Pipeline will now only publish to git.reslate.systems on main branch

Instead of generating a tuple comprised of the one sequence ID repeated

.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",
-	// 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",
+	"name": "Anaconda (Python 3)",
+	"build": { 
+		"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",
-	"customizations": {
-		"vscode": {
-			"extensions": [
-				"mechatroner.rainbow-csv"
-			]
-		}
-	}
+	// "postCreateCommand": "python --version",
 
 	// 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
-# Edit at https://www.toptal.com/developers/gitignore?templates=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,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
-*.private.*
+conda-bld

.vscode/extensions.json

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

.vscode/launch.json

@@ -1,25 +0,0 @@
-{
-    // Use IntelliSense to learn about possible attributes.
-    // Hover to view descriptions of existing attributes.
-    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
-    "version": "0.2.0",
-    "configurations": [
-        
-        {
-            "name": "autobigs info -lschema pubmlst_bordetella_seqdef",
-            "type": "debugpy",
-            "request": "launch",
-            "program": "${workspaceFolder}/src/autobigs/cli/program.py",
-            "console": "integratedTerminal",
-            "args": [
-                "info",
-                "-lschemas",
-                "pubmlst_bordetella_seqdef"
-            ],
-            "cwd": "${workspaceFolder}/src",
-            "env": {
-                "PYTHONPATH": "${workspaceFolder}/src"
-            }
-        }
-    ]
-}

Jenkinsfile

@@ -2,14 +2,14 @@ pipeline {
     agent {
         kubernetes {
             cloud 'rsys-devel'
-            defaultContainer 'pip'
-            inheritFrom 'pip'
+            defaultContainer 'miniforge3'
+            inheritFrom 'miniforge'
         }
     }
     stages {
         stage("install") {
             steps {
-                sh 'python -m pip install -r requirements.txt'
+                sh 'conda env update -n base -f environment.yml'
             }
         }
         stage("unit tests") {
@@ -22,21 +22,29 @@ 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") {
             parallel {
                 stage ("git.reslate.systems") {
+                    when {
+                        branch '**/main'
+                    }
+
                     environment {
                         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 ${CREDS_USR}:${CREDS_PSW} --upload-file conda-bld/**/*.conda https://git.reslate.systems/api/packages/${CREDS_USR}/conda/$(basename conda-bld/**/*.conda)'
                     }
                 }
                 stage ("pypi.org") {

README.md

@@ -1,13 +1,14 @@
-# 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:
 - Import multiple `FASTA` files
 - Fetch the available BIGSdb databases that is currently live and available
-- Fetch the available BIGSdb database schemas for a given MLST database
+- Fetch the available BIGSdb database schemes for a given MLST database
 - Retrieve exact/non-exact MLST allele variant IDs based off a sequence
 - Retrieve MLST sequence type IDs based off a sequence
 - Output all results to a single CSV
@@ -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.

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 +1,16 @@
+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

pyproject.toml

@@ -13,11 +13,12 @@ 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/RealYHD/autoBIGS.engine"
-Source = "https://github.com/RealYHD/autoBIGS.engine"
-Issues = "https://github.com/RealYHD/autoBIGS.engine/issues"
+Homepage = "https://github.com/Syph-and-VPD-Lab/autoBIGS.engine"
+Source = "https://github.com/Syph-and-VPD-Lab/autoBIGS.engine"
+Issues = "https://github.com/Syph-and-VPD-Lab/autoBIGS.engine/issues"
 
 [tool.setuptools_scm]
 

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

@@ -7,7 +7,7 @@ from os import path
 import os
 import shutil
 import tempfile
-from typing import Any, AsyncGenerator, AsyncIterable, Iterable, Mapping, Sequence, Set, Union
+from typing import Any, AsyncGenerator, AsyncIterable, Coroutine, Iterable, Mapping, Sequence, Set, Union
 
 from aiohttp import ClientSession, ClientTimeout
 
@@ -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
@@ -43,23 +43,23 @@ class BIGSdbMLSTProfiler(AbstractAsyncContextManager):
 
 class RemoteBIGSdbMLSTProfiler(BIGSdbMLSTProfiler):
 
-    def __init__(self, database_api: str, database_name: str, schema_id: int):
+    def __init__(self, database_api: str, database_name: str, scheme_id: int):
         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._scheme_id = scheme_id
+        self._base_url = f"{database_api}/db/{self._database_name}/schemes/{self._scheme_id}/"
         self._http_client = ClientSession(self._base_url, timeout=ClientTimeout(60))
 
     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._scheme_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
         }
@@ -106,31 +117,42 @@ class RemoteBIGSdbMLSTProfiler(BIGSdbMLSTProfiler):
             response_json: dict = await response.json()
             allele_set: Set[Allele] = set()
             response_json.setdefault("fields", dict())
-            schema_fields_returned: dict[str, str] = response_json["fields"]
-            schema_fields_returned.setdefault("ST", "unknown")
-            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)})")
+            scheme_fields_returned: dict[str, str] = response_json["fields"]
+            scheme_fields_returned.setdefault("ST", "unknown")
+            scheme_fields_returned.setdefault("clonal_complex", "unknown")
+            scheme_exact_matches: dict = response_json["exact_matches"]
+            for exact_match_locus, exact_match_alleles in scheme_exact_matches.items():
                 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, scheme_fields_returned["ST"], scheme_fields_returned["clonal_complex"])
+            if len(names_list) > 0:
+                result_mlst_profile = NamedMLSTProfile(str(tuple(names_list)) if len(set(names_list)) > 1 else names_list[0], 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: list[Coroutine[Any, Any, Union[NamedMLSTProfile, MLSTProfile]]] = []
         async for named_strings in query_named_string_groups:
-            for named_string in named_strings:
-                try:
-                    yield NamedMLSTProfile(named_string.name, (await self.profile_string([named_string.sequence])))
-                except NoBIGSdbMatchesException as e:
-                    if stop_on_fail:
-                        raise e
-                    yield NamedMLSTProfile(named_string.name, None)
+            tasks.append(self.profile_string(named_strings))
+        for task in asyncio.as_completed(tasks):
+            named_mlst_profile = await task
+            try:
+                if isinstance(named_mlst_profile, NamedMLSTProfile):
+                    yield named_mlst_profile
+                else:
+                    raise TypeError("MLST profile is not named.")
+            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)
 
     async def close(self):
         await self._http_client.close()
@@ -147,7 +169,7 @@ class BIGSdbIndex(AbstractAsyncContextManager):
     def __init__(self):
         self._http_client = ClientSession()
         self._known_seqdef_dbs_origin: Union[Mapping[str, str], None] = None
-        self._seqdefdb_schemas: dict[str, Union[Mapping[str, int], None]] = dict()
+        self._seqdefdb_schemes: dict[str, Union[Mapping[str, int], None]] = dict()
         super().__init__()
 
     async def __aenter__(self):
@@ -173,22 +195,22 @@ class BIGSdbIndex(AbstractAsyncContextManager):
             raise NoSuchBIGSdbDatabaseException(seqdef_db_name)
         return known_databases[seqdef_db_name]     
 
-    async def get_schemas_for_seqdefdb(self, seqdef_db_name: str, force: bool = False) -> Mapping[str, int]:
-        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
+    async def get_schemes_for_seqdefdb(self, seqdef_db_name: str, force: bool = False) -> Mapping[str, int]:
+        if seqdef_db_name in self._seqdefdb_schemes and not force:
+            return self._seqdefdb_schemes[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)}/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()
+            scheme_descriptions: Mapping[str, int] = dict()
             for scheme_definition in response_json["schemes"]:
                 scheme_id: int = int(str(scheme_definition["scheme"]).split("/")[-1])
                 scheme_desc: str = scheme_definition["description"]
-                schema_descriptions[scheme_desc] = scheme_id
-            self._seqdefdb_schemas[seqdef_db_name] = schema_descriptions
-            return self._seqdefdb_schemas[seqdef_db_name] # type: ignore
+                scheme_descriptions[scheme_desc] = scheme_id
+            self._seqdefdb_schemes[seqdef_db_name] = scheme_descriptions
+            return self._seqdefdb_schemes[seqdef_db_name] # type: ignore
 
-    async def build_profiler_from_seqdefdb(self, local: bool, dbseqdef_name: str, schema_id: int) -> BIGSdbMLSTProfiler:
-        return get_BIGSdb_MLST_profiler(local, await self.get_bigsdb_api_from_seqdefdb(dbseqdef_name), dbseqdef_name, schema_id)
+    async def build_profiler_from_seqdefdb(self, local: bool, dbseqdef_name: str, scheme_id: int) -> BIGSdbMLSTProfiler:
+        return get_BIGSdb_MLST_profiler(local, await self.get_bigsdb_api_from_seqdefdb(dbseqdef_name), dbseqdef_name, scheme_id)
 
     async def close(self):
         await self._http_client.close()
@@ -196,7 +218,7 @@ class BIGSdbIndex(AbstractAsyncContextManager):
     async def __aexit__(self, exc_type, exc_value, traceback):
         await self.close()
 
-def get_BIGSdb_MLST_profiler(local: bool, database_api: str, database_name: str, schema_id: int):
+def get_BIGSdb_MLST_profiler(local: bool, database_api: str, database_name: str, scheme_id: int):
     if local:
         raise NotImplementedError()
-    return RemoteBIGSdbMLSTProfiler(database_api=database_api, database_name=database_name, schema_id=schema_id)
+    return RemoteBIGSdbMLSTProfiler(database_api=database_api, database_name=database_name, scheme_id=scheme_id)

src/autobigs/engine/exceptions/database.py

@@ -5,17 +5,21 @@ class BIGSDbDatabaseAPIException(Exception):
 
 
 class NoBIGSdbMatchesException(BIGSDbDatabaseAPIException):
-    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 __init__(self, database_name: str, database_scheme_id: int, query_name: Union[None, str], *args):
+        self._query_name = query_name
+        super().__init__(f"No matches found with scheme with ID {database_scheme_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):
-        super().__init__(f"No exact match found with schema with ID {database_schema_id}  in the database \"{database_name}\".", *args)
+    def __init__(self, database_name: str, database_scheme_id: int, *args):
+        super().__init__(f"No exact match found with scheme with ID {database_scheme_id}  in the database \"{database_name}\".", *args)
 
 class NoSuchBIGSdbDatabaseException(BIGSDbDatabaseAPIException):
     def __init__(self, database_name: str, *args):
         super().__init__(f"No database \"{database_name}\" found.", *args)
 
-class NoSuchBigSdbSchemaException(BIGSDbDatabaseAPIException):
-    def __init__(self, database_name: str, database_schema_id: int, *args):
-        super().__init__(f"No schema with ID {database_schema_id}  in \"{database_name}\" found.", *args)
+class NoSuchBigSdbschemeException(BIGSDbDatabaseAPIException):
+    def __init__(self, database_name: str, database_scheme_id: int, *args):
+        super().__init__(f"No scheme with ID {database_scheme_id}  in \"{database_name}\" found.", *args)

src/autobigs/engine/reading.py

@@ -5,12 +5,16 @@ from Bio import SeqIO
 
 from autobigs.engine.structures.genomics import NamedString
 
-async def read_fasta(handle: Union[str, TextIOWrapper]) -> AsyncGenerator[NamedString, Any]:
+async def read_fasta(handle: Union[str, TextIOWrapper]) -> Iterable[NamedString]:
     fasta_sequences = asyncio.to_thread(SeqIO.parse, handle=handle, format="fasta")
+    results = []
     for fasta_sequence in await fasta_sequences:
-        yield NamedString(fasta_sequence.id, str(fasta_sequence.seq))
+        results.append(NamedString(fasta_sequence.id, str(fasta_sequence.seq)))
+    return results
 
-async def read_multiple_fastas(handles: Iterable[Union[str, TextIOWrapper]]) -> AsyncGenerator[NamedString, Any]:
+async def read_multiple_fastas(handles: Iterable[Union[str, TextIOWrapper]]) -> AsyncGenerator[Iterable[NamedString], Any]:
+    tasks = []
     for handle in handles:
-        async for named_seq in read_fasta(handle):
-            yield named_seq
+        tasks.append(read_fasta(handle))
+    for task in asyncio.as_completed(tasks):
+        yield await task

src/autobigs/engine/structures/genomics.py

@@ -25,7 +25,7 @@ class SangerTraceData(NamedString):
     analysis_proto_settings_name: str
     analysis_rpto_settings_ver: str
     analysis_proto_xml_data: str
-    analysis_proto_xml_schema_ver: str
+    analysis_proto_xml_scheme_ver: str
     sample_comment: Union[None, str]
     capillary_machine: bool
     container_identifier: str

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/analysis/test_bigsdb.py

@@ -71,14 +71,14 @@ hinfluenzae_2014_102_bad_profile = MLSTProfile((
     ), "unknown", "unknown")
 
 
-@pytest.mark.parametrize("local_db,database_api,database_name,schema_id,seq_path,feature_seqs_path,expected_profile,bad_profile", [
+@pytest.mark.parametrize("local_db,database_api,database_name,scheme_id,seq_path,feature_seqs_path,expected_profile,bad_profile", [
     (False, "https://bigsdb.pasteur.fr/api", "pubmlst_bordetella_seqdef", 3, "tohama_I_bpertussis.fasta", "tohama_I_bpertussis_features.fasta", bpertussis_tohamaI_profile, bpertussis_tohamaI_bad_profile),
     (False, "https://rest.pubmlst.org", "pubmlst_hinfluenzae_seqdef", 1, "2014-102_hinfluenza.fasta", "2014-102_hinfluenza_features.fasta", hinfluenzae_2014_102_profile, hinfluenzae_2014_102_bad_profile),
 ])
 class TestBIGSdbMLSTProfiler:
-    async def test_profiling_results_in_exact_matches_when_exact(self, local_db, database_api, database_name, schema_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
+    async def test_profiling_results_in_exact_matches_when_exact(self, local_db, database_api, database_name, scheme_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
         sequence = get_first_sequence_from_fasta(seq_path)
-        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, schema_id) as dummy_profiler:
+        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, scheme_id) as dummy_profiler:
             expected_alleles = mlst.alleles_to_mapping(expected_profile.alleles)
             targets_left = set(mlst.alleles_to_mapping(expected_profile.alleles).keys())
             async for exact_match in dummy_profiler.determine_mlst_allele_variants(query_sequence_strings=[sequence]):
@@ -89,10 +89,10 @@ class TestBIGSdbMLSTProfiler:
 
             assert len(targets_left) == 0
 
-    async def test_sequence_profiling_non_exact_returns_non_exact(self, local_db, database_api, database_name, schema_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
+    async def test_sequence_profiling_non_exact_returns_non_exact(self, local_db, database_api, database_name, scheme_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
         target_sequences = get_multiple_sequences_from_fasta(feature_seqs_path)
         mlst_targets = {x.lower() for x in mlst.alleles_to_mapping(expected_profile.alleles).keys()}
-        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, schema_id) as profiler:
+        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, scheme_id) as profiler:
             for target_sequence in target_sequences:
                 match = re.fullmatch(r".*\[gene=([\w\d]+)\].*", target_sequence.description)
                 if match is None:
@@ -102,31 +102,33 @@ class TestBIGSdbMLSTProfiler:
                     continue
                 scrambled = gene_scrambler(str(target_sequence.seq), 0.125)
                 async for partial_match in profiler.determine_mlst_allele_variants([scrambled]):
+                    assert isinstance(partial_match, Allele)
                     assert partial_match.partial_match_profile is not None
                     mlst_targets.remove(gene)
 
             assert len(mlst_targets) == 0
 
-    async def test_profiling_results_in_correct_mlst_st(self, local_db, database_api, database_name, schema_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
-        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, schema_id) as dummy_profiler:
+    async def test_profiling_results_in_correct_mlst_st(self, local_db, database_api, database_name, scheme_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
+        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, scheme_id) as dummy_profiler:
             mlst_st_data = await dummy_profiler.determine_mlst_st(expected_profile.alleles)
             assert mlst_st_data is not None
             assert isinstance(mlst_st_data, MLSTProfile)
             assert mlst_st_data.clonal_complex == expected_profile.clonal_complex
             assert mlst_st_data.sequence_type == expected_profile.sequence_type
 
-    async def test_profiling_non_exact_results_in_list_of_mlsts(self, local_db, database_api, database_name, schema_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
+    async def test_profiling_non_exact_results_in_list_of_mlsts(self, local_db, database_api, database_name, scheme_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
         dummy_alleles = bad_profile.alleles
-        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, schema_id) as dummy_profiler:
+        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, scheme_id) as dummy_profiler:
             mlst_profile = await dummy_profiler.determine_mlst_st(dummy_alleles)
+            assert isinstance(mlst_profile, MLSTProfile)
             assert mlst_profile.clonal_complex == "unknown"
             assert mlst_profile.sequence_type == "unknown"
 
 
-    async def test_bigsdb_profile_multiple_strings_same_string_twice(self, local_db, database_api, database_name, schema_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
+    async def test_bigsdb_profile_multiple_strings_same_string_twice(self, local_db, database_api, database_name, scheme_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
         sequence = get_first_sequence_from_fasta(seq_path)
         dummy_sequences = [[NamedString("seq1", sequence)], [NamedString("seq2", sequence)]]
-        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, schema_id) as dummy_profiler:
+        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, scheme_id) as dummy_profiler:
             async for named_profile in dummy_profiler.profile_multiple_strings(generate_async_iterable(dummy_sequences)):
                 name, profile = named_profile.name, named_profile.mlst_profile
                 assert profile is not None
@@ -134,10 +136,10 @@ class TestBIGSdbMLSTProfiler:
                 assert profile.clonal_complex == expected_profile.clonal_complex
                 assert profile.sequence_type == expected_profile.sequence_type
 
-    async def test_bigsdb_profile_multiple_strings_exactmatch_fail_second_no_stop(self, local_db, database_api, database_name, schema_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
+    async def test_bigsdb_profile_multiple_strings_exactmatch_fail_second_no_stop(self, local_db, database_api, database_name, scheme_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
         valid_seq = get_first_sequence_from_fasta(seq_path)
         dummy_sequences = [[NamedString("seq1", valid_seq)], [NamedString("should_fail", gene_scrambler(valid_seq, 0.3))], [NamedString("seq3", valid_seq)]]
-        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, schema_id) as dummy_profiler:
+        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, scheme_id) as dummy_profiler:
             async for name_profile in dummy_profiler.profile_multiple_strings(generate_async_iterable(dummy_sequences), True):
                 name, profile = name_profile.name, name_profile.mlst_profile
 
@@ -151,11 +153,11 @@ class TestBIGSdbMLSTProfiler:
                     assert profile.clonal_complex == expected_profile.clonal_complex
                     assert profile.sequence_type == expected_profile.sequence_type
 
-    async def test_bigsdb_profile_multiple_strings_nonexact_second_no_stop(self, local_db, database_api, database_name, schema_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
+    async def test_bigsdb_profile_multiple_strings_nonexact_second_no_stop(self, local_db, database_api, database_name, scheme_id, seq_path: str, feature_seqs_path: str, expected_profile: MLSTProfile, bad_profile: MLSTProfile):
         valid_seq = get_first_sequence_from_fasta(seq_path)
         dummy_sequences = [[NamedString("seq1", valid_seq)], [NamedString("should_fail", gene_scrambler(valid_seq, 0.3))], [NamedString("seq3", valid_seq)]]
 
-        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, schema_id) as dummy_profiler:
+        async with bigsdb.get_BIGSdb_MLST_profiler(local_db, database_api, database_name, scheme_id) as dummy_profiler:
             async for named_profile in dummy_profiler.profile_multiple_strings(generate_async_iterable(dummy_sequences), False):
                 name, profile = named_profile.name, named_profile.mlst_profile
                 
@@ -183,12 +185,12 @@ class TestBIGSdbIndex:
         async with BIGSdbIndex() as bigsdb_index:
             assert (await bigsdb_index.get_bigsdb_api_from_seqdefdb("pubmlst_bordetella_seqdef")) == "https://bigsdb.pasteur.fr/api"
 
-    async def test_bigsdb_index_get_schemas_for_bordetella(self):
+    async def test_bigsdb_index_get_schemes_for_bordetella(self):
         async with BIGSdbIndex() as index:
-            schemas = await index.get_schemas_for_seqdefdb(seqdef_db_name="pubmlst_bordetella_seqdef")
-            assert len(schemas.keys()) > 0
-            assert "MLST" in schemas
-            assert isinstance(schemas["MLST"], int)
+            schemes = await index.get_schemes_for_seqdefdb(seqdef_db_name="pubmlst_bordetella_seqdef")
+            assert len(schemes.keys()) > 0
+            assert "MLST" in schemes
+            assert isinstance(schemes["MLST"], int)
 
     async def test_bigsdb_index_get_databases_has_only_seqdef(self):
         async with BIGSdbIndex() as index:
@@ -207,5 +209,6 @@ class TestBIGSdbIndex:
             async with await bigsdb_index.build_profiler_from_seqdefdb(local, "pubmlst_bordetella_seqdef", 3) as profiler:
                 assert isinstance(profiler, BIGSdbMLSTProfiler)
                 profile = await profiler.profile_string(sequence)
+                assert isinstance(profile, MLSTProfile)
                 assert profile.clonal_complex == "ST-2 complex"
                 assert profile.sequence_type == "1"

tests/autobigs/engine/test_reading.py

@@ -2,6 +2,6 @@ from autobigs.engine.reading import read_fasta
 
 
 async def test_fasta_reader_not_none():
-    named_strings = read_fasta("tests/resources/tohama_I_bpertussis.fasta")
-    async for named_string in named_strings:
+    named_strings = await read_fasta("tests/resources/tohama_I_bpertussis.fasta")
+    for named_string in named_strings:
         assert named_string.name == "BX470248.1"

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):
-    mapping = alleles_to_text_map(dummy_alphabet_mlst_profile.alleles)
+async def test_alleles_to_text_map_mapping_is_correct(dummy_alphabet_mlst_profile: NamedMLSTProfile):
+    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]