Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
41 commits
Select commit Hold shift + click to select a range
03703a8
fix: correct isTPS label assignment for precursor-substr entries
SamusRam Mar 14, 2026
cac715f
feat: add phylo-fold configs and regenerate baseline v0 CSV
SamusRam Mar 14, 2026
320047a
feat: add offline MMseqs2 per-fold similarity computation script
SamusRam Mar 14, 2026
7bc11d5
feat: extend evaluation with configurable similarity bins and MMseqs …
SamusRam Mar 14, 2026
e0c6d30
feat: port data-preparation utils and negative filters from revision …
SamusRam Mar 14, 2026
b73699d
Merge branch 'feature/mmseqs-similarity-artifact' into feature/port-c…
SamusRam Mar 24, 2026
af8ce1f
Merge branch 'feature/extend-eval-similarity-bins' into feature/port-…
SamusRam Mar 24, 2026
4fcc050
feat: cross-dataset evaluation with synchronized folds
SamusRam Mar 24, 2026
5d43ed5
feat: add Track D cross-dataset evaluation and multi-track configs
SamusRam Mar 28, 2026
b8cd1a6
docs: add local validation protocol with four-track design
SamusRam Mar 28, 2026
12a21e9
feat: add cross-track comparison visualization script
SamusRam Mar 28, 2026
07ddb91
Add script for producing a json with the EC to TPS substrate mapping
segef Mar 28, 2026
16c3afa
Use the propagated EC to substrates mapping in CLEAN model
segef Mar 28, 2026
d0af5a0
Add a new script to prepare datasets for CLEAN retraining and evaluation
segef Mar 28, 2026
34fc0f2
Change file extension of prepped clean data file to csv
segef Mar 28, 2026
0bb8210
Support running CLEAN from retrained models for each fold
segef Mar 28, 2026
f59e233
Adjust the CLEAN config file for retrained models
segef Mar 28, 2026
c150731
fix: exclude prenyltransferases from per-type TPS detection
SamusRam Apr 2, 2026
6a9edb3
docs: restructure validation protocol with five-track design
SamusRam Apr 2, 2026
daa9d8f
feat: add evaluation, analysis, and model variant scripts
SamusRam Apr 2, 2026
90fd2fc
feat: add configs for Track E, cross-track, and model variants
SamusRam Apr 2, 2026
b6f5323
data: add Track E dataset, extended EC mapping, and updated main dataset
SamusRam Apr 2, 2026
9cb6238
docs: remove CLEANBetterDetection, keep only CLEANEcDetection variant
SamusRam Apr 2, 2026
0aa8ce9
docs: add figure PNGs referenced by local_validation_protocol.md
SamusRam Apr 2, 2026
213080a
Fix CLEAN prediction logic by supporting prediction of multiple EC nu…
segef Apr 7, 2026
6993f63
remove local files from repo
segef Apr 7, 2026
2bcee83
Change clean_installation_root config default
segef Apr 7, 2026
62d1845
fix: merge PR #34 CLEAN logic and remove 'other' from _NON_TPS_LABELS
SamusRam Apr 7, 2026
8e053ef
fix: prevent substrate-bearing negatives from getting isTPS=True
SamusRam Apr 7, 2026
60a11a5
refactor: remove per-type macro AP evaluation, simplify figures
SamusRam Apr 7, 2026
0db5155
test: add mAP comparison script (with/without precursor substr)
SamusRam Apr 7, 2026
acbde2b
fix: remove TPS detection from heatmap, fix fold_agg priority
SamusRam Apr 7, 2026
89b3826
feat: add major-substrate heatmap (Figure 7) and sweep analysis
SamusRam Apr 11, 2026
8c5643a
docs: update major-substrate subset to cover all terpene families
SamusRam Apr 11, 2026
6491806
docs: update Blastp metrics after e-value confidence fix
SamusRam Apr 12, 2026
5a78f6b
fix: re-run Blastp/Foldseek with e_threshold=0.1, update heatmap colo…
SamusRam Apr 13, 2026
d56cb70
fix: remove CLEAN, retrain HMM & PlmDomainsRF, fix predict_proba bug
SamusRam Apr 14, 2026
964ea2c
docs: add changelog noting improved domain detection pipeline
SamusRam Apr 14, 2026
d0aa9d0
docs: add PDF/SVG figures and new per-type/domain analysis plots
SamusRam Apr 14, 2026
9a3278a
chore: remove outdated two-panel combined figures
SamusRam Apr 14, 2026
25cac54
fix: regenerate all figures from retrained model data
SamusRam Apr 14, 2026
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -6,3 +6,5 @@ __pycache__/

# data
/scripts/data/
stratified_phylogeny_based_split_with_minor_products
temp_conversation_export.md
574 changes: 574 additions & 0 deletions README_results_atomic.md

Large diffs are not rendered by default.

14,243 changes: 14,243 additions & 0 deletions data/EnzymeExplorer_Dataset.csv

Large diffs are not rendered by default.

19,539 changes: 9,772 additions & 9,767 deletions data/TPS-Nov19_2023_verified_all_reactions_with_folds.csv

Large diffs are not rendered by default.

20,422 changes: 10,165 additions & 10,257 deletions data/TPS-Nov19_2023_verified_all_reactions_with_neg_with_folds.csv

Large diffs are not rendered by default.

12,074 changes: 12,074 additions & 0 deletions data/TPS-Nov19_2023_with_synced_folds.csv

Large diffs are not rendered by default.

Loading
Loading