ydeng/autoBIGS.engine
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Completed updating CLI to be more organized with bettert error messages

Browse Source
This commit is contained in:
Harrison Deng 2025-01-09 07:39:18 +00:00
parent 42d0f56b18
commit 9b8e448512
9 changed files with 107 additions and 87 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
.devcontainer/devcontainer.json
View File

@ -12,7 +12,14 @@
// "forwardPorts": [],
// Use 'postCreateCommand' to run commands after the container is created.
"postCreateCommand": "pip3 install --user -r requirements.txt"
"postCreateCommand": "pip3 install --user -r requirements.txt",
"customizations": {
"vscode": {
"extensions": [
"mechatroner.rainbow-csv"
]
}
}
// Configure tool-specific properties.
// "customizations": {},

8
.vscode/launch.json vendored
View File

@ -6,12 +6,16 @@
"configurations": [
{
"name": "CLI blank",
"name": "automlst info -lschema pubmlst_bordetella_seqdef",
"type": "debugpy",
"request": "launch",
"program": "${workspaceFolder}/src/automlst/cli/program.py",
"console": "integratedTerminal",
"args": [],
"args": [
"info",
"-lschemas",
"pubmlst_bordetella_seqdef"
],
"cwd": "${workspaceFolder}/src",
"env": {
"PYTHONPATH": "${workspaceFolder}/src"

48
src/automlst/cli/exactmatch.py Normal file
View File

@ -0,0 +1,48 @@
from argparse import ArgumentParser
import asyncio
import datetime
from automlst.engine.local.csv import write_mlst_profiles_as_csv
from automlst.engine.local.fasta import read_multiple_fastas
from automlst.engine.remote.databases.bigsdb import BIGSdbIndex
def setup_parser(parser: ArgumentParser):
parser.description = "Returns MLST exact profile matches."
parser.add_argument(
"fastas",
nargs="+",
action='extend',
default=[],
type=str,
help="The FASTA files to process. Multiple can be listed."
)
parser.add_argument(
"seqdefdb",
help="The BIGSdb seqdef database to use for typing."
)
parser.add_argument(
"schema",
type=int,
help="The BIGSdb seqdef database schema ID (integer) to use for typing."
)
parser.add_argument(
"out",
default=f'./{datetime.datetime.now().strftime(r"%Y%m%d%H%M%S")}',
help="The output CSV name (.csv will be appended)."
)
parser.set_defaults(func=run_asynchronously)
async def run(args):
async with BIGSdbIndex() as bigsdb_index:
gen_strings = read_multiple_fastas(args.fastas)
async with await bigsdb_index.build_profiler_from_seqdefdb(args.seqdefdb, args.schema) as mlst_profiler:
mlst_profiles = mlst_profiler.profile_multiple_strings(gen_strings)
await write_mlst_profiles_as_csv(mlst_profiles, args.out)
def run_asynchronously(args):
asyncio.run(run(args))

47
src/automlst/cli/info.py
View File

@ -1,36 +1,38 @@
from argparse import ArgumentParser
import asyncio
from automlst.cli import program
from automlst.engine.remote.databases.bigsdb import BIGSdbIndex
parser = program.subparsers.add_parser(__name__)
def setup_parser(parser: ArgumentParser):
parser.description = "Fetches the latest BIGSdb MLST database definitions."
parser.usage = "test"
parser.add_argument(
"--retrieve-bigsdbs", "-l",
action="store_true",
dest="list_dbs",
required=False,
default=False,
help="Lists all known BIGSdb MLST databases (fetched from known APIs and cached)."
)
parser.add_argument(
"--retrieve-bigsdbs", "-l",
action="store_true",
dest="list_dbs",
required=False,
default=False,
type=bool,
help="Lists all known BIGSdb MLST databases (fetched from known APIs and cached)."
)
parser.add_argument(
"--retrieve-bigsdb-schemas", "-lschemas",
nargs="+",
action="extend",
dest="list_bigsdb_schemas",
required=False,
default=[],
type=str,
help="Lists the known schema IDs for a given BIGSdb sequence definition database name. The name, and then the ID of the schema is given."
)
parser.add_argument(
"--retrieve-bigsdb-schemas", "-lschemas",
nargs="+",
action="extend",
dest="list_bigsdb_schemas",
required=False,
default=[],
type=str,
help="Lists the known schema IDs for a given BIGSdb sequence definition database name"
)
parser.set_defaults(func=run_asynchronously)
async def run(args):
async with BIGSdbIndex() as bigsdb_index:
if args.list_dbs:
known_seqdef_dbs = await bigsdb_index.get_known_seqdef_dbs(force=False)
print(", ".join(known_seqdef_dbs.keys()))
print("\n".join(known_seqdef_dbs.keys()))
for bigsdb_schema_name in args.list_bigsdb_schemas:
schemas = await bigsdb_index.get_schemas_for_seqdefdb(bigsdb_schema_name)
@ -40,4 +42,3 @@ async def run(args):
def run_asynchronously(args):
asyncio.run(run(args))
parser.set_defaults(func=run_asynchronously)

2
src/automlst/cli/meta.py Normal file
View File

@ -0,0 +1,2 @@
def get_module_base_name(name):
return name.split(".")[-1]

55
src/automlst/cli/profile.py
View File

@ -1,55 +0,0 @@
import asyncio
import datetime
from typing import Any, AsyncGenerator, AsyncIterable, Iterable, Sequence, Union
from automlst.cli import program
from automlst.engine.data.genomics import NamedString
from automlst.engine.data.mlst import MLSTProfile
from automlst.engine.local.abif import read_abif, reference_consensus_assembly
from automlst.engine.local.csv import write_mlst_profiles_as_csv
from automlst.engine.local.fasta import read_fasta, read_multiple_fastas
from automlst.engine.remote.databases.bigsdb import BIGSdbIndex, BigSDBMLSTProfiler
parser = program.subparsers.add_parser(__name__)
parser.add_argument(
"--fasta", "-fa", "-fst",
nargs="+",
action='extend',
dest="fastas",
required=False,
default=[],
type=str,
help="The FASTA files to process. Multiple can be listed."
)
parser.add_argument(
"seqdefdb",
help="The BIGSdb seqdef database to use for typing."
)
parser.add_argument(
"schema",
type=int,
help="The BIGSdb seqdef database schema ID (integer) to use for typing."
)
parser.add_argument(
"out",
default=f'./{datetime.datetime.now().strftime(r"%Y%m%d%H%M%S")}',
help="The output CSV name (.csv will be appended)."
)
async def run(args):
async with BIGSdbIndex() as bigsdb_index:
gen_strings = read_multiple_fastas(args.fastas)
async with await bigsdb_index.build_profiler_from_seqdefdb(args.seqdefdb, args.schema) as mlst_profiler:
mlst_profiles = mlst_profiler.profile_multiple_strings(gen_strings)
await write_mlst_profiles_as_csv(mlst_profiles, args.out)
def run_asynchronously(args):
asyncio.run(run(args))
parser.set_defaults(func=run_asynchronously)

7
src/automlst/cli/program.py
View File

@ -4,6 +4,8 @@ import datetime
from os import path
import os
from automlst.cli import exactmatch, info
from automlst.cli.meta import get_module_base_name
from automlst.engine.data.genomics import NamedString
from automlst.engine.local.abif import read_abif
from automlst.engine.local.csv import write_mlst_profiles_as_csv
@ -13,10 +15,13 @@ from automlst.engine.remote.databases.bigsdb import BIGSdbIndex
root_parser = argparse.ArgumentParser()
subparsers = root_parser.add_subparsers(required=True)
info.setup_parser(subparsers.add_parser(get_module_base_name(info.__name__)))
exactmatch.setup_parser(subparsers.add_parser(get_module_base_name(exactmatch.__name__)))
def run():
args = root_parser.parse_args()
args.func(args)
if __name__ == "__main__":
run()

2
src/automlst/engine/local/csv.py
View File

@ -21,7 +21,7 @@ async def write_mlst_profiles_as_csv(mlst_profiles_iterable: AsyncIterable[tuple
writer: Union[csv.DictWriter, None] = None
async for name, mlst_profile in mlst_profiles_iterable:
if writer is None:
header = ["st", "clonal-complex", "id", *mlst_profile.alleles.keys()]
header = ["id", "st", "clonal-complex", *mlst_profile.alleles.keys()]
writer = csv.DictWriter(filehandle, fieldnames=header)
writer.writeheader()
row_dictionary = {

16
src/automlst/engine/remote/databases/bigsdb.py
View File

@ -10,7 +10,9 @@ from automlst.engine.data.mlst import Allele, MLSTProfile
class BigSDBMLSTProfiler(AbstractAsyncContextManager):
def __init__(self, database_api: str, database_name: str, schema_id: int):
self._base_url = f"{database_api}/db/{database_name}/schemes/{schema_id}/"
self._database_name = database_name
self._schema_id = schema_id
self._base_url = f"{database_api}/db/{self._database_name}/schemes/{self._schema_id}/"
self._http_client = ClientSession(self._base_url, timeout=ClientTimeout(10000))
async def __aenter__(self):
@ -26,6 +28,9 @@ class BigSDBMLSTProfiler(AbstractAsyncContextManager):
if "exact_matches" not in sequence_response:
# TODO throw exception for not finding matches.
pass
if "exact_matches" not in sequence_response:
raise ValueError(f"Unable to find exact matches in \"{self._database_name}\" under schema ID \"{self._schema_id}\".")
exact_matches: dict[str, Sequence[dict[str, str]]] = sequence_response["exact_matches"]
for allele_loci, alleles in exact_matches.items():
for allele in alleles:
@ -100,12 +105,15 @@ class BIGSdbIndex(AbstractAsyncContextManager):
return self._known_seqdef_dbs_origin
async def get_bigsdb_api_from_seqdefdb(self, seqdef_db_name: str) -> str:
return (await self.get_known_seqdef_dbs())[seqdef_db_name]
known_databases = await self.get_known_seqdef_dbs()
if seqdef_db_name not in known_databases:
raise ValueError(f"The database \"{seqdef_db_name}\" could not be found.")
return known_databases[seqdef_db_name]
async def get_schemas_for_seqdefdb(self, seqdef_db_name: str, force: bool = False) -> Mapping[str, int]:
if self._seqdefdb_schemas[seqdef_db_name] is not None and not force:
if seqdef_db_name in self._seqdefdb_schemas and not force:
return self._seqdefdb_schemas[seqdef_db_name] # type: ignore since it's guaranteed to not be none by conditional
uri_path = f"{await self.get_bigsdb_api_from_seqdefdb(seqdef_db_name)}/{seqdef_db_name}/schemes"
uri_path = f"{await self.get_bigsdb_api_from_seqdefdb(seqdef_db_name)}/db/{seqdef_db_name}/schemes"
async with self._http_client.get(uri_path) as response:
response_json = await response.json()
schema_descriptions: Mapping[str, int] = dict()