Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: title, description, and content fuzzy search #193

Merged
merged 4 commits into from
Mar 6, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions backend/init.sql
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@
-- Generated columns:
-- https://www.postgresql.org/docs/current/ddl-generated-columns.html

CREATE EXTENSION pg_trgm; -- for trigram matching fuzzy search similarity() func

/*
* Species Table
*/
Expand All @@ -28,8 +30,8 @@ CREATE TABLE proteins (
description text,
length integer, -- length of amino acid sequence
mass numeric, -- mass in amu/daltons
content bytea, -- stored markdown for the protein article (TODO: consider having a limit to how big this can be)
refs bytea, -- bibtex references mentioned in the content/article
content text, -- stored markdown for the protein article (TODO: consider having a limit to how big this can be)
refs text, -- bibtex references mentioned in the content/article
species_id integer NOT NULL,
thumbnail bytea, -- thumbnail image of the protein in base64 format
FOREIGN KEY (species_id) REFERENCES species(id) ON UPDATE CASCADE ON DELETE CASCADE
Expand Down
12 changes: 4 additions & 8 deletions backend/src/api/protein.py
Original file line number Diff line number Diff line change
Expand Up @@ -164,10 +164,6 @@ def get_protein_entry(protein_name: str):
) = only_returned_entry

# if byte arrays are present, decode them into a string
if content is not None:
content = bytea_to_str(content)
if refs is not None:
refs = bytea_to_str(refs)
if thumbnail is not None:
thumbnail = bytea_to_str(thumbnail)

Expand Down Expand Up @@ -263,8 +259,8 @@ def upload_protein_entry(body: UploadBody, req: Request):
body.description,
pdb.num_amino_acids,
pdb.mass_daltons,
str_to_bytea(body.content),
str_to_bytea(body.refs),
body.content,
body.refs,
body.species_name,
],
)
Expand Down Expand Up @@ -310,7 +306,7 @@ def edit_protein_entry(body: EditBody, req: Request):
db.execute(
"""UPDATE proteins SET content = %s WHERE name = %s""",
[
str_to_bytea(body.new_content),
body.new_content,
body.old_name if not name_changed else body.new_name,
],
)
Expand All @@ -319,7 +315,7 @@ def edit_protein_entry(body: EditBody, req: Request):
db.execute(
"""UPDATE proteins SET refs = %s WHERE name = %s""",
[
str_to_bytea(body.new_refs),
body.new_refs,
body.old_name if not name_changed else body.new_name,
],
)
Expand Down
54 changes: 37 additions & 17 deletions backend/src/api/search.py
Original file line number Diff line number Diff line change
Expand Up @@ -74,41 +74,61 @@ def get_descriptions(protein_names: list[str]):


def gen_sql_filters(
species_table: str,
proteins_table: str,
species_filter: str | None,
length_filter: RangeFilter | None = None,
mass_filter: RangeFilter | None = None,
) -> str:
filters = [
category_where_clause("species.name", species_filter),
range_where_clause("proteins.length", length_filter),
range_where_clause("proteins.mass", mass_filter),
category_where_clause(f"{species_table}.name", species_filter),
range_where_clause(f"{proteins_table}.length", length_filter),
range_where_clause(f"{proteins_table}.mass", mass_filter),
]
return " AND " + combine_where_clauses(filters) if any(filters) else ""


@router.post("/search/proteins", response_model=SearchProteinsResults)
def search_proteins(body: SearchProteinsBody):
title_query = sanitize_query(body.query)
text_query = sanitize_query(body.query)
with Database() as db:
try:
filter_clauses = gen_sql_filters(
body.species_filter, body.length_filter, body.mass_filter
"species",
"proteins_scores",
body.species_filter,
body.length_filter,
body.mass_filter,
)
entries_query = """SELECT proteins.name,
proteins.description,
proteins.length,
proteins.mass,
threshold = 0
score_filter = (
f"(proteins_scores.name_score >= {threshold} OR proteins_scores.desc_score >= {threshold} OR proteins_scores.content_score >= {threshold})" # show only the scores > 0
if len(text_query) > 0
else "TRUE" # show all scores
)
# cursed shit, edit this at some point
# note that we have a sub query since postgres can't do where clauses on aliased tables
entries_query = """SELECT proteins_scores.name,
proteins_scores.description,
proteins_scores.length,
proteins_scores.mass,
species.name,
proteins.thumbnail
FROM proteins
JOIN species ON species.id = proteins.species_id
WHERE proteins.name ILIKE %s"""
proteins_scores.thumbnail
FROM (SELECT *,
similarity(name, %s) as name_score,
similarity(description, %s) as desc_score,
similarity(content, %s) as content_score
FROM proteins) as proteins_scores
JOIN species ON species.id = proteins_scores.species_id
WHERE {} {}
ORDER BY (proteins_scores.name_score*4 + proteins_scores.desc_score*2 + proteins_scores.content_score) DESC;
""".format(
score_filter, filter_clauses
) # numbers in order by correspond to weighting
log.warn(filter_clauses)
entries_result = db.execute_return(
sanitize_query(entries_query + filter_clauses),
[
f"%{title_query}%",
],
sanitize_query(entries_query),
[text_query, text_query, text_query],
)
if entries_result is not None:
return SearchProteinsResults(
Expand Down
1 change: 1 addition & 0 deletions galaxy/.gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
master_venom_galaxy/
Loading