Merge pull request #17 from nishaq503/feat/dim-red-tool

Added tools for dimension reduction and quality assesment

features/dimension-reduction-quality-metrics-tool/.bumpversion.cfg

@@ -0,0 +1,33 @@
+[bumpversion]
+current_version = 0.1.0-dev0
+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:src/polus/tabular/features/dimension_reduction_quality_metrics/__init__.py]
+
+[bumpversion:file:dimensionreductionqualitymetrics.cwl]
+
+[bumpversion:file:ict.yaml]
+
+[bumpversion:file:plugin.json]
+
+[bumpversion:file:README.md]
+
+[bumpversion:file:VERSION]

features/dimension-reduction-quality-metrics-tool/Dockerfile

@@ -0,0 +1,25 @@
+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=".feather"
+ENV POLUS_LOG="INFO"
+
+# Work directory defined in the base container
+WORKDIR ${EXEC_DIR}
+
+# TODO: Change the tool_dir to the tool directory
+ENV TOOL_DIR="features/dimension-reduction-quality-metrics-tool"
+
+# Copy the repository into the container
+RUN mkdir tabular-tools
+COPY . ${EXEC_DIR}/tabular-tools
+
+# Install the tool
+RUN pip3 install "${EXEC_DIR}/tabular-tools/${TOOL_DIR}" --no-cache-dir
+
+# Set the entrypoint
+# TODO: Change the entrypoint to the tool entrypoint
+ENTRYPOINT ["python3", "-m", "polus.tabular.features.dimension_reduction_quality_metrics"]
+CMD ["--help"]

features/dimension-reduction-quality-metrics-tool/README.md

@@ -0,0 +1,55 @@
+# Dimension Reduction Quality Metrics (v0.1.0-dev0)
+
+This tool is used to measure the quality of dimensionality reductions.
+It provides the following methods for dimensionality reduction:
+
+1. False Nearest Neighbors (FNN).
+
+## FNN
+
+Consider a query in the original space and some of its nearest neighbors.
+Find the nearest neighbors of the query in the reduced space.
+If the nearest neighbors in the reduced space are not the same as the nearest neighbors in the original space, then the reduced space is not a good representation of the original space.
+FNN is the mean recall of the nearest neighbors in the reduced space over a large number of queries.
+
+## Parameters
+
+This tool takes the following parameters:
+
+1. `--originalDir`: Directory containing the original data.
+2. `--originalPattern`: Pattern to parse original files.
+3. `--embeddedDir`: Directory containing the reduced data.
+4. `--embeddedPattern`: Pattern to parse reduced files.
+5. `--numQueries`: Number of queries to use.
+6. `--ks`: Comma separated list of numbers of nearest neighbors to consider.
+7. `--distanceMetrics`: Comma separated list of distance metrics to use.
+8. `--qualityMetrics`: Comma separated list of quality metrics to use.
+9. `--outDir`: Output directory.
+10. `--preview`: Generate JSON file with outputs without running the tool.
+
+## Docker Container
+
+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.
+For more information on WIPP, visit the [official WIPP page](https://isg.nist.gov/deepzoomweb/software/wipp).
+
+## Options
+
+This plugin takes seven input arguments and one output argument:
+
+| Name                | Description                                               | I/O    | Type        | Default            |
+| ------------------- | --------------------------------------------------------- | ------ | ----------- | ------------------ |
+| `--originalDir`     | Directory containing the original data.                   | Input  | genericData | N/A                |
+| `--originalPattern` | Pattern to parse original files.                          | Input  | string      | ".*"               |
+| `--embeddedDir`     | Directory containing the reduced data.                    | Input  | genericData | N/A                |
+| `--embeddedPattern` | Pattern to parse reduced files.                           | Input  | string      | ".*"               |
+| `--numQueries`      | Number of queries to use.                                 | Input  | int         | 1000               |
+| `--ks`              | Comma separated list of numbers of nearest neighbors.     | Input  | string      | "10,100"           |
+| `--distanceMetrics` | Comma separated list of distance metrics to use.          | Input  | string      | "euclidean,cosine" |
+| `--qualityMetrics`  | Comma separated list of quality metrics to use.           | Input  | string      | "fnn"              |
+| `--outDir`          | Output directory.                                         | Output | genericData | N/A                |
+| `--preview`         | Generate JSON file with outputs without running the tool. | Input  | boolean     | False              |

features/dimension-reduction-quality-metrics-tool/VERSION

@@ -0,0 +1 @@
+0.1.0-dev0

features/dimension-reduction-quality-metrics-tool/build-docker.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+
+# TODO: Change the name of the tool here
+tool_dir="features"
+tool_name="dimension-reduction-quality-metrics-tool"
+
+# The version is read from the VERSION file
+version=$(<VERSION)
+tag="polusai/${tool_name}:${version}"
+echo "Building docker image with tag: ${tag}"
+
+# The current directory and the repository root are saved in variables
+cur_dir=$(pwd)
+repo_root=$(git rev-parse --show-toplevel)
+
+# The Dockerfile and .dockerignore files are copied to the repository root before building the image
+cd ${repo_root}
+cp ./${tool_dir}/${tool_name}/Dockerfile .
+cp .gitingore .dockerignore
+docker build . -t ${tag}
+rm Dockerfile .dockerignore
+cd ${cur_dir}

features/dimension-reduction-quality-metrics-tool/dimensionreductionqualitymetrics.cwl

@@ -0,0 +1,56 @@
+class: CommandLineTool
+cwlVersion: v1.2
+inputs:
+  originalDir:
+    inputBinding:
+      prefix: --originalDir
+    type: Directory
+  originalPattern:
+    inputBinding:
+      prefix: --originalPattern
+    type: string?
+  embeddedDir:
+    inputBinding:
+      prefix: --embeddedDir
+    type: Directory
+  embeddedPattern:
+    inputBinding:
+      prefix: --embeddedPattern
+    type: string?
+  numQueries:
+    inputBinding:
+      prefix: --numQueries
+    type: int?
+  ks:
+    inputBinding:
+      prefix: --ks
+    type: string?
+  distanceMetrics:
+    inputBinding:
+      prefix: --distanceMetrics
+    type: string?
+  qualityMetrics:
+    inputBinding:
+      prefix: --qualityMetrics
+    type: string?
+  outDir:
+    inputBinding:
+      prefix: --outDir
+    type: Directory
+  preview:
+    inputBinding:
+      prefix: --preview
+    type: boolean?
+outputs:
+  outDir:
+    outputBinding:
+      glob: $(inputs.outDir.basename)
+    type: Directory
+requirements:
+  DockerRequirement:
+    dockerPull: polusai/dimension-reduction-quality-metrics-tool:0.1.0-dev0
+  InitialWorkDirRequirement:
+    listing:
+    - entry: $(inputs.outDir)
+      writable: true
+  InlineJavascriptRequirement: {}

features/dimension-reduction-quality-metrics-tool/ict.yaml

@@ -0,0 +1,129 @@
+author: Najib Ishaq
+contact: najib.ishaq@nih.gov
+container: polusai/dimension-reduction-quality-metrics-tool:0.1.0-dev0
+description: Dimension reduction with various methods
+entrypoint: python3 -m polus.tabular.transforms.dimension_reduction_quality_metrics
+
+inputs:
+
+- description: Original tabular data
+  format:
+  - originalDir
+  name: originalDir
+  required: true
+  type: path
+
+- description: File pattern for the original data
+  format:
+  - originalPattern
+  name: originalPattern
+  required: false
+  type: string
+
+- description: Dimension reduced tabular data
+  format:
+  - embeddedDir
+  name: embeddedDir
+  required: true
+  type: path
+
+- description: File pattern for the embedded data
+  format:
+  - embeddedPattern
+  name: embeddedPattern
+  required: false
+  type: string
+
+- description: Number of queries to use
+  format:
+  - numQueries
+  name: numQueries
+  required: false
+  type: integer
+
+- description: Numbers of neighbors to use
+  format:
+  - ks
+  name: ks
+  required: false
+  type: string
+
+- description: Distance metrics to use
+  format:
+  - metrics
+  name: metrics
+  required: false
+  type: string
+
+- description: Quality metrics to use
+  format:
+  - qualityMetrics
+  name: qualityMetrics
+  required: false
+  type: string
+
+name: polusai/dimension-reduction-quality-metrics
+
+outputs:
+
+- description: Output collection
+  format:
+  - outDir
+  name: outDir
+  required: true
+  type: path
+
+repository: https://github.com/polusai/tabular-tools
+
+specVersion: 1.0.0
+
+title: Dimension Reduction Quality Metrics
+
+ui:
+
+- description: Original tabular data
+  key: inputs.originalDir
+  title: Original tabular data
+  type: path
+
+- description: Pattern to parse original files
+  key: inputs.originalPattern
+  title: OriginalPattern
+  type: text
+
+- description: Dimension reduced tabular data
+  key: inputs.embeddedDir
+  title: Dimension reduced tabular data
+  type: path
+
+- description: Pattern to parse embedded files
+  key: inputs.embeddedPattern
+  title: EmbeddedPattern
+  type: text
+
+- description: Output a JSON preview of outputs produced by this plugin
+  key: inputs.preview
+  title: Preview
+  type: boolean
+
+- description: Number of queries to use
+  key: inputs.numQueries
+  title: numQueries
+  type: integer
+
+- description: Numbers of neighbors to use
+  key: inputs.ks
+  title: ks
+  type: string
+
+- description: Distance metrics to use
+  key: inputs.metrics
+  title: metrics
+  type: string
+
+- description: Quality metrics to use
+  key: inputs.qualityMetrics
+  title: qualityMetrics
+  type: string
+
+version: 0.1.0-dev0