Initial attempt at switching to a conda based build environment

.devcontainer/Dockerfile

@@ -0,0 +1,11 @@
+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>

.devcontainer/devcontainer.json

@@ -1,9 +1,11 @@
 // For format details, see https://aka.ms/devcontainer.json. For config options, see the
-// README at: https://github.com/devcontainers/templates/tree/main/src/python
+// README at: https://github.com/devcontainers/templates/tree/main/src/anaconda
 {
-	"name": "Python 3",
+	"name": "Anaconda (Python 3)",
-	// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+	"build": { 
-	"image": "mcr.microsoft.com/devcontainers/python:1-3.12-bullseye",
+		"context": "..",
+		"dockerfile": "Dockerfile"
+	}
 
 	// Features to add to the dev container. More info: https://containers.dev/features.
 	// "features": {},
@@ -12,14 +14,7 @@
 	// "forwardPorts": [],
 
 	// Use 'postCreateCommand' to run commands after the container is created.
-	"postCreateCommand": "pip3 install --user -r requirements.txt",
+	// "postCreateCommand": "python --version",
-	"customizations": {
-		"vscode": {
-			"extensions": [
-				"mechatroner.rainbow-csv"
-			]
-		}
-	}
 
 	// Configure tool-specific properties.
 	// "customizations": {},

.devcontainer/noop.txt

@@ -0,0 +1,3 @@
+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.

.gitignore

@@ -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,svelte,python,linux,node
+# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,linux,python
-# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,svelte,python,linux,node
+# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,linux,python
 
 ### Linux ###
 *~
@@ -17,146 +17,6 @@
 # .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__/
@@ -202,6 +62,7 @@ htmlcov/
 .nox/
 .coverage
 .coverage.*
+.cache
 nosetests.xml
 coverage.xml
 *.cover
@@ -215,6 +76,7 @@ cover/
 *.pot
 
 # Django stuff:
+*.log
 local_settings.py
 db.sqlite3
 db.sqlite3-journal
@@ -278,6 +140,7 @@ celerybeat.pid
 *.sage.py
 
 # Environments
+.env
 .venv
 env/
 venv/
@@ -326,13 +189,6 @@ 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
@@ -352,9 +208,8 @@ package
 .history
 .ionide
 
-# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,svelte,python,linux,node
+# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,linux,python
 
 # Custom rules (everything added below won't be overriden by 'Generate .gitignore File' if you use 'Update' option)
 
-output
+conda-bld
-*.private.*

.vscode/extensions.json

@@ -0,0 +1,5 @@
+{
+    "recommendations": [
+        "piotrpalarz.vscode-gitignore-generator"
+    ]
+}

Jenkinsfile

@@ -9,7 +9,7 @@ pipeline {
     stages {
         stage("install") {
             steps {
-                sh 'python -m pip install -r requirements.txt'
+                sh 'conda env update -n base -f environment.yml'
             }
         }
         stage("unit tests") {
@@ -22,11 +22,14 @@ 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', fingerprint: true, followSymlinks: false, onlyIfSuccessful: true
+                archiveArtifacts artifacts: 'dist/*.tar.gz, dist/*.whl, conda-bld/**/*.conda', fingerprint: true, followSymlinks: false, onlyIfSuccessful: true
             }
         }
         stage("publish") {
@@ -36,7 +39,8 @@ pipeline {
                         CREDS = credentials('username-password-rs-git')
                     }
                     steps {
-                        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/*'
+                        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 ${CREDS_USR}:${CRED_PSW} --upload-file conda-bld/**/*.conda https://git.reslate.systems/api/packages/${CRED_USR}/conda/$(basename conda-bld/**/*.conda)'
                     }
                 }
                 stage ("pypi.org") {

autobigs-engine/meta.yaml

@@ -0,0 +1,44 @@
+{% 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

environment.yml

@@ -0,0 +1,15 @@
+name: ci
+channels:
+  - bioconda
+  - conda-forge
+dependencies:
+  - aiohttp==3.11.*
+  - biopython==1.85
+  - pytest
+  - pytest-asyncio
+  - python-build
+  - conda-build
+  - twine
+  - setuptools_scm
+  - pytest-cov
+  - grayskull

pyproject.toml

@@ -13,6 +13,7 @@ dependencies = [
 ]
 requires-python = ">=3.12"
 description = "A library to rapidly fetch fetch MLST profiles given sequences for various diseases."
+license = {text = "GPL-3.0-or-later"}
 
 [project.urls]
 Homepage = "https://github.com/Syph-and-VPD-Lab/autoBIGS.engine"

requirements.txt

@@ -1,8 +0,0 @@
-aiohttp[speedups]==3.11.*
-biopython==1.85
-pytest
-pytest-asyncio
-build
-twine
-setuptools_scm
-pytest-cov

scripts/patch_recipe.py

@@ -0,0 +1,103 @@
+#!/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()

src/autobigs/engine/analysis/bigsdb.py

@@ -22,15 +22,15 @@ from Bio.Align import PairwiseAligner
 class BIGSdbMLSTProfiler(AbstractAsyncContextManager):
 
     @abstractmethod
-    def determine_mlst_allele_variants(self, query_sequence_strings: Iterable[str]) -> AsyncGenerator[Allele, Any]:
+    def determine_mlst_allele_variants(self, query_sequence_strings: Union[Iterable[Union[NamedString, str]], Union[NamedString, str]]) -> AsyncGenerator[Union[Allele, tuple[str, Allele]], Any]:
         pass
 
     @abstractmethod
-    async def determine_mlst_st(self, alleles: Union[AsyncIterable[Allele], Iterable[Allele]]) -> MLSTProfile:
+    async def determine_mlst_st(self, alleles: Union[AsyncIterable[Union[Allele, tuple[str, Allele]]], Iterable[Union[Allele, tuple[str, Allele]]]]) -> Union[MLSTProfile, NamedMLSTProfile]:
         pass
 
     @abstractmethod
-    async def profile_string(self, query_sequence_strings: Iterable[str]) -> MLSTProfile:
+    async def profile_string(self, query_sequence_strings: Iterable[Union[NamedString, str]]) -> Union[NamedMLSTProfile, 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[str], str]) -> AsyncGenerator[Allele, Any]:
+    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]:
         # See https://bigsdb.pasteur.fr/api/db/pubmlst_bordetella_seqdef/schemes
         uri_path = "sequence"
-        if isinstance(query_sequence_strings, str):
+        if isinstance(query_sequence_strings, str) or isinstance(query_sequence_strings, NamedString):
             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,
+                "sequence": sequence_string if isinstance(sequence_string, str) else sequence_string.sequence,
                 "partial_matches": True
             }) as response:
                 sequence_response: dict = await response.json()
@@ -70,7 +70,8 @@ class RemoteBIGSdbMLSTProfiler(BIGSdbMLSTProfiler):
                     for allele_loci, alleles in exact_matches.items():
                         for allele in alleles:
                             alelle_id = allele["allele_id"]
-                            yield Allele(allele_locus=allele_loci, allele_variant=alelle_id, partial_match_profile=None)
+                            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)
                 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():
@@ -82,23 +83,33 @@ class RemoteBIGSdbMLSTProfiler(BIGSdbMLSTProfiler):
                             gaps=int(partial_match["gaps"]),
                             match_metric=int(partial_match["bitscore"])
                         )
-                        yield Allele(
+                        result_allele = 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)
+                    raise NoBIGSdbMatchesException(self._database_name, self._schema_id, sequence_string.name if isinstance(sequence_string, NamedString) else None)
 
-    async def determine_mlst_st(self, alleles: Union[AsyncIterable[Allele], Iterable[Allele]]) -> MLSTProfile:
+    async def determine_mlst_st(self, alleles: Union[AsyncIterable[Union[Allele, tuple[str, Allele]]], Iterable[Union[Allele, tuple[str, Allele]]]]) -> Union[MLSTProfile, NamedMLSTProfile]:
         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:
-                allele_request_dict[allele.allele_locus].append({"allele": str(allele.allele_variant)})
+                insert_allele_to_request_dict(allele)
         else:
             for allele in alleles:
-                allele_request_dict[allele.allele_locus].append({"allele": str(allele.allele_variant)})
+                insert_allele_to_request_dict(allele)
         request_json = {
             "designations": allele_request_dict
         }
@@ -111,26 +122,33 @@ 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.")
-            return MLSTProfile(allele_set, schema_fields_returned["ST"], schema_fields_returned["clonal_complex"])
+            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
 
-    async def profile_string(self, query_sequence_strings: Iterable[str]) -> MLSTProfile:
+    async def profile_string(self, query_sequence_strings: Iterable[Union[NamedString, str]]) -> Union[NamedMLSTProfile, 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:
-            for named_string in named_strings:
+            tasks.append(self.profile_string(named_strings))
+            for task in asyncio.as_completed(tasks):
                 try:
-                    yield NamedMLSTProfile(named_string.name, (await self.profile_string([named_string.sequence])))
+                    yield await task
                 except NoBIGSdbMatchesException as e:
                     if stop_on_fail:
                         raise e
-                    yield NamedMLSTProfile(named_string.name, None)
+                    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)
 
     async def close(self):
         await self._http_client.close()

src/autobigs/engine/exceptions/database.py

@@ -5,8 +5,12 @@ class BIGSDbDatabaseAPIException(Exception):
 
 
 class NoBIGSdbMatchesException(BIGSDbDatabaseAPIException):
-    def __init__(self, database_name: str, database_schema_id: int, *args):
+    def __init__(self, database_name: str, database_schema_id: int, query_name: Union[None, str], *args):
+        self._query_name = query_name
         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):

src/autobigs/engine/reading.py

@@ -13,5 +13,8 @@ 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:
-        yield await read_fasta(handle)
+        tasks.append(read_fasta(handle))
+    for task in asyncio.as_completed(tasks):
+        yield await task

src/autobigs/engine/writing.py

@@ -3,7 +3,7 @@ import csv
 from os import PathLike
 from typing import AsyncIterable, Collection, Mapping, Sequence, Union
 
-from autobigs.engine.structures.mlst import Allele, MLSTProfile
+from autobigs.engine.structures.mlst import Allele, MLSTProfile, NamedMLSTProfile
 
 
 def alleles_to_text_map(alleles: Collection[Allele]) -> Mapping[str, Union[Sequence[str], str]]:
@@ -17,12 +17,14 @@ def alleles_to_text_map(alleles: Collection[Allele]) -> Mapping[str, Union[Seque
             result[locus] = tuple(result[locus]) # type: ignore
     return dict(result)
 
-async def write_mlst_profiles_as_csv(mlst_profiles_iterable: AsyncIterable[tuple[str, Union[MLSTProfile, None]]], handle: Union[str, bytes, PathLike[str], PathLike[bytes]]) -> Sequence[str]:
+async def write_mlst_profiles_as_csv(mlst_profiles_iterable: AsyncIterable[NamedMLSTProfile], handle: Union[str, bytes, PathLike[str], PathLike[bytes]]) -> Sequence[str]:
     failed = list()
     with open(handle, "w", newline='') as filehandle:
         header = None
         writer: Union[csv.DictWriter, None] = None
-        async for name, mlst_profile in mlst_profiles_iterable:
+        async for named_mlst_profile in mlst_profiles_iterable:
+            name = named_mlst_profile.name
+            mlst_profile = named_mlst_profile.mlst_profile
             if mlst_profile is None:
                 failed.append(name)
                 continue

tests/autobigs/engine/test_writing.py

@@ -3,7 +3,7 @@ from typing import AsyncIterable, Iterable
 import pytest
 from autobigs.engine.structures.alignment import AlignmentStats
 from autobigs.engine.writing import alleles_to_text_map, write_mlst_profiles_as_csv
-from autobigs.engine.structures.mlst import Allele, MLSTProfile
+from autobigs.engine.structures.mlst import Allele, MLSTProfile, NamedMLSTProfile
 import tempfile
 from csv import reader
 from os import path
@@ -11,20 +11,20 @@ from os import path
 
 @pytest.fixture
 def dummy_alphabet_mlst_profile():
-    return MLSTProfile((
+    return NamedMLSTProfile("name", MLSTProfile((
         Allele("A", "1", None),
         Allele("D", "1", None),
         Allele("B", "1", None),
         Allele("C", "1", None),
         Allele("C", "2", AlignmentStats(90, 10, 0, 90))
-    ), "mysterious", "very mysterious")
+    ), "mysterious", "very mysterious"))
 
 async def iterable_to_asynciterable(iterable: Iterable):
     for iterated in iterable:
         yield iterated
 
 async def test_column_order_is_same_as_expected_file(dummy_alphabet_mlst_profile: MLSTProfile):
-    dummy_profiles = [("test_1", dummy_alphabet_mlst_profile)]
+    dummy_profiles = [dummy_alphabet_mlst_profile]
     with tempfile.TemporaryDirectory() as temp_dir:
         output_path = path.join(temp_dir, "out.csv")
         await write_mlst_profiles_as_csv(iterable_to_asynciterable(dummy_profiles), output_path)
@@ -34,8 +34,8 @@ async def test_column_order_is_same_as_expected_file(dummy_alphabet_mlst_profile
             target_columns = lines[4:]
             assert target_columns == sorted(target_columns)
 
-async def test_alleles_to_text_map_mapping_is_correct(dummy_alphabet_mlst_profile: MLSTProfile):
+async def test_alleles_to_text_map_mapping_is_correct(dummy_alphabet_mlst_profile: NamedMLSTProfile):
-    mapping = alleles_to_text_map(dummy_alphabet_mlst_profile.alleles)
+    mapping = alleles_to_text_map(dummy_alphabet_mlst_profile.mlst_profile.alleles) # type: ignore
     expected_mapping = {
         "A": "1",
         "B": "1",
@@ -44,4 +44,4 @@ async def test_alleles_to_text_map_mapping_is_correct(dummy_alphabet_mlst_profil
     }
     for allele_name, allele_ids in mapping.items():
         assert allele_name in expected_mapping
-        assert allele_ids == expected_mapping[allele_name]
+        assert allele_ids == expected_mapping[allele_name]