Added tool for RT-CETSA MoltProt Regression

regression/rt-cetsa-moltprot-tool/.bumpversion.cfg

@@ -0,0 +1,31 @@
+[bumpversion]
+current_version = 0.1.0
+commit = True
+tag = False
+parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<dev>\d+))?
+serialize = 
+	{major}.{minor}.{patch}-{release}{dev}
+	{major}.{minor}.{patch}
+
+[bumpversion:part:release]
+optional_value = _
+first_value = dev
+values = 
+	dev
+	_
+
+[bumpversion:part:dev]
+
+[bumpversion:file:pyproject.toml]
+search = version = "{current_version}"
+replace = version = "{new_version}"
+
+[bumpversion:file:plugin.json]
+
+[bumpversion:file:VERSION]
+
+[bumpversion:file:README.md]
+
+[bumpversion:file:src/polus/tabular/regression/rt_cetsa_moltprot/__init__.py]
+
+[bumpversion:file:ict.yml]

regression/rt-cetsa-moltprot-tool/Dockerfile

@@ -0,0 +1,20 @@
+FROM polusai/bfio:2.3.6
+
+# environment variables defined in polusai/bfio
+ENV EXEC_DIR="/opt/executables"
+ENV POLUS_IMG_EXT=".ome.tif"
+ENV POLUS_TAB_EXT=".arrow"
+ENV POLUS_LOG="INFO"
+
+# Work directory defined in the base container
+WORKDIR ${EXEC_DIR}
+
+COPY pyproject.toml ${EXEC_DIR}
+COPY VERSION ${EXEC_DIR}
+COPY README.md ${EXEC_DIR}
+COPY src ${EXEC_DIR}/src
+
+RUN pip3 install ${EXEC_DIR} --no-cache-dir
+
+ENTRYPOINT ["python3", "-m", "polus.tabular.regression.rt_cetsa_moltprot"]
+CMD ["--help"]

regression/rt-cetsa-moltprot-tool/README.md

@@ -0,0 +1,24 @@
+# RT_CETSA Moltprot Regression (v0.1.0)
+
+This WIPP plugin runs regression analysis for the RT-CETSA pipeline.
+The input csv file should be sorted by `Temperature` column.
+
+## Building
+
+To build the Docker image for the conversion plugin, run
+`./build-docker.sh`.
+
+## Install WIPP Plugin
+
+If WIPP is running, navigate to the plugins page and add a new plugin. Paste the contents of `plugin.json` into the pop-up window and submit.
+
+## Options
+
+This plugin takes eight input argument and one output argument:
+
+| Name        | Description                                        | I/O    | Type        |
+|-------------|----------------------------------------------------|--------|-------------|
+| `--inpDir`  | Input data collection to be processed by this tool | Input  | genericData |
+| `--pattern` | Pattern to parse input files                       | Input  | string      |
+| `--outDir`  | Output file                                        | Output | genericData |
+| `--preview` | Generate JSON file with outputs                    | Output | JSON        |

regression/rt-cetsa-moltprot-tool/VERSION

@@ -0,0 +1 @@
+0.1.0

regression/rt-cetsa-moltprot-tool/ict.yml

@@ -0,0 +1,51 @@
+author:
+- Nick Schaub
+- Najib Ishaq
+contact: nick.schaub@nih.gov
+container: polusai/rt-cetsa-moltprot-tool:0.1.0
+description: Run regression analysis for the RT-CETSA pipeline.
+entrypoint: python3 -m polus.tabular.regression.rt_cetsa_moltprot
+inputs:
+- description: Input data collection to be processed by this tool
+  format:
+  - inpDir
+  name: inpDir
+  required: true
+  type: path
+- description: Filepattern to parse input files
+  format:
+  - pattern
+  name: pattern
+  required: false
+  type: string
+- description: Generate an output preview.
+  format:
+  - preview
+  name: preview
+  required: false
+  type: boolean
+name: polusai/RTCETSAMoltprot
+outputs:
+- description: Output collection
+  format:
+  - outDir
+  name: outDir
+  required: true
+  type: path
+repository: https://github.com/PolusAI/tabular-tools
+specVersion: 1.0.0
+title: RT-CETSA Moltprot
+ui:
+- description: Input data collection
+  key: inputs.inpDir
+  title: Input data collection
+  type: path
+- description: Filepattern to parse input files
+  key: inputs.pattern
+  title: pattern
+  type: text
+- description: Generate an output preview.
+  key: inputs.preview
+  title: Preview example output of this plugin
+  type: checkbox
+version: 0.1.0

regression/rt-cetsa-moltprot-tool/plugin.json

@@ -0,0 +1,52 @@
+{
+  "name": "RT-CETSA Moltprot",
+  "version": "0.1.0",
+  "title": "RT-CETSA Moltprot",
+  "description": "Run regression analysis for the RT-CETSA pipeline.",
+  "author": "Nicholas Schaub (nick.schaub@nih.gov), Najib Ishaq (najib.ishaq@nih.gov)",
+  "institution": "National Center for Advancing Translational Sciences, National Institutes of Health",
+  "repository": "https://github.com/PolusAI/tabular-tools",
+  "website": "https://ncats.nih.gov/preclinical/core/informatics",
+  "citation": "",
+  "containerId": "polusai/rt-cetsa-moltprot-tool:0.1.0",
+  "baseCommand": [
+    "python3",
+    "-m",
+    "polus.tabular.regression.rt_cetsa_moltprot"
+  ],
+  "inputs": [
+    {
+      "name": "inpDir",
+      "type": "genericData",
+      "description": "Input data collection to be processed by this tool",
+      "required": true
+    },
+    {
+      "name": "pattern",
+      "type": "string",
+      "description": "Pattern to parse input files",
+      "default": ".+",
+      "required": false
+    }
+  ],
+  "outputs": [
+    {
+      "name": "outDir",
+      "type": "genericData",
+      "description": "Output data collection"
+    }
+  ],
+  "ui": [
+    {
+      "key": "inputs.inpDir",
+      "title": "Input collection",
+      "description": "Input data collection to be processed by this plugin"
+    },
+    {
+      "key": "inputs.pattern",
+      "title": "pattern",
+      "description": "Pattern to parse input files",
+      "default": ".+"
+    }
+  ]
+}

regression/rt-cetsa-moltprot-tool/pyproject.toml

@@ -0,0 +1,76 @@
+[tool.poetry]
+name = "polus_tabular_regression_rt_cetsa_moltprot"
+version = "0.1.0"
+description = "Run regression analysis for the RT-CETSA pipeline."
+authors = [
+    "Nick Schaub <nick.schaub@nih.gov>",
+    "Najib Ishaq <najib.ishaq@nih.gov>",
+]
+readme = "README.md"
+packages = [{include = "polus", from = "src"}]
+
+[tool.poetry.dependencies]
+python = ">=3.9,<3.12"
+typer = "^0.7.0"
+filepattern = "^2.0.5"
+pandas = "^2.2.2"
+matplotlib = "^3.8.4"
+scipy = "^1.13.0"
+
+[tool.poetry.group.dev.dependencies]
+bump2version = "^1.0.1"
+pre-commit = "^3.1.0"
+pytest = "^7.2.1"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.ruff]
+extend = "../../ruff.toml"
+extend-ignore = [
+    "RET505",  # Unnecessary `else` after `return` statement
+    "E501",  # Line too long
+    "ANN001",  # Missing type annotation
+    "D102",  # Missing docstring in public method
+    "ANN201",  # Missing return type annotation
+    "N806",  # Variable in function should be lowercase
+    "D205",  # 1 blank line required between summary line and description
+    "N803",  # Argument name should be lowercase
+    "PLR0913",  # Too many arguments
+    "D415",  # First line should end with a period, question mark, or exclamation point
+    "PLR2004",  # Magic value used in comparison
+    "B006",  # Do not use mutable default arguments
+    "D107",  # Missing docstring
+    "D101",  # Missing docstring
+    "E731",  # Do not assign a lambda expression, use a def
+    "E402",  # Module level import not at top of file
+    "PTH123",  # `open()` should be replaced with `Path.open()`
+    "PTH118",  # `os.path.join()` should be replaced with `/` operator
+    "PTH100",  # `os.path.abspath()` should be replaced with `Path.resolve()`
+    "PLR0915",  # Too many statements
+    "PLR0912",  # Too many branches
+    "C901",  # Function is too complex
+    "T201",  # `print` used
+    "E722",  # Do not use bare 'except'
+    "B904",  # Within an `except` clause, raise exceptions with `raise ... from err` or `raise ... from None` to distinguish them from errors in exception handling
+    "ANN202",  # Missing return type annotation for private function
+    "ARG002",  # Unused method argument
+    "N802",  # Function name should be lowercase
+    "PTH103",  # `os.makedirs()` should be replaced with `Path.mkdir(parents=True)`
+    "ANN003",  # Missing type annotation for `**kwargs`
+    "B007",  # Loop control variable not used within the loop body
+    "ANN204",  # Missing return type annotation for magic method
+    "D417",  # Missing argument descriptions in the docstring
+    "ANN205",  # Missing return type annotation for static method
+    "PLR5501",  # Use `elif` instead of `else` following `if` condition to avoid unnecessary indentation
+    "EM102",  # Exception must not use an f-string literal
+    "D414",  # Section has no content
+    "RUF012",  # Mutable class attributes should be annotated with `typing.ClassVar`
+    "A001",  # Variable `input` is shadowing a Python builtin
+    "A002",  # Argument `input` is shadowing a Python builtin
+    "E741",  # Ambiguous variable name: `l`
+    "PTH120",  # `os.path.dirname()` should be replaced by `Path.parent`
+    "N816",  # Variable `cfFilename` in global scope should not be mixedCase
+    "PTH109",  # `os.getcwd()` should be replaced by `Path.cwd()`
+]

regression/rt-cetsa-moltprot-tool/run-plugin.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+version=$(<VERSION)
+datapath=$(readlink --canonicalize data)
+
+# Inputs
+inpDir=/data/input
+pattern=".*"
+
+# Output paths
+outDir=/data/output
+
+# Log level, must be one of ERROR, CRITICAL, WARNING, INFO, DEBUG
+LOGLEVEL=INFO
+
+docker run --mount type=bind,source=${datapath},target=/data/  \
+            --env POLUS_LOG=${LOGLEVEL} \
+            polusai/rt-cetsa-moltprot-tool:${version} \
+            --inpDir ${inpDir} \
+            --pattern ${pattern} \
+            --outDir ${outDir}

regression/rt-cetsa-moltprot-tool/src/polus/tabular/regression/rt_cetsa_moltprot/VERSION

@@ -0,0 +1 @@
+0.3.1-alpha

regression/rt-cetsa-moltprot-tool/src/polus/tabular/regression/rt_cetsa_moltprot/__init__.py

@@ -0,0 +1,45 @@
+"""RT_CETSA Moltprot Regression Tool."""
+
+__version__ = "0.1.0"
+
+import os
+import pathlib
+
+import pandas
+
+from . import core
+from . import models
+
+POLUS_TAB_EXT = os.environ.get("POLUS_TAB_EXT", ".csv")
+
+
+def fit_data(
+    file_path: pathlib.Path,
+    params: dict[str, float],
+) -> pandas.DataFrame:
+    """Fit data to a model using Moltprot."""
+    fit = core.MoltenProtFit(
+        filename=file_path,
+        input_type="csv",
+    )
+
+    fit.SetAnalysisOptions(
+        model="santoro1988",
+        blanks=[],
+        exclude=[],
+        invert=False,
+        mfilt=None,
+        shrink=None,
+        **params,
+    )
+
+    fit.PrepareData()
+    fit.ProcessData()
+
+    return fit.plate_results.sort_values("BS_factor")
+
+
+def gen_out_path(file_path: pathlib.Path, out_dir: pathlib.Path) -> pathlib.Path:
+    """Generate the output path."""
+    file_name = file_path.stem + "_moltprot" + POLUS_TAB_EXT
+    return out_dir / file_name