PharC commited on
Commit
68ceb7f
·
verified ·
1 Parent(s): 5fe20f5

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +286 -285
app.py CHANGED
@@ -1,286 +1,287 @@
1
- from flask import Flask, render_template, request, jsonify, send_file
2
- from Bio import Entrez, SeqIO
3
- import primer3
4
- import ssl
5
- import pandas as pd
6
- import io
7
- import json
8
- from datetime import datetime
9
-
10
- app = Flask(__name__)
11
- ssl._create_default_https_context = ssl._create_unverified_context
12
- def get_ready_for_primers(gene_symbol, species="human"):
13
- """获取基因序列和外显子交界点信息"""
14
- Entrez.email = "your_email@example.com"
15
-
16
- # 1. 搜索基因并获取 NCBI 内部 ID
17
- search_term = f"{gene_symbol}[Gene Name] AND {species}[Organism]"
18
- handle = Entrez.esearch(db="gene", term=search_term)
19
- record = Entrez.read(handle)
20
- if not record["IdList"]:
21
- return {"error": "未找到该基因"}
22
- gene_id = record["IdList"][0]
23
-
24
- # 2. 获取该基因关联的 NM_ 编号
25
- link_handle = Entrez.elink(dbfrom="gene", db="nucleotide", id=gene_id, term="srcdb_refseq[prop] AND mRNA[filter]")
26
- link_record = Entrez.read(link_handle)
27
-
28
- try:
29
- # 获取第一个关联的核苷酸 UID
30
- nucl_id = link_record[0]["LinkSetDb"][0]["Link"][0]["Id"]
31
-
32
- # 3. 下载完整的 GenBank 格式数据
33
- handle = Entrez.efetch(db="nucleotide", id=nucl_id, rettype="gb", retmode="text")
34
- seq_record = SeqIO.read(handle, "genbank")
35
-
36
- # 提取外显子分界点
37
- junctions = []
38
- current_pos = 0
39
- for feature in seq_record.features:
40
- if feature.type == "exon":
41
- start, end = feature.location.start, feature.location.end
42
- current_pos += (end - start)
43
- junctions.append(int(current_pos))
44
-
45
- if junctions:
46
- junctions.pop() # 移除最后一个边界
47
-
48
- return {
49
- "symbol": gene_symbol,
50
- "nm_id": seq_record.id,
51
- "sequence": str(seq_record.seq),
52
- "junctions": junctions
53
- }
54
- except Exception as e:
55
- return {"error": f"获取基因信息失败: {str(e)}"}
56
-
57
- def design_qpcr_primers(gene_data):
58
- """设计qPCR引物"""
59
- if "error" in gene_data:
60
- return gene_data
61
-
62
- seq_args = {
63
- 'SEQUENCE_ID': gene_data['nm_id'],
64
- 'SEQUENCE_TEMPLATE': gene_data['sequence'],
65
- 'SEQUENCE_OVERLAP_JUNCTION_LIST': gene_data['junctions'],
66
- }
67
-
68
- global_args = {
69
- 'PRIMER_OPT_SIZE': 20,
70
- 'PRIMER_MIN_SIZE': 18,
71
- 'PRIMER_MAX_SIZE': 25,
72
- 'PRIMER_OPT_TM': 60.0,
73
- 'PRIMER_MIN_TM': 57.0,
74
- 'PRIMER_MAX_TM': 63.0,
75
- 'PRIMER_TM_MAX_DIFF': 1.0,
76
- 'PRIMER_MIN_GC': 40.0,
77
- 'PRIMER_MAX_GC': 60.0,
78
- 'PRIMER_PRODUCT_SIZE_RANGE': [120, 300],
79
- 'PRIMER_NUM_RETURN': 5,
80
- }
81
-
82
- try:
83
- results = primer3.bindings.design_primers(seq_args, global_args)
84
-
85
- primer_pairs = []
86
- for i in range(global_args['PRIMER_NUM_RETURN']):
87
- try:
88
- pair = {
89
- "id": i + 1,
90
- "forward": results[f'PRIMER_LEFT_{i}_SEQUENCE'],
91
- "reverse": results[f'PRIMER_RIGHT_{i}_SEQUENCE'],
92
- "f_tm": f"{results[f'PRIMER_LEFT_{i}_TM']:.2f}",
93
- "r_tm": f"{results[f'PRIMER_RIGHT_{i}_TM']:.2f}",
94
- "product_size": results[f'PRIMER_PAIR_{i}_PRODUCT_SIZE'],
95
- "junction_info": "跨越外显子交界点"
96
- }
97
- primer_pairs.append(pair)
98
- except KeyError:
99
- break
100
-
101
- return {"primers": primer_pairs, "gene_info": gene_data}
102
- except Exception as e:
103
- return {"error": f"引物设计失败: {str(e)}"}
104
-
105
- @app.route('/')
106
- def index():
107
- return render_template('index.html')
108
-
109
- @app.route('/design_primers', methods=['POST'])
110
- def design_primers_api():
111
- data = request.json
112
- gene_symbol = data.get('gene_symbol', '').strip()
113
- species = data.get('species', 'human')
114
-
115
- if not gene_symbol:
116
- return jsonify({"error": "请输入基因名称"})
117
-
118
- # 获取基因信息
119
- gene_data = get_ready_for_primers(gene_symbol, species)
120
-
121
- # 设计引物
122
- result = design_qpcr_primers(gene_data)
123
-
124
- return jsonify(result)
125
-
126
- @app.route('/batch_design_primers', methods=['POST'])
127
- def batch_design_primers_api():
128
- data = request.json
129
- gene_list = data.get('gene_list', [])
130
- species = data.get('species', 'human')
131
-
132
- if not gene_list:
133
- return jsonify({"error": "请输入基因列表"})
134
-
135
- results = []
136
- for gene_symbol in gene_list:
137
- gene_symbol = gene_symbol.strip()
138
- if not gene_symbol:
139
- continue
140
-
141
- # 获取基因信息
142
- gene_data = get_ready_for_primers(gene_symbol, species)
143
-
144
- # 设计引物
145
- result = design_qpcr_primers(gene_data)
146
-
147
- if "error" in result:
148
- results.append({
149
- "gene": gene_symbol,
150
- "status": "failed",
151
- "error": result["error"]
152
- })
153
- else:
154
- results.append({
155
- "gene": gene_symbol,
156
- "status": "success",
157
- "data": result
158
- })
159
-
160
- return jsonify({"results": results})
161
-
162
- @app.route('/export_primers', methods=['POST'])
163
- def export_primers():
164
- data = request.json
165
- export_format = data.get('format', 'excel') # excel, csv, json
166
- results_data = data.get('data', [])
167
-
168
- if export_format == 'excel':
169
- return export_to_excel(results_data)
170
- elif export_format == 'csv':
171
- return export_to_csv(results_data)
172
- elif export_format == 'json':
173
- return export_to_json(results_data)
174
- else:
175
- return jsonify({"error": "不支持的导出格式"})
176
-
177
- def export_to_excel(results_data):
178
- """导出为Excel格式"""
179
- rows = []
180
-
181
- for result in results_data:
182
- if result.get('status') == 'success':
183
- gene_info = result['data']['gene_info']
184
- primers = result['data']['primers']
185
-
186
- for primer in primers:
187
- rows.append({
188
- '基因名称': gene_info['symbol'],
189
- 'RefSeq ID': gene_info['nm_id'],
190
- '引物对编号': primer['id'],
191
- '正向引物序列': primer['forward'],
192
- '反向引物序列': primer['reverse'],
193
- '正向引物Tm(°C)': primer['f_tm'],
194
- '反向引物Tm(°C)': primer['r_tm'],
195
- '产物长度(bp)': primer['product_size'],
196
- '外显子交界点': ', '.join(map(str, gene_info['junctions'])),
197
- '设计时间': datetime.now().strftime('%Y-%m-%d %H:%M:%S')
198
- })
199
- else:
200
- rows.append({
201
- '基因名称': result['gene'],
202
- 'RefSeq ID': 'N/A',
203
- '引物对编号': 'N/A',
204
- '正向引物序列': 'N/A',
205
- '反向引物序列': 'N/A',
206
- '正向引物Tm(°C)': 'N/A',
207
- '反向引物Tm(°C)': 'N/A',
208
- '产物长度(bp)': 'N/A',
209
- '外显子交界点': 'N/A',
210
- '设计时间': datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
211
- '错误信息': result.get('error', '未知错误')
212
- })
213
-
214
- df = pd.DataFrame(rows)
215
-
216
- # 创建Excel文件
217
- output = io.BytesIO()
218
- with pd.ExcelWriter(output, engine='openpyxl') as writer:
219
- df.to_excel(writer, sheet_name='引物设计结果', index=False)
220
-
221
- output.seek(0)
222
- filename = f"qPCR_primers_{datetime.now().strftime('%Y%m%d_%H%M%S')}.xlsx"
223
-
224
- return send_file(
225
- output,
226
- mimetype='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
227
- as_attachment=True,
228
- download_name=filename
229
- )
230
-
231
- def export_to_csv(results_data):
232
- """导出为CSV格式"""
233
- rows = []
234
-
235
- for result in results_data:
236
- if result.get('status') == 'success':
237
- gene_info = result['data']['gene_info']
238
- primers = result['data']['primers']
239
-
240
- for primer in primers:
241
- rows.append({
242
- '基因名称': gene_info['symbol'],
243
- 'RefSeq ID': gene_info['nm_id'],
244
- '引物对编号': primer['id'],
245
- '正向引物序列': primer['forward'],
246
- '反向引物序列': primer['reverse'],
247
- '正向引物Tm(°C)': primer['f_tm'],
248
- '反向引物Tm(°C)': primer['r_tm'],
249
- '产物长度(bp)': primer['product_size'],
250
- '外显子交界点': ', '.join(map(str, gene_info['junctions'])),
251
- '设计时间': datetime.now().strftime('%Y-%m-%d %H:%M:%S')
252
- })
253
-
254
- df = pd.DataFrame(rows)
255
-
256
- output = io.StringIO()
257
- df.to_csv(output, index=False, encoding='utf-8-sig')
258
-
259
- filename = f"qPCR_primers_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv"
260
-
261
- return send_file(
262
- io.BytesIO(output.getvalue().encode('utf-8-sig')),
263
- mimetype='text/csv',
264
- as_attachment=True,
265
- download_name=filename
266
- )
267
-
268
- def export_to_json(results_data):
269
- """导出为JSON格式"""
270
- export_data = {
271
- "export_time": datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
272
- "total_genes": len(results_data),
273
- "results": results_data
274
- }
275
-
276
- filename = f"qPCR_primers_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
277
-
278
- return send_file(
279
- io.BytesIO(json.dumps(export_data, ensure_ascii=False, indent=2).encode('utf-8')),
280
- mimetype='application/json',
281
- as_attachment=True,
282
- download_name=filename
283
- )
284
-
285
- if __name__ == '__main__':
 
286
  app.run(debug=True, host='0.0.0.0', port=5000)
 
1
+ from flask import Flask, render_template, request, jsonify, send_file
2
+ from Bio import Entrez, SeqIO
3
+ import primer3
4
+ import ssl
5
+ import pandas as pd
6
+ import io
7
+ import json
8
+ from datetime import datetime
9
+ import time
10
+
11
+ app = Flask(__name__)
12
+ ssl._create_default_https_context = ssl._create_unverified_context
13
+ def get_ready_for_primers(gene_symbol, species="human"):
14
+ """获取基因序列和外显子交界点信息"""
15
+ Entrez.email = "your_email@example.com"
16
+
17
+ # 1. 搜索基因并获取 NCBI 内部 ID
18
+ search_term = f"{gene_symbol}[Gene Name] AND {species}[Organism]"
19
+ handle = Entrez.esearch(db="gene", term=search_term)
20
+ record = Entrez.read(handle)
21
+ if not record["IdList"]:
22
+ return {"error": "未找到该基因"}
23
+ gene_id = record["IdList"][0]
24
+
25
+ # 2. 获取该基因关联的 NM_ 编号
26
+ link_handle = Entrez.elink(dbfrom="gene", db="nucleotide", id=gene_id, term="srcdb_refseq[prop] AND mRNA[filter]")
27
+ link_record = Entrez.read(link_handle)
28
+
29
+ try:
30
+ # 获取第一个关联的核苷酸 UID
31
+ nucl_id = link_record[0]["LinkSetDb"][0]["Link"][0]["Id"]
32
+
33
+ # 3. 下载完整的 GenBank 格式数据
34
+ handle = Entrez.efetch(db="nucleotide", id=nucl_id, rettype="gb", retmode="text")
35
+ seq_record = SeqIO.read(handle, "genbank")
36
+
37
+ # 提取外显子分界点
38
+ junctions = []
39
+ current_pos = 0
40
+ for feature in seq_record.features:
41
+ if feature.type == "exon":
42
+ start, end = feature.location.start, feature.location.end
43
+ current_pos += (end - start)
44
+ junctions.append(int(current_pos))
45
+
46
+ if junctions:
47
+ junctions.pop() # 移除最后一个边界
48
+
49
+ return {
50
+ "symbol": gene_symbol,
51
+ "nm_id": seq_record.id,
52
+ "sequence": str(seq_record.seq),
53
+ "junctions": junctions
54
+ }
55
+ except Exception as e:
56
+ return {"error": f"获取基因信息失败: {str(e)}"}
57
+
58
+ def design_qpcr_primers(gene_data):
59
+ """设计qPCR引物"""
60
+ if "error" in gene_data:
61
+ return gene_data
62
+
63
+ seq_args = {
64
+ 'SEQUENCE_ID': gene_data['nm_id'],
65
+ 'SEQUENCE_TEMPLATE': gene_data['sequence'],
66
+ 'SEQUENCE_OVERLAP_JUNCTION_LIST': gene_data['junctions'],
67
+ }
68
+
69
+ global_args = {
70
+ 'PRIMER_OPT_SIZE': 20,
71
+ 'PRIMER_MIN_SIZE': 18,
72
+ 'PRIMER_MAX_SIZE': 25,
73
+ 'PRIMER_OPT_TM': 60.0,
74
+ 'PRIMER_MIN_TM': 57.0,
75
+ 'PRIMER_MAX_TM': 63.0,
76
+ 'PRIMER_TM_MAX_DIFF': 1.0,
77
+ 'PRIMER_MIN_GC': 40.0,
78
+ 'PRIMER_MAX_GC': 60.0,
79
+ 'PRIMER_PRODUCT_SIZE_RANGE': [120, 300],
80
+ 'PRIMER_NUM_RETURN': 5,
81
+ }
82
+
83
+ try:
84
+ results = primer3.bindings.design_primers(seq_args, global_args)
85
+
86
+ primer_pairs = []
87
+ for i in range(global_args['PRIMER_NUM_RETURN']):
88
+ try:
89
+ pair = {
90
+ "id": i + 1,
91
+ "forward": results[f'PRIMER_LEFT_{i}_SEQUENCE'],
92
+ "reverse": results[f'PRIMER_RIGHT_{i}_SEQUENCE'],
93
+ "f_tm": f"{results[f'PRIMER_LEFT_{i}_TM']:.2f}",
94
+ "r_tm": f"{results[f'PRIMER_RIGHT_{i}_TM']:.2f}",
95
+ "product_size": results[f'PRIMER_PAIR_{i}_PRODUCT_SIZE'],
96
+ "junction_info": "跨越外显子交界点"
97
+ }
98
+ primer_pairs.append(pair)
99
+ except KeyError:
100
+ break
101
+
102
+ return {"primers": primer_pairs, "gene_info": gene_data}
103
+ except Exception as e:
104
+ return {"error": f"引物设计失败: {str(e)}"}
105
+
106
+ @app.route('/')
107
+ def index():
108
+ return render_template('index.html')
109
+
110
+ @app.route('/design_primers', methods=['POST'])
111
+ def design_primers_api():
112
+ data = request.json
113
+ gene_symbol = data.get('gene_symbol', '').strip()
114
+ species = data.get('species', 'human')
115
+
116
+ if not gene_symbol:
117
+ return jsonify({"error": "请输入基因名称"})
118
+
119
+ # 获取基因信息
120
+ gene_data = get_ready_for_primers(gene_symbol, species)
121
+
122
+ # 设计引物
123
+ result = design_qpcr_primers(gene_data)
124
+
125
+ return jsonify(result)
126
+
127
+ @app.route('/batch_design_primers', methods=['POST'])
128
+ def batch_design_primers_api():
129
+ data = request.json
130
+ gene_list = data.get('gene_list', [])
131
+ species = data.get('species', 'human')
132
+
133
+ if not gene_list:
134
+ return jsonify({"error": "请输入基因列表"})
135
+
136
+ results = []
137
+ for gene_symbol in gene_list:
138
+ gene_symbol = gene_symbol.strip()
139
+ if not gene_symbol:
140
+ continue
141
+ time.sleep(0.5)
142
+ # 获取基因信息
143
+ gene_data = get_ready_for_primers(gene_symbol, species)
144
+
145
+ # 设计引物
146
+ result = design_qpcr_primers(gene_data)
147
+
148
+ if "error" in result:
149
+ results.append({
150
+ "gene": gene_symbol,
151
+ "status": "failed",
152
+ "error": result["error"]
153
+ })
154
+ else:
155
+ results.append({
156
+ "gene": gene_symbol,
157
+ "status": "success",
158
+ "data": result
159
+ })
160
+
161
+ return jsonify({"results": results})
162
+
163
+ @app.route('/export_primers', methods=['POST'])
164
+ def export_primers():
165
+ data = request.json
166
+ export_format = data.get('format', 'excel') # excel, csv, json
167
+ results_data = data.get('data', [])
168
+
169
+ if export_format == 'excel':
170
+ return export_to_excel(results_data)
171
+ elif export_format == 'csv':
172
+ return export_to_csv(results_data)
173
+ elif export_format == 'json':
174
+ return export_to_json(results_data)
175
+ else:
176
+ return jsonify({"error": "不支持的导出格式"})
177
+
178
+ def export_to_excel(results_data):
179
+ """导出为Excel格式"""
180
+ rows = []
181
+
182
+ for result in results_data:
183
+ if result.get('status') == 'success':
184
+ gene_info = result['data']['gene_info']
185
+ primers = result['data']['primers']
186
+
187
+ for primer in primers:
188
+ rows.append({
189
+ '基因名称': gene_info['symbol'],
190
+ 'RefSeq ID': gene_info['nm_id'],
191
+ '引物对编号': primer['id'],
192
+ '正向引物序列': primer['forward'],
193
+ '反向引物序列': primer['reverse'],
194
+ '正向引物Tm(°C)': primer['f_tm'],
195
+ '反向引物Tm(°C)': primer['r_tm'],
196
+ '产物长度(bp)': primer['product_size'],
197
+ '外显子交界点': ', '.join(map(str, gene_info['junctions'])),
198
+ '设计时间': datetime.now().strftime('%Y-%m-%d %H:%M:%S')
199
+ })
200
+ else:
201
+ rows.append({
202
+ '基因名称': result['gene'],
203
+ 'RefSeq ID': 'N/A',
204
+ '引物对编号': 'N/A',
205
+ '正向引物序列': 'N/A',
206
+ '反向引物序列': 'N/A',
207
+ '正向引物Tm(°C)': 'N/A',
208
+ '反向引物Tm(°C)': 'N/A',
209
+ '产物长度(bp)': 'N/A',
210
+ '外显子交界点': 'N/A',
211
+ '设计时间': datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
212
+ '错误信息': result.get('error', '未知错误')
213
+ })
214
+
215
+ df = pd.DataFrame(rows)
216
+
217
+ # 创建Excel文件
218
+ output = io.BytesIO()
219
+ with pd.ExcelWriter(output, engine='openpyxl') as writer:
220
+ df.to_excel(writer, sheet_name='引物设计结果', index=False)
221
+
222
+ output.seek(0)
223
+ filename = f"qPCR_primers_{datetime.now().strftime('%Y%m%d_%H%M%S')}.xlsx"
224
+
225
+ return send_file(
226
+ output,
227
+ mimetype='application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
228
+ as_attachment=True,
229
+ download_name=filename
230
+ )
231
+
232
+ def export_to_csv(results_data):
233
+ """导出为CSV格式"""
234
+ rows = []
235
+
236
+ for result in results_data:
237
+ if result.get('status') == 'success':
238
+ gene_info = result['data']['gene_info']
239
+ primers = result['data']['primers']
240
+
241
+ for primer in primers:
242
+ rows.append({
243
+ '基因名称': gene_info['symbol'],
244
+ 'RefSeq ID': gene_info['nm_id'],
245
+ '引物对编号': primer['id'],
246
+ '正向引物序列': primer['forward'],
247
+ '反向引物序列': primer['reverse'],
248
+ '正向引物Tm(°C)': primer['f_tm'],
249
+ '反向引物Tm(°C)': primer['r_tm'],
250
+ '产物长度(bp)': primer['product_size'],
251
+ '外显子交界点': ', '.join(map(str, gene_info['junctions'])),
252
+ '设计时间': datetime.now().strftime('%Y-%m-%d %H:%M:%S')
253
+ })
254
+
255
+ df = pd.DataFrame(rows)
256
+
257
+ output = io.StringIO()
258
+ df.to_csv(output, index=False, encoding='utf-8-sig')
259
+
260
+ filename = f"qPCR_primers_{datetime.now().strftime('%Y%m%d_%H%M%S')}.csv"
261
+
262
+ return send_file(
263
+ io.BytesIO(output.getvalue().encode('utf-8-sig')),
264
+ mimetype='text/csv',
265
+ as_attachment=True,
266
+ download_name=filename
267
+ )
268
+
269
+ def export_to_json(results_data):
270
+ """导出为JSON格式"""
271
+ export_data = {
272
+ "export_time": datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
273
+ "total_genes": len(results_data),
274
+ "results": results_data
275
+ }
276
+
277
+ filename = f"qPCR_primers_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
278
+
279
+ return send_file(
280
+ io.BytesIO(json.dumps(export_data, ensure_ascii=False, indent=2).encode('utf-8')),
281
+ mimetype='application/json',
282
+ as_attachment=True,
283
+ download_name=filename
284
+ )
285
+
286
+ if __name__ == '__main__':
287
  app.run(debug=True, host='0.0.0.0', port=5000)