Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 62ce1c9b2f |
@ -1,11 +0,0 @@
|
||||
FROM mcr.microsoft.com/devcontainers/anaconda:1-3
|
||||
|
||||
# Copy environment.yml (if found) to a temp location so we update the environment. Also
|
||||
# copy "noop.txt" so the COPY instruction does not fail if no environment.yml exists.
|
||||
COPY environment.yml* .devcontainer/noop.txt /tmp/conda-tmp/
|
||||
RUN if [ -f "/tmp/conda-tmp/environment.yml" ]; then umask 0002 && /opt/conda/bin/conda env update -n base -f /tmp/conda-tmp/environment.yml; fi \
|
||||
&& rm -rf /tmp/conda-tmp
|
||||
|
||||
# [Optional] Uncomment this section to install additional OS packages.
|
||||
# RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
|
||||
# && apt-get -y install --no-install-recommends <your-package-list-here>
|
||||
@ -1,11 +1,9 @@
|
||||
// For format details, see https://aka.ms/devcontainer.json. For config options, see the
|
||||
// README at: https://github.com/devcontainers/templates/tree/main/src/anaconda
|
||||
// README at: https://github.com/devcontainers/templates/tree/main/src/python
|
||||
{
|
||||
"name": "Anaconda (Python 3)",
|
||||
"build": {
|
||||
"context": "..",
|
||||
"dockerfile": "Dockerfile"
|
||||
}
|
||||
"name": "Python 3",
|
||||
// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
|
||||
"image": "mcr.microsoft.com/devcontainers/python:1-3.12-bullseye",
|
||||
|
||||
// Features to add to the dev container. More info: https://containers.dev/features.
|
||||
// "features": {},
|
||||
@ -14,7 +12,14 @@
|
||||
// "forwardPorts": [],
|
||||
|
||||
// Use 'postCreateCommand' to run commands after the container is created.
|
||||
// "postCreateCommand": "python --version",
|
||||
"postCreateCommand": "pip3 install --user -r requirements.txt",
|
||||
"customizations": {
|
||||
"vscode": {
|
||||
"extensions": [
|
||||
"mechatroner.rainbow-csv"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
// Configure tool-specific properties.
|
||||
// "customizations": {},
|
||||
|
||||
@ -1,3 +0,0 @@
|
||||
This file copied into the container along with environment.yml* from the parent
|
||||
folder. This file is included to prevents the Dockerfile COPY instruction from
|
||||
failing if no environment.yml is found.
|
||||
159
.gitignore
vendored
159
.gitignore
vendored
@ -1,6 +1,6 @@
|
||||
# File created using '.gitignore Generator' for Visual Studio Code: https://bit.ly/vscode-gig
|
||||
# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,linux,python
|
||||
# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,linux,python
|
||||
# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,svelte,python,linux,node
|
||||
# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,svelte,python,linux,node
|
||||
|
||||
### Linux ###
|
||||
*~
|
||||
@ -17,6 +17,146 @@
|
||||
# .nfs files are created when an open file is removed but is still being accessed
|
||||
.nfs*
|
||||
|
||||
### Node ###
|
||||
# Logs
|
||||
logs
|
||||
*.log
|
||||
npm-debug.log*
|
||||
yarn-debug.log*
|
||||
yarn-error.log*
|
||||
lerna-debug.log*
|
||||
.pnpm-debug.log*
|
||||
|
||||
# Diagnostic reports (https://nodejs.org/api/report.html)
|
||||
report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
|
||||
|
||||
# Runtime data
|
||||
pids
|
||||
*.pid
|
||||
*.seed
|
||||
*.pid.lock
|
||||
|
||||
# Directory for instrumented libs generated by jscoverage/JSCover
|
||||
lib-cov
|
||||
|
||||
# Coverage directory used by tools like istanbul
|
||||
coverage
|
||||
*.lcov
|
||||
|
||||
# nyc test coverage
|
||||
.nyc_output
|
||||
|
||||
# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
|
||||
.grunt
|
||||
|
||||
# Bower dependency directory (https://bower.io/)
|
||||
bower_components
|
||||
|
||||
# node-waf configuration
|
||||
.lock-wscript
|
||||
|
||||
# Compiled binary addons (https://nodejs.org/api/addons.html)
|
||||
build/Release
|
||||
|
||||
# Dependency directories
|
||||
node_modules/
|
||||
jspm_packages/
|
||||
|
||||
# Snowpack dependency directory (https://snowpack.dev/)
|
||||
web_modules/
|
||||
|
||||
# TypeScript cache
|
||||
*.tsbuildinfo
|
||||
|
||||
# Optional npm cache directory
|
||||
.npm
|
||||
|
||||
# Optional eslint cache
|
||||
.eslintcache
|
||||
|
||||
# Optional stylelint cache
|
||||
.stylelintcache
|
||||
|
||||
# Microbundle cache
|
||||
.rpt2_cache/
|
||||
.rts2_cache_cjs/
|
||||
.rts2_cache_es/
|
||||
.rts2_cache_umd/
|
||||
|
||||
# Optional REPL history
|
||||
.node_repl_history
|
||||
|
||||
# Output of 'npm pack'
|
||||
*.tgz
|
||||
|
||||
# Yarn Integrity file
|
||||
.yarn-integrity
|
||||
|
||||
# dotenv environment variable files
|
||||
.env
|
||||
.env.development.local
|
||||
.env.test.local
|
||||
.env.production.local
|
||||
.env.local
|
||||
|
||||
# parcel-bundler cache (https://parceljs.org/)
|
||||
.cache
|
||||
.parcel-cache
|
||||
|
||||
# Next.js build output
|
||||
.next
|
||||
out
|
||||
|
||||
# Nuxt.js build / generate output
|
||||
.nuxt
|
||||
dist
|
||||
|
||||
# Gatsby files
|
||||
.cache/
|
||||
# Comment in the public line in if your project uses Gatsby and not Next.js
|
||||
# https://nextjs.org/blog/next-9-1#public-directory-support
|
||||
# public
|
||||
|
||||
# vuepress build output
|
||||
.vuepress/dist
|
||||
|
||||
# vuepress v2.x temp and cache directory
|
||||
.temp
|
||||
|
||||
# Docusaurus cache and generated files
|
||||
.docusaurus
|
||||
|
||||
# Serverless directories
|
||||
.serverless/
|
||||
|
||||
# FuseBox cache
|
||||
.fusebox/
|
||||
|
||||
# DynamoDB Local files
|
||||
.dynamodb/
|
||||
|
||||
# TernJS port file
|
||||
.tern-port
|
||||
|
||||
# Stores VSCode versions used for testing VSCode extensions
|
||||
.vscode-test
|
||||
|
||||
# yarn v2
|
||||
.yarn/cache
|
||||
.yarn/unplugged
|
||||
.yarn/build-state.yml
|
||||
.yarn/install-state.gz
|
||||
.pnp.*
|
||||
|
||||
### Node Patch ###
|
||||
# Serverless Webpack directories
|
||||
.webpack/
|
||||
|
||||
# Optional stylelint cache
|
||||
|
||||
# SvelteKit build / generate output
|
||||
.svelte-kit
|
||||
|
||||
### Python ###
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
@ -62,7 +202,6 @@ htmlcov/
|
||||
.nox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
@ -76,7 +215,6 @@ cover/
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
@ -140,7 +278,6 @@ celerybeat.pid
|
||||
*.sage.py
|
||||
|
||||
# Environments
|
||||
.env
|
||||
.venv
|
||||
env/
|
||||
venv/
|
||||
@ -189,6 +326,13 @@ poetry.toml
|
||||
# LSP config files
|
||||
pyrightconfig.json
|
||||
|
||||
### Svelte ###
|
||||
# gitignore template for the SvelteKit, frontend web component framework
|
||||
# website: https://kit.svelte.dev/
|
||||
|
||||
.svelte-kit/
|
||||
package
|
||||
|
||||
### VisualStudioCode ###
|
||||
.vscode/*
|
||||
!.vscode/settings.json
|
||||
@ -208,8 +352,9 @@ pyrightconfig.json
|
||||
.history
|
||||
.ionide
|
||||
|
||||
# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,linux,python
|
||||
# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,svelte,python,linux,node
|
||||
|
||||
# Custom rules (everything added below won't be overriden by 'Generate .gitignore File' if you use 'Update' option)
|
||||
|
||||
conda-bld
|
||||
output
|
||||
*.private.*
|
||||
5
.vscode/extensions.json
vendored
5
.vscode/extensions.json
vendored
@ -1,5 +0,0 @@
|
||||
{
|
||||
"recommendations": [
|
||||
"piotrpalarz.vscode-gitignore-generator"
|
||||
]
|
||||
}
|
||||
14
Jenkinsfile
vendored
14
Jenkinsfile
vendored
@ -2,14 +2,14 @@ pipeline {
|
||||
agent {
|
||||
kubernetes {
|
||||
cloud 'rsys-devel'
|
||||
defaultContainer 'miniforge3'
|
||||
inheritFrom 'miniforge'
|
||||
defaultContainer 'pip'
|
||||
inheritFrom 'pip'
|
||||
}
|
||||
}
|
||||
stages {
|
||||
stage("install") {
|
||||
steps {
|
||||
sh 'conda env update -n base -f environment.yml'
|
||||
sh 'python -m pip install -r requirements.txt'
|
||||
}
|
||||
}
|
||||
stage("unit tests") {
|
||||
@ -22,14 +22,11 @@ pipeline {
|
||||
stage("build") {
|
||||
steps {
|
||||
sh "python -m build"
|
||||
sh "grayskull pypi dist/*.tar.gz --maintainers 'Harrison Deng'"
|
||||
sh "python scripts/patch_recipe.py"
|
||||
sh 'conda build autobigs-engine -c bioconda --output-folder conda-bld --verify'
|
||||
}
|
||||
}
|
||||
stage("archive") {
|
||||
steps {
|
||||
archiveArtifacts artifacts: 'dist/*.tar.gz, dist/*.whl, conda-bld/**/*.conda', fingerprint: true, followSymlinks: false, onlyIfSuccessful: true
|
||||
archiveArtifacts artifacts: 'dist/*.tar.gz, dist/*.whl', fingerprint: true, followSymlinks: false, onlyIfSuccessful: true
|
||||
}
|
||||
}
|
||||
stage("publish") {
|
||||
@ -39,8 +36,7 @@ pipeline {
|
||||
CREDS = credentials('username-password-rs-git')
|
||||
}
|
||||
steps {
|
||||
sh 'python -m twine upload --repository-url https://git.reslate.systems/api/packages/ydeng/pypi -u ${CREDS_USR} -p ${CREDS_PSW} --non-interactive --disable-progress-bar --verbose dist/*'
|
||||
sh 'curl --user ${CREDS_USR}:${CREDS_PSW} --upload-file conda-bld/**/*.conda https://git.reslate.systems/api/packages/${CREDS_USR}/conda/$(basename conda-bld/**/*.conda)'
|
||||
sh returnStatus: true, script: 'python -m twine upload --repository-url https://git.reslate.systems/api/packages/ydeng/pypi -u ${CREDS_USR} -p ${CREDS_PSW} --non-interactive --disable-progress-bar --verbose dist/*'
|
||||
}
|
||||
}
|
||||
stage ("pypi.org") {
|
||||
|
||||
17
README.md
17
README.md
@ -1,7 +1,8 @@
|
||||
# autoBIGS.Engine
|
||||
# autoBIGS.engine
|
||||
|
||||
A python library implementing common BIGSdb MLST schemes and databases accesses for the purpose of typing sequences automatically. Implementation follows the RESTful API outlined by the official [BIGSdb documentation](https://bigsdb.readthedocs.io/en/latest/rest.html) up to `V1.50.0`.
|
||||
|
||||
|
||||
## Features
|
||||
|
||||
Briefly, this library can:
|
||||
@ -22,4 +23,16 @@ Then, it's as easy as running `pip install autobigs-engine` in any terminal that
|
||||
|
||||
### CLI usage
|
||||
|
||||
This is a independent python library and thus does not have any form of direct user interface. One way of using it could be to create your own Python script that makes calls to this libraries functions. Alternatively, you may use `autobigs-cli`, a `Python` package that implements a CLI for calling this library.
|
||||
This is a independent python library and thus does not have any form of direct user interface. One way of using it could be to create your own Python script that makes calls to this libraries functions. Alternatively, you may use `autobigs-cli`, a `Python` package that implements a CLI for calling this library.
|
||||
|
||||
## Versioning
|
||||
|
||||
the autoBIGS project follows [semantic versioning](https://semver.org/) where the three numbers may be interpreted as MAJOR.MINOR.PATCH.
|
||||
|
||||
Note regarding major version 0 ([spec item 4](https://semver.org/#spec-item-4)), the following adaptation of semantic versioning definition is as follows:
|
||||
|
||||
1. Given x.Y.z, Y is only incremented when a backwards incompatible change is made.
|
||||
|
||||
2. Given x.y.Z, Z is only incremented when a backwards compatible change is made.
|
||||
|
||||
Versions of autoBIGS items with a major version number of 0 will introduce numerous changes and patches. As such, changes between such versions should be considered highly variable.
|
||||
@ -1,44 +0,0 @@
|
||||
{% set name = "autoBIGS.engine" %}
|
||||
{% set version = "0.12.1.dev1+gb8cebb8.d20250221" %}
|
||||
|
||||
package:
|
||||
name: {{ name|lower|replace(".", "-") }}
|
||||
version: {{ version }}
|
||||
|
||||
source:
|
||||
url: file:///workspaces/autoBIGS.engine/dist/autobigs_engine-0.12.1.dev1%2Bgb8cebb8.d20250221.tar.gz
|
||||
sha256: c86441b94f935cfa414ff28ca4c026a070e0fb15988ea3bb7d1a942859a09b16
|
||||
|
||||
build:
|
||||
noarch: python
|
||||
script: {{ PYTHON }} -m pip install . -vv --no-deps --no-build-isolation
|
||||
number: 0
|
||||
run_exports:
|
||||
- {{ pin_subpackage( name|lower|replace(".", "-"), max_pin="x.x") }}
|
||||
requirements:
|
||||
host:
|
||||
- python >=3.12
|
||||
- setuptools >=64
|
||||
- setuptools-scm >=8
|
||||
- pip
|
||||
run:
|
||||
- python >=3.12
|
||||
- biopython ==1.85
|
||||
- aiohttp ==3.11.*
|
||||
|
||||
test:
|
||||
imports:
|
||||
- autobigs
|
||||
commands:
|
||||
- pip check
|
||||
requires:
|
||||
- pip
|
||||
|
||||
about:
|
||||
summary: A library to rapidly fetch fetch MLST profiles given sequences for various diseases.
|
||||
license: GPL-3.0-or-later
|
||||
license_file: LICENSE
|
||||
home: https://github.com/Syph-and-VPD-Lab/autoBIGS.engine
|
||||
extra:
|
||||
recipe-maintainers:
|
||||
- Harrison Deng
|
||||
@ -1,16 +0,0 @@
|
||||
name: ci
|
||||
channels:
|
||||
- bioconda
|
||||
- conda-forge
|
||||
dependencies:
|
||||
- aiohttp==3.11.*
|
||||
- biopython==1.85
|
||||
- pytest
|
||||
- pytest-asyncio
|
||||
- python-build
|
||||
- conda-build
|
||||
- twine==6.0.1
|
||||
- setuptools_scm
|
||||
- pytest-cov
|
||||
- grayskull
|
||||
- curl
|
||||
8
requirements.txt
Normal file
8
requirements.txt
Normal file
@ -0,0 +1,8 @@
|
||||
aiohttp[speedups]==3.11.*
|
||||
biopython==1.85
|
||||
pytest
|
||||
pytest-asyncio
|
||||
build
|
||||
twine
|
||||
setuptools_scm
|
||||
pytest-cov
|
||||
@ -1,103 +0,0 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
import argparse
|
||||
from os import fdopen, path
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
from sys import argv
|
||||
import tempfile
|
||||
|
||||
INDENTATION = " "
|
||||
GRAYSKULL_OUTPUT_PATH = "autoBIGS.engine"
|
||||
RUN_EXPORTED_VALUE = r'{{ pin_subpackage( name|lower|replace(".", "-"), max_pin="x.x") }}'
|
||||
LICENSE_SUFFIX = "-or-later"
|
||||
HOME_PAGE = "https://github.com/Syph-and-VPD-Lab/autoBIGS.engine"
|
||||
|
||||
def _calc_indentation(line: str):
|
||||
return len(re.findall(INDENTATION, line.split(line.strip())[0])) if line != "\n" else 0
|
||||
|
||||
def read_grayskull_output():
|
||||
original_recipe = path.abspath(GRAYSKULL_OUTPUT_PATH)
|
||||
original_meta = path.join(original_recipe, "meta.yaml")
|
||||
meta_file = open(original_meta)
|
||||
lines = meta_file.readlines()
|
||||
meta_file.close()
|
||||
return lines
|
||||
|
||||
def update_naming_scheme(lines):
|
||||
modified_lines = []
|
||||
for line in lines:
|
||||
matches = re.finditer(r"\{\{\s*name\|lower()\s+\}\}", line)
|
||||
modified_line = line
|
||||
for match in matches:
|
||||
modified_line = modified_line[:match.start(1)] + r'|replace(".", "-")' + modified_line[match.end(1):]
|
||||
modified_lines.append(modified_line)
|
||||
return modified_lines
|
||||
|
||||
def inject_run_exports(lines: list[str]):
|
||||
package_indent = False
|
||||
modified_lines = []
|
||||
for line in lines:
|
||||
indentation_count = _calc_indentation(line)
|
||||
if line == "build:\n" and indentation_count == 0:
|
||||
package_indent = True
|
||||
modified_lines.append(line)
|
||||
elif package_indent and indentation_count == 0:
|
||||
modified_lines.append(INDENTATION*1 + "run_exports:\n")
|
||||
modified_lines.append(INDENTATION*2 + "- " + RUN_EXPORTED_VALUE + "\n")
|
||||
package_indent = False
|
||||
else:
|
||||
modified_lines.append(line)
|
||||
return modified_lines
|
||||
|
||||
def suffix_license(lines: list[str]):
|
||||
about_indent = False
|
||||
modified_lines = []
|
||||
for line in lines:
|
||||
indentation_count = _calc_indentation(line)
|
||||
if line == "about:\n" and indentation_count == 0:
|
||||
about_indent = True
|
||||
modified_lines.append(line)
|
||||
elif about_indent and indentation_count == 1 and line.lstrip().startswith("license:"):
|
||||
modified_lines.append(line.rstrip() + LICENSE_SUFFIX + "\n")
|
||||
about_indent = False
|
||||
else:
|
||||
modified_lines.append(line)
|
||||
return modified_lines
|
||||
|
||||
def inject_home_page(lines: list[str]):
|
||||
about_indent = False
|
||||
modified_lines = []
|
||||
for line in lines:
|
||||
indentation_count = _calc_indentation(line)
|
||||
if line == "about:\n" and indentation_count == 0:
|
||||
about_indent = True
|
||||
modified_lines.append(line)
|
||||
elif about_indent and indentation_count == 0:
|
||||
modified_lines.append(INDENTATION + "home: " + HOME_PAGE + "\n")
|
||||
about_indent = False
|
||||
else:
|
||||
modified_lines.append(line)
|
||||
return modified_lines
|
||||
|
||||
def write_to_original(lines: list[str]):
|
||||
original_recipe = path.abspath(GRAYSKULL_OUTPUT_PATH)
|
||||
original_meta = path.join(original_recipe, "meta.yaml")
|
||||
with open(original_meta, "w") as file:
|
||||
file.writelines(lines)
|
||||
|
||||
def rename_recipe_dir():
|
||||
new_recipe_name = path.abspath(path.join(GRAYSKULL_OUTPUT_PATH.replace(".", "-").lower()))
|
||||
shutil.rmtree(new_recipe_name, ignore_errors=True)
|
||||
os.replace(path.abspath(GRAYSKULL_OUTPUT_PATH), new_recipe_name)
|
||||
|
||||
if __name__ == "__main__":
|
||||
original_grayskull_out = read_grayskull_output()
|
||||
modified_recipe_meta = None
|
||||
modified_recipe_meta = update_naming_scheme(original_grayskull_out)
|
||||
modified_recipe_meta = inject_run_exports(modified_recipe_meta)
|
||||
modified_recipe_meta = suffix_license(modified_recipe_meta)
|
||||
modified_recipe_meta = inject_home_page(modified_recipe_meta)
|
||||
write_to_original(modified_recipe_meta)
|
||||
rename_recipe_dir()
|
||||
@ -22,15 +22,15 @@ from Bio.Align import PairwiseAligner
|
||||
class BIGSdbMLSTProfiler(AbstractAsyncContextManager):
|
||||
|
||||
@abstractmethod
|
||||
def determine_mlst_allele_variants(self, query_sequence_strings: Union[Iterable[Union[NamedString, str]], Union[NamedString, str]]) -> AsyncGenerator[Union[Allele, tuple[str, Allele]], Any]:
|
||||
def determine_mlst_allele_variants(self, query_sequence_strings: Iterable[str]) -> AsyncGenerator[Allele, Any]:
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
async def determine_mlst_st(self, alleles: Union[AsyncIterable[Union[Allele, tuple[str, Allele]]], Iterable[Union[Allele, tuple[str, Allele]]]]) -> Union[MLSTProfile, NamedMLSTProfile]:
|
||||
async def determine_mlst_st(self, alleles: Union[AsyncIterable[Allele], Iterable[Allele]]) -> MLSTProfile:
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
async def profile_string(self, query_sequence_strings: Iterable[Union[NamedString, str]]) -> Union[NamedMLSTProfile, MLSTProfile]:
|
||||
async def profile_string(self, query_sequence_strings: Iterable[str]) -> MLSTProfile:
|
||||
pass
|
||||
|
||||
@abstractmethod
|
||||
@ -52,14 +52,14 @@ class RemoteBIGSdbMLSTProfiler(BIGSdbMLSTProfiler):
|
||||
async def __aenter__(self):
|
||||
return self
|
||||
|
||||
async def determine_mlst_allele_variants(self, query_sequence_strings: Union[Iterable[Union[NamedString, str]], Union[NamedString, str]]) -> AsyncGenerator[Union[Allele, tuple[str, Allele]], Any]:
|
||||
async def determine_mlst_allele_variants(self, query_sequence_strings: Union[Iterable[str], str]) -> AsyncGenerator[Allele, Any]:
|
||||
# See https://bigsdb.pasteur.fr/api/db/pubmlst_bordetella_seqdef/schemes
|
||||
uri_path = "sequence"
|
||||
if isinstance(query_sequence_strings, str) or isinstance(query_sequence_strings, NamedString):
|
||||
if isinstance(query_sequence_strings, str):
|
||||
query_sequence_strings = [query_sequence_strings]
|
||||
for sequence_string in query_sequence_strings:
|
||||
async with self._http_client.post(uri_path, json={
|
||||
"sequence": sequence_string if isinstance(sequence_string, str) else sequence_string.sequence,
|
||||
"sequence": sequence_string,
|
||||
"partial_matches": True
|
||||
}) as response:
|
||||
sequence_response: dict = await response.json()
|
||||
@ -70,8 +70,7 @@ class RemoteBIGSdbMLSTProfiler(BIGSdbMLSTProfiler):
|
||||
for allele_loci, alleles in exact_matches.items():
|
||||
for allele in alleles:
|
||||
alelle_id = allele["allele_id"]
|
||||
result_allele = Allele(allele_locus=allele_loci, allele_variant=alelle_id, partial_match_profile=None)
|
||||
yield result_allele if isinstance(sequence_string, str) else (sequence_string.name, result_allele)
|
||||
yield Allele(allele_locus=allele_loci, allele_variant=alelle_id, partial_match_profile=None)
|
||||
elif "partial_matches" in sequence_response:
|
||||
partial_matches: dict[str, dict[str, Union[str, float, int]]] = sequence_response["partial_matches"]
|
||||
for allele_loci, partial_match in partial_matches.items():
|
||||
@ -83,33 +82,23 @@ class RemoteBIGSdbMLSTProfiler(BIGSdbMLSTProfiler):
|
||||
gaps=int(partial_match["gaps"]),
|
||||
match_metric=int(partial_match["bitscore"])
|
||||
)
|
||||
result_allele = Allele(
|
||||
yield Allele(
|
||||
allele_locus=allele_loci,
|
||||
allele_variant=str(partial_match["allele"]),
|
||||
partial_match_profile=partial_match_profile
|
||||
)
|
||||
yield result_allele if isinstance(sequence_string, str) else (sequence_string.name, result_allele)
|
||||
else:
|
||||
raise NoBIGSdbMatchesException(self._database_name, self._schema_id, sequence_string.name if isinstance(sequence_string, NamedString) else None)
|
||||
raise NoBIGSdbMatchesException(self._database_name, self._schema_id)
|
||||
|
||||
async def determine_mlst_st(self, alleles: Union[AsyncIterable[Union[Allele, tuple[str, Allele]]], Iterable[Union[Allele, tuple[str, Allele]]]]) -> Union[MLSTProfile, NamedMLSTProfile]:
|
||||
async def determine_mlst_st(self, alleles: Union[AsyncIterable[Allele], Iterable[Allele]]) -> MLSTProfile:
|
||||
uri_path = "designations"
|
||||
allele_request_dict: dict[str, list[dict[str, str]]] = defaultdict(list)
|
||||
names_list = []
|
||||
def insert_allele_to_request_dict(allele: Union[Allele, tuple[str, Allele]]):
|
||||
if isinstance(allele, Allele):
|
||||
allele_val = allele
|
||||
else:
|
||||
allele_val = allele[1]
|
||||
names_list.append(allele[0])
|
||||
allele_request_dict[allele_val.allele_locus].append({"allele": str(allele_val.allele_variant)})
|
||||
|
||||
if isinstance(alleles, AsyncIterable):
|
||||
async for allele in alleles:
|
||||
insert_allele_to_request_dict(allele)
|
||||
allele_request_dict[allele.allele_locus].append({"allele": str(allele.allele_variant)})
|
||||
else:
|
||||
for allele in alleles:
|
||||
insert_allele_to_request_dict(allele)
|
||||
allele_request_dict[allele.allele_locus].append({"allele": str(allele.allele_variant)})
|
||||
request_json = {
|
||||
"designations": allele_request_dict
|
||||
}
|
||||
@ -122,33 +111,30 @@ class RemoteBIGSdbMLSTProfiler(BIGSdbMLSTProfiler):
|
||||
schema_fields_returned.setdefault("clonal_complex", "unknown")
|
||||
schema_exact_matches: dict = response_json["exact_matches"]
|
||||
for exact_match_locus, exact_match_alleles in schema_exact_matches.items():
|
||||
if len(exact_match_alleles) > 1:
|
||||
raise ValueError(f"Unexpected number of alleles returned for exact match (Expected 1, retrieved {len(exact_match_alleles)})")
|
||||
allele_set.add(Allele(exact_match_locus, exact_match_alleles[0]["allele_id"], None))
|
||||
if len(allele_set) == 0:
|
||||
raise ValueError("Passed in no alleles.")
|
||||
result_mlst_profile = MLSTProfile(allele_set, schema_fields_returned["ST"], schema_fields_returned["clonal_complex"])
|
||||
if len(names_list) > 0:
|
||||
result_mlst_profile = NamedMLSTProfile(str(tuple(names_list)), result_mlst_profile)
|
||||
return result_mlst_profile
|
||||
return MLSTProfile(allele_set, schema_fields_returned["ST"], schema_fields_returned["clonal_complex"])
|
||||
|
||||
async def profile_string(self, query_sequence_strings: Iterable[Union[NamedString, str]]) -> Union[NamedMLSTProfile, MLSTProfile]:
|
||||
async def profile_string(self, query_sequence_strings: Iterable[str]) -> MLSTProfile:
|
||||
alleles = self.determine_mlst_allele_variants(query_sequence_strings)
|
||||
return await self.determine_mlst_st(alleles)
|
||||
|
||||
async def profile_multiple_strings(self, query_named_string_groups: AsyncIterable[Iterable[NamedString]], stop_on_fail: bool = False) -> AsyncGenerator[NamedMLSTProfile, Any]:
|
||||
tasks = []
|
||||
async for named_strings in query_named_string_groups:
|
||||
tasks.append(self.profile_string(named_strings))
|
||||
for task in asyncio.as_completed(tasks):
|
||||
try:
|
||||
yield await task
|
||||
except NoBIGSdbMatchesException as e:
|
||||
if stop_on_fail:
|
||||
raise e
|
||||
causal_name = e.get_causal_query_name()
|
||||
if causal_name is None:
|
||||
raise ValueError("Missing query name despite requiring names.")
|
||||
else:
|
||||
yield NamedMLSTProfile(causal_name, None)
|
||||
names: list[str] = list()
|
||||
sequences: list[str] = list()
|
||||
for named_string in named_strings:
|
||||
names.append(named_string.name)
|
||||
sequences.append(named_string.sequence)
|
||||
try:
|
||||
yield NamedMLSTProfile("-".join(names), (await self.profile_string(sequences)))
|
||||
except NoBIGSdbMatchesException as e:
|
||||
if stop_on_fail:
|
||||
raise e
|
||||
yield NamedMLSTProfile("-".join(names), None)
|
||||
|
||||
async def close(self):
|
||||
await self._http_client.close()
|
||||
|
||||
@ -5,12 +5,8 @@ class BIGSDbDatabaseAPIException(Exception):
|
||||
|
||||
|
||||
class NoBIGSdbMatchesException(BIGSDbDatabaseAPIException):
|
||||
def __init__(self, database_name: str, database_schema_id: int, query_name: Union[None, str], *args):
|
||||
self._query_name = query_name
|
||||
def __init__(self, database_name: str, database_schema_id: int, *args):
|
||||
super().__init__(f"No matches found with schema with ID {database_schema_id} in the database \"{database_name}\".", *args)
|
||||
|
||||
def get_causal_query_name(self) -> Union[str, None]:
|
||||
return self._query_name
|
||||
|
||||
class NoBIGSdbExactMatchesException(NoBIGSdbMatchesException):
|
||||
def __init__(self, database_name: str, database_schema_id: int, *args):
|
||||
|
||||
@ -13,8 +13,5 @@ async def read_fasta(handle: Union[str, TextIOWrapper]) -> Iterable[NamedString]
|
||||
return results
|
||||
|
||||
async def read_multiple_fastas(handles: Iterable[Union[str, TextIOWrapper]]) -> AsyncGenerator[Iterable[NamedString], Any]:
|
||||
tasks = []
|
||||
for handle in handles:
|
||||
tasks.append(read_fasta(handle))
|
||||
for task in asyncio.as_completed(tasks):
|
||||
yield await task
|
||||
yield await read_fasta(handle)
|
||||
Loading…
x
Reference in New Issue
Block a user