feat: add optional FINE_TUNE_MODELS step for DL model fine-tuning#54
Open
feat: add optional FINE_TUNE_MODELS step for DL model fine-tuning#54
Conversation
When --enable_fine_tuning is enabled, the pipeline: 1. Runs the standard flow through ASSEMBLE_EMPIRICAL_LIBRARY 2. Fine-tunes RT/IM (optionally fragment) models on the empirical library 3. Re-generates the in-silico library using tuned models (--tokens, --rt-model, --im-model) 4. Uses the tuned library for INDIVIDUAL_ANALYSIS and FINAL_QUANTIFICATION New parameters: --enable_fine_tuning (default: false) — enable the fine-tuning step --tune_fr (default: false) — also fine-tune the fragmentation model --tune_lr (default: DIA-NN's 0.0005) — fine-tuning learning rate New module: modules/local/diann/fine_tune_models/ - Takes empirical library + FASTA + diann_config - Runs diann --tune-lib --tune-rt --tune-im - Outputs: dict.txt, rt.d0.pt, im.d0.pt (optionally fr.d0.pt) INSILICO_LIBRARY_GENERATION updated with optional tuned model inputs (pass [] when not fine-tuning, actual files when fine-tuning). Version guard: requires DIA-NN >= 2.0. Cannot be combined with --skip_preliminary_analysis. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
Important Review skippedAuto reviews are disabled on base/target branches other than the default branch. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
Per Vadim Demichev's recommendation, fine-tuning should run as a separate phase BEFORE the main analysis, not mid-pipeline: Phase 0 (when --enable_fine_tuning): 1. INSILICO_LIBRARY_GENERATION (default models) 2. TUNE_PRELIMINARY_ANALYSIS (on --tune_n_files subset) 3. TUNE_ASSEMBLE_LIBRARY (empirical library from subset) 4. FINE_TUNE_MODELS (train RT/IM/fragment models) 5. TUNED_LIBRARY_GENERATION (re-generate with tuned models) Phase 1 (always, the standard pipeline): Uses tuned in-silico library (or default if no fine-tuning) PRELIMINARY_ANALYSIS → ASSEMBLE → INDIVIDUAL → FINAL New parameter: --tune_n_files (default: 3) — number of files for the tuning search subset. Uses Nextflow process aliases (TUNE_PRELIMINARY_ANALYSIS, TUNE_ASSEMBLE_LIBRARY, TUNED_LIBRARY_GENERATION) to avoid duplicate process invocation conflicts. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds an optional model fine-tuning step to the pipeline, eliminating the need for two separate pipeline runs when working with non-standard modifications.
How it works
When
--enable_fine_tuningis enabled:FINE_TUNE_MODELStrains RT/IM models on the empirical library (--tune-lib --tune-rt --tune-im)TUNED_LIBRARY_GENERATIONregenerates the in-silico library with tuned models (--tokens,--rt-model,--im-model)New parameters
--enable_fine_tuningfalse--tune_frfalse--tune_lrnullWhen to use
Fine-tuning is beneficial for:
Standard modifications (Phospho, Oxidation, Acetylation, etc.) do not need fine-tuning.
Version requirement
Requires DIA-NN >= 2.0. Cannot be combined with
--skip_preliminary_analysis.Test plan
--enable_fine_tuning false(default) — verify no FINE_TUNE step appears--enable_fine_tuning trueon DIA-NN 2.x — verify tuning + library regeneration--enable_fine_tuning trueon DIA-NN 1.8.1 — verify version guard error--enable_fine_tuning true --skip_preliminary_analysis true— verify conflict error🤖 Generated with Claude Code