1 /* $Id: BioSource.hpp 546450 2017-09-18 18:15:29Z bollin $
2 * ===========================================================================
3 *
4 * PUBLIC DOMAIN NOTICE
5 * National Center for Biotechnology Information
6 *
7 * This software/database is a "United States Government Work" under the
8 * terms of the United States Copyright Act. It was written as part of
9 * the author's official duties as a United States Government employee and
10 * thus cannot be copyrighted. This software/database is freely available
11 * to the public for use. The National Library of Medicine and the U.S.
12 * Government have not placed any restriction on its use or reproduction.
13 *
14 * Although all reasonable efforts have been taken to ensure the accuracy
15 * and reliability of the software and data, the NLM and the U.S.
16 * Government do not and cannot warrant the performance or results that
17 * may be obtained by using this software or data. The NLM and the U.S.
18 * Government disclaim all warranties, express or implied, including
19 * warranties of performance, merchantability or fitness for any particular
20 * purpose.
21 *
22 * Please cite the author in any work or product based on this material.
23 *
24 * ===========================================================================
25 *
26 * Author: .......
27 *
28 * File Description:
29 * .......
30 *
31 * Remark:
32 * This code was originally generated by application DATATOOL
33 * using specifications from the data definition file
34 * 'seqfeat.asn'.
35 */
36
37 #ifndef OBJECTS_SEQFEAT_BIOSOURCE_HPP
38 #define OBJECTS_SEQFEAT_BIOSOURCE_HPP
39
40
41 // generated includes
42 #include <objects/seqfeat/BioSource_.hpp>
43 #include <objects/seqfeat/SubSource.hpp>
44
45 // generated classes
46
47 BEGIN_NCBI_SCOPE
48
49 BEGIN_objects_SCOPE // namespace ncbi::objects::
50
51 class COrgName;
52 class CFieldDiff;
53 class CSubSource;
54
55 typedef vector< CRef<CFieldDiff> > TFieldDiffList;
56
57
58 class NCBI_SEQFEAT_EXPORT CBioSource : public CBioSource_Base
59 {
60 typedef CBioSource_Base Tparent;
61 public:
62 // constructor
63 CBioSource(void);
64 // destructor
65 ~CBioSource(void);
66
67 // Get the appropriate gene code from this BioSource.
68 int GetGenCode(int def = 1) const;
69
70 // function for getting genome value from organelle name
71 static CBioSource::EGenome GetGenomeByOrganelle (const string& organelle, NStr::ECase use_case = NStr::eCase, bool starts_with = false);
72
73 // function for getting organelle name from genome value
74 static string GetOrganelleByGenome (unsigned int genome);
75
76 // function for getting origin value from origin name
77 static CBioSource::EOrigin GetOriginByString (const string& origin, NStr::ECase use_case = NStr::eCase, bool starts_with = false);
78
79 // function for getting organelle name from genome value
80 static string GetStringFromOrigin (unsigned int origin);
81
82
83 // shortcut access to selected Org-ref and OrgName methods
84 bool IsSetTaxname(void) const;
85 const string& GetTaxname(void) const;
86
87 bool IsSetCommon(void) const;
88 const string& GetCommon(void) const;
89
90 bool IsSetLineage(void) const;
91 const string& GetLineage(void) const;
92
93 bool IsSetGcode(void) const;
94 int GetGcode(void) const;
95
96 bool IsSetMgcode(void) const;
97 int GetMgcode(void) const;
98
99 bool IsSetPgcode(void) const;
100 int GetPgcode(void) const;
101
102 bool IsSetDivision(void) const;
103 const string& GetDivision(void) const;
104
105 bool IsSetOrgname(void) const;
106 const COrgName& GetOrgname(void) const;
107
108 bool IsSetOrgMod(void) const;
109
110 // for GenColl
111 string GetRepliconName (void) const;
112 string GetBioprojectType (void) const;
113 string GetBioprojectLocation (void) const;
114
115 // for Taxonomy
116 void SetDisableStrainForwarding(bool val);
117 bool GetDisableStrainForwarding() const;
118
119 // for BioSample
120 void UpdateWithBioSample(const CBioSource& biosample, bool force, bool is_local_copy = false);
121 static bool ShouldIgnoreConflict(const string& label, string src_val, string sample_val, bool is_local_copy = false);
122
123 TFieldDiffList GetBiosampleDiffs(const CBioSource& biosample, bool is_local_copy = false) const;
124 bool BiosampleDiffsOkForUpdate(const TFieldDiffList& diffs) const;
125
126 typedef pair<string, string> TNameVal;
127 typedef vector<TNameVal> TNameValList;
128
129 TNameValList GetNameValPairs() const;
130
131 static bool IsStopWord(const string& value);
132
133 void AutoFix();
134 void RemoveCultureNotes(bool is_species_level = true);
135 bool RemoveLineageSourceNotes();
136
137 bool RemoveSubSource(int subtype);
138 bool RemoveSubSource(int subtype, const string& val);
139 bool RemoveOrgMod(int subtype);
140 bool RemoveOrgMod(int subtype, const string& val);
141
142 //If taxname starts with uncultured, set environmental-sample to true
143 //If metagenomic, set environmental_sample
144 // Add environmental_sample to BioSource if BioSource.org.orgname.div == "ENV"
145 // Add metagenomic(and environmental_sample) if BioSource.org.orgname.lineage contains "metagenomes"
146 // Add metagenomic(and environmental_sample) if BioSource has / metagenome_source qualifier
147 // returns true if change was made
148 bool FixEnvironmentalSample();
149
150 // Remove null terms from SubSource values and OrgMod values
151 bool RemoveNullTerms();
152
153 // do not allow sex qualifier if virus, bacteria, Archaea, or fungus
154 static bool AllowSexQualifier(const string& lineage);
155 bool AllowSexQualifier() const;
156
157 // do not allow mating_type qualifier if animal, plant, or virus
158 static bool AllowMatingTypeQualifier(const string& lineage);
159 bool AllowMatingTypeQualifier() const;
160
161 //Remove /sex qualifier from virus, bacteria, archaea, fungus organisms
162 //Remove /mating_type qualifier from animal, plant, and virus organisms
163 //Move /mating_type qualifier that is valid /sex qualifier word to /sex qualifier
164 bool FixSexMatingTypeInconsistencies();
165
166 //Remove qualifiers not appropriate for virus organisms from Virus organisms
167 bool RemoveUnexpectedViralQualifiers();
168
169 bool FixGenomeForQualifiers();
170
171 static bool IsViral(const string& lineage);
172 bool IsViral() const;
173
174 bool HasSubtype(CSubSource::TSubtype subtype) const;
175
176 CRef<CBioSource> MakeCommon( const CBioSource& other) const;
177 CRef<CBioSource> MakeCommonExceptOrg(const CBioSource& other) const;
178
179 private:
180 // Prohibit copy constructor and assignment operator
181 CBioSource(const CBioSource& value);
182 CBioSource& operator=(const CBioSource& value);
183
184 void x_ClearCoordinatedBioSampleSubSources();
185 void x_ClearCoordinatedBioSampleOrgMods();
186 TNameValList x_GetOrgModNameValPairs() const;
187 TNameValList x_GetSubtypeNameValPairs() const;
188 void x_RemoveNameElementDiffs(const CBioSource& biosample, TFieldDiffList& diff_list) const;
189 bool x_ShouldIgnoreNoteForBiosample() const;
190
191 // for handling StopWords from BioSample
192 static void x_InitStopWords(void);
193
194 static void x_RemoveStopWords(COrg_ref& org_ref);
195 };
196
197
198
199 /////////////////// CBioSource inline methods
200
201 // constructor
202 inline
CBioSource(void)203 CBioSource::CBioSource(void)
204 {
205 }
206
207
208 /////////////////// end of CBioSource inline methods
209
210
211 // =============================================================================
212 // For representing differences between BioSample and BioSource
213 // =============================================================================
214
215 class NCBI_SEQFEAT_EXPORT CFieldDiff : public CObject
216 {
217 public:
CFieldDiff()218 CFieldDiff() {};
CFieldDiff(string field_name,string src_val,string sample_val)219 CFieldDiff(string field_name, string src_val, string sample_val) :
220 m_FieldName(field_name), m_SrcVal(src_val), m_SampleVal(sample_val)
221 {};
222
~CFieldDiff(void)223 ~CFieldDiff(void) {};
224
GetFieldName() const225 const string& GetFieldName() const { return m_FieldName; };
GetSrcVal() const226 const string& GetSrcVal() const { return m_SrcVal; };
GetSampleVal() const227 const string& GetSampleVal() const { return m_SampleVal; };
228
229 private:
230 string m_FieldName;
231 string m_SrcVal;
232 string m_SampleVal;
233 };
234
235
236
237
238
239 END_objects_SCOPE // namespace ncbi::objects::
240
241 END_NCBI_SCOPE
242
243 #endif // OBJECTS_SEQFEAT_BIOSOURCE_HPP
244 /* Original file checksum: lines: 93, chars: 2400, CRC32: 29efac3b */
245