Merge branch 'master' into develop

Wrong package name given in 'setup.cfg' is now fixed.

.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

@@ -0,0 +1,35 @@
+// 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
+{
+	"name": "Anaconda (Python 3)",
+	"build": { 
+		"context": "..",
+		"dockerfile": "Dockerfile"
+	},
+	"customizations": {
+		"vscode": {
+			"extensions": [
+				"ms-python.debugpy",
+				"ms-python.python",
+				"ms-python.vscode-pylance",
+				"ms-python.black-formatter",
+				"ms-python.flake8"
+			]
+		}
+	}
+
+	// Features to add to the dev container. More info: https://containers.dev/features.
+	// "features": {},
+
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+
+	// Use 'postCreateCommand' to run commands after the container is created.
+	// "postCreateCommand": "python --version",
+
+	// Configure tool-specific properties.
+	// "customizations": {},
+
+	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "root"
+}

.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.

.vscode/launch.json

@@ -8,15 +8,16 @@
             "name": "Splitter Single Gene with Translation",
             "type": "python",
             "request": "launch",
-            "program": "${workspaceFolder}/msa_splitter.py",
+            "program": "${workspaceFolder}/splitmsa/splitmsa.py",
             "args": [
                 "${workspaceFolder}/tests/resources/test_msa-shortened.fa",
-                "--gene-list", "${workspaceFolder}/tests/resources/gene_list.csv",
+                "--gene-list",
+                "${workspaceFolder}/tests/resources/gene_list.csv",
                 "-C",
-                "-E", "DEBUG",
+                "-E",
+                "DEBUG",
                 "--do-translate",
                 "--gen-cut-stop-codon"
-
             ],
             "console": "integratedTerminal",
             "justMyCode": true

Jenkinsfile

@@ -1,15 +1,31 @@
 pipeline {
-    agent any
+    agent {
+        kubernetes {
+            cloud 'Reslate Systems'
+            defaultContainer 'conda'
+        }
+    }
     stages {
         stage("install") {
             steps {
-                sh 'mamba env update --file environment.yml'
-                sh 'echo "mamba activate splitmsa" >> ~/.bashrc'
+                sh 'conda update conda -y -q'
+                sh 'conda env update -n base --file environment.yml'
             }
         }
         stage("build") {
             steps {
-                sh "python -m build"
+                sh "conda run -n base python -m build"
+            }
+        }
+        stage("test") {
+            steps {
+                sh "conda run -n base pip install dist/*.whl"
+                sh "conda run -n base splitmsa -h"
+            }
+        }
+        stage("archive") {
+            steps {
+                archiveArtifacts artifacts: 'dist/*.tar.gz, dist/*.whl', fingerprint: true, followSymlinks: false, onlyIfSuccessful: true
             }
         }
         stage("publish") {
@@ -18,7 +34,7 @@ pipeline {
             }
             steps {
                 withCredentials([usernamePassword(credentialsId: 'rs-git-package-registry-ydeng', passwordVariable: 'PASS', usernameVariable: 'USER')]) {
-                    sh "python -m twine upload --repository-url https://git.reslate.systems/api/packages/${USER}/pypi -u ${USER} -p ${PASS} --non-interactive --disable-progress-bar --verbose dist/*"
+                    sh returnStatus: true, script: 'conda run -n base python -m twine upload --repository-url https://git.reslate.systems/api/packages/${USER}/pypi -u ${USER} -p ${PASS} --non-interactive --disable-progress-bar --verbose dist/*'
                 }
             }
         }

environment.yml

@@ -4,5 +4,7 @@ channels:
 dependencies:
   - build=0.7.0
   - pytest=7.2.2
-  - twine=4.0.2
+  - twine
   - biopython=1.81
+  - python=3.9
+prefix: ./env

requirements.txt

@@ -1 +0,0 @@
-Bio==1.5.6

setup.cfg

@@ -1,12 +1,12 @@
 [metadata]
 name = splitmsa
-version = 0.0.1
+version = 0.0.4
 
 [options]
 packages = splitmsa
 install_requires =
-    Bio
+    biopython ==1.81; python_version == "3.9"
 
 [options.entry_points]
 console_scripts =
-    splitmsa = splitmsa.splitmsa:main
+    splitmsa = splitmsa.splitmsa:main

splitmsa/splitmsa.py

@@ -247,6 +247,67 @@ def output_as_csv(gene: str, problems: list[list[str]], output_path: str):
         writer.writerows(problems)
 
 
+def run(args):
+    msa_records = list(read_msa_file(args.input))
+    info(f"MSA records read complete. Found {len(msa_records)} records.")
+    genes = []
+    if args.gene_list:
+        genes = read_genes_from_csv(args.gene_list)
+        info(f"Gene list read from {args.gene_list} resulted in {len(genes)} " "genes.")
+    else:
+        if args.gene_name and args.start and args.end:
+            genes.append([args.gene_name, args.start, args.end])
+            info(
+                f"Extracting {args.gene_name} starting at {args.start} to "
+                f"{args.end}."
+            )
+        else:
+            raise Exception(
+                "Need either a gene list by --gene-list or a start and end "
+                "via --start, and --end respectively."
+            )
+    for gene_name, start, end in genes:
+        info(f"Started on gene {gene_name} ({start} - {end})")
+        (
+            nt_sequence_records,
+            nt_no_stop_sequence_records,
+            aa_sequence_records,
+            aa_no_stop_sequence_records,
+            problems,
+        ) = trim(
+            start,
+            end,
+            args.gen_cut_stop_codon,
+            args.do_translate,
+            msa_records,
+            correction_range=args.correction_range,
+        )
+        if len(problems) > 0:
+            warning(
+                f"There were {len(problems)} problems " f"during trimming {gene_name}!"
+            )
+        if args.catalogue_problems:
+            output_as_csv(
+                gene_name,
+                problems,
+                os.path.join(args.output_dir, f"{gene_name} - problems.csv"),
+            )
+        write_to_file(
+            args.output_dir,
+            gene_name,
+            start,
+            end,
+            args.full_suffix,
+            args.ns_suffix,
+            args.aa_suffix,
+            nt_sequence_records,
+            nt_no_stop_sequence_records,
+            aa_sequence_records,
+            aa_no_stop_sequence_records,
+        )
+        info(f"Completed gene {gene_name} ({start} - {end})")
+
+
 def main():
     parser = argparse.ArgumentParser(
         prog="splitmsa",
@@ -391,69 +452,9 @@ def main():
     )
 
     args = parser.parse_args()
-
     logging.basicConfig(level=args.log_level.upper())
-
-    msa_records = list(read_msa_file(args.input))
-    info(f"MSA records read complete. Found {len(msa_records)} records.")
-    genes = []
-    if args.gene_list:
-        genes = read_genes_from_csv(args.gene_list)
-        info(f"Gene list read from {args.gene_list} resulted in {len(genes)} " "genes.")
-    else:
-        if args.gene_name and args.start and args.end:
-            genes.append([args.gene_name, args.start, args.end])
-            info(
-                f"Extracting {args.gene_name} starting at {args.start} to "
-                f"{args.end}."
-            )
-        else:
-            raise Exception(
-                "Need either a gene list by --gene-list or a start and end "
-                "via --start, and --end respectively."
-            )
-    for gene_name, start, end in genes:
-        info(f"Started on gene {gene_name} ({start} - {end})")
-        (
-            nt_sequence_records,
-            nt_no_stop_sequence_records,
-            aa_sequence_records,
-            aa_no_stop_sequence_records,
-            problems,
-        ) = trim(
-            start,
-            end,
-            args.gen_cut_stop_codon,
-            args.do_translate,
-            msa_records,
-            correction_range=args.correction_range,
-        )
-        if len(problems) > 0:
-            warning(
-                f"There were {len(problems)} problems " f"during trimming {gene_name}!"
-            )
-        if args.catalogue_problems:
-            output_as_csv(
-                gene_name,
-                problems,
-                os.path.join(args.output_dir, f"{gene_name} - problems.csv"),
-            )
-        write_to_file(
-            args.output_dir,
-            gene_name,
-            start,
-            end,
-            args.full_suffix,
-            args.ns_suffix,
-            args.aa_suffix,
-            nt_sequence_records,
-            nt_no_stop_sequence_records,
-            aa_sequence_records,
-            aa_no_stop_sequence_records,
-        )
-        info(f"Completed gene {gene_name} ({start} - {end})")
+    run(args)
 
 
 if __name__ == "__main__":
-
     main()