Upload folder using huggingface_hub

README.md

@@ -0,0 +1,140 @@
+---
+license: mit
+pipeline_tag: tabular-regression
+tags:
+- chemistry
+- microbiology
+- antibiotics
+library_name: duvida
+datasets:
+- scbirlab/thomas-2018-spark-wt
+---
+
+# Predictor of _Streptococcus pneumoniae_ MICs 
+
+_Updated:_ Fri 28 Mar 18:11:42 GMT 2025
+
+Trained on the _Streptococcus pneumoniae_, WT accumulator phenotype subset of the [human-curated SPARK dataset](https://doi.org/10.1021/acsinfecdis.8b00193) ( rows in total for _Streptococcus pneumoniae_).
+
+## Model details
+
+This model was trained using [our Duvida framework](https://github.com/scbirlab/duvida), 
+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 Spearman's $\rho$ on a held-out test set not used in training or early stopping. 
+
+### Model architecture
+
+- **Regression**
+
+```json
+
+{
+    "dropout": 0.2,
+    "ensemble_size": 10,
+    "extra_featurizers": null,
+    "learning_rate": 0.0001,
+    "model_class": "ChempropModelBox",
+    "n_hidden": 5,
+    "n_units": 256,
+    "use_2d": true,
+    "use_fp": true
+}
+```
+
+### Model usage
+
+You can use this model with:
+
+```python
+from duvida.autoclasses import AutoModelBox
+modelbox = AutoModelBox.from_pretrained("hf://scbirlab/spark-dv-2503-spne")
+modelbox.predict(filename=..., inputs=[...], columns=[...])  # make predictions on your own data
+```
+
+## Training details
+
+- **Dataset:** [SPARK, WT accumulator, _Streptococcus pneumoniae_ subset](https://huggingface.co/datasets/scbirlab/thomas-2018-spark-wt)
+- **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:
+
+<img src="training-log.png" width=450>
+
+And these are the evaluation scores.
+
+Train (6 rows):
+
+```json
+
+{
+    "Pearson r": 0.4138370404282536,
+    "RMSE": 0.3910311758518219,
+    "Spearman rho": 0.818181818181818
+}
+```
+
+Validation (17 rows):
+
+```json
+
+{
+    "Pearson r": 0.954468386191219,
+    "RMSE": 1.128600001335144,
+    "Spearman rho": 0.8730841616511641
+}
+```
+
+
+Test (5 rows):
+
+```json
+
+{
+    "Pearson r": 0.3867792333436302,
+    "RMSE": 0.8993263244628906,
+    "Spearman rho": 0.09999999999999999
+}
+```
+
+## 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
+
+- **Repository:** https://www.collaborativedrug.com/spark-data-downloads
+- **Paper:** https://doi.org/10.1021/acsinfecdis.8b00193
+
+### Data Collection and Processing
+
+Data were processed using [schemist](https://github.com/scbirlab/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

data-config.json

@@ -0,0 +1,17 @@
+{
+    "_default_cache": "cache/duvida/data",
+    "_in_key": "inputs",
+    "_input_cols": [
+        "smiles"
+    ],
+    "_label_cols": [
+        "pmic"
+    ],
+    "_out_key": "labels",
+    "input_shape": [
+        2248
+    ],
+    "output_shape": [
+        1
+    ]
+}

data-load-args.json

@@ -0,0 +1,10 @@
+{
+    "cache": "/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/models/spark/Streptococcus-pneumoniae/79/cache",
+    "features": [
+        "smiles"
+    ],
+    "filename": "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-train.csv.gz",
+    "labels": [
+        "pmic"
+    ]
+}

eval-metrics_test.json

@@ -0,0 +1,5 @@
+{
+    "Pearson r": 0.3867792333436302,
+    "RMSE": 0.8993263244628906,
+    "Spearman rho": 0.09999999999999999
+}

eval-metrics_train.json

@@ -0,0 +1,5 @@
+{
+    "Pearson r": 0.4138370404282536,
+    "RMSE": 0.3910311758518219,
+    "Spearman rho": 0.818181818181818
+}

eval-metrics_validation.json

@@ -0,0 +1,5 @@
+{
+    "Pearson r": 0.954468386191219,
+    "RMSE": 1.128600001335144,
+    "Spearman rho": 0.8730841616511641
+}

input-data.hf/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664224d98a51c44eb85b3aa3c2ee0ac092ef6ec90caa9f2d0b6358e75ec94af3
+size 1944

input-data.hf/dataset_info.json

@@ -0,0 +1,52 @@
+{
+  "builder_name": "csv",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "csv",
+  "dataset_size": 2735,
+  "description": "",
+  "download_checksums": {
+    "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-train.csv.gz": {
+      "num_bytes": 1012,
+      "checksum": null
+    }
+  },
+  "download_size": 1012,
+  "features": {
+    "smiles": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "inputs": {
+      "feature": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "labels": {
+      "feature": {
+        "dtype": "float64",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 3747,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 2735,
+      "num_examples": 6,
+      "dataset_name": "csv"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

input-data.hf/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "cc1fa05b3dc69da9",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": "train"
+}

logs-csv/lightning_logs/version_0/hparams.yaml

@@ -0,0 +1 @@
+{}

logs-csv/lightning_logs/version_0/metrics.csv

@@ -0,0 +1,107 @@
+epoch,loss,step,val_loss
+0,,0,28.506013870239258
+0,35.035179138183594,0,
+1,,1,28.133272171020508
+1,34.59953308105469,1,
+2,,2,27.75455093383789
+2,34.28255081176758,2,
+3,,3,27.360851287841797
+3,33.872459411621094,3,
+4,,4,26.94652557373047
+4,33.49507141113281,4,
+5,,5,26.503360748291016
+5,32.932044982910156,5,
+6,,6,26.024642944335938
+6,32.40605163574219,6,
+7,,7,25.50464630126953
+7,31.995607376098633,7,
+8,,8,24.93709945678711
+8,31.35414695739746,8,
+9,,9,24.317028045654297
+9,30.852384567260742,9,
+10,,10,23.639673233032227
+10,30.293041229248047,10,
+11,,11,22.898895263671875
+11,29.3199462890625,11,
+12,,12,22.09198760986328
+12,28.761568069458008,12,
+13,,13,21.21438980102539
+13,27.734697341918945,13,
+14,,14,20.263683319091797
+14,26.935657501220703,14,
+15,,15,19.238662719726562
+15,25.863750457763672,15,
+16,,16,18.138511657714844
+16,24.692529678344727,16,
+17,,17,16.965312957763672
+17,23.58732795715332,17,
+18,,18,15.723073959350586
+18,22.249080657958984,18,
+19,,19,14.418327331542969
+19,20.945390701293945,19,
+20,,20,13.059042930603027
+20,19.49625587463379,20,
+21,,21,11.65770435333252
+21,18.035572052001953,21,
+22,,22,10.229310035705566
+22,16.04208755493164,22,
+23,,23,8.793594360351562
+23,14.609708786010742,23,
+24,,24,7.373780250549316
+24,12.870007514953613,24,
+25,,25,5.998498916625977
+25,11.573694229125977,25,
+26,,26,4.699665546417236
+26,9.815820693969727,26,
+27,,27,3.513622283935547
+27,7.948325157165527,27,
+28,,28,2.480156421661377
+28,6.660716533660889,28,
+29,,29,1.6397855281829834
+29,5.119527339935303,29,
+30,,30,1.0356911420822144
+30,3.504617214202881,30,
+31,,31,0.7050375938415527
+31,2.7646963596343994,31,
+32,,32,0.6781078577041626
+32,1.6973930597305298,32,
+33,,33,0.9667624831199646
+33,1.075992226600647,33,
+34,,34,1.556015133857727
+34,0.6845546960830688,34,
+35,,35,2.3837873935699463
+35,0.3879012167453766,35,
+36,,36,3.3532373905181885
+36,0.4765850305557251,36,
+37,,37,4.322829723358154
+37,0.8820050954818726,37,
+38,,38,5.122341632843018
+38,1.508744478225708,38,
+39,,39,5.632863998413086
+39,2.0902042388916016,39,
+40,,40,5.850592136383057
+40,1.9949707984924316,40,
+41,,41,5.758612632751465
+41,2.3712332248687744,41,
+42,,42,5.433818817138672
+42,2.0827255249023438,42,
+43,,43,4.966310977935791
+43,1.8089426755905151,43,
+44,,44,4.401313781738281
+44,1.557389497756958,44,
+45,,45,3.8155436515808105
+45,1.2402079105377197,45,
+46,,46,3.2567148208618164
+46,0.9037799835205078,46,
+47,,47,2.732806444168091
+47,0.9471979141235352,47,
+48,,48,2.27205228805542
+48,0.7469801306724548,48,
+49,,49,1.8864364624023438
+49,0.53239905834198,49,
+50,,50,1.578837513923645
+50,0.5718014240264893,50,
+51,,51,1.3402189016342163
+51,0.43722790479660034,51,
+52,,52,1.1567370891571045
+52,0.531734824180603,52,

logs/lightning_logs/version_0/events.out.tfevents.1743098122.cn039.615154.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01026284649bd26dad5e642d94360445033c0f20a21b44c3fda6d3ddc3b61108
+size 9302

logs/lightning_logs/version_0/hparams.yaml

@@ -0,0 +1 @@
+{}

metrics.csv

@@ -0,0 +1,4 @@
+split,split_filename,config_i,model_class,n_parameters,filename,features,labels,cache,extra_featurizers,use_2d,use_fp,dropout,ensemble_size,learning_rate,n_hidden,n_units,val_filename,epochs,batch_size,RMSE,Pearson r,Spearman rho
+train,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-train.csv.gz,79,ChempropModelBox,11436690,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-train.csv.gz,['smiles'],['pmic'],/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/models/spark/Streptococcus-pneumoniae/79/cache,,True,True,0.2,10,0.0001,5,256,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-validation.csv.gz,2000,16,0.3910311758518219,0.4138370404282536,0.818181818181818
+validation,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-validation.csv.gz,79,ChempropModelBox,11436690,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-train.csv.gz,['smiles'],['pmic'],/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/models/spark/Streptococcus-pneumoniae/79/cache,,True,True,0.2,10,0.0001,5,256,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-validation.csv.gz,2000,16,1.128600001335144,0.954468386191219,0.8730841616511641
+test,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-test.csv.gz,79,ChempropModelBox,11436690,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-train.csv.gz,['smiles'],['pmic'],/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/models/spark/Streptococcus-pneumoniae/79/cache,,True,True,0.2,10,0.0001,5,256,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-validation.csv.gz,2000,16,0.8993263244628906,0.3867792333436302,0.09999999999999999

modelbox-config.json

@@ -0,0 +1,11 @@
+{
+    "dropout": 0.2,
+    "ensemble_size": 10,
+    "extra_featurizers": null,
+    "learning_rate": 0.0001,
+    "model_class": "ChempropModelBox",
+    "n_hidden": 5,
+    "n_units": 256,
+    "use_2d": true,
+    "use_fp": true
+}

params.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac12ca4b6def3792ab54b181a5f8b19a4c632e58463c984653d1737eb073574
+size 45891124

predictions_test.csv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aed6f1c8276839685b16d13f7d6f571fcd17fb157ad34851ef81aa34106cc5e
+size 7574

predictions_train.csv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a231424702e72c000ec5b88a63f57267b8841098c66b4b951711051bb7076d4d
+size 7686

predictions_validation.csv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54bf2abbe83b4390bf1b89e15f6c33c316a18cfad25b37f3d23a383c00c6ac4
+size 24216

repo-name.txt

@@ -0,0 +1 @@
+scbirlab/spark-dv-2503-spne

training-args.json

@@ -0,0 +1,5 @@
+{
+    "batch_size": 16,
+    "epochs": 2000,
+    "val_filename": "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-validation.csv.gz"
+}

training-data.hf/cache-6e45fb8cb7c74a86.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3574722ef381aa5d70726ae87ce52b80ff89880f28716357175dfbee702afb94
+size 199416

training-data.hf/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fde13bc580827883581c9f2d2800e155336859943053dc80c7135280c5bd409
+size 198824

training-data.hf/dataset_info.json

@@ -0,0 +1,126 @@
+{
+  "builder_name": "csv",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "csv",
+  "dataset_size": 2735,
+  "description": "",
+  "download_checksums": {
+    "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Streptococcus-pneumoniae/scaffold-split-train.csv.gz": {
+      "num_bytes": 1012,
+      "checksum": null
+    }
+  },
+  "download_size": 1012,
+  "features": {
+    "smiles": {
+      "feature": {
+        "dtype": "string",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "inputs": {
+      "V_d": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "gt_mask": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "lt_mask": {
+        "dtype": "null",
+        "_type": "Value"
+      },
+      "mg": {
+        "E": {
+          "feature": {
+            "feature": {
+              "dtype": "float32",
+              "_type": "Value"
+            },
+            "_type": "Sequence"
+          },
+          "_type": "Sequence"
+        },
+        "V": {
+          "feature": {
+            "feature": {
+              "dtype": "float32",
+              "_type": "Value"
+            },
+            "_type": "Sequence"
+          },
+          "_type": "Sequence"
+        },
+        "edge_index": {
+          "feature": {
+            "feature": {
+              "dtype": "float32",
+              "_type": "Value"
+            },
+            "_type": "Sequence"
+          },
+          "_type": "Sequence"
+        },
+        "rev_edge_index": {
+          "feature": {
+            "dtype": "float32",
+            "_type": "Value"
+          },
+          "_type": "Sequence"
+        }
+      },
+      "weight": {
+        "dtype": "float32",
+        "_type": "Value"
+      },
+      "x_d": {
+        "feature": {
+          "dtype": "float32",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      },
+      "y": {
+        "feature": {
+          "dtype": "float32",
+          "_type": "Value"
+        },
+        "_type": "Sequence"
+      }
+    },
+    "labels": {
+      "feature": {
+        "dtype": "float64",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    },
+    "extra_features": {
+      "feature": {
+        "dtype": "float32",
+        "_type": "Value"
+      },
+      "_type": "Sequence"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 3747,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 2735,
+      "num_examples": 6,
+      "dataset_name": "csv"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

training-data.hf/state.json

@@ -0,0 +1,15 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "518d6c3dd41538bb",
+  "_format_columns": null,
+  "_format_kwargs": {
+    "dtype": "float"
+  },
+  "_format_type": "numpy",
+  "_output_all_columns": false,
+  "_split": "train"
+}

training-log.csv

@@ -0,0 +1,54 @@
+epoch,step,loss,val_loss
+0,0,35.035179138183594,28.506013870239254
+1,1,34.59953308105469,28.133272171020508
+2,2,34.28255081176758,27.75455093383789
+3,3,33.872459411621094,27.3608512878418
+4,4,33.49507141113281,26.94652557373047
+5,5,32.93204498291016,26.503360748291016
+6,6,32.40605163574219,26.024642944335938
+7,7,31.995607376098636,25.50464630126953
+8,8,31.35414695739746,24.93709945678711
+9,9,30.852384567260746,24.317028045654297
+10,10,30.293041229248047,23.639673233032227
+11,11,29.3199462890625,22.898895263671875
+12,12,28.761568069458008,22.09198760986328
+13,13,27.734697341918945,21.21438980102539
+14,14,26.935657501220703,20.2636833190918
+15,15,25.863750457763672,19.23866271972656
+16,16,24.692529678344727,18.138511657714844
+17,17,23.58732795715332,16.965312957763672
+18,18,22.249080657958984,15.723073959350586
+19,19,20.945390701293945,14.418327331542969
+20,20,19.49625587463379,13.059042930603027
+21,21,18.035572052001957,11.65770435333252
+22,22,16.04208755493164,10.229310035705566
+23,23,14.609708786010742,8.793594360351562
+24,24,12.870007514953612,7.373780250549316
+25,25,11.573694229125977,5.998498916625977
+26,26,9.815820693969728,4.699665546417236
+27,27,7.948325157165527,3.513622283935547
+28,28,6.660716533660889,2.480156421661377
+29,29,5.119527339935303,1.6397855281829834
+30,30,3.504617214202881,1.0356911420822144
+31,31,2.7646963596343994,0.7050375938415527
+32,32,1.6973930597305298,0.6781078577041626
+33,33,1.075992226600647,0.9667624831199646
+34,34,0.6845546960830688,1.556015133857727
+35,35,0.3879012167453766,2.3837873935699463
+36,36,0.4765850305557251,3.3532373905181885
+37,37,0.8820050954818726,4.322829723358154
+38,38,1.508744478225708,5.122341632843018
+39,39,2.0902042388916016,5.632863998413086
+40,40,1.994970798492432,5.850592136383057
+41,41,2.3712332248687744,5.758612632751465
+42,42,2.082725524902344,5.433818817138672
+43,43,1.8089426755905151,4.966310977935791
+44,44,1.557389497756958,4.401313781738281
+45,45,1.2402079105377195,3.8155436515808105
+46,46,0.9037799835205078,3.2567148208618164
+47,47,0.9471979141235352,2.732806444168091
+48,48,0.7469801306724548,2.27205228805542
+49,49,0.53239905834198,1.886436462402344
+50,50,0.5718014240264893,1.578837513923645
+51,51,0.4372279047966003,1.3402189016342163
+52,52,0.531734824180603,1.1567370891571045