Spaces:
Running
Running
File size: 16,591 Bytes
f94920a 0767cb0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 |
from Bio import Entrez, Medline
#import model
import mtdna_classifier
from NER.html import extractHTML
import data_preprocess
import pipeline
import aiohttp
import asyncio
# Setup
def fetch_ncbi(accession_number):
try:
Entrez.email = "your.email@example.com" # Required by NCBI, REPLACE WITH YOUR EMAIL
handle = Entrez.efetch(db="nucleotide", id=str(accession_number), rettype="gb", retmode="xml")
record = Entrez.read(handle)
handle.close()
outputs = {"authors":"unknown",
"institution":"unknown",
"isolate":"unknown",
"definition":"unknown",
"title":"unknown",
"seq_comment":"unknown",
"collection_date":"unknown" } #'GBSeq_update-date': '25-OCT-2023', 'GBSeq_create-date'
gb_seq = None
# Validate record structure: It should be a list with at least one element (a dict)
if isinstance(record, list) and len(record) > 0:
if isinstance(record[0], dict):
gb_seq = record[0]
else:
print(f"Warning: record[0] is not a dictionary for {accession_number}. Type: {type(record[0])}")
# extract collection date
if "GBSeq_create-date" in gb_seq and outputs["collection_date"]=="unknown":
outputs["collection_date"] = gb_seq["GBSeq_create-date"]
else:
if "GBSeq_update-date" in gb_seq and outputs["collection_date"]=="unknown":
outputs["collection_date"] = gb_seq["GBSeq_update-date"]
# extract definition
if "GBSeq_definition" in gb_seq and outputs["definition"]=="unknown":
outputs["definition"] = gb_seq["GBSeq_definition"]
# extract related-reference things
if "GBSeq_references" in gb_seq:
for ref in gb_seq["GBSeq_references"]:
# extract authors
if "GBReference_authors" in ref and outputs["authors"]=="unknown":
outputs["authors"] = "and ".join(ref["GBReference_authors"])
# extract title
if "GBReference_title" in ref and outputs["title"]=="unknown":
outputs["title"] = ref["GBReference_title"]
# extract submitted journal
if 'GBReference_journal' in ref and outputs["institution"]=="unknown":
outputs["institution"] = ref['GBReference_journal']
# extract seq_comment
if 'GBSeq_comment'in gb_seq and outputs["seq_comment"]=="unknown":
outputs["seq_comment"] = gb_seq["GBSeq_comment"]
# extract isolate
if "GBSeq_feature-table" in gb_seq:
if 'GBFeature_quals' in gb_seq["GBSeq_feature-table"][0]:
for ref in gb_seq["GBSeq_feature-table"][0]["GBFeature_quals"]:
if ref['GBQualifier_name'] == "isolate" and outputs["isolate"]=="unknown":
outputs["isolate"] = ref["GBQualifier_value"]
else:
print(f"Warning: No valid record or empty record list from NCBI for {accession_number}.")
# If gb_seq is still None, return defaults
if gb_seq is None:
return {"authors":"unknown",
"institution":"unknown",
"isolate":"unknown",
"definition":"unknown",
"title":"unknown",
"seq_comment":"unknown",
"collection_date":"unknown" }
return outputs
except:
print("error in fetching ncbi data")
return {"authors":"unknown",
"institution":"unknown",
"isolate":"unknown",
"definition":"unknown",
"title":"unknown",
"seq_comment":"unknown",
"collection_date":"unknown" }
# Fallback if NCBI crashed or cannot find accession on NBCI
def google_accession_search(accession_id):
"""
Search for metadata by accession ID using Google Custom Search.
Falls back to known biological databases and archives.
"""
queries = [
f"{accession_id}",
f"{accession_id} site:ncbi.nlm.nih.gov",
f"{accession_id} site:pubmed.ncbi.nlm.nih.gov",
f"{accession_id} site:europepmc.org",
f"{accession_id} site:researchgate.net",
f"{accession_id} mtDNA",
f"{accession_id} mitochondrial DNA"
]
links = []
for query in queries:
search_results = mtdna_classifier.search_google_custom(query, 2)
for link in search_results:
if link not in links:
links.append(link)
return links
# Method 1: Smarter Google
def smart_google_queries(metadata: dict):
queries = []
# Extract useful fields
isolate = metadata.get("isolate")
author = metadata.get("authors")
institution = metadata.get("institution")
title = metadata.get("title")
combined = []
# Construct queries
if isolate and isolate!="unknown" and isolate!="Unpublished":
queries.append(f'"{isolate}" mitochondrial DNA')
queries.append(f'"{isolate}" site:ncbi.nlm.nih.gov')
if author and author!="unknown" and author!="Unpublished":
# try:
# author_name = ".".join(author.split(' ')[0].split(".")[:-1]) # Use last name only
# except:
# try:
# author_name = author.split(',')[0] # Use last name only
# except:
# author_name = author
try:
author_name = author.split(',')[0] # Use last name only
except:
author_name = author
queries.append(f'"{author_name}" mitochondrial DNA')
queries.append(f'"{author_name}" mtDNA site:researchgate.net')
if institution and institution!="unknown" and institution!="Unpublished":
try:
short_inst = ",".join(institution.split(',')[:2]) # Take first part of institution
except:
try:
short_inst = institution.split(',')[0]
except:
short_inst = institution
queries.append(f'"{short_inst}" mtDNA sequence')
#queries.append(f'"{short_inst}" isolate site:nature.com')
if title and title!='unknown' and title!="Unpublished":
if title!="Direct Submission":
queries.append(title)
return queries
# def filter_links_by_metadata(search_results, saveLinkFolder, accession=None, stop_flag=None):
# TRUSTED_DOMAINS = [
# "ncbi.nlm.nih.gov",
# "pubmed.ncbi.nlm.nih.gov",
# "pmc.ncbi.nlm.nih.gov",
# "biorxiv.org",
# "researchgate.net",
# "nature.com",
# "sciencedirect.com"
# ]
# if stop_flag is not None and stop_flag.value:
# print(f"🛑 Stop detected {accession}, aborting early...")
# return []
# def is_trusted_link(link):
# for domain in TRUSTED_DOMAINS:
# if domain in link:
# return True
# return False
# def is_relevant_title_snippet(link, saveLinkFolder, accession=None):
# output = []
# keywords = ["mtDNA", "mitochondrial", "accession", "isolate", "Homo sapiens", "sequence"]
# if accession:
# keywords = [accession] + keywords
# title_snippet = link.lower()
# print("save link folder inside this filter function: ", saveLinkFolder)
# success_process, output_process = pipeline.run_with_timeout(data_preprocess.extract_text,args=(link,saveLinkFolder),timeout=60)
# if stop_flag is not None and stop_flag.value:
# print(f"🛑 Stop detected {accession}, aborting early...")
# return []
# if success_process:
# article_text = output_process
# print("yes succeed for getting article text")
# else:
# print("no suceed, fallback to no link")
# article_text = ""
# #article_text = data_preprocess.extract_text(link,saveLinkFolder)
# print("article text")
# #print(article_text)
# if stop_flag is not None and stop_flag.value:
# print(f"🛑 Stop detected {accession}, aborting early...")
# return []
# try:
# ext = link.split(".")[-1].lower()
# if ext not in ["pdf", "docx", "xlsx"]:
# html = extractHTML.HTML("", link)
# if stop_flag is not None and stop_flag.value:
# print(f"🛑 Stop detected {accession}, aborting early...")
# return []
# jsonSM = html.getSupMaterial()
# if jsonSM:
# output += sum((jsonSM[key] for key in jsonSM), [])
# except Exception:
# pass # continue silently
# for keyword in keywords:
# if keyword.lower() in article_text.lower():
# if link not in output:
# output.append([link,keyword.lower()])
# print("link and keyword for article text: ", link, keyword)
# return output
# if keyword.lower() in title_snippet.lower():
# if link not in output:
# output.append([link,keyword.lower()])
# print("link and keyword for title: ", link, keyword)
# return output
# return output
# filtered = []
# better_filter = []
# if len(search_results) > 0:
# for link in search_results:
# # if is_trusted_link(link):
# # if link not in filtered:
# # filtered.append(link)
# # else:
# print(link)
# if stop_flag is not None and stop_flag.value:
# print(f"🛑 Stop detected {accession}, aborting early...")
# return []
# if link:
# output_link = is_relevant_title_snippet(link,saveLinkFolder, accession)
# print("output link: ")
# print(output_link)
# for out_link in output_link:
# if isinstance(out_link,list) and len(out_link) > 1:
# print(out_link)
# kw = out_link[1]
# print("kw and acc: ", kw, accession.lower())
# if accession and kw == accession.lower():
# better_filter.append(out_link[0])
# filtered.append(out_link[0])
# else: filtered.append(out_link)
# print("done with link and here is filter: ",filtered)
# if better_filter:
# filtered = better_filter
# return filtered
async def process_link(session, link, saveLinkFolder, keywords, accession):
output = []
title_snippet = link.lower()
# use async extractor for web, fallback to sync for local files
if link.startswith("http"):
article_text = await data_preprocess.async_extract_text(link, saveLinkFolder)
else:
article_text = data_preprocess.extract_text(link, saveLinkFolder)
for keyword in keywords:
if article_text and keyword.lower() in article_text.lower():
output.append([link, keyword.lower(), article_text])
return output
if keyword.lower() in title_snippet:
output.append([link, keyword.lower()])
return output
return output
async def async_filter_links_by_metadata(search_results, saveLinkFolder, accession=None):
TRUSTED_DOMAINS = [
"ncbi.nlm.nih.gov", "pubmed.ncbi.nlm.nih.gov", "pmc.ncbi.nlm.nih.gov",
"biorxiv.org", "researchgate.net", "nature.com", "sciencedirect.com"
]
keywords = ["mtDNA", "mitochondrial", "accession", "isolate", "Homo sapiens", "sequence"]
if accession:
keywords = [accession] + keywords
filtered, better_filter = {}, {}
print("before doing session")
async with aiohttp.ClientSession() as session:
tasks = []
for link in search_results:
if link:
print("link: ", link)
tasks.append(process_link(session, link, saveLinkFolder, keywords, accession))
print("done")
results = await asyncio.gather(*tasks)
print("outside session")
# merge results
for output_link in results:
for out_link in output_link:
if isinstance(out_link, list) and len(out_link) > 1:
kw = out_link[1]
if accession and kw == accession.lower():
if len(out_link) == 2:
better_filter[out_link[0]] = ""
elif len(out_link) == 3:
better_filter[out_link[0]] = out_link[2]
if len(out_link) == 2:
better_filter[out_link[0]] = ""
elif len(out_link) == 3:
better_filter[out_link[0]] = out_link[2]
else:
filtered[out_link] = ""
return better_filter or filtered
def filter_links_by_metadata(search_results, saveLinkFolder, accession=None):
TRUSTED_DOMAINS = [
"ncbi.nlm.nih.gov",
"pubmed.ncbi.nlm.nih.gov",
"pmc.ncbi.nlm.nih.gov",
"biorxiv.org",
"researchgate.net",
"nature.com",
"sciencedirect.com"
]
def is_trusted_link(link):
for domain in TRUSTED_DOMAINS:
if domain in link:
return True
return False
def is_relevant_title_snippet(link, saveLinkFolder, accession=None):
output = []
keywords = ["mtDNA", "mitochondrial", "Homo sapiens"]
#keywords = ["mtDNA", "mitochondrial"]
if accession:
keywords = [accession] + keywords
title_snippet = link.lower()
#print("save link folder inside this filter function: ", saveLinkFolder)
article_text = data_preprocess.extract_text(link,saveLinkFolder)
print("article text done")
#print(article_text)
try:
ext = link.split(".")[-1].lower()
if ext not in ["pdf", "docx", "xlsx"]:
html = extractHTML.HTML("", link)
jsonSM = html.getSupMaterial()
if jsonSM:
output += sum((jsonSM[key] for key in jsonSM), [])
except Exception:
pass # continue silently
for keyword in keywords:
if article_text:
if keyword.lower() in article_text.lower():
if link not in output:
output.append([link,keyword.lower(), article_text])
return output
if keyword.lower() in title_snippet.lower():
if link not in output:
output.append([link,keyword.lower()])
print("link and keyword for title: ", link, keyword)
return output
return output
filtered = {}
better_filter = {}
if len(search_results) > 0:
print(search_results)
for link in search_results:
# if is_trusted_link(link):
# if link not in filtered:
# filtered.append(link)
# else:
print(link)
if link:
output_link = is_relevant_title_snippet(link,saveLinkFolder, accession)
print("output link: ")
print(output_link)
for out_link in output_link:
if isinstance(out_link,list) and len(out_link) > 1:
print(out_link)
kw = out_link[1]
if accession and kw == accession.lower():
if len(out_link) == 2:
better_filter[out_link[0]] = ""
elif len(out_link) == 3:
# save article
better_filter[out_link[0]] = out_link[2]
if len(out_link) == 2:
better_filter[out_link[0]] = ""
elif len(out_link) == 3:
# save article
better_filter[out_link[0]] = out_link[2]
else: filtered[out_link] = ""
print("done with link and here is filter: ",filtered)
if better_filter:
filtered = better_filter
return filtered
def smart_google_search(metadata):
queries = smart_google_queries(metadata)
links = []
for q in queries:
#print("\n🔍 Query:", q)
results = mtdna_classifier.search_google_custom(q,2)
for link in results:
#print(f"- {link}")
if link not in links:
links.append(link)
#filter_links = filter_links_by_metadata(links)
return links
# Method 2: Prompt LLM better or better ai search api with all
# the total information from even ncbi and all search |