diff options
| -rwxr-xr-x | more_functions.py | 16 | ||||
| -rwxr-xr-x | server.py | 35 |
2 files changed, 35 insertions, 16 deletions
diff --git a/more_functions.py b/more_functions.py index 35e3646..5d48adc 100755 --- a/more_functions.py +++ b/more_functions.py @@ -113,6 +113,22 @@ def hybrid_fetch_abstracts(pmid_list): abstracts += extra return abstracts +def getabstracts_batch(genes, query): + """Fetch abstracts for multiple genes in a single PubMed query. + + Builds: (keywords) AND (gene1 [tiab] OR gene2 [tiab] OR ...) + Returns tab-separated lines: PMID, ArticleTitle, AbstractText + """ + genes_clause = " OR ".join(g + " [tiab]" for g in genes) + full_query = "\"(" + query + ") AND (" + genes_clause + ")\"" + pmid_list = esearch_pmids(full_query) + if not pmid_list: + print(f" no PMIDs found for {genes}") + return "" + print(f" PMIDs ({len(pmid_list)}): {' '.join(pmid_list[:20])}{'...' if len(pmid_list) > 20 else ''}") + abstracts = hybrid_fetch_abstracts(pmid_list) + return abstracts + def getabstracts(gene,query): """ 1. esearch -db pubmed -query ... -- searches PubMed for the gene + keyword query, returns matching record IDs diff --git a/server.py b/server.py index 79dda7d..25ccad5 100755 --- a/server.py +++ b/server.py @@ -64,7 +64,7 @@ import re import ast from more_functions import * from nltk.tokenize import sent_tokenize -from more_functions import getabstracts, undic, gene_category +from more_functions import getabstracts, getabstracts_batch, undic, gene_category GENECUP_PROMPT_TEMPLATE = "" try: @@ -983,22 +983,25 @@ def search(): progress+=percent yield "data:"+str(progress)+"\n\n" - for gene in genes: - print(f"Fetching info for gene {gene}\n") - abstracts_raw = getabstracts(gene,all_d) # all_d might be empty if no search_type matches - print(abstracts_raw) - sentences_ls=[] + # Batch fetch all abstracts in a single PubMed query + print(f"Batch fetching abstracts for {len(genes)} genes") + all_abstracts_raw = getabstracts_batch(genes, all_d) if all_d else "" + # Parse all sentences once + all_sentences = [] + for row in all_abstracts_raw.split("\n"): + if not row.strip(): continue + tiab = row.split("\t") + pmid = tiab.pop(0) + tiab_text = " ".join(tiab) + for sent_tok in sent_tokenize(tiab_text): + all_sentences.append(pmid + ' ' + sent_tok) - for row in abstracts_raw.split("\n"): - if not row.strip(): continue # Skip empty lines - tiab=row.split("\t") - pmid = tiab.pop(0) - tiab_text = " ".join(tiab) # Renamed to avoid conflict - sentences_tok = sent_tokenize(tiab_text) - for sent_tok in sentences_tok: - sent_tok = pmid + ' ' + sent_tok - sentences_ls.append(sent_tok) - gene=gene.replace("-"," ") + for gene in genes: + gene = gene.replace("-", " ") + # Filter sentences that mention this gene + gene_re = re.compile(r'\b' + re.escape(gene) + r'\b', re.IGNORECASE) + sentences_ls = [s for s in all_sentences if gene_re.search(s)] + print(f" Gene {gene}: {len(sentences_ls)} sentences") geneEdges = "" |