Predictor of Streptococcus pneumoniae MICs
Updated: Tue 1 Apr 08:02:53 BST 2025
Trained on the
Streptococcus pneumoniae, WT accumulator phenotype subset of the
human-curated SPARK dataset (1254 rows in total for
Streptococcus pneumoniae).
Model details
This model was trained using
our Duvida framework,
as a result of hyperparameter searches and selecting the model that performs best on unseen test data
(from a scaffold split).
Duvida also saves the training data in this checkpoint to allows the calculation of uncertainty metrics
based on that training data.
This model is the best regression model from a hyperparameter search, determined
by Pearson's $$r$$ on a held-out test set not used in training or early stopping.
Model architecture
1
2{
3 "dropout": 0.2,
4 "ensemble_size": 3,
5 "extra_featurizers": null,
6 "learning_rate": 0.0001,
7 "model_class": "ChempropModelBox",
8 "n_hidden": 5,
9 "n_units": 256,
10 "use_2d": true,
11 "use_fp": true
12}
Model usage
You can use this model with:
1from duvida.autoclasses import AutoModelBox
2modelbox = AutoModelBox.from_pretrained("hf://scbirlab/spark-dv-2503-spne")
3modelbox.predict(filename=..., inputs=[...], columns=[...]) # make predictions on your own data
Training details
- Dataset: SPARK, WT accumulator, Streptococcus pneumoniae subset (1254 rows in total for Streptococcus pneumoniae)
- Input column: smiles
- Output column: pmic
- Split type: Murcko scaffold
- Split proportions:
- 70% training (6 rows)
- 15% validation (for early stopping) (17 rows)
- 15% test (for selecting hyperparameters) (5 rows)
Here is the training log:
And these are the evaluation scores.
Train (6 rows):
1
2{
3 "Pearson r": 0.9940835972030041,
4 "RMSE": 0.06840968132019043,
5 "Spearman rho": 0.9851843661437779
6}
Validation (17 rows):
1
2{
3 "Pearson r": 0.9466036791965707,
4 "RMSE": 1.2293813228607178,
5 "Spearman rho": 0.8179032806479304
6}
Test (5 rows):
1
2{
3 "Pearson r": 0.5688338775794037,
4 "RMSE": 0.8309100866317749,
5 "Spearman rho": 0.3
6}
Training data details
The training data were collated by the authors of:
Joe Thomas, Marc Navre, Aileen Rubio, and Allan Coukell
Shared Platform for Antibiotic Research and Knowledge: A Collaborative Tool to SPARK Antibiotic Discovery
ACS Infectious Diseases 2018 4 (11), 1536-1539
DOI: 10.1021/acsinfecdis.8b00193
We cleaned the original SPARK dataset to subset the most relevant columns, remove empty values,
give succint column titles, and split by species.
This particular dataset retains only measurements on bacteria with wild-type accumulation phenotypes.
Dataset Sources
Data Collection and Processing
Data were processed using
schemist, a tool for processing chemical datasets.
The SMILES strings have been canonicalized, and split into training (70%), validation (15%), and test (15%) sets
by Murcko scaffold for each species with more than 1000 entries. Additional features like molecular weight and
topological polar surface area have also been calculated.
Who are the source data producers?
Joe Thomas, Marc Navre, Aileen Rubio, and Allan Coukell
