Spaces:
Running
Running
reverse old app
Browse files- OpenAITools/CrinicalTrialTools.py +234 -274
- OpenAITools/{CrinicalTrialTools_old.py → CrinicalTrialTools_new.py} +274 -234
- app copy.py +0 -106
- app.py +73 -288
- app_new.py +321 -0
- requirements.txt → requirements_new.txt +0 -0
OpenAITools/CrinicalTrialTools.py
CHANGED
@@ -2,73 +2,35 @@ from langchain_community.agent_toolkits import create_sql_agent
|
|
2 |
from langchain_openai import ChatOpenAI
|
3 |
from langchain_groq import ChatGroq
|
4 |
from langchain_core.prompts import ChatPromptTemplate
|
5 |
-
|
6 |
-
try:
|
7 |
-
from pydantic import BaseModel, Field
|
8 |
-
except ImportError:
|
9 |
-
from langchain_core.pydantic_v1 import BaseModel, Field
|
10 |
-
|
11 |
import pandas as pd
|
12 |
-
import
|
13 |
-
import re
|
14 |
-
from typing import Optional
|
15 |
|
16 |
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
17 |
from langchain_community.vectorstores import Chroma
|
18 |
-
|
19 |
-
try:
|
20 |
-
from langchain_community.embeddings import HuggingFaceEmbeddings
|
21 |
-
except ImportError:
|
22 |
-
from langchain.embeddings import HuggingFaceEmbeddings
|
23 |
-
|
24 |
from langchain_core.runnables import RunnablePassthrough
|
25 |
from langchain_core.output_parsers import StrOutputParser
|
26 |
|
27 |
-
# 修正: モジュールレベルでの初期化を削除
|
28 |
-
# gpt = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
|
29 |
|
30 |
-
|
|
|
|
|
|
|
|
|
31 |
from langchain_community.utilities import SQLDatabase
|
32 |
from sqlalchemy import create_engine
|
|
|
33 |
from langchain.prompts import ChatPromptTemplate
|
34 |
from langchain.schema import SystemMessage
|
35 |
from langchain_core.prompts import MessagesPlaceholder
|
|
|
36 |
|
37 |
from OpenAITools.FetchTools import fetch_clinical_trials, fetch_clinical_trials_jp
|
38 |
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
try:
|
43 |
-
return ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
|
44 |
-
except Exception as e:
|
45 |
-
print(f"OpenAI初期化エラー: {e}")
|
46 |
-
return None
|
47 |
-
|
48 |
-
# エラーハンドリング用のデコレータ
|
49 |
-
def retry_on_error(max_retries=3, delay=1):
|
50 |
-
"""エラー時のリトライデコレータ"""
|
51 |
-
def decorator(func):
|
52 |
-
def wrapper(*args, **kwargs):
|
53 |
-
for attempt in range(max_retries):
|
54 |
-
try:
|
55 |
-
return func(*args, **kwargs)
|
56 |
-
except Exception as e:
|
57 |
-
if attempt < max_retries - 1:
|
58 |
-
print(f"エラーが発生しました (試行 {attempt + 1}/{max_retries}): {e}")
|
59 |
-
if "no healthy upstream" in str(e) or "InternalServerError" in str(e):
|
60 |
-
time.sleep(delay * 2) # サーバーエラーの場合は長めに待機
|
61 |
-
else:
|
62 |
-
time.sleep(delay)
|
63 |
-
continue
|
64 |
-
else:
|
65 |
-
print(f"最大リトライ回数に達しました: {e}")
|
66 |
-
raise e
|
67 |
-
return None
|
68 |
-
return wrapper
|
69 |
-
return decorator
|
70 |
-
|
71 |
-
## Cancer Name の抽出
|
72 |
class ExtractTumorName(BaseModel):
|
73 |
"""Extract tumor name from the user's question."""
|
74 |
tumor_name: str = Field(description="Extracted tumor name from the question, or 'None' if no tumor found")
|
@@ -76,12 +38,16 @@ class ExtractTumorName(BaseModel):
|
|
76 |
class TumorNameExtractor:
|
77 |
def __init__(self, llm):
|
78 |
self.llm = llm
|
|
|
|
|
79 |
self.structured_llm_extractor = self.llm.with_structured_output(ExtractTumorName)
|
80 |
|
81 |
-
|
82 |
-
|
83 |
-
|
|
|
84 |
|
|
|
85 |
self.grade_prompt = ChatPromptTemplate.from_messages(
|
86 |
[
|
87 |
("system", self.system_prompt),
|
@@ -89,18 +55,20 @@ class TumorNameExtractor:
|
|
89 |
]
|
90 |
)
|
91 |
|
92 |
-
@retry_on_error(max_retries=3, delay=2)
|
93 |
def extract_tumor_name(self, question: str) -> str:
|
94 |
-
"""
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
-
|
101 |
-
|
102 |
-
|
|
|
103 |
### 質問変更システム
|
|
|
|
|
104 |
class ModifyQuestion(BaseModel):
|
105 |
"""Class for modifying a question by inserting NCTID."""
|
106 |
modified_question: str = Field(description="The modified question with the inserted NCTID.")
|
@@ -108,15 +76,18 @@ class ModifyQuestion(BaseModel):
|
|
108 |
class QuestionModifier:
|
109 |
def __init__(self, llm):
|
110 |
self.llm = llm
|
|
|
|
|
111 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
112 |
|
113 |
-
#
|
114 |
-
self.system_prompt = """あなたは、ユーザーの質問に対して適切なNCTID
|
115 |
-
質問文にNCTID
|
116 |
-
例えば16
|
117 |
-
16歳男性の神経膠腫の患者さんは{
|
118 |
-
NCTIDは {
|
119 |
|
|
|
120 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
121 |
[
|
122 |
("system", self.system_prompt),
|
@@ -124,27 +95,34 @@ NCTIDは {{nct_id}} を使用してください。"""
|
|
124 |
]
|
125 |
)
|
126 |
|
127 |
-
@retry_on_error(max_retries=3, delay=2)
|
128 |
def modify_question(self, question: str, nct_id: str) -> str:
|
129 |
-
"""
|
130 |
-
|
131 |
-
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
|
136 |
-
|
|
|
|
|
|
|
137 |
|
138 |
class QuestionModifierSecond:
|
139 |
def __init__(self, llm):
|
140 |
self.llm = llm
|
|
|
|
|
141 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
142 |
|
143 |
-
|
144 |
-
|
145 |
-
|
146 |
-
16
|
|
|
|
|
147 |
|
|
|
148 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
149 |
[
|
150 |
("system", self.system_prompt),
|
@@ -152,27 +130,34 @@ class QuestionModifierSecond:
|
|
152 |
]
|
153 |
)
|
154 |
|
155 |
-
@retry_on_error(max_retries=3, delay=2)
|
156 |
def modify_question(self, question: str) -> str:
|
157 |
-
"""
|
158 |
-
|
159 |
-
|
160 |
-
|
161 |
-
|
162 |
-
|
163 |
-
|
164 |
-
|
165 |
-
|
|
|
|
|
|
|
166 |
class QuestionModifierEnglish:
|
167 |
def __init__(self, llm):
|
168 |
self.llm = llm
|
|
|
|
|
169 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
170 |
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
|
|
|
|
175 |
|
|
|
176 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
177 |
[
|
178 |
("system", self.system_prompt),
|
@@ -180,34 +165,41 @@ Can a 16 year old male patient with glioma participate in this clinical trial?
|
|
180 |
]
|
181 |
)
|
182 |
|
183 |
-
@retry_on_error(max_retries=3, delay=2)
|
184 |
def modify_question(self, question: str) -> str:
|
185 |
-
"""
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
193 |
|
194 |
-
### Make criteria check Agent
|
195 |
class ClinicalTrialAgent:
|
196 |
def __init__(self, llm, db):
|
197 |
self.llm = llm
|
198 |
self.db = db
|
199 |
|
|
|
200 |
self.system_prompt = """
|
201 |
あなたは患者さんに適した治験を探すエージェントです。
|
202 |
データベースのEligibility Criteriaをチェックして患者さんがその治験を受けることが可能かどうか答えて下さい
|
203 |
"""
|
204 |
|
|
|
205 |
self.prompt = ChatPromptTemplate.from_messages(
|
206 |
[("system", self.system_prompt),
|
207 |
("human", "{input}"),
|
208 |
MessagesPlaceholder("agent_scratchpad")]
|
209 |
)
|
210 |
|
|
|
211 |
self.agent_executor = self.create_sql_agent(self.llm, self.db, self.prompt)
|
212 |
|
213 |
def create_sql_agent(self, llm, db, prompt):
|
@@ -221,56 +213,59 @@ class ClinicalTrialAgent:
|
|
221 |
)
|
222 |
return agent_executor
|
223 |
|
224 |
-
@retry_on_error(max_retries=3, delay=2)
|
225 |
def get_agent_judgment(self, modify_question: str) -> str:
|
226 |
-
"""
|
227 |
-
|
228 |
-
|
229 |
-
|
230 |
-
|
231 |
-
|
232 |
-
|
|
|
|
|
233 |
|
234 |
class SimpleClinicalTrialAgent:
|
235 |
def __init__(self, llm):
|
236 |
self.llm = llm
|
237 |
|
238 |
-
@retry_on_error(max_retries=3, delay=2)
|
239 |
def evaluate_eligibility(self, TargetCriteria: str, question: str) -> str:
|
240 |
-
"""
|
241 |
-
|
242 |
-
|
243 |
-
|
244 |
-
|
245 |
-
|
246 |
-
|
247 |
-
|
248 |
-
|
249 |
-
|
250 |
-
|
251 |
-
|
252 |
-
|
253 |
-
|
254 |
-
|
255 |
-
|
256 |
-
|
257 |
-
|
258 |
-
|
259 |
-
|
260 |
-
|
261 |
-
|
262 |
-
|
263 |
-
|
264 |
-
|
265 |
-
|
266 |
-
|
267 |
-
|
268 |
-
|
269 |
-
|
270 |
-
|
271 |
-
|
272 |
-
|
273 |
-
|
|
|
|
|
|
|
274 |
|
275 |
### output 評価システム
|
276 |
class TrialEligibilityGrader(BaseModel):
|
@@ -282,14 +277,18 @@ class TrialEligibilityGrader(BaseModel):
|
|
282 |
class GraderAgent:
|
283 |
def __init__(self, llm):
|
284 |
self.llm = llm
|
|
|
|
|
285 |
self.structured_llm_grader = self.llm.with_structured_output(TrialEligibilityGrader)
|
286 |
|
|
|
287 |
self.system_prompt = """
|
288 |
あなたは治験に参加する患者の適合性を評価するGraderです。
|
289 |
以下のドキュメントを読み、患者が治験に参加可能かどうかを判断してください。
|
290 |
'yes'(参加可能)、'no'(参加不可能)、'unclear'(判断できない)の3値で答えてください。
|
291 |
"""
|
292 |
|
|
|
293 |
self.grade_prompt = ChatPromptTemplate.from_messages(
|
294 |
[
|
295 |
("system", self.system_prompt),
|
@@ -300,31 +299,34 @@ class GraderAgent:
|
|
300 |
]
|
301 |
)
|
302 |
|
303 |
-
@retry_on_error(max_retries=3, delay=2)
|
304 |
def evaluate_eligibility(self, AgentJudgment_output: str) -> str:
|
305 |
-
"""
|
306 |
-
|
307 |
-
|
308 |
-
|
309 |
-
|
310 |
-
|
311 |
-
|
312 |
-
|
|
|
|
|
|
|
313 |
|
314 |
class LLMTranslator:
|
315 |
def __init__(self, llm):
|
316 |
self.llm = llm
|
317 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
318 |
|
319 |
-
self.system_prompt = """
|
320 |
-
|
321 |
-
|
322 |
-
self.system_prompt2 = """
|
323 |
-
|
324 |
-
MainQuestion:
|
325 |
-
Known gene mutation:
|
326 |
-
Measurable tumour:
|
327 |
-
Biopsiable tumour:
|
|
|
328 |
|
329 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
330 |
[
|
@@ -341,123 +343,81 @@ Biopsiable tumour:"""
|
|
341 |
)
|
342 |
|
343 |
def is_english(self, text: str) -> bool:
|
344 |
-
"""
|
|
|
|
|
|
|
|
|
|
|
345 |
return bool(re.match(r'^[A-Za-z0-9\s.,?!]+$', text))
|
346 |
|
347 |
-
@retry_on_error(max_retries=3, delay=2)
|
348 |
def translate(self, question: str) -> str:
|
349 |
-
"""
|
350 |
-
|
351 |
-
|
352 |
-
|
353 |
-
|
354 |
-
|
355 |
-
|
356 |
-
return result.modified_question
|
357 |
-
except Exception as e:
|
358 |
-
print(f"翻訳エラー: {e}")
|
359 |
return question
|
360 |
-
|
361 |
-
|
|
|
|
|
|
|
|
|
|
|
362 |
def translateQuestion(self, question: str) -> str:
|
363 |
-
"""
|
364 |
-
|
365 |
-
|
366 |
-
|
367 |
-
|
368 |
-
|
369 |
-
|
370 |
-
|
|
|
371 |
|
372 |
def generate_ex_question(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
373 |
-
|
374 |
-
|
375 |
-
|
376 |
-
|
377 |
-
|
378 |
-
|
379 |
-
|
380 |
-
|
381 |
-
|
382 |
-
|
383 |
-
|
384 |
-
|
385 |
-
|
386 |
-
# 質問文の生成
|
387 |
-
ex_question = f"""{age}歳{sex}の{tumor_type}患者さんはこの治験に参加することができますか?
|
388 |
判明している遺伝子変異: {gene_mutation_text}
|
389 |
Meseable tumor: {meseable_text}
|
390 |
Biopsiable tumor: {biopsiable_text}
|
391 |
-
です。
|
392 |
-
|
393 |
-
|
394 |
-
print(f"日本語質問生成エラー: {e}")
|
395 |
-
return f"{age}歳{sex}の{tumor_type}患者さんの治験参加について"
|
396 |
|
397 |
def generate_ex_question_English(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
398 |
-
""
|
399 |
-
|
400 |
-
|
401 |
-
|
402 |
-
|
403 |
-
|
404 |
-
|
405 |
-
|
406 |
-
|
407 |
-
|
408 |
-
|
409 |
-
|
410 |
-
|
411 |
-
|
412 |
-
|
413 |
-
|
414 |
-
# 英語での質問文を生成
|
415 |
-
ex_question = f"""Can a {age}-year-old {sex_text} patient with {tumor_type} participate in this clinical trial?
|
416 |
Known gene mutation: {gene_mutation_text}
|
417 |
Measurable tumor: {meseable_text}
|
418 |
-
Biopsiable tumor: {biopsiable_text}
|
419 |
-
|
420 |
-
|
421 |
-
print(f"英語質問生成エラー: {e}")
|
422 |
-
return f"Can a {age}-year-old patient with {tumor_type} participate in this clinical trial?"
|
423 |
-
|
424 |
-
# テスト関数
|
425 |
-
def test_clinical_trial_tools():
|
426 |
-
"""臨床試験ツールのテスト関数"""
|
427 |
-
try:
|
428 |
-
from langchain_groq import ChatGroq
|
429 |
-
|
430 |
-
# Groqクライアントの初期化
|
431 |
-
groq = ChatGroq(model_name="llama3-70b-8192", temperature=0)
|
432 |
-
|
433 |
-
# 各エージェントの初期化テスト
|
434 |
-
translator = LLMTranslator(groq)
|
435 |
-
criteria_agent = SimpleClinicalTrialAgent(groq)
|
436 |
-
grader_agent = GraderAgent(groq)
|
437 |
-
|
438 |
-
print("✅ 全てのエージェントが正常に初期化されました")
|
439 |
-
|
440 |
-
# サンプル質問の生成テスト
|
441 |
-
sample_question = generate_ex_question_English(
|
442 |
-
age="45",
|
443 |
-
sex="女性",
|
444 |
-
tumor_type="breast cancer",
|
445 |
-
GeneMutation="HER2",
|
446 |
-
Meseable="有り",
|
447 |
-
Biopsiable="有り"
|
448 |
-
)
|
449 |
-
|
450 |
-
print(f"✅ サンプル質問生成成功: {sample_question}")
|
451 |
-
return True
|
452 |
-
|
453 |
-
except Exception as e:
|
454 |
-
print(f"❌ テスト中にエラーが発生しました: {e}")
|
455 |
-
return False
|
456 |
-
|
457 |
-
if __name__ == "__main__":
|
458 |
-
print("ClinicalTrialTools のテストを開始します...")
|
459 |
-
success = test_clinical_trial_tools()
|
460 |
-
if success:
|
461 |
-
print("✅ テストが正常に完了しました。")
|
462 |
-
else:
|
463 |
-
print("❌ テストでエラーが発生しました。")
|
|
|
2 |
from langchain_openai import ChatOpenAI
|
3 |
from langchain_groq import ChatGroq
|
4 |
from langchain_core.prompts import ChatPromptTemplate
|
5 |
+
from langchain_core.pydantic_v1 import BaseModel, Field
|
|
|
|
|
|
|
|
|
|
|
6 |
import pandas as pd
|
7 |
+
from pydantic import BaseModel, Field
|
|
|
|
|
8 |
|
9 |
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
10 |
from langchain_community.vectorstores import Chroma
|
11 |
+
from langchain.embeddings import HuggingFaceEmbeddings
|
|
|
|
|
|
|
|
|
|
|
12 |
from langchain_core.runnables import RunnablePassthrough
|
13 |
from langchain_core.output_parsers import StrOutputParser
|
14 |
|
|
|
|
|
15 |
|
16 |
+
|
17 |
+
gpt = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
|
18 |
+
#agent_gpt_executor = create_sql_agent(gpt, db=db, agent_type="tool-calling", verbose=True)
|
19 |
+
|
20 |
+
## make database
|
21 |
from langchain_community.utilities import SQLDatabase
|
22 |
from sqlalchemy import create_engine
|
23 |
+
|
24 |
from langchain.prompts import ChatPromptTemplate
|
25 |
from langchain.schema import SystemMessage
|
26 |
from langchain_core.prompts import MessagesPlaceholder
|
27 |
+
#agent_groq_executor = create_sql_agent(llm, db=db, agent_type="tool-calling", verbose=True)
|
28 |
|
29 |
from OpenAITools.FetchTools import fetch_clinical_trials, fetch_clinical_trials_jp
|
30 |
|
31 |
+
|
32 |
+
|
33 |
+
## Cancer Name の抽出
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
class ExtractTumorName(BaseModel):
|
35 |
"""Extract tumor name from the user's question."""
|
36 |
tumor_name: str = Field(description="Extracted tumor name from the question, or 'None' if no tumor found")
|
|
|
38 |
class TumorNameExtractor:
|
39 |
def __init__(self, llm):
|
40 |
self.llm = llm
|
41 |
+
|
42 |
+
# LLMの出力を構造化するための設定
|
43 |
self.structured_llm_extractor = self.llm.with_structured_output(ExtractTumorName)
|
44 |
|
45 |
+
# システムプロンプトを設定
|
46 |
+
self.system_prompt = """あなたは、ユーザーの質問に基づいて腫瘍名を英語で抽出するシステムです。\n
|
47 |
+
質問文に腫瘍の種類や名前が含まれている場合、それを英語で返してください。\n
|
48 |
+
質問文に腫瘍名がない場合は 'None' と返答してください。"""
|
49 |
|
50 |
+
# プロンプトテンプレート
|
51 |
self.grade_prompt = ChatPromptTemplate.from_messages(
|
52 |
[
|
53 |
("system", self.system_prompt),
|
|
|
55 |
]
|
56 |
)
|
57 |
|
|
|
58 |
def extract_tumor_name(self, question: str) -> str:
|
59 |
+
"""
|
60 |
+
腫瘍名を抽出するメソッド。
|
61 |
+
:param question: 質問文
|
62 |
+
:return: 抽出された腫瘍名
|
63 |
+
"""
|
64 |
+
# 質問から腫瘍名を抽出する処理
|
65 |
+
tumor_extractor = self.grade_prompt | self.structured_llm_extractor
|
66 |
+
result = tumor_extractor.invoke({"question": question})
|
67 |
+
return result.tumor_name
|
68 |
+
|
69 |
### 質問変更システム
|
70 |
+
|
71 |
+
# ModifyQuestionの出力形式を定義
|
72 |
class ModifyQuestion(BaseModel):
|
73 |
"""Class for modifying a question by inserting NCTID."""
|
74 |
modified_question: str = Field(description="The modified question with the inserted NCTID.")
|
|
|
76 |
class QuestionModifier:
|
77 |
def __init__(self, llm):
|
78 |
self.llm = llm
|
79 |
+
|
80 |
+
# LLMの出力を構造化するための設定
|
81 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
82 |
|
83 |
+
# システムプロンプトを設定
|
84 |
+
self.system_prompt = """あなたは、ユーザーの質問に対して適切なNCTIDを挿入して質問を変更するシステムです。\n
|
85 |
+
質問文にNCTIDを挿入し、形式に基づいて新しい質問を生成してください。\n
|
86 |
+
例えば16歳男性の神経膠腫の患者さんが参加できる臨床治験を教えて下さいという質問に対しては\n
|
87 |
+
16歳男性の神経膠腫の患者さんは{nct_id}に参加できますか?と変更して下さい\n
|
88 |
+
NCTIDは {nct_id} を使用してください。"""
|
89 |
|
90 |
+
# プロンプトテンプレート
|
91 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
92 |
[
|
93 |
("system", self.system_prompt),
|
|
|
95 |
]
|
96 |
)
|
97 |
|
|
|
98 |
def modify_question(self, question: str, nct_id: str) -> str:
|
99 |
+
"""
|
100 |
+
質問を変更するメソッド。
|
101 |
+
:param question: 質問文
|
102 |
+
:param nct_id: NCTID
|
103 |
+
:return: NCTIDを挿入した新しい質問
|
104 |
+
"""
|
105 |
+
# 質問を変更するプロセス
|
106 |
+
question_modifier = self.modify_prompt | self.structured_llm_modifier
|
107 |
+
result = question_modifier.invoke({"question": question, "nct_id": nct_id})
|
108 |
+
modify_question = result.modified_question
|
109 |
+
return modify_question
|
110 |
|
111 |
class QuestionModifierSecond:
|
112 |
def __init__(self, llm):
|
113 |
self.llm = llm
|
114 |
+
|
115 |
+
# LLMの出力を構造化するための設定
|
116 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
117 |
|
118 |
+
# システムプロンプトを設定
|
119 |
+
self.system_prompt = """あなたは、ユーザーの質問を変更するシステムです。\n
|
120 |
+
形式に基づいて新しい質問を生成してください。\n
|
121 |
+
例えば16歳男性の神経膠腫の患者さんが参加できる臨床治験を教えて下さいという質問に対しては\n
|
122 |
+
16歳男性の神経膠腫の患者さんはlこの治験に参加できますか?と変更して下さい\n
|
123 |
+
"""
|
124 |
|
125 |
+
# プロンプトテンプレート
|
126 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
127 |
[
|
128 |
("system", self.system_prompt),
|
|
|
130 |
]
|
131 |
)
|
132 |
|
|
|
133 |
def modify_question(self, question: str) -> str:
|
134 |
+
"""
|
135 |
+
質問を変更するメソッド。
|
136 |
+
:param question: 質問文
|
137 |
+
:param nct_id: NCTID
|
138 |
+
:return: NCTIDを挿入した新しい質問
|
139 |
+
"""
|
140 |
+
# 質問を変更するプロセス
|
141 |
+
question_modifier = self.modify_prompt | self.structured_llm_modifier
|
142 |
+
result = question_modifier.invoke({"question": question})
|
143 |
+
modify_question = result.modified_question
|
144 |
+
return modify_question
|
145 |
+
|
146 |
class QuestionModifierEnglish:
|
147 |
def __init__(self, llm):
|
148 |
self.llm = llm
|
149 |
+
|
150 |
+
# LLMの出力を構造化するための設定
|
151 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
152 |
|
153 |
+
# システムプロンプトを設定
|
154 |
+
self.system_prompt = """あなたは、ユーザーの質問を変更し英語に翻訳するシステムです。\n
|
155 |
+
形式に基づいて新しい質問を生成してください。\n
|
156 |
+
例えば16歳男性の神経膠腫の患者さんが参加できる臨床治験を教えて下さいという質問に対しては\n
|
157 |
+
Can a 16 year old male patient with glioma participate in this clinical trial?と変更して下さい\n
|
158 |
+
"""
|
159 |
|
160 |
+
# プロンプトテンプレート
|
161 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
162 |
[
|
163 |
("system", self.system_prompt),
|
|
|
165 |
]
|
166 |
)
|
167 |
|
|
|
168 |
def modify_question(self, question: str) -> str:
|
169 |
+
"""
|
170 |
+
質問を変更するメソッド。
|
171 |
+
:param question: 質問文
|
172 |
+
:param nct_id: NCTID
|
173 |
+
:return: NCTIDを挿入した新しい質問
|
174 |
+
"""
|
175 |
+
# 質問を変更するプロセス
|
176 |
+
question_modifier = self.modify_prompt | self.structured_llm_modifier
|
177 |
+
result = question_modifier.invoke({"question": question})
|
178 |
+
modify_question = result.modified_question
|
179 |
+
return modify_question
|
180 |
+
|
181 |
+
|
182 |
+
### Make criteria check Agent
|
183 |
|
|
|
184 |
class ClinicalTrialAgent:
|
185 |
def __init__(self, llm, db):
|
186 |
self.llm = llm
|
187 |
self.db = db
|
188 |
|
189 |
+
# システムプロンプトの定義
|
190 |
self.system_prompt = """
|
191 |
あなたは患者さんに適した治験を探すエージェントです。
|
192 |
データベースのEligibility Criteriaをチェックして患者さんがその治験を受けることが可能かどうか答えて下さい
|
193 |
"""
|
194 |
|
195 |
+
# プロンプトテンプレートを作成
|
196 |
self.prompt = ChatPromptTemplate.from_messages(
|
197 |
[("system", self.system_prompt),
|
198 |
("human", "{input}"),
|
199 |
MessagesPlaceholder("agent_scratchpad")]
|
200 |
)
|
201 |
|
202 |
+
# SQL Agentの設定
|
203 |
self.agent_executor = self.create_sql_agent(self.llm, self.db, self.prompt)
|
204 |
|
205 |
def create_sql_agent(self, llm, db, prompt):
|
|
|
213 |
)
|
214 |
return agent_executor
|
215 |
|
|
|
216 |
def get_agent_judgment(self, modify_question: str) -> str:
|
217 |
+
"""
|
218 |
+
Modify���れた質問を元に、患者さんが治験に参加可能かどうかのエージェント判断を取得。
|
219 |
+
:param modify_question: NCTIDが挿入された質問
|
220 |
+
:return: エージェントの判断 (AgentJudgment)
|
221 |
+
"""
|
222 |
+
# LLMに質問を投げて、判断を得る
|
223 |
+
result = self.agent_executor.invoke({"input": modify_question})
|
224 |
+
return result
|
225 |
+
|
226 |
|
227 |
class SimpleClinicalTrialAgent:
|
228 |
def __init__(self, llm):
|
229 |
self.llm = llm
|
230 |
|
|
|
231 |
def evaluate_eligibility(self, TargetCriteria: str, question: str) -> str:
|
232 |
+
"""
|
233 |
+
臨床試験の参加適格性を評価するメソッド。
|
234 |
+
:param TargetCriteria: 試験基準 (Inclusion/Exclusion criteria)
|
235 |
+
:param question: 患者の条件に関する質問
|
236 |
+
:return: 臨床試験に参加可能かどうかのLLMからの応答
|
237 |
+
"""
|
238 |
+
|
239 |
+
# プロンプトの定義
|
240 |
+
prompt_template = """
|
241 |
+
You are an agent looking for a suitable clinical trial for a patient.
|
242 |
+
Please answer whether the patient is eligible for this clinical trial based on the following criteria. If you do not know the answer, say you do not know. Your answer should be brief, no more than 3 sentences.
|
243 |
+
Question: {question}
|
244 |
+
Criteria:
|
245 |
+
""" + TargetCriteria
|
246 |
+
|
247 |
+
# プロンプトテンプレートの作成
|
248 |
+
criteria_prompt = ChatPromptTemplate.from_messages(
|
249 |
+
[
|
250 |
+
(
|
251 |
+
"human",
|
252 |
+
prompt_template
|
253 |
+
)
|
254 |
+
]
|
255 |
+
)
|
256 |
+
|
257 |
+
# RAGチェーンの作成
|
258 |
+
rag_chain = (
|
259 |
+
{"question": RunnablePassthrough()}
|
260 |
+
| criteria_prompt
|
261 |
+
| self.llm
|
262 |
+
| StrOutputParser()
|
263 |
+
)
|
264 |
+
|
265 |
+
# 質問をチェーンに渡して、応答を得る
|
266 |
+
response = rag_chain.invoke(question)
|
267 |
+
return response
|
268 |
+
|
269 |
|
270 |
### output 評価システム
|
271 |
class TrialEligibilityGrader(BaseModel):
|
|
|
277 |
class GraderAgent:
|
278 |
def __init__(self, llm):
|
279 |
self.llm = llm
|
280 |
+
|
281 |
+
# LLMの出力を構造化するための設定
|
282 |
self.structured_llm_grader = self.llm.with_structured_output(TrialEligibilityGrader)
|
283 |
|
284 |
+
# Graderの入力プロンプト
|
285 |
self.system_prompt = """
|
286 |
あなたは治験に参加する患者の適合性を評価するGraderです。
|
287 |
以下のドキュメントを読み、患者が治験に参加可能かどうかを判断してください。
|
288 |
'yes'(参加可能)、'no'(参加不可能)、'unclear'(判断できない)の3値で答えてください。
|
289 |
"""
|
290 |
|
291 |
+
# 評価のためのプロンプトを作成
|
292 |
self.grade_prompt = ChatPromptTemplate.from_messages(
|
293 |
[
|
294 |
("system", self.system_prompt),
|
|
|
299 |
]
|
300 |
)
|
301 |
|
|
|
302 |
def evaluate_eligibility(self, AgentJudgment_output: str) -> str:
|
303 |
+
"""
|
304 |
+
AgentJudgment['output']を基に患者が治験に参加可能かどうかを評価し、スコア(AgentGrade)を返す。
|
305 |
+
:param AgentJudgment_output: エージェント判断の 'output' の値
|
306 |
+
:return: 評価されたスコア (AgentGrade)
|
307 |
+
"""
|
308 |
+
GraderAgent = self.grade_prompt | self.structured_llm_grader
|
309 |
+
result = GraderAgent.invoke({"document": AgentJudgment_output})
|
310 |
+
AgentGrade = result.score
|
311 |
+
return AgentGrade
|
312 |
+
|
313 |
+
import re
|
314 |
|
315 |
class LLMTranslator:
|
316 |
def __init__(self, llm):
|
317 |
self.llm = llm
|
318 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
319 |
|
320 |
+
self.system_prompt = """あなたは、優秀な翻訳者です。\n
|
321 |
+
日本語を英語に翻訳して下さい。\n
|
322 |
+
"""
|
323 |
+
self.system_prompt2 = """あなたは、優秀な翻訳者です。\n
|
324 |
+
日本語を英語に以下のフォーマットに従って翻訳して下さい。\n
|
325 |
+
MainQuestion:
|
326 |
+
Known gene mutation:
|
327 |
+
Measurable tumour:
|
328 |
+
Biopsiable tumour:
|
329 |
+
"""
|
330 |
|
331 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
332 |
[
|
|
|
343 |
)
|
344 |
|
345 |
def is_english(self, text: str) -> bool:
|
346 |
+
"""
|
347 |
+
簡易的にテキストが英語かどうかを判定する関数
|
348 |
+
:param text: 判定するテキスト
|
349 |
+
:return: 英語の場合True、日本語の場合False
|
350 |
+
"""
|
351 |
+
# 英語のアルファベットが多く含まれているかを確認
|
352 |
return bool(re.match(r'^[A-Za-z0-9\s.,?!]+$', text))
|
353 |
|
|
|
354 |
def translate(self, question: str) -> str:
|
355 |
+
"""
|
356 |
+
質問を翻訳するメソッド。英語の質問はそのまま返す。
|
357 |
+
:param question: 質問文
|
358 |
+
:return: 翻訳済みの質問文、または元の質問文(英語の場合)
|
359 |
+
"""
|
360 |
+
# 質問が英語の場合、そのまま返す
|
361 |
+
if self.is_english(question):
|
|
|
|
|
|
|
362 |
return question
|
363 |
+
|
364 |
+
# 日本語の質問は翻訳プロセスにかける
|
365 |
+
question_modifier = self.modify_prompt | self.structured_llm_modifier
|
366 |
+
result = question_modifier.invoke({"question": question})
|
367 |
+
modify_question = result.modified_question
|
368 |
+
return modify_question
|
369 |
+
|
370 |
def translateQuestion(self, question: str) -> str:
|
371 |
+
"""
|
372 |
+
フォーマット付きで質問を翻訳するメソッド。
|
373 |
+
:param question: 質問文
|
374 |
+
:return: フォーマットに従った翻訳済みの質問
|
375 |
+
"""
|
376 |
+
question_modifier = self.modify_prompt2 | self.structured_llm_modifier
|
377 |
+
result = question_modifier.invoke({"question": question})
|
378 |
+
modify_question = result.modified_question
|
379 |
+
return modify_question
|
380 |
|
381 |
def generate_ex_question(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
382 |
+
# GeneMutationが空の場合はUnknownに設定
|
383 |
+
gene_mutation_text = GeneMutation if GeneMutation else "Unknown"
|
384 |
+
|
385 |
+
# MeseableとBiopsiableの値をYes, No, Unknownに変換
|
386 |
+
meseable_text = (
|
387 |
+
"Yes" if Meseable == "有り" else "No" if Meseable == "無し" else "Unknown"
|
388 |
+
)
|
389 |
+
biopsiable_text = (
|
390 |
+
"Yes" if Biopsiable == "有り" else "No" if Biopsiable == "無し" else "Unknown"
|
391 |
+
)
|
392 |
+
|
393 |
+
# 質問文の生成
|
394 |
+
ex_question = f"""{age}歳{sex}の{tumor_type}患者さんはこの治験に参加することができますか?
|
|
|
|
|
395 |
判明している遺伝子変異: {gene_mutation_text}
|
396 |
Meseable tumor: {meseable_text}
|
397 |
Biopsiable tumor: {biopsiable_text}
|
398 |
+
です。
|
399 |
+
"""
|
400 |
+
return ex_question
|
|
|
|
|
401 |
|
402 |
def generate_ex_question_English(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
403 |
+
# GeneMutationが空の場合は"Unknown"に設定
|
404 |
+
gene_mutation_text = GeneMutation if GeneMutation else "Unknown"
|
405 |
+
|
406 |
+
# sexの値を male または female に変換
|
407 |
+
sex_text = "male" if sex == "男性" else "female" if sex == "女性" else "Unknown"
|
408 |
+
|
409 |
+
# MeseableとBiopsiableの値を "Yes", "No", "Unknown" に変換
|
410 |
+
meseable_text = (
|
411 |
+
"Yes" if Meseable == "有り" else "No" if Meseable == "無し" else "Unknown"
|
412 |
+
)
|
413 |
+
biopsiable_text = (
|
414 |
+
"Yes" if Biopsiable == "有り" else "No" if Biopsiable == "無し" else "Unknown"
|
415 |
+
)
|
416 |
+
|
417 |
+
# 英語での質問文を生成
|
418 |
+
ex_question = f"""Can a {age}-year-old {sex_text} patient with {tumor_type} participate in this clinical trial?
|
|
|
|
|
419 |
Known gene mutation: {gene_mutation_text}
|
420 |
Measurable tumor: {meseable_text}
|
421 |
+
Biopsiable tumor: {biopsiable_text}
|
422 |
+
"""
|
423 |
+
return ex_question
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
OpenAITools/{CrinicalTrialTools_old.py → CrinicalTrialTools_new.py}
RENAMED
@@ -2,35 +2,73 @@ from langchain_community.agent_toolkits import create_sql_agent
|
|
2 |
from langchain_openai import ChatOpenAI
|
3 |
from langchain_groq import ChatGroq
|
4 |
from langchain_core.prompts import ChatPromptTemplate
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
6 |
import pandas as pd
|
7 |
-
|
|
|
|
|
8 |
|
9 |
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
10 |
from langchain_community.vectorstores import Chroma
|
11 |
-
|
|
|
|
|
|
|
|
|
|
|
12 |
from langchain_core.runnables import RunnablePassthrough
|
13 |
from langchain_core.output_parsers import StrOutputParser
|
14 |
|
|
|
|
|
15 |
|
16 |
-
|
17 |
-
gpt = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
|
18 |
-
#agent_gpt_executor = create_sql_agent(gpt, db=db, agent_type="tool-calling", verbose=True)
|
19 |
-
|
20 |
-
## make database
|
21 |
from langchain_community.utilities import SQLDatabase
|
22 |
from sqlalchemy import create_engine
|
23 |
-
|
24 |
from langchain.prompts import ChatPromptTemplate
|
25 |
from langchain.schema import SystemMessage
|
26 |
from langchain_core.prompts import MessagesPlaceholder
|
27 |
-
#agent_groq_executor = create_sql_agent(llm, db=db, agent_type="tool-calling", verbose=True)
|
28 |
|
29 |
from OpenAITools.FetchTools import fetch_clinical_trials, fetch_clinical_trials_jp
|
30 |
|
31 |
-
|
32 |
-
|
33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
class ExtractTumorName(BaseModel):
|
35 |
"""Extract tumor name from the user's question."""
|
36 |
tumor_name: str = Field(description="Extracted tumor name from the question, or 'None' if no tumor found")
|
@@ -38,16 +76,12 @@ class ExtractTumorName(BaseModel):
|
|
38 |
class TumorNameExtractor:
|
39 |
def __init__(self, llm):
|
40 |
self.llm = llm
|
41 |
-
|
42 |
-
# LLMの出力を構造化するための設定
|
43 |
self.structured_llm_extractor = self.llm.with_structured_output(ExtractTumorName)
|
44 |
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
質問文に腫瘍名がない場合は 'None' と返答してください。"""
|
49 |
|
50 |
-
# プロンプトテンプレート
|
51 |
self.grade_prompt = ChatPromptTemplate.from_messages(
|
52 |
[
|
53 |
("system", self.system_prompt),
|
@@ -55,20 +89,18 @@ class TumorNameExtractor:
|
|
55 |
]
|
56 |
)
|
57 |
|
|
|
58 |
def extract_tumor_name(self, question: str) -> str:
|
59 |
-
"""
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
|
67 |
-
return result.tumor_name
|
68 |
-
|
69 |
-
### 質問変更システム
|
70 |
|
71 |
-
|
72 |
class ModifyQuestion(BaseModel):
|
73 |
"""Class for modifying a question by inserting NCTID."""
|
74 |
modified_question: str = Field(description="The modified question with the inserted NCTID.")
|
@@ -76,18 +108,15 @@ class ModifyQuestion(BaseModel):
|
|
76 |
class QuestionModifier:
|
77 |
def __init__(self, llm):
|
78 |
self.llm = llm
|
79 |
-
|
80 |
-
# LLMの出力を構造化するための設定
|
81 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
82 |
|
83 |
-
#
|
84 |
-
self.system_prompt = """あなたは、ユーザーの質問に対して適切なNCTID
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
|
90 |
-
# プロンプトテンプレート
|
91 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
92 |
[
|
93 |
("system", self.system_prompt),
|
@@ -95,34 +124,27 @@ class QuestionModifier:
|
|
95 |
]
|
96 |
)
|
97 |
|
|
|
98 |
def modify_question(self, question: str, nct_id: str) -> str:
|
99 |
-
"""
|
100 |
-
|
101 |
-
|
102 |
-
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
result = question_modifier.invoke({"question": question, "nct_id": nct_id})
|
108 |
-
modify_question = result.modified_question
|
109 |
-
return modify_question
|
110 |
|
111 |
class QuestionModifierSecond:
|
112 |
def __init__(self, llm):
|
113 |
self.llm = llm
|
114 |
-
|
115 |
-
# LLMの出力を構造化するための設定
|
116 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
117 |
|
118 |
-
|
119 |
-
|
120 |
-
|
121 |
-
|
122 |
-
16歳男性の神経膠腫の患者さんはlこの治験に参加できますか?と変更して下さい\n
|
123 |
-
"""
|
124 |
|
125 |
-
# プロンプトテンプレート
|
126 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
127 |
[
|
128 |
("system", self.system_prompt),
|
@@ -130,34 +152,27 @@ class QuestionModifierSecond:
|
|
130 |
]
|
131 |
)
|
132 |
|
|
|
133 |
def modify_question(self, question: str) -> str:
|
134 |
-
"""
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
|
142 |
-
|
143 |
-
modify_question = result.modified_question
|
144 |
-
return modify_question
|
145 |
-
|
146 |
class QuestionModifierEnglish:
|
147 |
def __init__(self, llm):
|
148 |
self.llm = llm
|
149 |
-
|
150 |
-
# LLMの出力を構造化するための設定
|
151 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
152 |
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
|
157 |
-
Can a 16 year old male patient with glioma participate in this clinical trial?と変更して下さい\n
|
158 |
-
"""
|
159 |
|
160 |
-
# プロンプトテンプレート
|
161 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
162 |
[
|
163 |
("system", self.system_prompt),
|
@@ -165,41 +180,34 @@ class QuestionModifierEnglish:
|
|
165 |
]
|
166 |
)
|
167 |
|
|
|
168 |
def modify_question(self, question: str) -> str:
|
169 |
-
"""
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
result = question_modifier.invoke({"question": question})
|
178 |
-
modify_question = result.modified_question
|
179 |
-
return modify_question
|
180 |
-
|
181 |
-
|
182 |
-
### Make criteria check Agent
|
183 |
|
|
|
184 |
class ClinicalTrialAgent:
|
185 |
def __init__(self, llm, db):
|
186 |
self.llm = llm
|
187 |
self.db = db
|
188 |
|
189 |
-
# システムプロンプトの定義
|
190 |
self.system_prompt = """
|
191 |
あなたは患者さんに適した治験を探すエージェントです。
|
192 |
データベースのEligibility Criteriaをチェックして患者さんがその治験を受けることが可能かどうか答えて下さい
|
193 |
"""
|
194 |
|
195 |
-
# プロンプトテンプレートを作成
|
196 |
self.prompt = ChatPromptTemplate.from_messages(
|
197 |
[("system", self.system_prompt),
|
198 |
("human", "{input}"),
|
199 |
MessagesPlaceholder("agent_scratchpad")]
|
200 |
)
|
201 |
|
202 |
-
# SQL Agentの設定
|
203 |
self.agent_executor = self.create_sql_agent(self.llm, self.db, self.prompt)
|
204 |
|
205 |
def create_sql_agent(self, llm, db, prompt):
|
@@ -213,59 +221,56 @@ class ClinicalTrialAgent:
|
|
213 |
)
|
214 |
return agent_executor
|
215 |
|
|
|
216 |
def get_agent_judgment(self, modify_question: str) -> str:
|
217 |
-
"""
|
218 |
-
|
219 |
-
|
220 |
-
|
221 |
-
|
222 |
-
|
223 |
-
|
224 |
-
return result
|
225 |
-
|
226 |
|
227 |
class SimpleClinicalTrialAgent:
|
228 |
def __init__(self, llm):
|
229 |
self.llm = llm
|
230 |
|
|
|
231 |
def evaluate_eligibility(self, TargetCriteria: str, question: str) -> str:
|
232 |
-
"""
|
233 |
-
|
234 |
-
|
235 |
-
|
236 |
-
|
237 |
-
|
238 |
-
|
239 |
-
|
240 |
-
|
241 |
-
|
242 |
-
|
243 |
-
|
244 |
-
|
245 |
-
|
246 |
-
|
247 |
-
|
248 |
-
|
249 |
-
|
250 |
-
|
251 |
-
|
252 |
-
|
253 |
-
|
254 |
-
|
255 |
-
|
256 |
-
|
257 |
-
|
258 |
-
|
259 |
-
|
260 |
-
|
261 |
-
|
262 |
-
|
263 |
-
|
264 |
-
|
265 |
-
|
266 |
-
response = rag_chain.invoke(question)
|
267 |
-
return response
|
268 |
-
|
269 |
|
270 |
### output 評価システム
|
271 |
class TrialEligibilityGrader(BaseModel):
|
@@ -277,18 +282,14 @@ class TrialEligibilityGrader(BaseModel):
|
|
277 |
class GraderAgent:
|
278 |
def __init__(self, llm):
|
279 |
self.llm = llm
|
280 |
-
|
281 |
-
# LLMの出力を構造化するための設定
|
282 |
self.structured_llm_grader = self.llm.with_structured_output(TrialEligibilityGrader)
|
283 |
|
284 |
-
# Graderの入力プロンプト
|
285 |
self.system_prompt = """
|
286 |
あなたは治験に参加する患者の適合性を評価するGraderです。
|
287 |
以下のドキュメントを読み、患者が治験に参加可能かどうかを判断してください。
|
288 |
'yes'(参加可能)、'no'(参加不可能)、'unclear'(判断できない)の3値で答えてください。
|
289 |
"""
|
290 |
|
291 |
-
# 評価のためのプロンプトを作成
|
292 |
self.grade_prompt = ChatPromptTemplate.from_messages(
|
293 |
[
|
294 |
("system", self.system_prompt),
|
@@ -299,34 +300,31 @@ class GraderAgent:
|
|
299 |
]
|
300 |
)
|
301 |
|
|
|
302 |
def evaluate_eligibility(self, AgentJudgment_output: str) -> str:
|
303 |
-
"""
|
304 |
-
|
305 |
-
|
306 |
-
|
307 |
-
|
308 |
-
|
309 |
-
|
310 |
-
|
311 |
-
return AgentGrade
|
312 |
-
|
313 |
-
import re
|
314 |
|
315 |
class LLMTranslator:
|
316 |
def __init__(self, llm):
|
317 |
self.llm = llm
|
318 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
319 |
|
320 |
-
self.system_prompt = """
|
321 |
-
|
322 |
-
|
323 |
-
self.system_prompt2 = """
|
324 |
-
|
325 |
-
|
326 |
-
|
327 |
-
|
328 |
-
|
329 |
-
"""
|
330 |
|
331 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
332 |
[
|
@@ -343,81 +341,123 @@ class LLMTranslator:
|
|
343 |
)
|
344 |
|
345 |
def is_english(self, text: str) -> bool:
|
346 |
-
"""
|
347 |
-
簡易的にテキストが英語かどうかを判定する関数
|
348 |
-
:param text: 判定するテキスト
|
349 |
-
:return: 英語の場合True、日本語の場合False
|
350 |
-
"""
|
351 |
-
# 英語のアルファベットが多く含まれているかを確認
|
352 |
return bool(re.match(r'^[A-Za-z0-9\s.,?!]+$', text))
|
353 |
|
|
|
354 |
def translate(self, question: str) -> str:
|
355 |
-
"""
|
356 |
-
|
357 |
-
|
358 |
-
|
359 |
-
|
360 |
-
|
361 |
-
|
|
|
|
|
|
|
362 |
return question
|
363 |
-
|
364 |
-
|
365 |
-
question_modifier = self.modify_prompt | self.structured_llm_modifier
|
366 |
-
result = question_modifier.invoke({"question": question})
|
367 |
-
modify_question = result.modified_question
|
368 |
-
return modify_question
|
369 |
-
|
370 |
def translateQuestion(self, question: str) -> str:
|
371 |
-
"""
|
372 |
-
|
373 |
-
|
374 |
-
|
375 |
-
|
376 |
-
|
377 |
-
|
378 |
-
|
379 |
-
return modify_question
|
380 |
|
381 |
def generate_ex_question(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
382 |
-
|
383 |
-
|
384 |
-
|
385 |
-
|
386 |
-
|
387 |
-
|
388 |
-
|
389 |
-
|
390 |
-
|
391 |
-
|
392 |
-
|
393 |
-
|
394 |
-
|
|
|
|
|
395 |
判明している遺伝子変異: {gene_mutation_text}
|
396 |
Meseable tumor: {meseable_text}
|
397 |
Biopsiable tumor: {biopsiable_text}
|
398 |
-
です。
|
399 |
-
|
400 |
-
|
|
|
|
|
401 |
|
402 |
def generate_ex_question_English(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
403 |
-
|
404 |
-
|
405 |
-
|
406 |
-
|
407 |
-
|
408 |
-
|
409 |
-
|
410 |
-
|
411 |
-
|
412 |
-
|
413 |
-
|
414 |
-
|
415 |
-
|
416 |
-
|
417 |
-
|
418 |
-
|
|
|
|
|
419 |
Known gene mutation: {gene_mutation_text}
|
420 |
Measurable tumor: {meseable_text}
|
421 |
-
Biopsiable tumor: {biopsiable_text}
|
422 |
-
|
423 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
from langchain_openai import ChatOpenAI
|
3 |
from langchain_groq import ChatGroq
|
4 |
from langchain_core.prompts import ChatPromptTemplate
|
5 |
+
# 修正: pydantic v1の非推奨警告を解決
|
6 |
+
try:
|
7 |
+
from pydantic import BaseModel, Field
|
8 |
+
except ImportError:
|
9 |
+
from langchain_core.pydantic_v1 import BaseModel, Field
|
10 |
+
|
11 |
import pandas as pd
|
12 |
+
import time
|
13 |
+
import re
|
14 |
+
from typing import Optional
|
15 |
|
16 |
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
17 |
from langchain_community.vectorstores import Chroma
|
18 |
+
# 修正: HuggingFaceEmbeddingsの非推奨警告を解決
|
19 |
+
try:
|
20 |
+
from langchain_community.embeddings import HuggingFaceEmbeddings
|
21 |
+
except ImportError:
|
22 |
+
from langchain.embeddings import HuggingFaceEmbeddings
|
23 |
+
|
24 |
from langchain_core.runnables import RunnablePassthrough
|
25 |
from langchain_core.output_parsers import StrOutputParser
|
26 |
|
27 |
+
# 修正: モジュールレベルでの初期化を削除
|
28 |
+
# gpt = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
|
29 |
|
30 |
+
## Database関連のインポート
|
|
|
|
|
|
|
|
|
31 |
from langchain_community.utilities import SQLDatabase
|
32 |
from sqlalchemy import create_engine
|
|
|
33 |
from langchain.prompts import ChatPromptTemplate
|
34 |
from langchain.schema import SystemMessage
|
35 |
from langchain_core.prompts import MessagesPlaceholder
|
|
|
36 |
|
37 |
from OpenAITools.FetchTools import fetch_clinical_trials, fetch_clinical_trials_jp
|
38 |
|
39 |
+
# GPT初期化を関数として追加
|
40 |
+
def get_openai_client():
|
41 |
+
"""OpenAIクライアントを安全に初期化"""
|
42 |
+
try:
|
43 |
+
return ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
|
44 |
+
except Exception as e:
|
45 |
+
print(f"OpenAI初期化エラー: {e}")
|
46 |
+
return None
|
47 |
+
|
48 |
+
# エラーハンドリング用のデコレータ
|
49 |
+
def retry_on_error(max_retries=3, delay=1):
|
50 |
+
"""エラー時のリトライデコレータ"""
|
51 |
+
def decorator(func):
|
52 |
+
def wrapper(*args, **kwargs):
|
53 |
+
for attempt in range(max_retries):
|
54 |
+
try:
|
55 |
+
return func(*args, **kwargs)
|
56 |
+
except Exception as e:
|
57 |
+
if attempt < max_retries - 1:
|
58 |
+
print(f"エラーが発生しました (試行 {attempt + 1}/{max_retries}): {e}")
|
59 |
+
if "no healthy upstream" in str(e) or "InternalServerError" in str(e):
|
60 |
+
time.sleep(delay * 2) # サーバーエラーの場合は長めに待機
|
61 |
+
else:
|
62 |
+
time.sleep(delay)
|
63 |
+
continue
|
64 |
+
else:
|
65 |
+
print(f"最大リトライ回数に達しました: {e}")
|
66 |
+
raise e
|
67 |
+
return None
|
68 |
+
return wrapper
|
69 |
+
return decorator
|
70 |
+
|
71 |
+
## Cancer Name の抽出
|
72 |
class ExtractTumorName(BaseModel):
|
73 |
"""Extract tumor name from the user's question."""
|
74 |
tumor_name: str = Field(description="Extracted tumor name from the question, or 'None' if no tumor found")
|
|
|
76 |
class TumorNameExtractor:
|
77 |
def __init__(self, llm):
|
78 |
self.llm = llm
|
|
|
|
|
79 |
self.structured_llm_extractor = self.llm.with_structured_output(ExtractTumorName)
|
80 |
|
81 |
+
self.system_prompt = """あなたは、ユーザーの質問に基づいて腫瘍名を英語で抽出するシステムです。
|
82 |
+
質問文に腫瘍の種類や名前が含まれている場合、それを英語で返してください。
|
83 |
+
質問文に腫瘍名がない場合は 'None' と返答してください。"""
|
|
|
84 |
|
|
|
85 |
self.grade_prompt = ChatPromptTemplate.from_messages(
|
86 |
[
|
87 |
("system", self.system_prompt),
|
|
|
89 |
]
|
90 |
)
|
91 |
|
92 |
+
@retry_on_error(max_retries=3, delay=2)
|
93 |
def extract_tumor_name(self, question: str) -> str:
|
94 |
+
"""腫瘍名を抽出するメソッド"""
|
95 |
+
try:
|
96 |
+
tumor_extractor = self.grade_prompt | self.structured_llm_extractor
|
97 |
+
result = tumor_extractor.invoke({"question": question})
|
98 |
+
return result.tumor_name
|
99 |
+
except Exception as e:
|
100 |
+
print(f"腫瘍名抽出エラー: {e}")
|
101 |
+
return "None"
|
|
|
|
|
|
|
102 |
|
103 |
+
### 質問変更システム
|
104 |
class ModifyQuestion(BaseModel):
|
105 |
"""Class for modifying a question by inserting NCTID."""
|
106 |
modified_question: str = Field(description="The modified question with the inserted NCTID.")
|
|
|
108 |
class QuestionModifier:
|
109 |
def __init__(self, llm):
|
110 |
self.llm = llm
|
|
|
|
|
111 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
112 |
|
113 |
+
# 修正: 中括弧をエスケープ
|
114 |
+
self.system_prompt = """あなたは、ユーザーの質問に対して適切なNCTIDを挿入して質問を変更するシステムです。
|
115 |
+
質問文にNCTIDを挿入し、形式に基づいて新しい質問を生成してください。
|
116 |
+
例えば16歳男性の神経膠腫の患者さんが参加できる臨床治験を教えて下さいという質問に対しては
|
117 |
+
16歳男性の神経膠腫の患者さんは{{nct_id}}に参加できますか?と変更して下さい
|
118 |
+
NCTIDは {{nct_id}} を使用してください。"""
|
119 |
|
|
|
120 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
121 |
[
|
122 |
("system", self.system_prompt),
|
|
|
124 |
]
|
125 |
)
|
126 |
|
127 |
+
@retry_on_error(max_retries=3, delay=2)
|
128 |
def modify_question(self, question: str, nct_id: str) -> str:
|
129 |
+
"""質問を変更するメソッド"""
|
130 |
+
try:
|
131 |
+
question_modifier = self.modify_prompt | self.structured_llm_modifier
|
132 |
+
result = question_modifier.invoke({"question": question, "nct_id": nct_id})
|
133 |
+
return result.modified_question
|
134 |
+
except Exception as e:
|
135 |
+
print(f"質問変更エラー: {e}")
|
136 |
+
return f"{question} (NCTID: {nct_id})"
|
|
|
|
|
|
|
137 |
|
138 |
class QuestionModifierSecond:
|
139 |
def __init__(self, llm):
|
140 |
self.llm = llm
|
|
|
|
|
141 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
142 |
|
143 |
+
self.system_prompt = """あなたは、ユーザーの質問を変更するシステムです。
|
144 |
+
形式に基づいて新しい質問を生成してください。
|
145 |
+
例えば16歳男性の神経膠腫の患者さんが参加できる臨床治験を教えて下さいという質問に対しては
|
146 |
+
16歳男性の神経膠腫の患者さんはこの治験に参加できますか?と変更して下さい"""
|
|
|
|
|
147 |
|
|
|
148 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
149 |
[
|
150 |
("system", self.system_prompt),
|
|
|
152 |
]
|
153 |
)
|
154 |
|
155 |
+
@retry_on_error(max_retries=3, delay=2)
|
156 |
def modify_question(self, question: str) -> str:
|
157 |
+
"""質問を変更するメソッド"""
|
158 |
+
try:
|
159 |
+
question_modifier = self.modify_prompt | self.structured_llm_modifier
|
160 |
+
result = question_modifier.invoke({"question": question})
|
161 |
+
return result.modified_question
|
162 |
+
except Exception as e:
|
163 |
+
print(f"質問変更エラー: {e}")
|
164 |
+
return question
|
165 |
+
|
|
|
|
|
|
|
166 |
class QuestionModifierEnglish:
|
167 |
def __init__(self, llm):
|
168 |
self.llm = llm
|
|
|
|
|
169 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
170 |
|
171 |
+
self.system_prompt = """あなたは、ユーザーの質問を変更し英語に翻訳するシステムです。
|
172 |
+
形式に基づいて新しい質問を生成してください。
|
173 |
+
例えば16歳男性の神経膠腫の患者さんが参加できる臨床治験を教えて下さいという質問に対しては
|
174 |
+
Can a 16 year old male patient with glioma participate in this clinical trial?と変更して下さい"""
|
|
|
|
|
175 |
|
|
|
176 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
177 |
[
|
178 |
("system", self.system_prompt),
|
|
|
180 |
]
|
181 |
)
|
182 |
|
183 |
+
@retry_on_error(max_retries=3, delay=2)
|
184 |
def modify_question(self, question: str) -> str:
|
185 |
+
"""質問を変更するメソッド"""
|
186 |
+
try:
|
187 |
+
question_modifier = self.modify_prompt | self.structured_llm_modifier
|
188 |
+
result = question_modifier.invoke({"question": question})
|
189 |
+
return result.modified_question
|
190 |
+
except Exception as e:
|
191 |
+
print(f"英語質問変更エラー: {e}")
|
192 |
+
return question
|
|
|
|
|
|
|
|
|
|
|
|
|
193 |
|
194 |
+
### Make criteria check Agent
|
195 |
class ClinicalTrialAgent:
|
196 |
def __init__(self, llm, db):
|
197 |
self.llm = llm
|
198 |
self.db = db
|
199 |
|
|
|
200 |
self.system_prompt = """
|
201 |
あなたは患者さんに適した治験を探すエージェントです。
|
202 |
データベースのEligibility Criteriaをチェックして患者さんがその治験を受けることが可能かどうか答えて下さい
|
203 |
"""
|
204 |
|
|
|
205 |
self.prompt = ChatPromptTemplate.from_messages(
|
206 |
[("system", self.system_prompt),
|
207 |
("human", "{input}"),
|
208 |
MessagesPlaceholder("agent_scratchpad")]
|
209 |
)
|
210 |
|
|
|
211 |
self.agent_executor = self.create_sql_agent(self.llm, self.db, self.prompt)
|
212 |
|
213 |
def create_sql_agent(self, llm, db, prompt):
|
|
|
221 |
)
|
222 |
return agent_executor
|
223 |
|
224 |
+
@retry_on_error(max_retries=3, delay=2)
|
225 |
def get_agent_judgment(self, modify_question: str) -> str:
|
226 |
+
"""Modifyされた質問を元に、患者さんが治験に参加可能かどうかのエージェント判断を取得"""
|
227 |
+
try:
|
228 |
+
result = self.agent_executor.invoke({"input": modify_question})
|
229 |
+
return result
|
230 |
+
except Exception as e:
|
231 |
+
print(f"エージェント判断エラー: {e}")
|
232 |
+
return f"エラー: {str(e)}"
|
|
|
|
|
233 |
|
234 |
class SimpleClinicalTrialAgent:
|
235 |
def __init__(self, llm):
|
236 |
self.llm = llm
|
237 |
|
238 |
+
@retry_on_error(max_retries=3, delay=2)
|
239 |
def evaluate_eligibility(self, TargetCriteria: str, question: str) -> str:
|
240 |
+
"""臨床試験の参加適格性を評価するメソッド"""
|
241 |
+
try:
|
242 |
+
# 修正: プロンプト内の中括弧を適切にエスケープ
|
243 |
+
prompt_template = """
|
244 |
+
You are an agent looking for a suitable clinical trial for a patient.
|
245 |
+
Please answer whether the patient is eligible for this clinical trial based on the following criteria. If you do not know the answer, say you do not know. Your answer should be brief, no more than 3 sentences.
|
246 |
+
|
247 |
+
Question: {{question}}
|
248 |
+
|
249 |
+
Criteria:
|
250 |
+
{criteria}""".format(criteria=TargetCriteria)
|
251 |
+
|
252 |
+
criteria_prompt = ChatPromptTemplate.from_messages(
|
253 |
+
[
|
254 |
+
(
|
255 |
+
"human",
|
256 |
+
prompt_template
|
257 |
+
)
|
258 |
+
]
|
259 |
+
)
|
260 |
+
|
261 |
+
rag_chain = (
|
262 |
+
{"question": RunnablePassthrough()}
|
263 |
+
| criteria_prompt
|
264 |
+
| self.llm
|
265 |
+
| StrOutputParser()
|
266 |
+
)
|
267 |
+
|
268 |
+
response = rag_chain.invoke(question)
|
269 |
+
return response
|
270 |
+
|
271 |
+
except Exception as e:
|
272 |
+
print(f"適格性評価エラー: {e}")
|
273 |
+
return f"評価エラー: {str(e)}"
|
|
|
|
|
|
|
274 |
|
275 |
### output 評価システム
|
276 |
class TrialEligibilityGrader(BaseModel):
|
|
|
282 |
class GraderAgent:
|
283 |
def __init__(self, llm):
|
284 |
self.llm = llm
|
|
|
|
|
285 |
self.structured_llm_grader = self.llm.with_structured_output(TrialEligibilityGrader)
|
286 |
|
|
|
287 |
self.system_prompt = """
|
288 |
あなたは治験に参加する患者の適合性を評価するGraderです。
|
289 |
以下のドキュメントを読み、患者が治験に参加可能かどうかを判断してください。
|
290 |
'yes'(参加可能)、'no'(参加不可能)、'unclear'(判断できない)の3値で答えてください。
|
291 |
"""
|
292 |
|
|
|
293 |
self.grade_prompt = ChatPromptTemplate.from_messages(
|
294 |
[
|
295 |
("system", self.system_prompt),
|
|
|
300 |
]
|
301 |
)
|
302 |
|
303 |
+
@retry_on_error(max_retries=3, delay=2)
|
304 |
def evaluate_eligibility(self, AgentJudgment_output: str) -> str:
|
305 |
+
"""AgentJudgment['output']を基に患者が治験に参加可能かどうかを評価し、スコア(AgentGrade)を返す"""
|
306 |
+
try:
|
307 |
+
GraderAgent = self.grade_prompt | self.structured_llm_grader
|
308 |
+
result = GraderAgent.invoke({"document": AgentJudgment_output})
|
309 |
+
return result.score
|
310 |
+
except Exception as e:
|
311 |
+
print(f"グレード評価エラー: {e}")
|
312 |
+
return "unclear"
|
|
|
|
|
|
|
313 |
|
314 |
class LLMTranslator:
|
315 |
def __init__(self, llm):
|
316 |
self.llm = llm
|
317 |
self.structured_llm_modifier = self.llm.with_structured_output(ModifyQuestion)
|
318 |
|
319 |
+
self.system_prompt = """あなたは、優秀な翻訳者です。
|
320 |
+
日本語を英語に翻訳して下さい。"""
|
321 |
+
|
322 |
+
self.system_prompt2 = """あなたは、優秀な翻訳者です。
|
323 |
+
日本語を英語に以下のフォーマットに従って翻訳して下さい。
|
324 |
+
MainQuestion:
|
325 |
+
Known gene mutation:
|
326 |
+
Measurable tumour:
|
327 |
+
Biopsiable tumour:"""
|
|
|
328 |
|
329 |
self.modify_prompt = ChatPromptTemplate.from_messages(
|
330 |
[
|
|
|
341 |
)
|
342 |
|
343 |
def is_english(self, text: str) -> bool:
|
344 |
+
"""簡易的にテキストが英語かどうかを判定する関数"""
|
|
|
|
|
|
|
|
|
|
|
345 |
return bool(re.match(r'^[A-Za-z0-9\s.,?!]+$', text))
|
346 |
|
347 |
+
@retry_on_error(max_retries=3, delay=2)
|
348 |
def translate(self, question: str) -> str:
|
349 |
+
"""質問を翻訳するメソッド。英語の質問はそのまま返す。"""
|
350 |
+
try:
|
351 |
+
if self.is_english(question):
|
352 |
+
return question
|
353 |
+
|
354 |
+
question_modifier = self.modify_prompt | self.structured_llm_modifier
|
355 |
+
result = question_modifier.invoke({"question": question})
|
356 |
+
return result.modified_question
|
357 |
+
except Exception as e:
|
358 |
+
print(f"翻訳エラー: {e}")
|
359 |
return question
|
360 |
+
|
361 |
+
@retry_on_error(max_retries=3, delay=2)
|
|
|
|
|
|
|
|
|
|
|
362 |
def translateQuestion(self, question: str) -> str:
|
363 |
+
"""フォーマット付きで質問を翻訳するメソッド"""
|
364 |
+
try:
|
365 |
+
question_modifier = self.modify_prompt2 | self.structured_llm_modifier
|
366 |
+
result = question_modifier.invoke({"question": question})
|
367 |
+
return result.modified_question
|
368 |
+
except Exception as e:
|
369 |
+
print(f"フォーマット翻訳エラー: {e}")
|
370 |
+
return question
|
|
|
371 |
|
372 |
def generate_ex_question(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
373 |
+
"""日本語での質問文を生成"""
|
374 |
+
try:
|
375 |
+
# GeneMutationが空の場合はUnknownに設定
|
376 |
+
gene_mutation_text = GeneMutation if GeneMutation else "Unknown"
|
377 |
+
|
378 |
+
# MeseableとBiopsiableの値をYes, No, Unknownに変換
|
379 |
+
meseable_text = (
|
380 |
+
"Yes" if Meseable == "有り" else "No" if Meseable == "無し" else "Unknown"
|
381 |
+
)
|
382 |
+
biopsiable_text = (
|
383 |
+
"Yes" if Biopsiable == "有り" else "No" if Biopsiable == "無し" else "Unknown"
|
384 |
+
)
|
385 |
+
|
386 |
+
# 質問文の生成
|
387 |
+
ex_question = f"""{age}歳{sex}の{tumor_type}患者さんはこの治験に参加することができますか?
|
388 |
判明している遺伝子変異: {gene_mutation_text}
|
389 |
Meseable tumor: {meseable_text}
|
390 |
Biopsiable tumor: {biopsiable_text}
|
391 |
+
です。"""
|
392 |
+
return ex_question
|
393 |
+
except Exception as e:
|
394 |
+
print(f"日本語質問生成エラー: {e}")
|
395 |
+
return f"{age}歳{sex}の{tumor_type}患者さんの治験参加について"
|
396 |
|
397 |
def generate_ex_question_English(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
398 |
+
"""英語での質問文を生成"""
|
399 |
+
try:
|
400 |
+
# GeneMutationが空の場合は"Unknown"に設定
|
401 |
+
gene_mutation_text = GeneMutation if GeneMutation else "Unknown"
|
402 |
+
|
403 |
+
# sexの値を male または female に変換
|
404 |
+
sex_text = "male" if sex == "男性" else "female" if sex == "女性" else "Unknown"
|
405 |
+
|
406 |
+
# MeseableとBiopsiableの値を "Yes", "No", "Unknown" に変換
|
407 |
+
meseable_text = (
|
408 |
+
"Yes" if Meseable == "有り" else "No" if Meseable == "無し" else "Unknown"
|
409 |
+
)
|
410 |
+
biopsiable_text = (
|
411 |
+
"Yes" if Biopsiable == "有り" else "No" if Biopsiable == "無し" else "Unknown"
|
412 |
+
)
|
413 |
+
|
414 |
+
# 英語での質問文を生成
|
415 |
+
ex_question = f"""Can a {age}-year-old {sex_text} patient with {tumor_type} participate in this clinical trial?
|
416 |
Known gene mutation: {gene_mutation_text}
|
417 |
Measurable tumor: {meseable_text}
|
418 |
+
Biopsiable tumor: {biopsiable_text}"""
|
419 |
+
return ex_question
|
420 |
+
except Exception as e:
|
421 |
+
print(f"英語質問生成エラー: {e}")
|
422 |
+
return f"Can a {age}-year-old patient with {tumor_type} participate in this clinical trial?"
|
423 |
+
|
424 |
+
# テスト関数
|
425 |
+
def test_clinical_trial_tools():
|
426 |
+
"""臨床試験ツールのテスト関数"""
|
427 |
+
try:
|
428 |
+
from langchain_groq import ChatGroq
|
429 |
+
|
430 |
+
# Groqクライアントの初期化
|
431 |
+
groq = ChatGroq(model_name="llama3-70b-8192", temperature=0)
|
432 |
+
|
433 |
+
# 各エージェントの初期化テスト
|
434 |
+
translator = LLMTranslator(groq)
|
435 |
+
criteria_agent = SimpleClinicalTrialAgent(groq)
|
436 |
+
grader_agent = GraderAgent(groq)
|
437 |
+
|
438 |
+
print("✅ 全てのエージェントが正常に初期化されました")
|
439 |
+
|
440 |
+
# サンプル質問の生成テスト
|
441 |
+
sample_question = generate_ex_question_English(
|
442 |
+
age="45",
|
443 |
+
sex="女性",
|
444 |
+
tumor_type="breast cancer",
|
445 |
+
GeneMutation="HER2",
|
446 |
+
Meseable="有り",
|
447 |
+
Biopsiable="有り"
|
448 |
+
)
|
449 |
+
|
450 |
+
print(f"✅ サンプル質問生成成功: {sample_question}")
|
451 |
+
return True
|
452 |
+
|
453 |
+
except Exception as e:
|
454 |
+
print(f"❌ テスト中にエラーが発生しました: {e}")
|
455 |
+
return False
|
456 |
+
|
457 |
+
if __name__ == "__main__":
|
458 |
+
print("ClinicalTrialTools のテストを開始します...")
|
459 |
+
success = test_clinical_trial_tools()
|
460 |
+
if success:
|
461 |
+
print("✅ テストが正常に完了しました。")
|
462 |
+
else:
|
463 |
+
print("❌ テストでエラーが発生しました。")
|
app copy.py
DELETED
@@ -1,106 +0,0 @@
|
|
1 |
-
import gradio as gr
|
2 |
-
import pandas as pd
|
3 |
-
from OpenAITools.FetchTools import fetch_clinical_trials
|
4 |
-
from langchain_openai import ChatOpenAI
|
5 |
-
from langchain_groq import ChatGroq
|
6 |
-
from OpenAITools.CrinicalTrialTools import SimpleClinicalTrialAgent, GraderAgent, LLMTranslator, generate_ex_question_English
|
7 |
-
|
8 |
-
# モデルとエージェントの初期化
|
9 |
-
groq = ChatGroq(model_name="llama3-70b-8192", temperature=0)
|
10 |
-
translator = LLMTranslator(groq)
|
11 |
-
CriteriaCheckAgent = SimpleClinicalTrialAgent(groq)
|
12 |
-
grader_agent = GraderAgent(groq)
|
13 |
-
|
14 |
-
# データフレームを生成する関数
|
15 |
-
def generate_dataframe(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
16 |
-
# 日本語の腫瘍タイプを英語に翻訳
|
17 |
-
TumorName = translator.translate(tumor_type)
|
18 |
-
|
19 |
-
# 質問文を生成
|
20 |
-
ex_question = generate_ex_question_English(age, sex, TumorName, GeneMutation, Meseable, Biopsiable)
|
21 |
-
|
22 |
-
# 臨床試験データの取得
|
23 |
-
df = fetch_clinical_trials(TumorName)
|
24 |
-
df['AgentJudgment'] = None
|
25 |
-
df['AgentGrade'] = None
|
26 |
-
|
27 |
-
# 臨床試験の適格性の評価
|
28 |
-
NCTIDs = list(df['NCTID'])
|
29 |
-
progress = gr.Progress(track_tqdm=True)
|
30 |
-
for i, nct_id in enumerate(NCTIDs):
|
31 |
-
target_criteria = df.loc[df['NCTID'] == nct_id, 'Eligibility Criteria'].values[0]
|
32 |
-
agent_judgment = CriteriaCheckAgent.evaluate_eligibility(target_criteria, ex_question)
|
33 |
-
agent_grade = grader_agent.evaluate_eligibility(agent_judgment)
|
34 |
-
|
35 |
-
# データフレームの更新
|
36 |
-
df.loc[df['NCTID'] == nct_id, 'AgentJudgment'] = agent_judgment
|
37 |
-
df.loc[df['NCTID'] == nct_id, 'AgentGrade'] = agent_grade
|
38 |
-
progress((i + 1) / len(NCTIDs))
|
39 |
-
|
40 |
-
# 列を指定した順に並び替え
|
41 |
-
columns_order = ['NCTID', 'AgentGrade', 'Title', 'AgentJudgment', 'Japanes Locations',
|
42 |
-
'Primary Completion Date', 'Cancer', 'Summary', 'Eligibility Criteria']
|
43 |
-
df = df[columns_order]
|
44 |
-
|
45 |
-
return df, df # フィルタ用と表示用にデータフレームを返す
|
46 |
-
|
47 |
-
# 特定のAgentGrade(yes, no, unclear)に基づいて行をフィルタリングする関数
|
48 |
-
def filter_rows_by_grade(original_df, grade):
|
49 |
-
df_filtered = original_df[original_df['AgentGrade'] == grade]
|
50 |
-
return df_filtered, df_filtered
|
51 |
-
|
52 |
-
# CSVとして保存しダウンロードする関数
|
53 |
-
def download_filtered_csv(df):
|
54 |
-
file_path = "filtered_data.csv"
|
55 |
-
df.to_csv(file_path, index=False)
|
56 |
-
return file_path
|
57 |
-
|
58 |
-
# 全体結果をCSVとして保存しダウンロードする関数
|
59 |
-
def download_full_csv(df):
|
60 |
-
file_path = "full_data.csv"
|
61 |
-
df.to_csv(file_path, index=False)
|
62 |
-
return file_path
|
63 |
-
|
64 |
-
# Gradioインターフェースの作成
|
65 |
-
with gr.Blocks() as demo:
|
66 |
-
gr.Markdown("## 臨床試験適格性評価インターフェース")
|
67 |
-
|
68 |
-
# 各種入力フィールド
|
69 |
-
age_input = gr.Textbox(label="Age", placeholder="例: 65")
|
70 |
-
sex_input = gr.Dropdown(choices=["男性", "女性"], label="Sex")
|
71 |
-
tumor_type_input = gr.Textbox(label="Tumor Type", placeholder="例: gastric cancer, 日本でも良いですが英語の方が精度が高いです。")
|
72 |
-
gene_mutation_input = gr.Textbox(label="Gene Mutation", placeholder="例: HER2")
|
73 |
-
measurable_input = gr.Dropdown(choices=["有り", "無し", "不明"], label="Measurable Tumor")
|
74 |
-
biopsiable_input = gr.Dropdown(choices=["有り", "無し", "不明"], label="Biopsiable Tumor")
|
75 |
-
|
76 |
-
# データフレーム表示エリア
|
77 |
-
dataframe_output = gr.DataFrame()
|
78 |
-
original_df = gr.State()
|
79 |
-
filtered_df = gr.State()
|
80 |
-
|
81 |
-
# データフレーム生成ボタン
|
82 |
-
generate_button = gr.Button("Generate Clinical Trials Data")
|
83 |
-
|
84 |
-
# フィルタリングボタン
|
85 |
-
yes_button = gr.Button("Show Eligible Trials")
|
86 |
-
no_button = gr.Button("Show Ineligible Trials")
|
87 |
-
unclear_button = gr.Button("Show Unclear Trials")
|
88 |
-
|
89 |
-
# ダウンロードボタン
|
90 |
-
download_filtered_button = gr.Button("Download Filtered Data")
|
91 |
-
download_filtered_output = gr.File(label="Download Filtered Data")
|
92 |
-
|
93 |
-
download_full_button = gr.Button("Download Full Data")
|
94 |
-
download_full_output = gr.File(label="Download Full Data")
|
95 |
-
|
96 |
-
|
97 |
-
# ボタン動作の設定
|
98 |
-
generate_button.click(fn=generate_dataframe, inputs=[age_input, sex_input, tumor_type_input, gene_mutation_input, measurable_input, biopsiable_input], outputs=[dataframe_output, original_df])
|
99 |
-
yes_button.click(fn=filter_rows_by_grade, inputs=[original_df, gr.State("yes")], outputs=[dataframe_output, filtered_df])
|
100 |
-
no_button.click(fn=filter_rows_by_grade, inputs=[original_df, gr.State("no")], outputs=[dataframe_output, filtered_df])
|
101 |
-
unclear_button.click(fn=filter_rows_by_grade, inputs=[original_df, gr.State("unclear")], outputs=[dataframe_output, filtered_df])
|
102 |
-
download_filtered_button.click(fn=download_filtered_csv, inputs=filtered_df, outputs=download_filtered_output)
|
103 |
-
download_full_button.click(fn=download_full_csv, inputs=original_df, outputs=download_full_output)
|
104 |
-
|
105 |
-
if __name__ == "__main__":
|
106 |
-
demo.launch()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
app.py
CHANGED
@@ -1,321 +1,106 @@
|
|
1 |
import gradio as gr
|
2 |
import pandas as pd
|
3 |
-
import time
|
4 |
-
import traceback
|
5 |
-
import os
|
6 |
from OpenAITools.FetchTools import fetch_clinical_trials
|
7 |
from langchain_openai import ChatOpenAI
|
8 |
from langchain_groq import ChatGroq
|
9 |
from OpenAITools.CrinicalTrialTools import SimpleClinicalTrialAgent, GraderAgent, LLMTranslator, generate_ex_question_English
|
10 |
|
11 |
-
#
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
if not os.getenv("GROQ_API_KEY"):
|
17 |
-
missing_vars.append("GROQ_API_KEY")
|
18 |
-
|
19 |
-
if not os.getenv("OPENAI_API_KEY"):
|
20 |
-
missing_vars.append("OPENAI_API_KEY")
|
21 |
-
|
22 |
-
if missing_vars:
|
23 |
-
print(f"⚠️ 環境変数が設定されていません: {', '.join(missing_vars)}")
|
24 |
-
print("一部の機能が制限される可能性があります。")
|
25 |
-
|
26 |
-
return len(missing_vars) == 0
|
27 |
-
|
28 |
-
# 環境変数チェック実行
|
29 |
-
env_ok = check_environment()
|
30 |
-
|
31 |
-
# モデルとエージェントの安全な初期化
|
32 |
-
def safe_init_agents():
|
33 |
-
"""エージェントを安全に初期化"""
|
34 |
-
try:
|
35 |
-
groq = ChatGroq(model_name="llama3-70b-8192", temperature=0)
|
36 |
-
translator = LLMTranslator(groq)
|
37 |
-
criteria_agent = SimpleClinicalTrialAgent(groq)
|
38 |
-
grader_agent = GraderAgent(groq)
|
39 |
-
return translator, criteria_agent, grader_agent
|
40 |
-
except Exception as e:
|
41 |
-
print(f"エージェント初期化エラー: {e}")
|
42 |
-
return None, None, None
|
43 |
-
|
44 |
-
# エージェント初期化
|
45 |
-
translator, CriteriaCheckAgent, grader_agent = safe_init_agents()
|
46 |
-
|
47 |
-
# エラーハンドリング付きでエージェント評価を実行する関数
|
48 |
-
def evaluate_with_retry(agent, criteria, question, max_retries=3):
|
49 |
-
"""エラーハンドリング付きでエージェント評価を実行"""
|
50 |
-
if agent is None:
|
51 |
-
return "評価エラー: エージェントが初期化されていません。API keyを確認してください。"
|
52 |
-
|
53 |
-
for attempt in range(max_retries):
|
54 |
-
try:
|
55 |
-
return agent.evaluate_eligibility(criteria, question)
|
56 |
-
except Exception as e:
|
57 |
-
if "missing variables" in str(e):
|
58 |
-
# プロンプトテンプレートの変数エラーの場合
|
59 |
-
print(f"プロンプトテンプレートエラー (試行 {attempt + 1}/{max_retries}): {e}")
|
60 |
-
return "評価エラー: プロンプトテンプレートの設定に問題があります"
|
61 |
-
elif "no healthy upstream" in str(e) or "InternalServerError" in str(e):
|
62 |
-
# Groqサーバーエラーの場合
|
63 |
-
print(f"Groqサーバーエラー (試行 {attempt + 1}/{max_retries}): {e}")
|
64 |
-
if attempt < max_retries - 1:
|
65 |
-
time.sleep(2) # 2秒待機してリトライ
|
66 |
-
continue
|
67 |
-
else:
|
68 |
-
return "評価エラー: サーバーに接続できませんでした"
|
69 |
-
elif "API key" in str(e) or "authentication" in str(e).lower():
|
70 |
-
return "評価エラー: API keyが無効または設定されていません"
|
71 |
-
else:
|
72 |
-
print(f"予期しないエラー (試行 {attempt + 1}/{max_retries}): {e}")
|
73 |
-
if attempt < max_retries - 1:
|
74 |
-
time.sleep(1)
|
75 |
-
continue
|
76 |
-
else:
|
77 |
-
return f"評価エラー: {str(e)}"
|
78 |
-
return "評価エラー: 最大リトライ回数に達しました"
|
79 |
-
|
80 |
-
def evaluate_grade_with_retry(agent, judgment, max_retries=3):
|
81 |
-
"""エラーハンドリング付きでグレード評価を実行"""
|
82 |
-
if agent is None:
|
83 |
-
return "unclear"
|
84 |
-
|
85 |
-
for attempt in range(max_retries):
|
86 |
-
try:
|
87 |
-
return agent.evaluate_eligibility(judgment)
|
88 |
-
except Exception as e:
|
89 |
-
if "no healthy upstream" in str(e) or "InternalServerError" in str(e):
|
90 |
-
print(f"Groqサーバーエラー (グレード評価 - 試行 {attempt + 1}/{max_retries}): {e}")
|
91 |
-
if attempt < max_retries - 1:
|
92 |
-
time.sleep(2)
|
93 |
-
continue
|
94 |
-
else:
|
95 |
-
return "unclear"
|
96 |
-
elif "API key" in str(e) or "authentication" in str(e).lower():
|
97 |
-
return "unclear"
|
98 |
-
else:
|
99 |
-
print(f"予期しないエラー (グレード評価 - 試行 {attempt + 1}/{max_retries}): {e}")
|
100 |
-
if attempt < max_retries - 1:
|
101 |
-
time.sleep(1)
|
102 |
-
continue
|
103 |
-
else:
|
104 |
-
return "unclear"
|
105 |
-
return "unclear"
|
106 |
|
107 |
# データフレームを生成する関数
|
108 |
def generate_dataframe(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
|
117 |
-
|
118 |
-
|
119 |
-
|
120 |
-
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
-
ex_question = generate_ex_question_English(age, sex, TumorName, GeneMutation, Meseable, Biopsiable)
|
128 |
-
except Exception as e:
|
129 |
-
print(f"質問生成エラー: {e}")
|
130 |
-
return pd.DataFrame(), pd.DataFrame()
|
131 |
-
|
132 |
-
# 臨床試験データの取得
|
133 |
-
try:
|
134 |
-
df = fetch_clinical_trials(TumorName)
|
135 |
-
if df.empty:
|
136 |
-
print("臨床試験データが見つかりませんでした")
|
137 |
-
return pd.DataFrame(), pd.DataFrame()
|
138 |
-
except Exception as e:
|
139 |
-
print(f"臨床試験データ取得エラー: {e}")
|
140 |
-
return pd.DataFrame(), pd.DataFrame()
|
141 |
-
|
142 |
-
df['AgentJudgment'] = None
|
143 |
-
df['AgentGrade'] = None
|
144 |
-
|
145 |
-
# 臨床試験の適格性の評価
|
146 |
-
NCTIDs = list(df['NCTID'])
|
147 |
-
progress = gr.Progress(track_tqdm=True)
|
148 |
|
149 |
-
|
150 |
-
|
151 |
-
|
152 |
-
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
|
157 |
-
|
158 |
-
df.loc[df['NCTID'] == nct_id, 'AgentJudgment'] = agent_judgment
|
159 |
-
df.loc[df['NCTID'] == nct_id, 'AgentGrade'] = agent_grade
|
160 |
-
|
161 |
-
except Exception as e:
|
162 |
-
print(f"NCTID {nct_id} の評価中にエラー: {e}")
|
163 |
-
df.loc[df['NCTID'] == nct_id, 'AgentJudgment'] = f"エラー: {str(e)}"
|
164 |
-
df.loc[df['NCTID'] == nct_id, 'AgentGrade'] = "unclear"
|
165 |
-
|
166 |
-
progress((i + 1) / len(NCTIDs))
|
167 |
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
df = df[available_columns]
|
175 |
-
|
176 |
-
return df, df # フィルタ用と表示用にデータフレームを返す
|
177 |
-
|
178 |
-
except Exception as e:
|
179 |
-
print(f"データフレーム生成中に予期しないエラー: {e}")
|
180 |
-
traceback.print_exc()
|
181 |
-
return pd.DataFrame(), pd.DataFrame()
|
182 |
|
183 |
# CSVとして保存しダウンロードする関数
|
184 |
def download_filtered_csv(df):
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
file_path = "filtered_data.csv"
|
189 |
-
df.to_csv(file_path, index=False)
|
190 |
-
return file_path
|
191 |
-
except Exception as e:
|
192 |
-
print(f"CSV保存エラー: {e}")
|
193 |
-
return None
|
194 |
|
195 |
# 全体結果をCSVとして保存しダウンロードする関数
|
196 |
def download_full_csv(df):
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
file_path = "full_data.csv"
|
201 |
-
df.to_csv(file_path, index=False)
|
202 |
-
return file_path
|
203 |
-
except Exception as e:
|
204 |
-
print(f"CSV保存エラー: {e}")
|
205 |
-
return None
|
206 |
|
207 |
# Gradioインターフェースの作成
|
208 |
-
with gr.Blocks(
|
209 |
gr.Markdown("## 臨床試験適格性評価インターフェース")
|
210 |
-
|
211 |
-
# 環境変数状態の表示
|
212 |
-
if env_ok:
|
213 |
-
gr.Markdown("✅ **ステータス**: 全ての環境変数が設定されています")
|
214 |
-
else:
|
215 |
-
gr.Markdown("⚠️ **注意**: 一部の環境変数が設定されていません。機能が制限される可能性があります。")
|
216 |
-
|
217 |
-
gr.Markdown("💡 **使用方法**: 患者情報を入力して「Generate Clinical Trials Data」をクリックしてください。")
|
218 |
|
219 |
# 各種入力フィールド
|
220 |
-
|
221 |
-
|
222 |
-
|
223 |
-
|
224 |
-
|
225 |
-
|
226 |
-
with gr.Column():
|
227 |
-
gene_mutation_input = gr.Textbox(label="Gene Mutation", placeholder="例: HER2", value="")
|
228 |
-
measurable_input = gr.Dropdown(choices=["有り", "無し", "不明"], label="Measurable Tumor", value=None)
|
229 |
-
biopsiable_input = gr.Dropdown(choices=["有り", "無し", "不明"], label="Biopsiable Tumor", value=None)
|
230 |
|
231 |
# データフレーム表示エリア
|
232 |
-
dataframe_output = gr.DataFrame(
|
233 |
-
|
234 |
-
|
235 |
-
value=None
|
236 |
-
)
|
237 |
-
|
238 |
-
# 内部状態用の非表示コンポーネント
|
239 |
-
original_df_state = gr.State(value=None)
|
240 |
-
filtered_df_state = gr.State(value=None)
|
241 |
|
242 |
-
#
|
243 |
-
|
244 |
-
|
245 |
-
|
246 |
-
|
247 |
-
|
248 |
-
|
249 |
-
unclear_button = gr.Button("Show Unclear Trials", variant="secondary")
|
250 |
-
|
251 |
-
with gr.Row():
|
252 |
-
download_filtered_button = gr.Button("Download Filtered Data")
|
253 |
-
download_full_button = gr.Button("Download Full Data")
|
254 |
|
255 |
-
#
|
256 |
-
|
257 |
-
|
258 |
|
259 |
-
|
260 |
-
|
261 |
-
"""データフレーム生成と状態更新"""
|
262 |
-
df, _ = generate_dataframe(age, sex, tumor_type, gene_mutation, measurable, biopsiable)
|
263 |
-
return df, df, df
|
264 |
|
265 |
-
def filter_and_update(original_df, grade):
|
266 |
-
"""フィルタリングと表示更新"""
|
267 |
-
if original_df is None or len(original_df) == 0:
|
268 |
-
return original_df, original_df
|
269 |
-
|
270 |
-
try:
|
271 |
-
df_filtered = original_df[original_df['AgentGrade'] == grade]
|
272 |
-
return df_filtered, df_filtered
|
273 |
-
except Exception as e:
|
274 |
-
print(f"フィルタリングエラー: {e}")
|
275 |
-
return original_df, original_df
|
276 |
|
277 |
# ボタン動作の設定
|
278 |
-
generate_button.click(
|
279 |
-
|
280 |
-
|
281 |
-
|
282 |
-
)
|
283 |
-
|
284 |
-
yes_button.click(
|
285 |
-
fn=lambda df: filter_and_update(df, "yes"),
|
286 |
-
inputs=[original_df_state],
|
287 |
-
outputs=[dataframe_output, filtered_df_state]
|
288 |
-
)
|
289 |
-
|
290 |
-
no_button.click(
|
291 |
-
fn=lambda df: filter_and_update(df, "no"),
|
292 |
-
inputs=[original_df_state],
|
293 |
-
outputs=[dataframe_output, filtered_df_state]
|
294 |
-
)
|
295 |
-
|
296 |
-
unclear_button.click(
|
297 |
-
fn=lambda df: filter_and_update(df, "unclear"),
|
298 |
-
inputs=[original_df_state],
|
299 |
-
outputs=[dataframe_output, filtered_df_state]
|
300 |
-
)
|
301 |
-
|
302 |
-
download_filtered_button.click(
|
303 |
-
fn=download_filtered_csv,
|
304 |
-
inputs=[filtered_df_state],
|
305 |
-
outputs=[download_filtered_output]
|
306 |
-
)
|
307 |
-
|
308 |
-
download_full_button.click(
|
309 |
-
fn=download_full_csv,
|
310 |
-
inputs=[original_df_state],
|
311 |
-
outputs=[download_full_output]
|
312 |
-
)
|
313 |
|
314 |
if __name__ == "__main__":
|
315 |
-
demo.launch(
|
316 |
-
server_name="0.0.0.0",
|
317 |
-
server_port=7860,
|
318 |
-
share=False,
|
319 |
-
debug=False,
|
320 |
-
show_error=True
|
321 |
-
)
|
|
|
1 |
import gradio as gr
|
2 |
import pandas as pd
|
|
|
|
|
|
|
3 |
from OpenAITools.FetchTools import fetch_clinical_trials
|
4 |
from langchain_openai import ChatOpenAI
|
5 |
from langchain_groq import ChatGroq
|
6 |
from OpenAITools.CrinicalTrialTools import SimpleClinicalTrialAgent, GraderAgent, LLMTranslator, generate_ex_question_English
|
7 |
|
8 |
+
# モデルとエージェントの初期化
|
9 |
+
groq = ChatGroq(model_name="llama3-70b-8192", temperature=0)
|
10 |
+
translator = LLMTranslator(groq)
|
11 |
+
CriteriaCheckAgent = SimpleClinicalTrialAgent(groq)
|
12 |
+
grader_agent = GraderAgent(groq)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
# データフレームを生成する関数
|
15 |
def generate_dataframe(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
16 |
+
# 日本語の腫瘍タイプを英語に翻訳
|
17 |
+
TumorName = translator.translate(tumor_type)
|
18 |
+
|
19 |
+
# 質問文を生成
|
20 |
+
ex_question = generate_ex_question_English(age, sex, TumorName, GeneMutation, Meseable, Biopsiable)
|
21 |
+
|
22 |
+
# 臨床試験データの取得
|
23 |
+
df = fetch_clinical_trials(TumorName)
|
24 |
+
df['AgentJudgment'] = None
|
25 |
+
df['AgentGrade'] = None
|
26 |
+
|
27 |
+
# 臨床試験の適格性の評価
|
28 |
+
NCTIDs = list(df['NCTID'])
|
29 |
+
progress = gr.Progress(track_tqdm=True)
|
30 |
+
for i, nct_id in enumerate(NCTIDs):
|
31 |
+
target_criteria = df.loc[df['NCTID'] == nct_id, 'Eligibility Criteria'].values[0]
|
32 |
+
agent_judgment = CriteriaCheckAgent.evaluate_eligibility(target_criteria, ex_question)
|
33 |
+
agent_grade = grader_agent.evaluate_eligibility(agent_judgment)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
|
35 |
+
# データフレームの更新
|
36 |
+
df.loc[df['NCTID'] == nct_id, 'AgentJudgment'] = agent_judgment
|
37 |
+
df.loc[df['NCTID'] == nct_id, 'AgentGrade'] = agent_grade
|
38 |
+
progress((i + 1) / len(NCTIDs))
|
39 |
+
|
40 |
+
# 列を指定した順に並び替え
|
41 |
+
columns_order = ['NCTID', 'AgentGrade', 'Title', 'AgentJudgment', 'Japanes Locations',
|
42 |
+
'Primary Completion Date', 'Cancer', 'Summary', 'Eligibility Criteria']
|
43 |
+
df = df[columns_order]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
|
45 |
+
return df, df # フィルタ用と表示用にデータフレームを返す
|
46 |
+
|
47 |
+
# 特定のAgentGrade(yes, no, unclear)に基づいて行をフィルタリングする関数
|
48 |
+
def filter_rows_by_grade(original_df, grade):
|
49 |
+
df_filtered = original_df[original_df['AgentGrade'] == grade]
|
50 |
+
return df_filtered, df_filtered
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
# CSVとして保存しダウンロードする関数
|
53 |
def download_filtered_csv(df):
|
54 |
+
file_path = "filtered_data.csv"
|
55 |
+
df.to_csv(file_path, index=False)
|
56 |
+
return file_path
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
|
58 |
# 全体結果をCSVとして保存しダウンロードする関数
|
59 |
def download_full_csv(df):
|
60 |
+
file_path = "full_data.csv"
|
61 |
+
df.to_csv(file_path, index=False)
|
62 |
+
return file_path
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
|
64 |
# Gradioインターフェースの作成
|
65 |
+
with gr.Blocks() as demo:
|
66 |
gr.Markdown("## 臨床試験適格性評価インターフェース")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
|
68 |
# 各種入力フィールド
|
69 |
+
age_input = gr.Textbox(label="Age", placeholder="例: 65")
|
70 |
+
sex_input = gr.Dropdown(choices=["男性", "女性"], label="Sex")
|
71 |
+
tumor_type_input = gr.Textbox(label="Tumor Type", placeholder="例: gastric cancer, 日本でも良いですが英語の方が精度が高いです。")
|
72 |
+
gene_mutation_input = gr.Textbox(label="Gene Mutation", placeholder="例: HER2")
|
73 |
+
measurable_input = gr.Dropdown(choices=["有り", "無し", "不明"], label="Measurable Tumor")
|
74 |
+
biopsiable_input = gr.Dropdown(choices=["有り", "無し", "不明"], label="Biopsiable Tumor")
|
|
|
|
|
|
|
|
|
75 |
|
76 |
# データフレーム表示エリア
|
77 |
+
dataframe_output = gr.DataFrame()
|
78 |
+
original_df = gr.State()
|
79 |
+
filtered_df = gr.State()
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
|
81 |
+
# データフレーム生成ボタン
|
82 |
+
generate_button = gr.Button("Generate Clinical Trials Data")
|
83 |
+
|
84 |
+
# フィルタリングボタン
|
85 |
+
yes_button = gr.Button("Show Eligible Trials")
|
86 |
+
no_button = gr.Button("Show Ineligible Trials")
|
87 |
+
unclear_button = gr.Button("Show Unclear Trials")
|
|
|
|
|
|
|
|
|
|
|
88 |
|
89 |
+
# ダウンロードボタン
|
90 |
+
download_filtered_button = gr.Button("Download Filtered Data")
|
91 |
+
download_filtered_output = gr.File(label="Download Filtered Data")
|
92 |
|
93 |
+
download_full_button = gr.Button("Download Full Data")
|
94 |
+
download_full_output = gr.File(label="Download Full Data")
|
|
|
|
|
|
|
95 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
96 |
|
97 |
# ボタン動作の設定
|
98 |
+
generate_button.click(fn=generate_dataframe, inputs=[age_input, sex_input, tumor_type_input, gene_mutation_input, measurable_input, biopsiable_input], outputs=[dataframe_output, original_df])
|
99 |
+
yes_button.click(fn=filter_rows_by_grade, inputs=[original_df, gr.State("yes")], outputs=[dataframe_output, filtered_df])
|
100 |
+
no_button.click(fn=filter_rows_by_grade, inputs=[original_df, gr.State("no")], outputs=[dataframe_output, filtered_df])
|
101 |
+
unclear_button.click(fn=filter_rows_by_grade, inputs=[original_df, gr.State("unclear")], outputs=[dataframe_output, filtered_df])
|
102 |
+
download_filtered_button.click(fn=download_filtered_csv, inputs=filtered_df, outputs=download_filtered_output)
|
103 |
+
download_full_button.click(fn=download_full_csv, inputs=original_df, outputs=download_full_output)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
104 |
|
105 |
if __name__ == "__main__":
|
106 |
+
demo.launch()
|
|
|
|
|
|
|
|
|
|
|
|
app_new.py
ADDED
@@ -0,0 +1,321 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import pandas as pd
|
3 |
+
import time
|
4 |
+
import traceback
|
5 |
+
import os
|
6 |
+
from OpenAITools.FetchTools import fetch_clinical_trials
|
7 |
+
from langchain_openai import ChatOpenAI
|
8 |
+
from langchain_groq import ChatGroq
|
9 |
+
from OpenAITools.CrinicalTrialTools import SimpleClinicalTrialAgent, GraderAgent, LLMTranslator, generate_ex_question_English
|
10 |
+
|
11 |
+
# 環境変数チェック
|
12 |
+
def check_environment():
|
13 |
+
"""環境変数をチェックし、不足している場合は警告"""
|
14 |
+
missing_vars = []
|
15 |
+
|
16 |
+
if not os.getenv("GROQ_API_KEY"):
|
17 |
+
missing_vars.append("GROQ_API_KEY")
|
18 |
+
|
19 |
+
if not os.getenv("OPENAI_API_KEY"):
|
20 |
+
missing_vars.append("OPENAI_API_KEY")
|
21 |
+
|
22 |
+
if missing_vars:
|
23 |
+
print(f"⚠️ 環境変数が設定されていません: {', '.join(missing_vars)}")
|
24 |
+
print("一部の機能が制限される可能性があります。")
|
25 |
+
|
26 |
+
return len(missing_vars) == 0
|
27 |
+
|
28 |
+
# 環境変数チェック実行
|
29 |
+
env_ok = check_environment()
|
30 |
+
|
31 |
+
# モデルとエージェントの安全な初期化
|
32 |
+
def safe_init_agents():
|
33 |
+
"""エージェントを安全に初期化"""
|
34 |
+
try:
|
35 |
+
groq = ChatGroq(model_name="llama3-70b-8192", temperature=0)
|
36 |
+
translator = LLMTranslator(groq)
|
37 |
+
criteria_agent = SimpleClinicalTrialAgent(groq)
|
38 |
+
grader_agent = GraderAgent(groq)
|
39 |
+
return translator, criteria_agent, grader_agent
|
40 |
+
except Exception as e:
|
41 |
+
print(f"エージェント初期化エラー: {e}")
|
42 |
+
return None, None, None
|
43 |
+
|
44 |
+
# エージェント初期化
|
45 |
+
translator, CriteriaCheckAgent, grader_agent = safe_init_agents()
|
46 |
+
|
47 |
+
# エラーハンドリング付きでエージェント評価を実行する関数
|
48 |
+
def evaluate_with_retry(agent, criteria, question, max_retries=3):
|
49 |
+
"""エラーハンドリング付きでエージェント評価を実行"""
|
50 |
+
if agent is None:
|
51 |
+
return "評価エラー: エージェントが初期化されていません。API keyを確認してください。"
|
52 |
+
|
53 |
+
for attempt in range(max_retries):
|
54 |
+
try:
|
55 |
+
return agent.evaluate_eligibility(criteria, question)
|
56 |
+
except Exception as e:
|
57 |
+
if "missing variables" in str(e):
|
58 |
+
# プロンプトテンプレートの変数エラーの場合
|
59 |
+
print(f"プロンプトテンプレートエラー (試行 {attempt + 1}/{max_retries}): {e}")
|
60 |
+
return "評価エラー: プロンプトテンプレートの設定に問題があります"
|
61 |
+
elif "no healthy upstream" in str(e) or "InternalServerError" in str(e):
|
62 |
+
# Groqサーバーエラーの場合
|
63 |
+
print(f"Groqサーバーエラー (試行 {attempt + 1}/{max_retries}): {e}")
|
64 |
+
if attempt < max_retries - 1:
|
65 |
+
time.sleep(2) # 2秒待機してリトライ
|
66 |
+
continue
|
67 |
+
else:
|
68 |
+
return "評価エラー: サーバーに接続できませんでした"
|
69 |
+
elif "API key" in str(e) or "authentication" in str(e).lower():
|
70 |
+
return "評価エラー: API keyが無効または設定されていません"
|
71 |
+
else:
|
72 |
+
print(f"予期しないエラー (試行 {attempt + 1}/{max_retries}): {e}")
|
73 |
+
if attempt < max_retries - 1:
|
74 |
+
time.sleep(1)
|
75 |
+
continue
|
76 |
+
else:
|
77 |
+
return f"評価エラー: {str(e)}"
|
78 |
+
return "評価エラー: 最大リトライ回数に達しました"
|
79 |
+
|
80 |
+
def evaluate_grade_with_retry(agent, judgment, max_retries=3):
|
81 |
+
"""エラーハンドリング付きでグレード評価を実行"""
|
82 |
+
if agent is None:
|
83 |
+
return "unclear"
|
84 |
+
|
85 |
+
for attempt in range(max_retries):
|
86 |
+
try:
|
87 |
+
return agent.evaluate_eligibility(judgment)
|
88 |
+
except Exception as e:
|
89 |
+
if "no healthy upstream" in str(e) or "InternalServerError" in str(e):
|
90 |
+
print(f"Groqサーバーエラー (グレード評価 - 試行 {attempt + 1}/{max_retries}): {e}")
|
91 |
+
if attempt < max_retries - 1:
|
92 |
+
time.sleep(2)
|
93 |
+
continue
|
94 |
+
else:
|
95 |
+
return "unclear"
|
96 |
+
elif "API key" in str(e) or "authentication" in str(e).lower():
|
97 |
+
return "unclear"
|
98 |
+
else:
|
99 |
+
print(f"予期しないエラー (グレード評価 - 試行 {attempt + 1}/{max_retries}): {e}")
|
100 |
+
if attempt < max_retries - 1:
|
101 |
+
time.sleep(1)
|
102 |
+
continue
|
103 |
+
else:
|
104 |
+
return "unclear"
|
105 |
+
return "unclear"
|
106 |
+
|
107 |
+
# データフレームを生成する関数
|
108 |
+
def generate_dataframe(age, sex, tumor_type, GeneMutation, Meseable, Biopsiable):
|
109 |
+
try:
|
110 |
+
# 入力検証
|
111 |
+
if not all([age, sex, tumor_type]):
|
112 |
+
return pd.DataFrame(), pd.DataFrame()
|
113 |
+
|
114 |
+
# 日本語の腫瘍タイプを英語に翻訳
|
115 |
+
try:
|
116 |
+
if translator is not None:
|
117 |
+
TumorName = translator.translate(tumor_type)
|
118 |
+
else:
|
119 |
+
print("翻訳エージェントが利用できません。元の値を使用します。")
|
120 |
+
TumorName = tumor_type
|
121 |
+
except Exception as e:
|
122 |
+
print(f"翻訳エラー: {e}")
|
123 |
+
TumorName = tumor_type # 翻訳に失敗した場合は元の値を使用
|
124 |
+
|
125 |
+
# 質問文を生成
|
126 |
+
try:
|
127 |
+
ex_question = generate_ex_question_English(age, sex, TumorName, GeneMutation, Meseable, Biopsiable)
|
128 |
+
except Exception as e:
|
129 |
+
print(f"質問生成エラー: {e}")
|
130 |
+
return pd.DataFrame(), pd.DataFrame()
|
131 |
+
|
132 |
+
# 臨床試験データの取得
|
133 |
+
try:
|
134 |
+
df = fetch_clinical_trials(TumorName)
|
135 |
+
if df.empty:
|
136 |
+
print("臨床試験データが見つかりませんでした")
|
137 |
+
return pd.DataFrame(), pd.DataFrame()
|
138 |
+
except Exception as e:
|
139 |
+
print(f"臨床試験データ取得エラー: {e}")
|
140 |
+
return pd.DataFrame(), pd.DataFrame()
|
141 |
+
|
142 |
+
df['AgentJudgment'] = None
|
143 |
+
df['AgentGrade'] = None
|
144 |
+
|
145 |
+
# 臨床試験の適格性の評価
|
146 |
+
NCTIDs = list(df['NCTID'])
|
147 |
+
progress = gr.Progress(track_tqdm=True)
|
148 |
+
|
149 |
+
for i, nct_id in enumerate(NCTIDs):
|
150 |
+
try:
|
151 |
+
target_criteria = df.loc[df['NCTID'] == nct_id, 'Eligibility Criteria'].values[0]
|
152 |
+
|
153 |
+
# エラーハンドリング付きで評価実行
|
154 |
+
agent_judgment = evaluate_with_retry(CriteriaCheckAgent, target_criteria, ex_question)
|
155 |
+
agent_grade = evaluate_grade_with_retry(grader_agent, agent_judgment)
|
156 |
+
|
157 |
+
# データフレームの更新
|
158 |
+
df.loc[df['NCTID'] == nct_id, 'AgentJudgment'] = agent_judgment
|
159 |
+
df.loc[df['NCTID'] == nct_id, 'AgentGrade'] = agent_grade
|
160 |
+
|
161 |
+
except Exception as e:
|
162 |
+
print(f"NCTID {nct_id} の評価中にエラー: {e}")
|
163 |
+
df.loc[df['NCTID'] == nct_id, 'AgentJudgment'] = f"エラー: {str(e)}"
|
164 |
+
df.loc[df['NCTID'] == nct_id, 'AgentGrade'] = "unclear"
|
165 |
+
|
166 |
+
progress((i + 1) / len(NCTIDs))
|
167 |
+
|
168 |
+
# 列を指定した順に並び替え
|
169 |
+
columns_order = ['NCTID', 'AgentGrade', 'Title', 'AgentJudgment', 'Japanes Locations',
|
170 |
+
'Primary Completion Date', 'Cancer', 'Summary', 'Eligibility Criteria']
|
171 |
+
|
172 |
+
# 存在する列のみを選択
|
173 |
+
available_columns = [col for col in columns_order if col in df.columns]
|
174 |
+
df = df[available_columns]
|
175 |
+
|
176 |
+
return df, df # フィルタ用と表示用にデータフレームを返す
|
177 |
+
|
178 |
+
except Exception as e:
|
179 |
+
print(f"データフレーム生成中に予期しないエラー: {e}")
|
180 |
+
traceback.print_exc()
|
181 |
+
return pd.DataFrame(), pd.DataFrame()
|
182 |
+
|
183 |
+
# CSVとして保存しダウンロードする関数
|
184 |
+
def download_filtered_csv(df):
|
185 |
+
try:
|
186 |
+
if df is None or len(df) == 0:
|
187 |
+
return None
|
188 |
+
file_path = "filtered_data.csv"
|
189 |
+
df.to_csv(file_path, index=False)
|
190 |
+
return file_path
|
191 |
+
except Exception as e:
|
192 |
+
print(f"CSV保存エラー: {e}")
|
193 |
+
return None
|
194 |
+
|
195 |
+
# 全体結果をCSVとして保存しダウンロードする関数
|
196 |
+
def download_full_csv(df):
|
197 |
+
try:
|
198 |
+
if df is None or len(df) == 0:
|
199 |
+
return None
|
200 |
+
file_path = "full_data.csv"
|
201 |
+
df.to_csv(file_path, index=False)
|
202 |
+
return file_path
|
203 |
+
except Exception as e:
|
204 |
+
print(f"CSV保存エラー: {e}")
|
205 |
+
return None
|
206 |
+
|
207 |
+
# Gradioインターフェースの作成
|
208 |
+
with gr.Blocks(title="臨床試験適格性評価", theme=gr.themes.Soft()) as demo:
|
209 |
+
gr.Markdown("## 臨床試験適格性評価インターフェース")
|
210 |
+
|
211 |
+
# 環境変数状態の表示
|
212 |
+
if env_ok:
|
213 |
+
gr.Markdown("✅ **ステータス**: 全ての環境変数が設定されています")
|
214 |
+
else:
|
215 |
+
gr.Markdown("⚠️ **注意**: 一部の環境変数が設定されていません。機能が制限される可能性があります。")
|
216 |
+
|
217 |
+
gr.Markdown("💡 **使用方法**: 患者情報を入力して「Generate Clinical Trials Data」をクリックしてください。")
|
218 |
+
|
219 |
+
# 各種入力フィールド
|
220 |
+
with gr.Row():
|
221 |
+
with gr.Column():
|
222 |
+
age_input = gr.Textbox(label="Age", placeholder="例: 65", value="")
|
223 |
+
sex_input = gr.Dropdown(choices=["男性", "女性"], label="Sex", value=None)
|
224 |
+
tumor_type_input = gr.Textbox(label="Tumor Type", placeholder="例: gastric cancer", value="")
|
225 |
+
|
226 |
+
with gr.Column():
|
227 |
+
gene_mutation_input = gr.Textbox(label="Gene Mutation", placeholder="例: HER2", value="")
|
228 |
+
measurable_input = gr.Dropdown(choices=["有り", "無し", "不明"], label="Measurable Tumor", value=None)
|
229 |
+
biopsiable_input = gr.Dropdown(choices=["有り", "無し", "不明"], label="Biopsiable Tumor", value=None)
|
230 |
+
|
231 |
+
# データフレーム表示エリア
|
232 |
+
dataframe_output = gr.DataFrame(
|
233 |
+
headers=["NCTID", "AgentGrade", "Title", "AgentJudgment", "Status"],
|
234 |
+
datatype=["str", "str", "str", "str", "str"],
|
235 |
+
value=None
|
236 |
+
)
|
237 |
+
|
238 |
+
# 内部状態用の非表示コンポーネント
|
239 |
+
original_df_state = gr.State(value=None)
|
240 |
+
filtered_df_state = gr.State(value=None)
|
241 |
+
|
242 |
+
# ボタン類
|
243 |
+
with gr.Row():
|
244 |
+
generate_button = gr.Button("Generate Clinical Trials Data", variant="primary")
|
245 |
+
|
246 |
+
with gr.Row():
|
247 |
+
yes_button = gr.Button("Show Eligible Trials", variant="secondary")
|
248 |
+
no_button = gr.Button("Show Ineligible Trials", variant="secondary")
|
249 |
+
unclear_button = gr.Button("Show Unclear Trials", variant="secondary")
|
250 |
+
|
251 |
+
with gr.Row():
|
252 |
+
download_filtered_button = gr.Button("Download Filtered Data")
|
253 |
+
download_full_button = gr.Button("Download Full Data")
|
254 |
+
|
255 |
+
# ダウンロードファイル
|
256 |
+
download_filtered_output = gr.File(label="Download Filtered Data", visible=False)
|
257 |
+
download_full_output = gr.File(label="Download Full Data", visible=False)
|
258 |
+
|
259 |
+
# イベントハンドリング
|
260 |
+
def update_dataframe_and_state(age, sex, tumor_type, gene_mutation, measurable, biopsiable):
|
261 |
+
"""データフレーム生成と状態更新"""
|
262 |
+
df, _ = generate_dataframe(age, sex, tumor_type, gene_mutation, measurable, biopsiable)
|
263 |
+
return df, df, df
|
264 |
+
|
265 |
+
def filter_and_update(original_df, grade):
|
266 |
+
"""フィルタリングと表示更新"""
|
267 |
+
if original_df is None or len(original_df) == 0:
|
268 |
+
return original_df, original_df
|
269 |
+
|
270 |
+
try:
|
271 |
+
df_filtered = original_df[original_df['AgentGrade'] == grade]
|
272 |
+
return df_filtered, df_filtered
|
273 |
+
except Exception as e:
|
274 |
+
print(f"フィルタリングエラー: {e}")
|
275 |
+
return original_df, original_df
|
276 |
+
|
277 |
+
# ボタン動作の設定
|
278 |
+
generate_button.click(
|
279 |
+
fn=update_dataframe_and_state,
|
280 |
+
inputs=[age_input, sex_input, tumor_type_input, gene_mutation_input, measurable_input, biopsiable_input],
|
281 |
+
outputs=[dataframe_output, original_df_state, filtered_df_state]
|
282 |
+
)
|
283 |
+
|
284 |
+
yes_button.click(
|
285 |
+
fn=lambda df: filter_and_update(df, "yes"),
|
286 |
+
inputs=[original_df_state],
|
287 |
+
outputs=[dataframe_output, filtered_df_state]
|
288 |
+
)
|
289 |
+
|
290 |
+
no_button.click(
|
291 |
+
fn=lambda df: filter_and_update(df, "no"),
|
292 |
+
inputs=[original_df_state],
|
293 |
+
outputs=[dataframe_output, filtered_df_state]
|
294 |
+
)
|
295 |
+
|
296 |
+
unclear_button.click(
|
297 |
+
fn=lambda df: filter_and_update(df, "unclear"),
|
298 |
+
inputs=[original_df_state],
|
299 |
+
outputs=[dataframe_output, filtered_df_state]
|
300 |
+
)
|
301 |
+
|
302 |
+
download_filtered_button.click(
|
303 |
+
fn=download_filtered_csv,
|
304 |
+
inputs=[filtered_df_state],
|
305 |
+
outputs=[download_filtered_output]
|
306 |
+
)
|
307 |
+
|
308 |
+
download_full_button.click(
|
309 |
+
fn=download_full_csv,
|
310 |
+
inputs=[original_df_state],
|
311 |
+
outputs=[download_full_output]
|
312 |
+
)
|
313 |
+
|
314 |
+
if __name__ == "__main__":
|
315 |
+
demo.launch(
|
316 |
+
server_name="0.0.0.0",
|
317 |
+
server_port=7860,
|
318 |
+
share=False,
|
319 |
+
debug=False,
|
320 |
+
show_error=True
|
321 |
+
)
|
requirements.txt → requirements_new.txt
RENAMED
File without changes
|