioButton (dlg->seq_type_constraint, "Proteins");
9179
SetValue (dlg->seq_type_constraint, 2);
9180
9181
dlg->other_constraint_type = HiddenGroup (p, 2, 0, ChangeSequenceConstraintType);
9182
RadioButton (dlg->other_constraint_type, "Any sequence");
9183
StaticPrompt (dlg->other_constraint_type, "", 0, dialogTextHeight, systemFont, 'l');
9184
9185
RadioButton (dlg->other_constraint_type, "Where sequence source");
9186
dlg->source_constraint = SourceConstraintDialog (dlg->other_constraint_type, FALSE);
9187
9188
RadioButton (dlg->other_constraint_type, "Where feature text");
9189
k = HiddenGroup (dlg->other_constraint_type, 2, 0, NULL);
9190
SetGroupSpacing (k, 10, 10);
9191
dlg->feature_list = FeatureSelectionDialog (k, TRUE, NULL, NULL);
9192
dlg->feature_string_constraint = StringConstraintDialog (k, NULL, FALSE);
9193
9194
RadioButton (dlg->other_constraint_type, "Where sequence ID");
9195
dlg->id_string_constraint = StringConstraintDialog (dlg->other_constraint_type, NULL, FALSE);
9196
9197
SetValue (dlg->other_constraint_type, CHOICE_CONSTRAINT_ANY);
9198
SetObjectExtra (dlg->other_constraint_type, dlg, NULL);
9199
9200
Disable (dlg->source_constraint);
9201
Disable (dlg->feature_string_constraint);
9202
Disable (dlg->id_string_constraint);
9203
9204
AlignObjects (ALIGN_CENTER, (HANDLE) dlg->seq_type_constraint,
9205
(HANDLE) dlg->other_constraint_type, NULL);
9206
9207
return (DialoG) p;
9208
9209
}
9210
9211
9212
static Boolean DoesIDListMeetStringConstraint (SeqIdPtr sip, StringConstraintPtr string_constraint)
9213
{
9214
Char id [41];
9215
SeqIdPtr tmp;
9216
9217
if (sip == NULL)
9218
{
9219
return FALSE;
9220
}
9221
if (string_constraint == NULL)
9222
{
9223
return TRUE;
9224
}
9225
9226
while (sip != NULL)
9227
{
9228
tmp = sip->next;
9229
sip->next = NULL;
9230
id [0] = '\0';
9231
SeqIdWrite (sip, id, PRINTID_FASTA_LONG, sizeof (id) - 1);
9232
sip->next = tmp;
9233
if (DoesStringMatchConstraint (id, string_constraint))
9234
{
9235
if (string_constraint->not_present)
9236
{
9237
return FALSE;
9238
}
9239
else
9240
{
9241
return TRUE;
9242
}
9243
}
9244
sip = sip->next;
9245
}
9246
if (string_constraint->not_present)
9247
{
9248
return TRUE;
9249
}
9250
else
9251
{
9252
return FALSE;
9253
}
9254
}
9255
9256
9257
static Boolean DoesSequenceMatchSequenceConstraint (BioseqPtr bsp, SequenceConstraintPtr scp)
9258
{
9259
SeqDescrPtr sdp;
9260
SeqMgrDescContext dcontext;
9261
9262
if (bsp == NULL) return FALSE;
9263
if (scp == NULL) return TRUE;
9264
if (!scp->nucs_ok && ISA_na (bsp->mol)) return FALSE;
9265
if (!scp->prots_ok && ISA_aa (bsp->mol)) return FALSE;
9266
switch (scp->other_constraint_type)
9267
{
9268
case SEQ_CONSTRAINT_ANY:
9269
return TRUE;
9270
break;
9271
case SEQ_CONSTRAINT_SOURCE:
9272
sdp = SeqMgrGetNextDescriptor (bsp, NULL, Seq_descr_source, &dcontext);
9273
if (sdp != NULL)
9274
{
9275
return DoesOneSourceMatchConstraint(sdp->data.ptrvalue, scp->source_constraint);
9276
}
9277
break;
9278
case SEQ_CONSTRAINT_FEATURE_TEXT:
9279
return DoBioseqFeaturesMatchSequenceConstraint (bsp, scp->feature_list, scp->string_constraint);
9280
break;
9281
case SEQ_CONSTRAINT_ID:
9282
return DoesIDListMeetStringConstraint(bsp->id, scp->string_constraint);
9283
break;
9284
}
9285
return FALSE;
9286
}
9287
8942
9288
typedef struct molinfoedit {
8943
9289
DESCRIPTOR_FORM_BLOCK
8944
9290
SeqEntryPtr sep;
8945
9291
MolInfoBlock from;
8946
9292
MolInfoBlock to;
8947
GrouP constraint;
8948
Boolean nucsOK;
8949
Boolean protsOK;
9293
DialoG sequence_constraint;
9294
SequenceConstraintPtr scp;
8950
9295
} MolInfoEdit, PNTR MolInfoEditPtr;
8951
9296
8952
9297
static CharPtr labels [] = {
9025
9370
if (IS_Bioseq (sep)) {
9026
9371
9027
9372
bsp = (BioseqPtr) sep->data.ptrvalue;
9028
if ((ISA_na (bsp->mol) && miep->nucsOK) ||
9029
(ISA_aa (bsp->mol) && miep->protsOK)) {
9373
if (DoesSequenceMatchSequenceConstraint (bsp, miep->scp)) {
9030
9374
if ((Uint1)GetValNodePopup (miep->from.molPopup,
9031
9375
miep->from.mol_values) == bsp->mol
9032
9376
|| GetValue (miep->from.molPopup) == 1)
9071
9415
} else if (IS_Bioseq_set (sep)) {
9072
9416
bssp = (BioseqSetPtr) sep->data.ptrvalue;
9073
9417
if (bssp->_class == 2 || bssp->_class == 4) {
9074
if (! miep->nucsOK) return;
9418
if (miep->scp != NULL && ! miep->scp->nucs_ok) return;
9075
9419
}
9076
9420
sdp = bssp->descr;
9077
9421
} else {
9120
9464
9121
9465
{
9122
9466
MolInfoEditPtr miep;
9123
Int2 val;
9124
9467
9125
9468
miep = (MolInfoEditPtr) GetObjectExtra (b);
9126
9469
if (miep == NULL) return;
9127
9470
Hide (miep->form);
9128
9471
WatchCursor ();
9129
9472
Update ();
9130
val = GetValue (miep->constraint);
9131
miep->nucsOK = (Boolean) (val == 1 || val == 2);
9132
miep->protsOK = (Boolean) (val == 1 || val == 3);
9473
9474
miep->scp = DialogToPointer (miep->sequence_constraint);
9475
9133
9476
SeqEntryExplore (miep->sep, (Pointer) miep, EditMolInfoCallback);
9134
9477
FreeMolInfoBlockData (&(miep->from));
9135
9478
FreeMolInfoBlockData (&(miep->to));
9479
miep->scp = SequenceConstraintFree (miep->scp);
9136
9480
ArrowCursor ();
9137
9481
Update ();
9138
9482
ObjMgrSetDirtyFlag (miep->input_entityID, TRUE);
9148
9492
GrouP c;
9149
9493
GrouP g;
9150
9494
GrouP h;
9151
GrouP k;
9152
9495
MolInfoEditPtr miep;
9153
9496
SeqEntryPtr sep;
9154
9497
WindoW w;
9171
9514
miep->sep = sep;
9172
9515
miep->input_entityID = bfp->input_entityID;
9173
9516
9174
k = HiddenGroup (w, 2, 0, NULL);
9175
StaticPrompt (k, "Constraint", 0, stdLineHeight, programFont, 'l');
9176
miep->constraint = HiddenGroup (k, 4, 0, NULL);
9177
RadioButton (miep->constraint, "All Sequences");
9178
RadioButton (miep->constraint, "Nucleotides");
9179
RadioButton (miep->constraint, "Proteins");
9180
SetValue (miep->constraint, 2);
9181
9182
9517
g = HiddenGroup (w, 2, 0, NULL);
9183
9518
h = HiddenGroup (g, 0, 2, NULL);
9184
9519
StaticPrompt (h, "From", 0, 0, programFont, 'c');
9187
9522
StaticPrompt (h, "To", 0, 0, programFont, 'c');
9188
9523
CreateMolInfoBlock (&miep->to, h, TRUE);
9189
9524
9525
miep->sequence_constraint = SequenceConstraintDialog (w);
9526
9190
9527
c = HiddenGroup (w, 2, 0, NULL);
9191
9528
b = DefaultButton (c, "Accept", DoProcessEditMolInfo);
9192
9529
SetObjectExtra (b, miep, NULL);
9193
9530
PushButton (c, "Cancel", StdCancelButtonProc);
9194
AlignObjects (ALIGN_CENTER, (HANDLE) k, (HANDLE) g, (HANDLE) c, NULL);
9531
AlignObjects (ALIGN_CENTER, (HANDLE) g, (HANDLE) miep->sequence_constraint, (HANDLE) c, NULL);
9195
9532
RealizeWindow (w);
9196
9533
Show (w);
9197
9534
Update ();
9289
9626
if (SeqEntryGetSeqDescr (sep, Seq_descr_molinfo, NULL) != NULL) return;
9290
9627
if (IS_Bioseq (sep)) {
9291
9628
bsp = (BioseqPtr) sep->data.ptrvalue;
9292
if ((ISA_na (bsp->mol) && miep->nucsOK) ||
9293
(ISA_aa (bsp->mol) && miep->protsOK)) {
9629
if (DoesSequenceMatchSequenceConstraint(bsp, miep->scp)) {
9294
9630
if ( GetValue (miep->to.molPopup) != 1)
9295
9631
{
9296
9632
bsp->mol = (Uint1) GetValNodePopup (miep->to.molPopup,
9310
9646
} else if (IS_Bioseq_set (sep)) {
9311
9647
bssp = (BioseqSetPtr) sep->data.ptrvalue;
9312
9648
if (bssp->_class == 2 || bssp->_class == 4) {
9313
if (! miep->nucsOK) return;
9649
if (miep->scp != NULL && ! miep->scp->nucs_ok) return;
9314
9650
}
9315
9651
} else return;
9316
9652
mip = MolInfoNew ();
9340
9676
9341
9677
{
9342
9678
MolInfoEditPtr miep;
9343
Int2 val;
9344
9679
9345
9680
miep = (MolInfoEditPtr) GetObjectExtra (b);
9346
9681
if (miep == NULL) return;
9347
9682
Hide (miep->form);
9348
9683
WatchCursor ();
9349
9684
Update ();
9350
val = GetValue (miep->constraint);
9351
miep->nucsOK = (Boolean) (val == 1);
9352
miep->protsOK = (Boolean) (val == 2);
9685
miep->scp = DialogToPointer (miep->sequence_constraint);
9353
9686
DoApplyMolInfo (miep->sep, miep);
9354
9687
FreeMolInfoBlockData (&miep->to);
9688
miep->scp = SequenceConstraintFree (miep->scp);
9355
9689
ArrowCursor ();
9356
9690
Update ();
9357
9691
ObjMgrSetDirtyFlag (miep->input_entityID, TRUE);
9367
9701
GrouP c;
9368
9702
GrouP g;
9369
9703
GrouP h;
9370
GrouP k;
9371
9704
MolInfoEditPtr miep;
9372
9705
SeqEntryPtr sep;
9373
9706
WindoW w;
9390
9723
miep->sep = sep;
9391
9724
miep->input_entityID = bfp->input_entityID;
9392
9725
9393
k = HiddenGroup (w, 2, 0, NULL);
9394
StaticPrompt (k, "Constraint", 0, stdLineHeight, programFont, 'l');
9395
miep->constraint = HiddenGroup (k, 4, 0, NULL);
9396
RadioButton (miep->constraint, "Nucleotides");
9397
RadioButton (miep->constraint, "Proteins");
9398
SetValue (miep->constraint, 0);
9399
9400
9726
g = HiddenGroup (w, 2, 0, NULL);
9401
9727
h = HiddenGroup (g, 0, 2, NULL);
9402
9728
CreateMolInfoBlock (&miep->to, h, TRUE);
9403
9729
9730
miep->sequence_constraint = SequenceConstraintDialog (w);
9731
9404
9732
c = HiddenGroup (w, 2, 0, NULL);
9405
9733
b = DefaultButton (c, "Accept", DoProcessApplyMolInfo);
9406
9734
SetObjectExtra (b, miep, NULL);
9407
9735
PushButton (c, "Cancel", StdCancelButtonProc);
9408
AlignObjects (ALIGN_CENTER, (HANDLE) k, (HANDLE) g, (HANDLE) c, NULL);
9736
AlignObjects (ALIGN_CENTER, (HANDLE) g, (HANDLE) miep->sequence_constraint, (HANDLE) c, NULL);
9409
9737
RealizeWindow (w);
9410
9738
Show (w);
9411
9739
Update ();
9752
10080
Update ();
9753
10081
}
9754
10082
9755
static void AddGenePseudoConstraint (IteM i)
9756
{
9757
GenePseudoConstraint (i, TRUE);
9758
}
9759
9760
10083
static void ClearGenePseudoConstraint (IteM i)
9761
10084
{
9762
10085
GenePseudoConstraint (i, FALSE);
11878
12201
OrgModPtr omp;
11879
12202
OrgNamePtr onp;
11880
12203
OrgRefPtr orp;
11881
CharPtr str;
12204
CharPtr str, cp_end;
11882
12205
ValNodePtr vnp;
11883
12206
11884
12207
if (biop == NULL) return;
11891
12214
str = StringISearch (omp->subname, "ATCC");
11892
12215
if (str != NULL)
11893
12216
{
12217
/* skip over ATCC */
11894
12218
str += 4;
12219
/* skip over colon and whitespace */
11895
12220
ch = *str;
11896
12221
while (IS_WHITESP (ch) || ch == ':') {
11897
12222
str++;
11898
12223
ch = *str;
11899
12224
}
11900
if (! StringHasNoText (str)) {
12225
12226
cp_end = StringChr (str, ';');
12227
if (cp_end != NULL)
12228
{
12229
*cp_end = 0;
12230
}
12231
if (! StringHasNoText (str)) {
11901
12232
for (vnp = orp->db; vnp != NULL; vnp = vnp->next) {
11902
12233
dbt = (DbtagPtr) vnp->data.ptrvalue;
11903
12234
if (dbt != NULL && StringICmp (dbt->db, "ATCC") == 0) {
11916
12247
dbt->tag = oip;
11917
12248
ValNodeAddPointer (&(orp->db), 0, (Pointer) dbt);
11918
12249
}
12250
if (cp_end != NULL)
12251
{
12252
*cp_end = ';';
12253
}
11919
12254
}
11920
12255
}
11921
12256
}
14080
14415
14081
14416
if (lip != NULL && lip->fp != NULL && slp != NULL)
14082
14417
{
14083
loc_str = SeqLocPrint(slp);
14418
loc_str = SeqLocPrintUseBestID(slp);
14084
14419
fprintf (lip->fp, "%s\n", loc_str);
14085
14420
MemFree(loc_str);
14086
14421
lip->data_in_log = TRUE;
14088
14423
14089
14424
}
14090
14425
14426
14091
14427
static void BioseqTrimNAndLog (BioseqPtr bsp, Pointer userdata)
14092
14428
{
14093
14429
TrimNAndLogPtr tnalp;
14095
14431
SeqLocPtr slp1 = NULL,
14096
14432
slp2 = NULL;
14097
14433
CharPtr str;
14098
Int4 j,
14099
lens;
14434
Int4 j, lens;
14100
14435
14101
14436
tnalp = (TrimNAndLogPtr) userdata;
14102
14437
if (bsp == NULL || ! ISA_na (bsp->mol) || tnalp == NULL)
14118
14453
{
14119
14454
slp1 = SeqLocIntNew (j+1, lens-1, Seq_strand_plus, sip);
14120
14455
SeqDeleteByLoc (slp1, TRUE, FALSE);
14456
TrimQualityScores (bsp, lens - 1 - j, FALSE);
14121
14457
}
14122
14458
j=0;
14123
14459
while (j<lens) {
14128
14464
if (j>0) {
14129
14465
slp2 = SeqLocIntNew (0, j-1, Seq_strand_plus, sip);
14130
14466
SeqDeleteByLoc (slp2, TRUE, FALSE);
14467
TrimQualityScores (bsp, j, TRUE);
14131
14468
}
14132
14469
if (slp1!=NULL) {
14133
14470
LogTrimmedLocation (tnalp->lip, slp1);
16567
16904
{ "bac", "BAC" },
16568
16905
{ "caenorhabditis elegans", "Caenorhabditis elegans" },
16569
16906
{ "cdna", "cDNA" },
16907
{ "cdnas", "cDNAs" },
16570
16908
{ "coi", "COI" },
16571
16909
{ "coii", "COII" },
16572
16910
{ "danio rerio", "Danio rerio" },
16674
17012
{ "But", "but" },
16675
17013
{ "By", "by" },
16676
17014
{ "In", "in" },
16677
{ "Is", "in" },
17015
{ "Is", "is" },
16678
17016
{ "Of", "of" },
16679
17017
{ "Or", "or" },
16680
17018
{ "The", "the" },
16739
17077
FixAbbreviationsInElement (pEl);
16740
17078
}
16741
17079
16742
static void FixCapitalizationInTitle (CharPtr PNTR pTitle, Boolean first_is_upper)
17080
17081
static void FixOrgNamesInString (CharPtr str, ValNodePtr org_names)
17082
{
17083
ValNodePtr vnp;
17084
CharPtr cp, taxname;
17085
Int4 taxname_len;
17086
17087
if (StringHasNoText (str) || org_names == NULL) return;
17088
for (vnp = org_names; vnp != NULL; vnp = vnp->next)
17089
{
17090
taxname = (CharPtr) org_names->data.ptrvalue;
17091
taxname_len = StringLen (taxname);
17092
cp = StringISearch (str, taxname);
17093
while (cp != NULL)
17094
{
17095
StringNCpy (cp, taxname, taxname_len);
17096
cp = StringISearch (cp + taxname_len, taxname);
17097
}
17098
}
17099
}
17100
17101
17102
extern void ResetCapitalization (Boolean first_is_upper, CharPtr pString)
16743
17103
{
16744
17104
CharPtr pCh;
16745
17105
Boolean was_digit = FALSE;
16746
17106
16747
if (pTitle == NULL) return;
16748
pCh = *pTitle;
17107
pCh = pString;
16749
17108
if (pCh == NULL) return;
16750
17109
if (*pCh == '\0') return;
16751
17110
16785
17144
*pCh = tolower (*pCh);
16786
17145
}
16787
17146
pCh++;
16788
}
17147
}
17148
}
17149
17150
17151
static void
17152
FixCapitalizationInTitle
17153
(CharPtr PNTR pTitle,
17154
Boolean first_is_upper,
17155
ValNodePtr org_names)
17156
{
17157
if (pTitle == NULL) return;
17158
ResetCapitalization (first_is_upper, *pTitle);
16789
17159
FixAbbreviationsInElement (pTitle);
17160
FixOrgNamesInString (*pTitle, org_names);
16790
17161
}
16791
17162
16792
17163
static void FixCapitalizationInAuthor (AuthorPtr pAuthor)
16895
17266
{
16896
17267
Int4 iType;
16897
17268
StringConstraintPtr author_scp;
17269
ValNodePtr org_names;
16898
17270
} FixPubdescData, PNTR FixPubdescPtr;
16899
17271
16900
17272
static void FixPubdesc (PubdescPtr pdp, Pointer userdata)
16972
17344
}
16973
17345
16974
17346
if(iType & FIX_PUB_TITLE_CAPITALIZATION ) {
16975
FixCapitalizationInTitle (title, TRUE);
17347
FixCapitalizationInTitle (title, TRUE, fpp->org_names);
16976
17348
}
16977
17349
16978
17350
if(alp == NULL) continue;
17021
17393
}
17022
17394
}
17023
17395
17396
17397
static void GetOrgNamesInRecordCallback (BioSourcePtr biop, Pointer userdata)
17398
{
17399
ValNodePtr PNTR org_names;
17400
17401
if (biop == NULL || biop->org == NULL || StringHasNoText (biop->org->taxname)
17402
|| userdata == NULL)
17403
{
17404
return;
17405
}
17406
17407
org_names = (ValNodePtr PNTR) userdata;
17408
17409
ValNodeAddPointer (org_names, 0, biop->org->taxname);
17410
}
17411
17412
17024
17413
/* This function is used to apply fixes to citations */
17025
17414
static void FixPubs (Uint2 entityID, Int4 iType, StringConstraintPtr author_scp)
17026
17415
{
17046
17435
fpd.iType = iType;
17047
17436
fpd.author_scp = author_scp;
17048
17437
17438
fpd.org_names = NULL;
17439
if (iType & FIX_PUB_TITLE_CAPITALIZATION)
17440
{
17441
VisitBioSourcesInSep (sep, &(fpd.org_names), GetOrgNamesInRecordCallback);
17442
}
17443
17049
17444
if(sel == NULL)
17050
17445
{
17051
17446
VisitPubdescsInSep (sep, (Pointer)&fpd, FixPubdesc);
17079
17474
sel = sel->next;
17080
17475
}
17081
17476
}
17477
17478
fpd.org_names = ValNodeFree (fpd.org_names);
17082
17479
17083
17480
ObjMgrSetDirtyFlag (entityID, TRUE);
17084
17481
ObjMgrSendMsg (OM_MSG_UPDATE, entityID, 0, 0);
17271
17668
for (vnp = prp->name; vnp != NULL; vnp = vnp->next)
17272
17669
{
17273
17670
product_name = (CharPtr)(vnp->data.ptrvalue);
17274
FixCapitalizationInTitle (&product_name, FALSE);
17671
FixCapitalizationInTitle (&product_name, FALSE, NULL);
17275
17672
vnp->data.ptrvalue = product_name;
17276
17673
}
17277
17674
}
17282
17679
if (rrp != NULL && rrp->ext.choice == 1)
17283
17680
{
17284
17681
product_name = (CharPtr)(rrp->ext.value.ptrvalue);
17285
FixCapitalizationInTitle (&product_name, FALSE);
17682
FixCapitalizationInTitle (&product_name, FALSE, NULL);
17286
17683
rrp->ext.value.ptrvalue = product_name;
17287
17684
}
17288
17685
}
17383
17780
17384
17781
static void FixDeltaSeqDataLen (IteM i)
17385
17782
{
17386
BaseFormPtr bfp;
17387
SeqEntryPtr sep;
17783
BaseFormPtr bfp;
17784
SeqEntryPtr sep;
17388
17785
17389
17786
#ifdef WIN_MAC
17390
17787
bfp = currentFormDataPtr;
17400
17797
Update ();
17401
17798
}
17402
17799
17800
static void InstantiateGapFeatCallback (BioseqPtr bsp, Pointer userdata)
17801
17802
{
17803
Char buf [32];
17804
Int4 currpos = 0;
17805
IntFuzzPtr fuzz;
17806
ImpFeatPtr ifp;
17807
SeqLitPtr litp;
17808
SeqFeatPtr sfp;
17809
SeqIdPtr sip;
17810
SeqLocPtr slp;
17811
ValNodePtr vnp;
17812
17813
if (bsp == NULL || bsp->repr != Seq_repr_delta || bsp->seq_ext_type != 4) return;
17814
sip = SeqIdFindBest (bsp->id, 0);
17815
if (sip == NULL) return;
17816
/* suppress on far delta contigs for now */
17817
if (! DeltaLitOnly (bsp)) return;
17818
17819
for (vnp = (ValNodePtr)(bsp->seq_ext); vnp != NULL; vnp = vnp->next) {
17820
if (vnp->choice == 1) {
17821
slp = (SeqLocPtr) vnp->data.ptrvalue;
17822
if (slp == NULL) continue;
17823
currpos += SeqLocLen (slp);
17824
}
17825
if (vnp->choice == 2) {
17826
litp = (SeqLitPtr) vnp->data.ptrvalue;
17827
if (litp == NULL) continue;
17828
if (litp->seq_data == NULL && litp->length > 0) {
17829
ifp = ImpFeatNew ();
17830
if (ifp == NULL) continue;
17831
ifp->key = StringSave ("gap");
17832
fuzz = litp->fuzz;
17833
sfp = CreateNewFeatureOnBioseq (bsp, SEQFEAT_IMP, NULL);
17834
if (sfp == NULL) continue;
17835
sfp->data.choice = SEQFEAT_IMP;
17836
sfp->data.value.ptrvalue = (Pointer) ifp;
17837
if (fuzz != NULL && fuzz->choice == 4 && fuzz->a == 0) {
17838
AddQualifierToFeature (sfp, "estimated_length", "unknown");
17839
sfp->location = SeqLocFree (sfp->location);
17840
sfp->location = AddIntervalToLocation (NULL, sip, currpos, currpos + litp->length - 1, FALSE, FALSE);
17841
} else {
17842
sprintf (buf, "%ld", (long) litp->length);
17843
AddQualifierToFeature (sfp, "estimated_length", buf);
17844
sfp->location = SeqLocFree (sfp->location);
17845
sfp->location = AddIntervalToLocation (NULL, sip, currpos, currpos + litp->length - 1, FALSE, FALSE);
17846
}
17847
}
17848
currpos += litp->length;
17849
}
17850
}
17851
}
17852
17853
static void InstantiateGapFeatures (IteM i)
17854
17855
{
17856
BaseFormPtr bfp;
17857
SeqEntryPtr sep;
17858
17859
#ifdef WIN_MAC
17860
bfp = currentFormDataPtr;
17861
#else
17862
bfp = GetObjectExtra (i);
17863
#endif
17864
if (bfp == NULL) return;
17865
17866
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
17867
VisitBioseqsInSep (sep, NULL, InstantiateGapFeatCallback);
17868
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
17869
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
17870
Update ();
17871
}
17872
17873
static void RemoveGapFeatCallback (SeqFeatPtr sfp, Pointer userdata)
17874
17875
{
17876
GBQualPtr gbq;
17877
17878
if (sfp == NULL) return;
17879
if (sfp->idx.subtype != FEATDEF_gap) return;
17880
if (StringDoesHaveText (sfp->comment)) return;
17881
for (gbq = sfp->qual; gbq != NULL; gbq = gbq->next) {
17882
if (StringICmp (gbq->qual, "estimated_length") != 0) return;
17883
}
17884
sfp->idx.deleteme = TRUE;
17885
}
17886
17887
static void RemoveUnnecessaryGapFeatures (IteM i)
17888
17889
{
17890
BaseFormPtr bfp;
17891
SeqEntryPtr sep;
17892
17893
#ifdef WIN_MAC
17894
bfp = currentFormDataPtr;
17895
#else
17896
bfp = GetObjectExtra (i);
17897
#endif
17898
if (bfp == NULL) return;
17899
17900
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
17901
VisitFeaturesInSep (sep, NULL, RemoveGapFeatCallback);
17902
17903
ObjMgrSelect (0, 0, 0, 0, NULL);
17904
17905
DeleteMarkedObjects (bfp->input_entityID, 0, NULL);
17906
17907
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
17908
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
17909
Update ();
17910
}
17911
17912
17913
static void RenormalizeNucProtSetsMenuItem (IteM i)
17914
{
17915
BaseFormPtr bfp;
17916
SeqEntryPtr sep;
17917
17918
/* Get the current data */
17919
17920
#ifdef WIN_MAC
17921
bfp = currentFormDataPtr;
17922
#else
17923
bfp = GetObjectExtra (i);
17924
#endif
17925
17926
if (bfp == NULL)
17927
return;
17928
17929
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
17930
if (sep == NULL) return;
17931
WatchCursor();
17932
Update();
17933
RenormalizeNucProtSets (sep, TRUE);
17934
17935
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
17936
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
17937
ArrowCursor ();
17938
Update ();
17939
17940
/* Return successfully */
17941
17942
return;
17943
}
17944
17945
17403
17946
extern void LookupAllPubs (IteM i);
17404
17947
extern void ResolveExistingLocalIDs (IteM i);
17405
17948
extern void PromoteAlignsToBestIDProc (IteM i);
17425
17968
static void NewAligmentViewer (IteM i)
17426
17969
{
17427
17970
BaseFormPtr bfp;
17428
ForM f;
17429
17971
BioseqPtr bsp;
17430
Int2 top;
17431
17972
ValNodePtr seq_annot_list;
17432
17973
SeqAnnotPtr sap;
17433
17974
SeqAlignPtr salp = NULL;
17459
18000
return;
17460
18001
}
17461
18002
18003
OpenNewAlignmentEditor (salp, bfp->input_entityID);
18004
18005
}
18006
18007
static void ShowDiscrepancyReport (IteM i)
18008
{
18009
BaseFormPtr bfp;
17462
18010
#ifdef WIN_MAC
17463
top = 53;
18011
bfp = currentFormDataPtr;
17464
18012
#else
17465
top = 33;
18013
bfp = GetObjectExtra (i);
17466
18014
#endif
17467
18015
17468
f = CreateAlnEditorWindow (33, top, "Alignment Assistant", salp, bfp->input_entityID);
17469
17470
if (f != NULL)
17471
{
17472
Show (f);
17473
Update ();
17474
Select (f);
17475
}
18016
if (bfp == NULL) return;
18017
18018
CreateDiscrepancyReportWindow (bfp);
17476
18019
}
17477
18020
17478
18021
static void TestTax3 (IteM i, Int4 taxid, CharPtr name)
17539
18082
TestTax3 (i, 0, "Escherichia coli");
17540
18083
}
17541
18084
18085
static void MakeFarProtRefXref (SeqFeatPtr sfp)
18086
18087
{
18088
BioseqPtr bsp;
18089
Uint2 entityID;
18090
SeqMgrFeatContext pcontext;
18091
SeqFeatPtr prot;
18092
ProtRefPtr prp;
18093
SeqIdPtr sip;
18094
SeqFeatXrefPtr xref;
18095
18096
for (xref = sfp->xref; xref != NULL; xref = xref->next) {
18097
if (xref->data.choice == SEQFEAT_PROT) return;
18098
}
18099
18100
sip = SeqLocIdForProduct (sfp->product);
18101
if (sip == NULL) return;
18102
bsp = BioseqLockById (sip);
18103
if (bsp == NULL) return;
18104
18105
entityID = ObjMgrGetEntityIDForPointer (bsp);
18106
if (entityID != 0 && SeqMgrFeaturesAreIndexed (entityID) == 0) {
18107
SeqMgrIndexFeatures (entityID, NULL);
18108
}
18109
18110
prot = SeqMgrGetBestProteinFeature (bsp, &pcontext);
18111
if (prot != NULL && prot->data.choice == SEQFEAT_PROT) {
18112
prp = (ProtRefPtr) prot->data.value.ptrvalue;
18113
if (prp != NULL) {
18114
xref = SeqFeatXrefNew ();
18115
if (xref != NULL) {
18116
xref->data.choice = SEQFEAT_PROT;
18117
xref->data.value.ptrvalue = AsnIoMemCopy ((Pointer) prp,
18118
(AsnReadFunc) ProtRefAsnRead,
18119
(AsnWriteFunc) ProtRefAsnWrite);
18120
xref->next = sfp->xref;
18121
sfp->xref = xref;
18122
}
18123
}
18124
}
18125
18126
BioseqUnlock (bsp);
18127
}
18128
18129
static void MakeRedundantGenomicProtXref (
18130
IteM i
18131
)
18132
18133
{
18134
BaseFormPtr bfp;
18135
BioseqPtr bsp;
18136
SeqMgrFeatContext fcontext;
18137
SeqEntryPtr sep;
18138
SeqFeatPtr sfp;
18139
18140
#ifdef WIN_MAC
18141
bfp = currentFormDataPtr;
18142
#else
18143
bfp = GetObjectExtra (i);
18144
#endif
18145
if (bfp == NULL) return;
18146
sep = GetTopSeqEntryForEntityID (bfp->input_entityID);
18147
if (sep == NULL) return;
18148
18149
/* find genomic sequence */
18150
bsp = FindNucBioseq (sep);
18151
if (bsp != NULL) {
18152
sfp = SeqMgrGetNextFeature (bsp, NULL, SEQFEAT_CDREGION, 0, &fcontext);
18153
while (sfp != NULL) {
18154
MakeFarProtRefXref (sfp);
18155
sfp = SeqMgrGetNextFeature (bsp, sfp, SEQFEAT_CDREGION, 0, &fcontext);
18156
}
18157
}
18158
18159
ObjMgrSetDirtyFlag (bfp->input_entityID, TRUE);
18160
ObjMgrSendMsg (OM_MSG_UPDATE, bfp->input_entityID, 0, 0);
18161
}
18162
17542
18163
extern void SetupSpecialMenu (MenU m, BaseFormPtr bfp)
17543
18164
17544
18165
{
17545
18166
IteM i;
17546
18167
MenU s;
17547
MenU x;
18168
MenU x, y, z;
17548
18169
17549
18170
s = SubMenu (m, "Def Line/ D");
17550
18171
x = SubMenu (s, "Automatic Def Line");
17590
18211
s = SubMenu (m, "Organism/ G");
17591
18212
i = CommandItem (s, "Parse Text", ParseDefLineToSourceQual);
17592
18213
SetObjectExtra (i, bfp, NULL);
17593
i = CommandItem (s, "Parse File to Source", ParseFileToSource);
17594
SetObjectExtra (i, bfp, NULL);
17595
18214
SeparatorItem (s);
17596
18215
i = CommandItem (s, "Parse ATCC Strain to Xref", AtccStrainToXref);
17597
18216
SetObjectExtra (i, bfp, NULL);
17598
18217
SeparatorItem (s);
17599
i = CommandItem (s, "Append Modifier to Organism", AddModToOrg);
17600
SetObjectExtra (i, bfp, NULL);
17601
SeparatorItem (s);
17602
18218
i = CommandItem (s, "Trim Organism Name", TrimOrganismName);
17603
18219
SetObjectExtra (i, bfp, NULL);
18220
i = CommandItem (s, "Genus-Species Fixup", GenSpecTaxonFixup);
18221
SetObjectExtra (i, bfp, NULL);
17604
18222
SeparatorItem (s);
17605
18223
i = CommandItem (s, "Prefix Authority with Organism", PrefixAuthorityWithOrganism);
17606
18224
SetObjectExtra (i, bfp, NULL);
18225
i = CommandItem (s, "Append Modifier to Organism", AddModToOrg);
18226
SetObjectExtra (i, bfp, NULL);
17607
18227
i = CommandItem (s, "Parse Trinomial into Subspecies", ParseTrinomial);
17608
18228
SetObjectExtra (i, bfp, NULL);
17609
18229
SeparatorItem (s);
17610
i = CommandItem (s, "Genus-Species Fixup", GenSpecTaxonFixup);
17611
SetObjectExtra (i, bfp, NULL);
17612
SeparatorItem (s);
17613
i = CommandItem (s, "Country Fixup", CountryLookup);
17614
SetObjectExtra (i, bfp, NULL);
17615
SeparatorItem (s);
17616
i = CommandItem (s, "Set Source Focus", SetSourceFocus);
17617
SetObjectExtra (i, bfp, NULL);
17618
i = CommandItem (s, "Clear Source Focus", ClearSourceFocus);
18230
x = SubMenu (s, "Country Fixup");
18231
i = CommandItem (x, "Do Not Fix Capitalization After Colon", CountryLookupWithoutCapFix);
18232
SetObjectExtra (i, bfp, NULL);
18233
i = CommandItem (x, "Fix Capitalization After Colon", CountryLookupWithCapFix);
18234
SetObjectExtra (i, bfp, NULL);
18235
SeparatorItem (s);
18236
x = SubMenu (s, "Parse CollectionDate formats");
18237
i = CommandItem (x, "Month First", ParseCollectionDateMonthFirst);
18238
SetObjectExtra (i, bfp, NULL);
18239
i = CommandItem (x, "Day First", ParseCollectionDateDayFirst);
18240
SetObjectExtra (i, bfp, NULL);
18241
SeparatorItem (s);
18242
x = SubMenu (s, "Source Focus");
18243
i = CommandItem (x, "Set", SetSourceFocus);
18244
SetObjectExtra (i, bfp, NULL);
18245
i = CommandItem (x, "Clear", ClearSourceFocus);
17619
18246
SetObjectExtra (i, bfp, NULL);
17620
18247
SeparatorItem (s);
17621
18248
i = CommandItem (s, "Consolidate Organism Notes", ConsolidateOrganismNotes);
17626
18253
i = CommandItem (x, "Without semicolons", ConsolidateLikeModifiersWithoutSemicolons);
17627
18254
SetObjectExtra (i, bfp, NULL);
17628
18255
SeparatorItem (s);
17629
i = CommandItem (s, "Load Organism Modifiers from File", LoadOrganismModifierTable);
17630
SetObjectExtra (i, bfp, NULL);
17631
i = CommandItem (s, "Export Organism Modifiers to File", ExportOrganismTable);
17632
SetObjectExtra (i, bfp, NULL);
17633
i = CommandItem (s, "Export Last Lineage Table", ExportLastLineage);
17634
SetObjectExtra (i, bfp, NULL);
18256
x = SubMenu(s, "Parse Organism Modifiers");
18257
i = CommandItem (x, "Load From File", LoadOrganismModifierTable);
18258
SetObjectExtra (i, bfp, NULL);
18259
i = CommandItem (x, "Export To File", ExportOrganismTable);
18260
SetObjectExtra (i, bfp, NULL);
18261
i = CommandItem (x, "Export Last Lineage Table", ExportLastLineage);
18262
SetObjectExtra (i, bfp, NULL);
18263
i = CommandItem (s, "Parse File to Source", ParseFileToSource);
18264
SetObjectExtra (i, bfp, NULL);
17635
18265
SeparatorItem (s);
17636
18266
x = SubMenu (s, "Add Type Strain Comments");
17637
18267
i = CommandItem (x, "To All", AddTypeStrainCommentsToAll);
17640
18270
SetObjectExtra (i, bfp, NULL);
17641
18271
SeparatorItem (s);
17642
18272
x = SubMenu (s, "Influenza Virus Names");
17643
i = CommandItem (x, "Parse Strain and Serotype from Influenza A Virus Organisms",
18273
i = CommandItem (x, "Parse Strain,Serotype from Names",
17644
18274
ParseInfluenzaAVirusNames);
17645
18275
SetObjectExtra (i, bfp, NULL);
17646
i = CommandItem (x, "Add Strain and Serotype to Influenza A Virus Organism Names",
18276
i = CommandItem (x, "Add Strain,Serotype to Names",
17647
18277
AddStrainAndSerotypeToInfluenzaAVirusNames);
17648
18278
SetObjectExtra (i, bfp, NULL);
18279
i = CommandItem (x, "Fixup Organism Names", FixupInfluenzaAVirusNames);
18280
SetObjectExtra (i, bfp, NULL);
17649
18281
17650
18282
s = SubMenu (m, "Apply/ A");
17651
18283
i = CommandItem (s, "Add CDS", ApplyCDS);
17669
18301
SeparatorItem (s);
17670
18302
i = CommandItem (s, "Add Gene Pseudo", AddGenePseudo);
17671
18303
SetObjectExtra (i, bfp, NULL);
17672
i = CommandItem (s, "Add Gene Pseudo with String Constraint", AddGenePseudoConstraint);
17673
SetObjectExtra (i, bfp, NULL);
17674
18304
i = CommandItem (s, "Add Gene Pseudo where Feature is Pseudo", MarkGenesWithPseudoFeaturesPseudo);
17675
18305
SetObjectExtra (i, bfp, NULL);
17676
x = SubMenu (s, "Apply GDS Keyword");
17677
i = CommandItem (x, "Without Constraint", ApplyGDSKeyword);
17678
SetObjectExtra (i, bfp, NULL);
17679
i = CommandItem (x, "With Constraint", ApplyGDSKeywordWithStringConstraint);
17680
SetObjectExtra (i, bfp, NULL);
18306
if (indexerVersion)
18307
{
18308
x = SubMenu (s, "Apply Keyword");
18309
i = CommandItem (x, "GDS", ApplyGDSKeyword);
18310
SetObjectExtra (i, bfp, NULL);
18311
i = CommandItem (x, "TPA:inferential", ApplyTPAInferentialKeyword);
18312
SetObjectExtra (i, bfp, NULL);
18313
i = CommandItem (x, "TPA:experimental", ApplyTPAExperimentalKeyword);
18314
SetObjectExtra (i, bfp, NULL);
18315
i = CommandItem (x, "With Constraint", ApplyKeywordWithStringConstraint);
18316
SetObjectExtra (i, bfp, NULL);
18317
}
18318
else
18319
{
18320
i = CommandItem (s, "GDS", ApplyGDSKeyword);
18321
SetObjectExtra (i, bfp, NULL);
18322
}
18323
17681
18324
17682
18325
i = CommandItem (s, "Apply Coding Region Frame", ApplyCDSFrame);
17683
18326
SetObjectExtra (i, bfp, NULL);
17693
18336
17694
18337
i = CommandItem (s, "Remove Qualifiers", RemoveGBQual);
17695
18338
SetObjectExtra (i, bfp, NULL);
18339
18340
if (indexerVersion)
18341
{
18342
i = CommandItem (s, "Remove Keywords", RemoveKeywordWithStringConstraint);
18343
SetObjectExtra (i, bfp, NULL);
18344
}
17696
18345
17697
18346
SeparatorItem (s);
17698
18347
i = CommandItem (s, "Remove Alignments", RemoveAlignment);
17699
18348
SetObjectExtra (i, bfp, NULL);
17700
18349
i = CommandItem (s, "Remove Graphs", RemoveGraph);
17701
18350
SetObjectExtra (i, bfp, NULL);
17702
i = CommandItem (s, "Remove Proteins", RemoveProteins);
18351
x = SubMenu (s, "Remove Proteins");
18352
i = CommandItem (x, "Just Remove Proteins", RemoveProteins);
17703
18353
SetObjectExtra (i, bfp, NULL);
17704
i = CommandItem (s, "Remove Proteins and Renormalize Nuc-Prot Sets", RemoveProteinsAndRenormalize);
18354
i = CommandItem (x, "Remove Proteins and Renormalize Nuc-Prot Sets", RemoveProteinsAndRenormalize);
17705
18355
SetObjectExtra (i, bfp, NULL);
17706
18356
SeparatorItem (s);
17707
18357
i = CommandItem (s, "Remove Source Qualifier", RemoveSourceQual);
17753
18403
SetObjectExtra (i, bfp, NULL);
17754
18404
i = CommandItem (x, "Feats", RemoveDuplicateFeats);
17755
18405
SetObjectExtra (i, bfp, NULL);
17756
i = CommandItem (s, "Remove Gene Xrefs", NewRemoveGeneXrefs);
17757
SetObjectExtra (i, bfp, NULL);
17758
i = CommandItem (s, "Remove Unnecessary Gene Xrefs", RemoveGeneXrefs);
17759
SetObjectExtra (i, bfp, NULL);
17760
i = CommandItem (s, "Remove Non-Suppressing Gene Xrefs", RemoveNSGeneXrefs);
17761
SetObjectExtra (i, bfp, NULL);
17762
i = CommandItem (s, "Remove Gene Xrefs with Orphan Gene Locus", RemoveGeneXrefsNoGene);
17763
SetObjectExtra (i, bfp, NULL);
17764
i = CommandItem (s, "Remove Gene Xrefs with Orphan Locus_tag", RemoveGeneXrefsNoLocTag);
17765
SetObjectExtra (i, bfp, NULL);
17766
i = CommandItem (s, "Remove ALL Gene Xrefs", RemoveAllGeneXrefs);
18406
x = SubMenu (s, "Remove Gene Xrefs");
18407
i = CommandItem (x, "Choose Types and Constraint", NewRemoveGeneXrefs);
18408
SetObjectExtra (i, bfp, NULL);
18409
i = CommandItem (x, "Unnecessary Gene Xrefs", RemoveGeneXrefs);
18410
SetObjectExtra (i, bfp, NULL);
18411
i = CommandItem (x, "Non-Suppressing Gene Xrefs", RemoveNSGeneXrefs);
18412
SetObjectExtra (i, bfp, NULL);
18413
i = CommandItem (x, "Gene Xrefs with Orphan Gene Locus", RemoveGeneXrefsNoGene);
18414
SetObjectExtra (i, bfp, NULL);
18415
i = CommandItem (x, "Gene Xrefs with Orphan Locus_tag", RemoveGeneXrefsNoLocTag);
18416
SetObjectExtra (i, bfp, NULL);
18417
i = CommandItem (x, "ALL Gene Xrefs", RemoveAllGeneXrefs);
17767
18418
SetObjectExtra (i, bfp, NULL);
17768
18419
SeparatorItem (s);
17769
18420
i = CommandItem (s, "Remove Selected Features", RemoveSelFeats);
17878
18529
i = CommandItem (s, "Convert RNA Qual", ConvertRNAQual);
17879
18530
SetObjectExtra (i, bfp, NULL);
17880
18531
17881
i = CommandItem (s, "CDS with internal Stop Codon to Misc Feat",
18532
i = CommandItem (s, "CDS with Internal Stop Codon to Misc Feat",
17882
18533
ConvertCDSWithStopCodons);
17883
18534
SetObjectExtra (i, bfp, NULL);
17884
18535
17885
x = SubMenu (s, "CDS with internal Stop Codon to Pseudo Gene");
18536
x = SubMenu (s, "CDS with Internal Stop Codon to Pseudo Gene");
17886
18537
i = CommandItem (x, "Keep CDS", ConvertCDSToPseudoGeneAndKeep);
17887
18538
SetObjectExtra (i, bfp, NULL);
17888
18539
i = CommandItem (x, "Remove CDS", ConvertCDSToPseudoGeneAndRemove);
17889
18540
SetObjectExtra (i, bfp, NULL);
17890
18541
17891
i = CommandItem (s, "Convert Protein Names for Pseudo-CDSs to Protein Descriptions", ConvertPseudoProteinNamesToProteinDescriptions);
18542
i = CommandItem (s, "Convert Bad Inference Qualifiers to Notes", ConvertBadInferenceToNote);
17892
18543
SetObjectExtra (i, bfp, NULL);
17893
18544
SeparatorItem (s);
17894
18545
17925
18576
SetObjectExtra (i, bfp, NULL);
17926
18577
SeparatorItem (s);
17927
18578
17928
i = CommandItem (s, "Pub Descriptor to Feature", ConvertPubDescToFeat);
18579
x = SubMenu (s, "Pub Descriptor To Feature");
18580
i = CommandItem (x, "All", ConvertPubDescToFeat);
17929
18581
SetObjectExtra (i, bfp, NULL);
17930
i = CommandItem (s, "Pub Descriptor to Feature by Constraint", CreateConvertPubDescStringConstraintDialog);
18582
i = CommandItem (x, "By Constraint", CreateConvertPubDescStringConstraintDialog);
17931
18583
SetObjectExtra (i, bfp, NULL);
17932
18584
i = CommandItem (s, "Source Descriptor to Feature", ConvertSrcDescToFeat);
17933
18585
SetObjectExtra (i, bfp, NULL);
17969
18621
i = CommandItem (s, "Convert SegSets to Delta Sequences", ConvertSegSetToDeltaItem);
17970
18622
SetObjectExtra (i, bfp, NULL);
17971
18623
#endif
17972
SeparatorItem (s);
17973
i = CommandItem (s, "Convert Selected Gaps to Known Length", ConvertSelectedGapFeaturesToKnown);
17974
SetObjectExtra (i, bfp, NULL);
17975
i = CommandItem (s, "Convert Selected Gaps to Unnown Length", ConvertSelectedGapFeaturesToUnknown);
17976
SetObjectExtra (i, bfp, NULL);
17977
i = CommandItem (s, "Convert Adjacent Known Length Gap Pairs to Single Known Length Gaps", ConvertAdjacentKnownGapsToSingleGaps);
17978
SetObjectExtra (i, bfp, NULL);
17979
18624
17980
18625
s = SubMenu (m, "Edit/ E");
17981
18626
i = CommandItem (s, "Edit Qualifiers", EditGBQual);
18007
18652
SetObjectExtra (i, bfp, NULL);
18008
18653
i = CommandItem (x, "Inference", FeatureInferenceEditor);
18009
18654
SetObjectExtra (i, bfp, NULL);
18655
i = CommandItem (x, "Pseudo", FeaturePseudoEditor);
18656
SetObjectExtra (i, bfp, NULL);
18010
18657
18011
18658
SeparatorItem (s);
18012
18659
i = CommandItem (s, "Extend Gene", ExtendGeneReg);
18107
18754
i = CommandItem (x, "With Comment", AddTranslExceptWithComment);
18108
18755
SetObjectExtra (i, bfp, NULL);
18109
18756
SeparatorItem (s);
18110
i = CommandItem (s, "Fix Publication Title Capitalization", FixTitleCapitalization);
18757
x = SubMenu (s, "Fix Publication Capitalization");
18758
i = CommandItem (x, "In Titles", FixTitleCapitalization);
18111
18759
SetObjectExtra (i, bfp, NULL);
18112
i = CommandItem (s, "Fix Publication Affiliation Capitalization", FixAffiliationCapitalization);
18760
i = CommandItem (x, "In Affiliations", FixAffiliationCapitalization);
18113
18761
SetObjectExtra (i, bfp, NULL);
18114
18762
SeparatorItem (s);
18115
18763
x = SubMenu (s, "Fix Authors");
18138
18786
SetObjectExtra (i, bfp, NULL);
18139
18787
18140
18788
SeparatorItem (s);
18141
i = CommandItem (s, "Parse CollectionDate formats, Month First",
18142
ParseCollectionDateMonthFirst);
18143
SetObjectExtra (i, bfp, NULL);
18144
i = CommandItem (s, "Parse CollectionDate formats, Day First",
18145
ParseCollectionDateDayFirst);
18146
SetObjectExtra (i, bfp, NULL);
18147
18789
i = CommandItem (s, "Renormalize Nuc-Prot Sets", RenormalizeNucProtSetsMenuItem);
18790
SetObjectExtra (i, bfp, NULL);
18791
18148
18792
s = SubMenu (m, "Select/ S");
18149
18793
i = CommandItem (s, "Select Descriptors", SelectDescriptor);
18150
18794
SetObjectExtra (i, bfp, NULL);
18176
18820
SetObjectExtra (i, bfp, NULL);
18177
18821
i = CommandItem (x, "Ignore Stop Codon Except at End of Complete CDS", RetranslateCdRegionsNoStopExceptEndCompleteCDS);
18178
18822
SetObjectExtra (i, bfp, NULL);
18179
i = CommandItem (s, "Adjust CDS Locations for Gaps", AdjustCDSLocationsForGaps);
18180
SetObjectExtra (i, bfp, NULL);
18181
18823
i = CommandItem (s, "Retranscribe mRNA Products", ReprocessmRNAProducts);
18182
18824
SetObjectExtra (i, bfp, NULL);
18183
18825
i = CommandItem (s, "Regenerate Peptide Products", ReprocessPeptideProducts);
18214
18856
SeparatorItem (s);
18215
18857
i = CommandItem (s, "Package Features on Parts", PackageOnParts);
18216
18858
SetObjectExtra (i, bfp, NULL);
18859
i = CommandItem (s, "Force Features into one SeqAnnot", ForceRepackage);
18860
SetObjectExtra (i, bfp, NULL);
18217
18861
SeparatorItem (s);
18218
18862
i = CommandItem (s, "Package Proteins on Nucleotides", PackageOnNucs);
18219
18863
SetObjectExtra (i, bfp, NULL);
18220
18864
SeparatorItem (s);
18221
i = CommandItem (s, "Delta or Segmented Sequence to Raw Sequence", SegSeqToRawSeq);
18222
SetObjectExtra (i, bfp, NULL);
18223
i = CommandItem (s, "Raw Sequence with Ns to Delta Sequence",
18865
18866
i = CommandItem (s, "Map Features to Protein Sequences", MapFeaturesToProteinSequence);
18867
SetObjectExtra (i, bfp, NULL);
18868
SeparatorItem (s);
18869
18870
x = SubMenu (s, "Gap Functions");
18871
y = SubMenu (x, "Create");
18872
i = CommandItem (y, "Delta or Segmented Sequence to Raw Sequence", SegSeqToRawSeq);
18873
SetObjectExtra (i, bfp, NULL);
18874
i = CommandItem (y, "Raw Sequence with Ns to Delta Sequence",
18224
18875
RawSeqToDeltaSeqUnknownWithUnknownLengthGaps);
18225
18876
SetObjectExtra (i, bfp, NULL);
18226
i = CommandItem (s, "Convert Raw Sequences To Delta Sequences with Known Gap Locations",
18877
i = CommandItem (y, "Raw Sequences To Delta Sequences with Known Gap Locations",
18227
18878
ConvertRawToDeltaWithGapLocations);
18228
18879
SetObjectExtra (i, bfp, NULL);
18880
y = SubMenu (x, "Convert");
18881
i = CommandItem (y, "Convert Selected Gaps to Known Length", ConvertSelectedGapFeaturesToKnown);
18882
SetObjectExtra (i, bfp, NULL);
18883
i = CommandItem (y, "Convert Selected Gaps to Unknown Length", ConvertSelectedGapFeaturesToUnknown);
18884
SetObjectExtra (i, bfp, NULL);
18885
i = CommandItem (y, "Convert Known-length Gaps to Unknown Length by Size", ConvertGapFeaturesToUnknown);
18886
SetObjectExtra (i, bfp, NULL);
18887
i = CommandItem (y, "Change Length of Selected Known-length Gaps", ChangeKnownGapLength);
18888
SetObjectExtra (i, bfp, NULL);
18889
i = CommandItem (y, "Expand Known-length Gaps to Include Flanking Ns", AddFlankingNsToKnownLengthGaps);
18890
SetObjectExtra (i, bfp, NULL);
18891
i = CommandItem (y, "Combine Adjacent Gaps", CombineAdjacentGaps);
18892
SetObjectExtra (i, bfp, NULL);
18893
SeparatorItem (y);
18894
z = SubMenu (y, "Adjust CDS Locations for Gaps");
18895
i = CommandItem (z, "Unknown Length Gaps Only", AdjustCDSLocationsForGaps);
18896
SetObjectExtra (i, bfp, NULL);
18897
i = CommandItem (z, "Known and Unknown Length Gaps", AdjustCDSLocationsForGapsKnownAndUnknown);
18898
SetObjectExtra (i, bfp, NULL);
18899
i = CommandItem (y, "Trim Coding Regions and mRNAs for Known Gaps", AdjustCodingRegionsEndingInGap);
18900
SetObjectExtra (i, bfp, NULL);
18901
i = CommandItem (y, "Convert Coding Regions with Internal Gaps to Misc_feat", ConvertCodingRegionsWithInternalKnownGapToMiscFeat);
18902
SetObjectExtra (i, bfp, NULL);
18903
SeparatorItem (y);
18904
i = CommandItem (y, "Fix Delta SeqDataLen", FixDeltaSeqDataLen);
18905
SetObjectExtra (i, bfp, NULL);
18906
18907
SeparatorItem (s);
18908
x = SubMenu (s, "Gap Features");
18909
i = CommandItem (x, "Instantiate from Delta Instructions", InstantiateGapFeatures);
18910
SetObjectExtra (i, bfp, NULL);
18911
SeparatorItem (x);
18912
i = CommandItem (x, "Remove Unnecessary Gap Features", RemoveUnnecessaryGapFeatures);
18913
SetObjectExtra (i, bfp, NULL);
18914
18229
18915
SeparatorItem (s);
18230
18916
x = SubMenu (s, "Generate GenProdSet Redundancy");
18231
18917
i = CommandItem (x, "With Descriptor Propagation", MakeRedundantGPSwithProp);
18235
18921
i = CommandItem (x, "Just Copy CDS Prot Xref", MakeRedundantGPSjustXref);
18236
18922
SetObjectExtra (i, bfp, NULL);
18237
18923
SeparatorItem (s);
18924
i = CommandItem (s, "Copy Far Prot Xref to CDS", MakeRedundantGenomicProtXref);
18925
SetObjectExtra (i, bfp, NULL);
18926
SeparatorItem (s);
18238
18927
i = CommandItem (s, "Convert Pseudo CDS to Misc_feat", ConvertPseudoCDSToMiscFeat);
18239
18928
SetObjectExtra (i, bfp, NULL);
18240
18929
i = CommandItem (s, "Process Pseudo Misc_feats", ProcessPseudoMiscFeat);
18314
19003
SeparatorItem (s);
18315
19004
i = CommandItem (s, "Gene Features From Other Features", FeatureToGene);
18316
19005
SetObjectExtra (i, bfp, NULL);
18317
i = CommandItem (s, "CDS Features from Gene", GeneToCds);
18318
SetObjectExtra (i, bfp, NULL);
18319
19006
i = CommandItem (s, "CDS Features from Gene, mRNA, or exon", FeatureToCds);
18320
19007
SetObjectExtra (i, bfp, NULL);
18321
19008
SeparatorItem (s);
18346
19033
i = CommandItem (s, "Reload Publications", LookupAllPubs);
18347
19034
SetObjectExtra (i, bfp, NULL);
18348
19035
SeparatorItem (s);
18349
i = CommandItem (s, "Fix Delta SeqDataLen", FixDeltaSeqDataLen);
18350
SetObjectExtra (i, bfp, NULL);
18351
SeparatorItem (s);
18352
19036
x = SubMenu (s, "Add BLAST tag to Seq-annot");
18353
19037
i = CommandItem (x, "BLASTN", AddBlastNToSeqAnnot);
18354
19038
SetObjectExtra (i, bfp, NULL);
18366
19050
}
18367
19051
18368
19052
s = SubMenu (m, "Link/ K");
18369
i = CommandItem (s, "Assign Feature IDs to CDS and mRNA", AssignFeatIDs);
19053
i = CommandItem (s, "Assign Feature IDs", AssignFeatIDs);
18370
19054
SetObjectExtra (i, bfp, NULL);
18371
19055
i = CommandItem (s, "Clear Feature IDs and Links", ClearFeatIDsAndLinks);
18372
19056
SetObjectExtra (i, bfp, NULL);
18381
19065
SeparatorItem (s);
18382
19066
i = CommandItem (s, "Show Linked CDS or mRNA Feature", SelCDSmRNALink);
18383
19067
SetObjectExtra (i, bfp, NULL);
19068
SeparatorItem (s);
19069
i = CommandItem (s, "Reassign Feature IDs", ReassignFeatIDs);
19070
SetObjectExtra (i, bfp, NULL);
18384
19071
18385
19072
SeparatorItem (m);
18386
19073
i = CommandItem (m, "Sort Unique Count/ U", SUCProc);
18426
19113
SetObjectExtra (i, bfp, NULL);
18427
19114
i = CommandItem (s, "Indexer", TestExtendSequenceSetIndexer);
18428
19115
SetObjectExtra (i, bfp, NULL);
18429
19116
SeparatorItem (m);
19117
i = CommandItem (m, "Discrepancy Report", ShowDiscrepancyReport);
19118
SetObjectExtra (i, bfp, NULL);
18430
19119
18431
19120
}
18432
19121
/*#ifdef INTERNAL_NCBI_SEQUIN*/
Loggerhead is a web-based interface for Breezy
Version: 2.0.1