Feat sklearn single baseline by tonyliang19 · Pull Request #115 · CompBio-Lab/MESSI-pipeline

tonyliang19 · 2026-09-29T14:20:37Z

No description provided.

Major change to prepare data, seed reproduce

feat: add the final samplesheet used for the pipeline

…temp var option

…cli and config

…ight classifiers

…funs

…d to sklearn logistic regressions only

Copilot

Copilot review overview

🟡 Changes recommended

The baseline is skipped by default, and independently generated modality folds may compare different subjects.

Review effort: Balanced
Findings: 2 · 1

Open (3)

Stale SGMR branch calls an undefined workflow · New
Row-position splits misalign samples across modalities · New
Single-modality mode skips its only sklearn consumer · New

What changed in this PR

This PR adds single-modality sklearn baselines to the MESSI benchmark pipeline and reorganizes related method and container configuration.

Changes:

Creates per-modality MuData datasets and routes them through splitting and cross-validation.
Adds sklearn reduction and classifier options, shared Python utilities, and revised metrics.
Centralizes container selection and removes simulation and unfinished method code.

File	Description
`workflows/messi_benchmark.nf`	Routes per-modality datasets into splitting and validation.
`subworkflows/splitting/main.nf`	Passes outcome type to splitting.
`subworkflows/simulation/main.nf`	Removes the simulation workflow.
`subworkflows/prepare_data/main.nf`	Emits per-modality MuData datasets.
`subworkflows/methods/sklearn/main.nf`	Adds reduction choices to sklearn training.
`subworkflows/methods/sgmr/main.nf`	Removes the SGMR workflow.
`subworkflows/cross_validation/r/main.nf`	Removes the SGMR import.
`subworkflows/cross_validation/python/main.nf`	Routes per-modality data to sklearn; removes GOAT routing.
`subworkflows/cross_validation/main.nf`	Joins per-modality data with split indices.
`nextflow.config`	Adds mode, reduction, outcome, and container settings.
`modules/split_train_test/resources/usr/bin/split_tr_te.py`	Adds outcome-aware splitting input.
`modules/split_train_test/main.nf`	Passes outcome type and uses a container label.
`modules/sklearn/train/resources/usr/bin/sklearn_train.py`	Adds modality-wise PCA training.
`modules/sklearn/train/resources/usr/bin/load_classifier_class.py`	Removes the local classifier registry.
`modules/sklearn/train/resources/usr/bin/combine_mdata2df.py`	Removes the local MuData converter.
`modules/sklearn/train/main.nf`	Passes reduction settings into training.
`modules/sklearn/select_feature/resources/usr/bin/sklearn_select_features.py`	Uses the shared converter and fitted search result.
`modules/sklearn/select_feature/resources/usr/bin/run_random_search_cv.py`	Searches over a scaling pipeline.
`modules/sklearn/select_feature/resources/usr/bin/combine_mdata2df.py`	Removes the local MuData converter.
`modules/sklearn/select_feature/main.nf`	Uses a sklearn container label.
`modules/sklearn/preprocess/main.nf`	Uses a sklearn container label.
`modules/sklearn/predict/resources/usr/bin/sklearn_predict.py`	Uses the shared MuData converter.
`modules/sklearn/predict/resources/usr/bin/combine_mdata2df.py`	Removes the local MuData converter.
`modules/sklearn/predict/main.nf`	Uses a sklearn container label.
`modules/simulation/simulate_mvn_data/resources/usr/bin/unique_matrices.R`	Removes an MVN simulation helper.
`modules/simulation/simulate_mvn_data/resources/usr/bin/simulate_data.R`	Removes the MVN simulation script.
`modules/simulation/simulate_mvn_data/resources/usr/bin/gen_simul_metadata.R`	Removes an MVN metadata helper.
`modules/simulation/simulate_mvn_data/resources/usr/bin/debug_simulate_data.R`	Removes an MVN debugging script.
`modules/simulation/simulate_mvn_data/main.nf`	Removes the MVN simulation process.
`modules/simulation/simulate_intersim/resources/usr/bin/simulate_InterSIM.R`	Removes the InterSIM script.
`modules/simulation/simulate_intersim/resources/usr/bin/save_mudata.py`	Removes an InterSIM output helper.
`modules/simulation/simulate_intersim/main.nf`	Removes the InterSIM process.
`modules/rgcca/train/main.nf`	Uses an RGCCA container label.
`modules/rgcca/select_feature/main.nf`	Uses an RGCCA container label.
`modules/rgcca/preprocess/main.nf`	Uses an RGCCA container label.
`modules/rgcca/predict/main.nf`	Uses an RGCCA container label.
`modules/prepare_data/uncompress_record/main.nf`	Uses a generic container label.
`modules/prepare_data/split_modality/resources/usr/bin/split_modalities.py`	Writes single-modality MuData files.
`modules/prepare_data/split_modality/main.nf`	Adds the modality-splitting process.
`modules/prepare_data/prepare_mu_data/main.nf`	Uses a generic container label.
`modules/prepare_data/prepare_mae_data/main.nf`	Uses a generic container label.
`modules/prepare_data/parse_metadata/main.nf`	Uses a generic container label.
`modules/mogonet/train/main.nf`	Uses a MOGONET container label.
`modules/mogonet/select_feature/main.nf`	Uses a MOGONET container label.
`modules/mogonet/preprocess/main.nf`	Uses a MOGONET container label.
`modules/mogonet/predict/main.nf`	Uses a MOGONET container label.
`modules/mofa/train/main.nf`	Uses a MOFA container label.
`modules/mofa/select_feature/main.nf`	Uses a MOFA container label.
`modules/mofa/preprocess/main.nf`	Uses a MOFA container label.
`modules/mofa/predict/main.nf`	Uses a MOFA container label.
`modules/merge_selected_features/main.nf`	Uses a CODIA container label.
`modules/merge_result_table/main.nf`	Uses a CODIA container label.
`modules/local/samplesheet_check/main.nf`	Uses a MOGONET container label.
`modules/integrao/train/main.nf`	Uses an INTEGRAO container label.
`modules/integrao/select_feature/main.nf`	Uses an INTEGRAO container label.
`modules/integrao/preprocess/main.nf`	Uses an INTEGRAO container label.
`modules/integrao/predict/main.nf`	Uses an INTEGRAO container label.
`modules/goat/resource/usr/bin/run_goat.py`	No textual diff was provided for this path.
`modules/goat/main.nf`	Removes the GOAT process.
`modules/diablo/train/main.nf`	Uses a CODIA container label.
`modules/diablo/select_feature/main.nf`	Uses a CODIA container label.
`modules/diablo/preprocess/main.nf`	Uses a CODIA container label.
`modules/diablo/predict/main.nf`	Uses a CODIA container label.
`modules/diablo/downstream/main.nf`	Uses a CODIA container label.
`modules/cooperative_learning/train/main.nf`	Uses a CODIA container label.
`modules/cooperative_learning/select_feature/main.nf`	Uses a CODIA container label.
`modules/cooperative_learning/preprocess/main.nf`	Uses a CODIA container label.
`modules/cooperative_learning/predict/main.nf`	Uses a CODIA container label.
`modules/caret_multimodal/train/main.nf`	Uses a caret container label.
`modules/caret_multimodal/select_feature/main.nf`	Uses a caret container label.
`modules/caret_multimodal/preprocess/main.nf`	Uses a caret container label.
`modules/caret_multimodal/predict/main.nf`	Uses a caret container label.
`modules/calculate_metrics/resources/usr/bin/calculate_metrics.py`	Revises classification metrics.
`modules/calculate_metrics/main.nf`	Uses a MOGONET container label.
`conf/real_data.config`	Corrects the feature-selection parameter name.
`bin/python_utils/load_classifier_class.py`	Expands the shared classifier registry.
`bin/python_utils/combine_mdata2df.py`	Adds a shared MuData converter.

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

+include { CARET_MULTIMODAL }      from "${subworkflowDir}/methods/caret_multimodal"
+include { DEMO_LOGIT }            from "${subworkflowDir}/methods/demo_logit"


+      //
+
+      SPLITTING (	
+        PREPARE_DATA.out.mu_data.mix ( PREPARE_DATA.out.mu_data_unimodal ), 


    if (!skip_sklearn) {
-        SKLEARN ( mu_copy )
+        // Mix inputs of mudata and unimodal
+        SKLEARN ( mu_copy.mix( mu_copy_unimodal ) )


tonyliang19 added 24 commits February 27, 2026 19:11

Merge pull request #110 from CompBio-Lab/dev

138cd5a

Major change to prepare data, seed reproduce

Merge pull request #111 from CompBio-Lab/dev

85b2b54

feat: add the final samplesheet used for the pipeline

fix: move container option to process level config, and remove stale …

e308292

…temp var option

fix: moved all container definition into config

b0c6ba5

fix: changed wrong syntax, adding args to pass in splitting modules, …

09c4905

…cli and config

fix: lint conf syntax, included back sklearn

0819287

rm: remove old files

5f7cd2e

rm: remove redundant staled configs

0ac61ac

fix: rename metric labels

2da5e23

rm: remove deprecated workflows

939ac4c

feat: sklearn to use pca50 or no reduction for more models

7944abd

fix: update method options

ec7e648

fix: include select feature for sklearn models

e5ef195

fix: correct sklearn reduction to list param rather than singleton

7c99113

fix: correct naming of parameter opt

6f0ee70

fix: make sure sklearn cv search works even with make_pipeline

0ce67f6

fix: use eipy container for sklearn as it contains xgboost, and use r…

b66e821

…ight classifiers

fix: moved common sklearn utils to bin/python_utils, and standardize …

e190ae8

…funs

fix: refactor code for sklearn select feature

e0956f7

feat: update sklearn random search cv params as roc

44547e9

fix: finalize models in sklearn

36a5963

feat: add new option of sklearn single modality

09fbe25

feat: include functionality to handle single modality running, limite…

eaefa01

…d to sklearn logistic regressions only

feat: include missing scripts of splitting modalities

43753b9

Copilot AI balanced review requested due to automatic review settings September 29, 2026 14:20

Copilot started reviewing on behalf of tonyliang19 September 29, 2026 14:21 View session

tonyliang19 merged commit 86c1816 into dev Sep 29, 2026
1 check passed

Copilot AI reviewed Sep 29, 2026

View reviewed changes

Navigation Menu

Repository navigation

Feat sklearn single baseline - #115

Feat sklearn single baseline#115
tonyliang19 merged 24 commits into
devfrom
feat-sklearn-single-baseline

tonyliang19 commented Sep 29, 2026

Uh oh!

Uh oh!

Copilot AI left a comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

		include { CARET_MULTIMODAL } from "${subworkflowDir}/methods/caret_multimodal"
		include { DEMO_LOGIT } from "${subworkflowDir}/methods/demo_logit"

Conversation

tonyliang19 commented Sep 29, 2026

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Copilot review overview

🟡 Changes recommended

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants