Upload folder using huggingface_hub

README.md

@@ -1,3 +1,140 @@
----
-license: mit
----
+---
+license: mit
+pipeline_tag: tabular-regression
+tags:
+- chemistry
+- microbiology
+- antibiotics
+library_name: duvida
+datasets:
+- scbirlab/thomas-2018-spark-wt
+---
+
+# Predictor of _Klebsiella pneumoniae_ MICs 
+
+_Updated:_ Fri 28 Mar 14:27:11 GMT 2025
+
+Trained on the _Klebsiella pneumoniae_, WT accumulator phenotype subset of the [human-curated SPARK dataset](https://doi.org/10.1021/acsinfecdis.8b00193) (3920 rows in total for _Klebsiella 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": 3,
+    "n_units": 16,
+    "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-kpne")
+modelbox.predict(filename=..., inputs=[...], columns=[...])  # make predictions on your own data
+```
+
+## Training details
+
+- **Dataset:** [SPARK, WT accumulator, _Klebsiella 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 (2045 rows)
+    - 15% validation (for early stopping) (723 rows)
+    - 15% test (for selecting hyperparameters) (646 rows)
+
+Here is the training log:
+
+<img src="training-log.png" width=450>
+
+And these are the evaluation scores.
+
+Train (2045 rows):
+
+```json
+
+{
+    "Pearson r": 0.879788014533255,
+    "RMSE": 0.4014032185077667,
+    "Spearman rho": 0.8235991116907959
+}
+```
+
+Validation (723 rows):
+
+```json
+
+{
+    "Pearson r": 0.7805225413538466,
+    "RMSE": 0.7095186710357666,
+    "Spearman rho": 0.6299348550927065
+}
+```
+
+
+Test (646 rows):
+
+```json
+
+{
+    "Pearson r": 0.4050551318825592,
+    "RMSE": 0.6779211163520813,
+    "Spearman rho": 0.4843227707887753
+}
+```
+
+## 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/Klebsiella-pneumoniae/61/cache",
+    "features": [
+        "smiles"
+    ],
+    "filename": "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Klebsiella-pneumoniae/scaffold-split-train.csv.gz",
+    "labels": [
+        "pmic"
+    ]
+}

eval-metrics_test.json

@@ -0,0 +1,5 @@
+{
+    "Pearson r": 0.4050551318825592,
+    "RMSE": 0.6779211163520813,
+    "Spearman rho": 0.4843227707887753
+}

eval-metrics_train.json

@@ -0,0 +1,5 @@
+{
+    "Pearson r": 0.879788014533255,
+    "RMSE": 0.4014032185077667,
+    "Spearman rho": 0.8235991116907959
+}

eval-metrics_validation.json

@@ -0,0 +1,5 @@
+{
+    "Pearson r": 0.7805225413538466,
+    "RMSE": 0.7095186710357666,
+    "Spearman rho": 0.6299348550927065
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb7f5cd91df22834ff43e89843609a6075e5f26ec1e7aebc9a9a05518a56ce3a
+size 264496

input-data.hf/dataset_info.json

@@ -0,0 +1,52 @@
+{
+  "builder_name": "csv",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "csv",
+  "dataset_size": 766413,
+  "description": "",
+  "download_checksums": {
+    "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Klebsiella-pneumoniae/scaffold-split-train.csv.gz": {
+      "num_bytes": 130202,
+      "checksum": null
+    }
+  },
+  "download_size": 130202,
+  "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": 896615,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 766413,
+      "num_examples": 2045,
+      "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": "a55666bc481927f9",
+  "_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 +1,91 @@
+epoch,loss,step,val_loss
+0,,127,3.1612131595611572
+0,11.470685958862305,127,
+1,,255,3.4212403297424316
+1,4.516500473022461,255,
+2,,383,2.7988340854644775
+2,4.001670837402344,383,
+3,,511,2.4266252517700195
+3,3.4878146648406982,511,
+4,,639,2.3812172412872314
+4,3.1538383960723877,639,
+5,,767,2.249669075012207
+5,2.8869502544403076,767,
+6,,895,2.1487362384796143
+6,2.6796183586120605,895,
+7,,1023,1.9302494525909424
+7,2.499631881713867,1023,
+8,,1151,1.895418405532837
+8,2.384538173675537,1151,
+9,,1279,1.8401507139205933
+9,2.2424700260162354,1279,
+10,,1407,1.7240188121795654
+10,2.1825485229492188,1407,
+11,,1535,1.6076897382736206
+11,2.0599634647369385,1535,
+12,,1663,1.5228654146194458
+12,1.9549221992492676,1663,
+13,,1791,1.3301759958267212
+13,1.8475960493087769,1791,
+14,,1919,1.197400689125061
+14,1.7222977876663208,1919,
+15,,2047,1.1432061195373535
+15,1.662263035774231,2047,
+16,,2175,1.1259466409683228
+16,1.5466835498809814,2175,
+17,,2303,1.133188247680664
+17,1.476884126663208,2303,
+18,,2431,1.1027441024780273
+18,1.4452625513076782,2431,
+19,,2559,1.158228874206543
+19,1.378151774406433,2559,
+20,,2687,1.0784740447998047
+20,1.318475365638733,2687,
+21,,2815,1.0715962648391724
+21,1.2622106075286865,2815,
+22,,2943,1.075689673423767
+22,1.2291003465652466,2943,
+23,,3071,1.0587623119354248
+23,1.1971018314361572,3071,
+24,,3199,1.0540975332260132
+24,1.1468651294708252,3199,
+25,,3327,1.07569420337677
+25,1.1313549280166626,3327,
+26,,3455,1.0563280582427979
+26,1.1012349128723145,3455,
+27,,3583,1.1024538278579712
+27,1.0781406164169312,3583,
+28,,3711,1.0793583393096924
+28,1.058035135269165,3711,
+29,,3839,1.0855896472930908
+29,1.0287179946899414,3839,
+30,,3967,1.1220470666885376
+30,1.0105702877044678,3967,
+31,,4095,1.0875941514968872
+31,0.9984549880027771,4095,
+32,,4223,1.0672334432601929
+32,0.987288236618042,4223,
+33,,4351,1.0616916418075562
+33,0.9705791473388672,4351,
+34,,4479,1.0746409893035889
+34,0.9425535798072815,4479,
+35,,4607,1.0884811878204346
+35,0.9292816519737244,4607,
+36,,4735,1.0922189950942993
+36,0.9182446599006653,4735,
+37,,4863,1.0835254192352295
+37,0.9015668034553528,4863,
+38,,4991,1.0907585620880127
+38,0.9176275134086609,4991,
+39,,5119,1.1213494539260864
+39,0.9064778089523315,5119,
+40,,5247,1.0660821199417114
+40,0.8878889083862305,5247,
+41,,5375,1.0989940166473389
+41,0.8802230358123779,5375,
+42,,5503,1.1001183986663818
+42,0.8679183721542358,5503,
+43,,5631,1.120335578918457
+43,0.8558708429336548,5631,
+44,,5759,1.1134792566299438
+44,0.8376833200454712,5759,

logs/lightning_logs/version_0/events.out.tfevents.1743097353.cn026.2190138.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06819b7813d597c5db3ccb8be5dc3e376772c9803a5afb9eaeb499e1524f015e
+size 8094

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/Klebsiella-pneumoniae/scaffold-split-train.csv.gz,61,ChempropModelBox,2690450,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Klebsiella-pneumoniae/scaffold-split-train.csv.gz,['smiles'],['pmic'],/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/models/spark/Klebsiella-pneumoniae/61/cache,,True,True,0.2,10,0.0001,3,16,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Klebsiella-pneumoniae/scaffold-split-validation.csv.gz,2000,16,0.4014032185077667,0.879788014533255,0.8235991116907959
+validation,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Klebsiella-pneumoniae/scaffold-split-validation.csv.gz,61,ChempropModelBox,2690450,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Klebsiella-pneumoniae/scaffold-split-train.csv.gz,['smiles'],['pmic'],/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/models/spark/Klebsiella-pneumoniae/61/cache,,True,True,0.2,10,0.0001,3,16,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Klebsiella-pneumoniae/scaffold-split-validation.csv.gz,2000,16,0.7095186710357666,0.7805225413538466,0.6299348550927065
+test,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Klebsiella-pneumoniae/scaffold-split-test.csv.gz,61,ChempropModelBox,2690450,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Klebsiella-pneumoniae/scaffold-split-train.csv.gz,['smiles'],['pmic'],/nemo/lab/johnsone/home/users/johnsoe/projects/abx-discovery-strategy/models/spark/Klebsiella-pneumoniae/61/cache,,True,True,0.2,10,0.0001,3,16,/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Klebsiella-pneumoniae/scaffold-split-validation.csv.gz,2000,16,0.6779211163520813,0.4050551318825592,0.4843227707887753

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": 3,
+    "n_units": 16,
+    "use_2d": true,
+    "use_fp": true
+}

params.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1801d43ebc3f74db8d31190366ad537b2b39238c6574eb1b110077ce9f385c
+size 10875372

predictions_test.csv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5584a18b5d753d00747d2809e5bb0424cec579aaad0ce24f00e4658bbf7a170c
+size 705987

predictions_train.csv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20695113483d5c2d973c00badeaf66c46e3ef2c9cf334b0af09ace0cacd31fc0
+size 1940344

predictions_validation.csv.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0e71ba4083d1dc0c1f0a99d43add1eaf03d0d5c1cab18aa58643d962df4d192
+size 997657

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/Klebsiella-pneumoniae/scaffold-split-validation.csv.gz"
+}

training-data.hf/cache-d4aeece68b087032.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3873a4aaf25229484a767fcf91a5c465713b58a1255b3b692925ef7d106faf0d
+size 61560848

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b27e7fb54789605b5ce5f5646274068f805585004de84caf37383446fe697a
+size 61282632

training-data.hf/dataset_info.json

@@ -0,0 +1,126 @@
+{
+  "builder_name": "csv",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "csv",
+  "dataset_size": 766413,
+  "description": "",
+  "download_checksums": {
+    "/nemo/lab/johnsone/home/users/johnsoe/data/datasets/thomas-2018-spark-wt/Klebsiella-pneumoniae/scaffold-split-train.csv.gz": {
+      "num_bytes": 130202,
+      "checksum": null
+    }
+  },
+  "download_size": 130202,
+  "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": 896615,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 766413,
+      "num_examples": 2045,
+      "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": "8e7bb11fd5ae4b41",
+  "_format_columns": null,
+  "_format_kwargs": {
+    "dtype": "float"
+  },
+  "_format_type": "numpy",
+  "_output_all_columns": false,
+  "_split": "train"
+}

training-log.csv

@@ -0,0 +1,46 @@
+epoch,step,loss,val_loss
+0,127,11.470685958862305,3.161213159561157
+1,255,4.516500473022461,3.421240329742432
+2,383,4.001670837402344,2.798834085464477
+3,511,3.4878146648406982,2.4266252517700195
+4,639,3.153838396072388,2.3812172412872314
+5,767,2.886950254440308,2.249669075012207
+6,895,2.6796183586120605,2.1487362384796143
+7,1023,2.499631881713867,1.9302494525909424
+8,1151,2.384538173675537,1.895418405532837
+9,1279,2.242470026016236,1.8401507139205933
+10,1407,2.1825485229492188,1.7240188121795654
+11,1535,2.0599634647369385,1.6076897382736206
+12,1663,1.954922199249268,1.5228654146194458
+13,1791,1.8475960493087769,1.3301759958267212
+14,1919,1.7222977876663208,1.197400689125061
+15,2047,1.662263035774231,1.1432061195373535
+16,2175,1.5466835498809814,1.1259466409683228
+17,2303,1.476884126663208,1.133188247680664
+18,2431,1.4452625513076782,1.1027441024780271
+19,2559,1.378151774406433,1.158228874206543
+20,2687,1.318475365638733,1.078474044799805
+21,2815,1.2622106075286863,1.0715962648391724
+22,2943,1.2291003465652466,1.075689673423767
+23,3071,1.1971018314361572,1.0587623119354248
+24,3199,1.1468651294708252,1.0540975332260132
+25,3327,1.1313549280166626,1.07569420337677
+26,3455,1.1012349128723145,1.056328058242798
+27,3583,1.0781406164169312,1.1024538278579712
+28,3711,1.058035135269165,1.0793583393096924
+29,3839,1.0287179946899414,1.0855896472930908
+30,3967,1.0105702877044678,1.1220470666885376
+31,4095,0.9984549880027772,1.0875941514968872
+32,4223,0.987288236618042,1.0672334432601929
+33,4351,0.9705791473388672,1.0616916418075562
+34,4479,0.9425535798072816,1.0746409893035889
+35,4607,0.9292816519737244,1.0884811878204346
+36,4735,0.9182446599006652,1.092218995094299
+37,4863,0.9015668034553528,1.0835254192352295
+38,4991,0.9176275134086608,1.0907585620880127
+39,5119,0.9064778089523317,1.1213494539260864
+40,5247,0.8878889083862305,1.0660821199417114
+41,5375,0.8802230358123779,1.0989940166473389
+42,5503,0.8679183721542358,1.1001183986663818
+43,5631,0.8558708429336548,1.120335578918457
+44,5759,0.8376833200454712,1.1134792566299438