Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clean paper #6

Merged
merged 74 commits into from
Jan 29, 2025
Merged
Changes from 1 commit
Commits
Show all changes
74 commits
Select commit Hold shift + click to select a range
d429e4b
add symlinks, update clean paper data notebook
Aug 6, 2024
09e387c
finalize ZINC processing
Aug 6, 2024
e5d4561
minor changes - renaming, moving files
Aug 6, 2024
4cadb55
RASSP prediction for PBS
ljocha Aug 7, 2024
4f938db
Merge pull request #2 from ljocha/clean_paper
hejjack Aug 7, 2024
a71e6a7
Finish data preprocessing notebook without RASSP part
Aug 7, 2024
5cf355b
Clear outputs data_preprocessing.ipynb
Aug 7, 2024
503382a
filter non-digestible moledules
ljocha Aug 7, 2024
80d3aaa
fix relative paths etc.
ljocha Aug 8, 2024
3ee55b6
Merge branch 'clean_paper' of github.com:ljocha/gc-ms_bart into clean…
ljocha Aug 8, 2024
255db96
split smiles for RASSP and describe how to run the prediction
ljocha Aug 9, 2024
612f254
add reference to RASSP dockerized repo
ljocha Aug 9, 2024
54343ef
Merge branch 'clean_paper' of github.com:ljocha/gc-ms_bart into clean…
ljocha Aug 9, 2024
6d26734
do not strip suffixes for final output
ljocha Aug 9, 2024
9f0470b
Merge branch 'clean_paper' of github.com:ljocha/gc-ms_bart into clean…
ljocha Aug 9, 2024
af4cc1a
tune rassp instructions
ljocha Aug 9, 2024
48d2996
Merge pull request #3 from ljocha/clean_paper
hejjack Aug 18, 2024
488c1fa
neims prediction
ljocha Aug 21, 2024
f8812d7
Merge pull request #4 from ljocha/clean_paper
hejjack Aug 22, 2024
5d20afa
try annotate wiley dataset - not complete
Aug 22, 2024
f674ea0
fixingg spectra_utils and semi-final progress on NEIMS training
Aug 22, 2024
44e853a
Finish ntb3 ntb4 and continue working on ntb2 and ntb5
Aug 30, 2024
01d616e
Finish notebooks 5 and 6, replace all the occurences of "denovo" for …
Sep 1, 2024
7e73503
update gitignore
Sep 1, 2024
f8e02b0
finalize notebooks
Sep 9, 2024
a16ac6a
make mace predicitons
Sep 9, 2024
c08f0b7
change first runscript
Sep 9, 2024
191f26b
new configs from training on alfrid
Sep 15, 2024
d2e9eea
add configs for wiley
Sep 18, 2024
2a2c379
commit stashed predictions
Sep 18, 2024
33be3e8
add fp_ ti simil_function everywehere
Sep 18, 2024
8ea1c2f
add config runners
Sep 18, 2024
7e7b8d6
add more runscripts and config files
Sep 30, 2024
d4c04f2
runscripts, predictons, MSEC integration
Sep 30, 2024
ce6c323
how to train RASSP
ljocha Oct 9, 2024
253857e
Merge pull request #5 from ljocha/clean_paper
hejjack Oct 9, 2024
801e1f2
the stashed stuff -predictions, checking statistical significance and…
Oct 9, 2024
3d60bfd
mainly whitespace diffrences but also exp7 configs
Oct 11, 2024
5f9f625
final configs
Oct 11, 2024
f580b0e
check statistical significance found, new datasets - HS_format is onl…
Oct 21, 2024
e9617ff
new configs
Oct 21, 2024
333b3a3
the original functionaluty of precomputing index restored
Oct 21, 2024
7664e7b
one more config and a little change in evaluation
Oct 21, 2024
593339e
create predict_db_search
Oct 21, 2024
381fb98
Merge branch 'clean_paper' into evaluation_pipeline_reworking
Oct 21, 2024
9e5a9c4
Merge branch 'clean_paper' of https://github.com/hejjack/SpecTRUM int…
Oct 21, 2024
6796995
extend the predict_db_search_functionality to easy recomputations for…
Oct 22, 2024
97b3b2a
adding MW to evaluation pipeline, new predictions - mainly db search
Oct 22, 2024
e39ded7
prediction configs and predictions
Oct 22, 2024
009baf6
new predictions and compare_models.py script
Oct 24, 2024
803b8b0
change "percentage_of_" to "rate_of_"
Oct 24, 2024
6824912
impolement scripts for compraing models' performance
Oct 30, 2024
acb4437
new predictions and evaluations on extra libraries (Biiiiig commit)
Nov 7, 2024
d7f3c0f
final run configs
Nov 7, 2024
b0e0379
new predicions and evaluations
Nov 13, 2024
c0498f9
evaluate rcx, update eval vizu notebooks
Nov 15, 2024
08416e2
add new comparisons and evaluations
Nov 26, 2024
8b6f7fe
new predicitons (deprecated 9M), new configs, cleaning the evaluaiton
Jan 4, 2025
d002286
add new config and NIST smi splits
hejjack Jan 4, 2025
dcb5398
predictions of the BIG model + new configs
Jan 6, 2025
5dd6673
new predictions youthful wave
Jan 7, 2025
2c7359e
slight changes to compare models
Jan 7, 2025
43efc11
youthful wave evaluated
Jan 7, 2025
d649a9f
tidy config_runers a bit
Jan 7, 2025
576b1ee
sort model comparisons into folders
Jan 7, 2025
7689290
new predictions
Jan 7, 2025
329ed18
new predictions
Jan 8, 2025
e959307
new runner exp8 eval
Jan 8, 2025
dc6886f
new predictions
Jan 14, 2025
74d15ae
update configs
Jan 14, 2025
fe4f0a2
new results and little things
Jan 14, 2025
8bf5e44
MassBank evaluation
Jan 26, 2025
9c7d425
new repository structure
Jan 28, 2025
7dc0953
tokenier trainer
Jan 29, 2025
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
Prev Previous commit
Next Next commit
add reference to RASSP dockerized repo
  • Loading branch information
ljocha committed Aug 9, 2024
commit 612f254c02ff5fd3ce561214dfa597183d75f9c5
4 changes: 3 additions & 1 deletion clean_paper/notebooks/3_data_preprocessing.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -866,7 +866,9 @@
" qsub -q gpu -l walltime=24:00:00 -l select=1:ncpus=8:ngpus=1:mem=32gb:scratch_local=32gb -- ./rassp-pbs.sh $s\n",
" done\n",
"\n",
"After the jobs are finished, corresponding `*.jsonl` files are copied to the same folder. Concatenate them a and copy back here."
"After the jobs are finished, corresponding `*.jsonl` files are copied to the same folder. Concatenate them and copy back here.\n",
"\n",
"The docker container was built with Dockerfile available in [our fork of original RASSP repository](https://github.com/ljocha/rassp-public/tree/ljocha)."
]
},
{
Expand Down