big refactoring

.example.env

@@ -0,0 +1 @@
+TOKEN=example_token

.gitignore

@@ -3,5 +3,8 @@ results.csv
 predict copy.py
 debug.py
 __pycache__
-tox21_test.csv
-predictions.json
+predictions.json
+notes.txt 
+logs/*
+data/*
+.env

LICENSE

@@ -0,0 +1,407 @@
+Attribution-NonCommercial 4.0 International
+
+=======================================================================
+
+Creative Commons Corporation ("Creative Commons") is not a law firm and
+does not provide legal services or legal advice. Distribution of
+Creative Commons public licenses does not create a lawyer-client or
+other relationship. Creative Commons makes its licenses and related
+information available on an "as-is" basis. Creative Commons gives no
+warranties regarding its licenses, any material licensed under their
+terms and conditions, or any related information. Creative Commons
+disclaims all liability for damages resulting from their use to the
+fullest extent possible.
+
+Using Creative Commons Public Licenses
+
+Creative Commons public licenses provide a standard set of terms and
+conditions that creators and other rights holders may use to share
+original works of authorship and other material subject to copyright
+and certain other rights specified in the public license below. The
+following considerations are for informational purposes only, are not
+exhaustive, and do not form part of our licenses.
+
+     Considerations for licensors: Our public licenses are
+     intended for use by those authorized to give the public
+     permission to use material in ways otherwise restricted by
+     copyright and certain other rights. Our licenses are
+     irrevocable. Licensors should read and understand the terms
+     and conditions of the license they choose before applying it.
+     Licensors should also secure all rights necessary before
+     applying our licenses so that the public can reuse the
+     material as expected. Licensors should clearly mark any
+     material not subject to the license. This includes other CC-
+     licensed material, or material used under an exception or
+     limitation to copyright. More considerations for licensors:
+    wiki.creativecommons.org/Considerations_for_licensors
+
+     Considerations for the public: By using one of our public
+     licenses, a licensor grants the public permission to use the
+     licensed material under specified terms and conditions. If
+     the licensor's permission is not necessary for any reason--for
+     example, because of any applicable exception or limitation to
+     copyright--then that use is not regulated by the license. Our
+     licenses grant only permissions under copyright and certain
+     other rights that a licensor has authority to grant. Use of
+     the licensed material may still be restricted for other
+     reasons, including because others have copyright or other
+     rights in the material. A licensor may make special requests,
+     such as asking that all changes be marked or described.
+     Although not required by our licenses, you are encouraged to
+     respect those requests where reasonable. More considerations
+     for the public:
+    wiki.creativecommons.org/Considerations_for_licensees
+
+=======================================================================
+
+Creative Commons Attribution-NonCommercial 4.0 International Public
+License
+
+By exercising the Licensed Rights (defined below), You accept and agree
+to be bound by the terms and conditions of this Creative Commons
+Attribution-NonCommercial 4.0 International Public License ("Public
+License"). To the extent this Public License may be interpreted as a
+contract, You are granted the Licensed Rights in consideration of Your
+acceptance of these terms and conditions, and the Licensor grants You
+such rights in consideration of benefits the Licensor receives from
+making the Licensed Material available under these terms and
+conditions.
+
+
+Section 1 -- Definitions.
+
+  a. Adapted Material means material subject to Copyright and Similar
+     Rights that is derived from or based upon the Licensed Material
+     and in which the Licensed Material is translated, altered,
+     arranged, transformed, or otherwise modified in a manner requiring
+     permission under the Copyright and Similar Rights held by the
+     Licensor. For purposes of this Public License, where the Licensed
+     Material is a musical work, performance, or sound recording,
+     Adapted Material is always produced where the Licensed Material is
+     synched in timed relation with a moving image.
+
+  b. Adapter's License means the license You apply to Your Copyright
+     and Similar Rights in Your contributions to Adapted Material in
+     accordance with the terms and conditions of this Public License.
+
+  c. Copyright and Similar Rights means copyright and/or similar rights
+     closely related to copyright including, without limitation,
+     performance, broadcast, sound recording, and Sui Generis Database
+     Rights, without regard to how the rights are labeled or
+     categorized. For purposes of this Public License, the rights
+     specified in Section 2(b)(1)-(2) are not Copyright and Similar
+     Rights.
+  d. Effective Technological Measures means those measures that, in the
+     absence of proper authority, may not be circumvented under laws
+     fulfilling obligations under Article 11 of the WIPO Copyright
+     Treaty adopted on December 20, 1996, and/or similar international
+     agreements.
+
+  e. Exceptions and Limitations means fair use, fair dealing, and/or
+     any other exception or limitation to Copyright and Similar Rights
+     that applies to Your use of the Licensed Material.
+
+  f. Licensed Material means the artistic or literary work, database,
+     or other material to which the Licensor applied this Public
+     License.
+
+  g. Licensed Rights means the rights granted to You subject to the
+     terms and conditions of this Public License, which are limited to
+     all Copyright and Similar Rights that apply to Your use of the
+     Licensed Material and that the Licensor has authority to license.
+
+  h. Licensor means the individual(s) or entity(ies) granting rights
+     under this Public License.
+
+  i. NonCommercial means not primarily intended for or directed towards
+     commercial advantage or monetary compensation. For purposes of
+     this Public License, the exchange of the Licensed Material for
+     other material subject to Copyright and Similar Rights by digital
+     file-sharing or similar means is NonCommercial provided there is
+     no payment of monetary compensation in connection with the
+     exchange.
+
+  j. Share means to provide material to the public by any means or
+     process that requires permission under the Licensed Rights, such
+     as reproduction, public display, public performance, distribution,
+     dissemination, communication, or importation, and to make material
+     available to the public including in ways that members of the
+     public may access the material from a place and at a time
+     individually chosen by them.
+
+  k. Sui Generis Database Rights means rights other than copyright
+     resulting from Directive 96/9/EC of the European Parliament and of
+     the Council of 11 March 1996 on the legal protection of databases,
+     as amended and/or succeeded, as well as other essentially
+     equivalent rights anywhere in the world.
+
+  l. You means the individual or entity exercising the Licensed Rights
+     under this Public License. Your has a corresponding meaning.
+
+
+Section 2 -- Scope.
+
+  a. License grant.
+
+       1. Subject to the terms and conditions of this Public License,
+          the Licensor hereby grants You a worldwide, royalty-free,
+          non-sublicensable, non-exclusive, irrevocable license to
+          exercise the Licensed Rights in the Licensed Material to:
+
+            a. reproduce and Share the Licensed Material, in whole or
+               in part, for NonCommercial purposes only; and
+
+            b. produce, reproduce, and Share Adapted Material for
+               NonCommercial purposes only.
+
+       2. Exceptions and Limitations. For the avoidance of doubt, where
+          Exceptions and Limitations apply to Your use, this Public
+          License does not apply, and You do not need to comply with
+          its terms and conditions.
+
+       3. Term. The term of this Public License is specified in Section
+          6(a).
+
+       4. Media and formats; technical modifications allowed. The
+          Licensor authorizes You to exercise the Licensed Rights in
+          all media and formats whether now known or hereafter created,
+          and to make technical modifications necessary to do so. The
+          Licensor waives and/or agrees not to assert any right or
+          authority to forbid You from making technical modifications
+          necessary to exercise the Licensed Rights, including
+          technical modifications necessary to circumvent Effective
+          Technological Measures. For purposes of this Public License,
+          simply making modifications authorized by this Section 2(a)
+          (4) never produces Adapted Material.
+
+       5. Downstream recipients.
+
+            a. Offer from the Licensor -- Licensed Material. Every
+               recipient of the Licensed Material automatically
+               receives an offer from the Licensor to exercise the
+               Licensed Rights under the terms and conditions of this
+               Public License.
+
+            b. No downstream restrictions. You may not offer or impose
+               any additional or different terms or conditions on, or
+               apply any Effective Technological Measures to, the
+               Licensed Material if doing so restricts exercise of the
+               Licensed Rights by any recipient of the Licensed
+               Material.
+
+       6. No endorsement. Nothing in this Public License constitutes or
+          may be construed as permission to assert or imply that You
+          are, or that Your use of the Licensed Material is, connected
+          with, or sponsored, endorsed, or granted official status by,
+          the Licensor or others designated to receive attribution as
+          provided in Section 3(a)(1)(A)(i).
+
+  b. Other rights.
+
+       1. Moral rights, such as the right of integrity, are not
+          licensed under this Public License, nor are publicity,
+          privacy, and/or other similar personality rights; however, to
+          the extent possible, the Licensor waives and/or agrees not to
+          assert any such rights held by the Licensor to the limited
+          extent necessary to allow You to exercise the Licensed
+          Rights, but not otherwise.
+
+       2. Patent and trademark rights are not licensed under this
+          Public License.
+
+       3. To the extent possible, the Licensor waives any right to
+          collect royalties from You for the exercise of the Licensed
+          Rights, whether directly or through a collecting society
+          under any voluntary or waivable statutory or compulsory
+          licensing scheme. In all other cases the Licensor expressly
+          reserves any right to collect such royalties, including when
+          the Licensed Material is used other than for NonCommercial
+          purposes.
+
+
+Section 3 -- License Conditions.
+
+Your exercise of the Licensed Rights is expressly made subject to the
+following conditions.
+
+  a. Attribution.
+
+       1. If You Share the Licensed Material (including in modified
+          form), You must:
+
+            a. retain the following if it is supplied by the Licensor
+               with the Licensed Material:
+
+                 i. identification of the creator(s) of the Licensed
+                    Material and any others designated to receive
+                    attribution, in any reasonable manner requested by
+                    the Licensor (including by pseudonym if
+                    designated);
+
+                ii. a copyright notice;
+
+               iii. a notice that refers to this Public License;
+
+                iv. a notice that refers to the disclaimer of
+                    warranties;
+
+                 v. a URI or hyperlink to the Licensed Material to the
+                    extent reasonably practicable;
+
+            b. indicate if You modified the Licensed Material and
+               retain an indication of any previous modifications; and
+
+            c. indicate the Licensed Material is licensed under this
+               Public License, and include the text of, or the URI or
+               hyperlink to, this Public License.
+
+       2. You may satisfy the conditions in Section 3(a)(1) in any
+          reasonable manner based on the medium, means, and context in
+          which You Share the Licensed Material. For example, it may be
+          reasonable to satisfy the conditions by providing a URI or
+          hyperlink to a resource that includes the required
+          information.
+
+       3. If requested by the Licensor, You must remove any of the
+          information required by Section 3(a)(1)(A) to the extent
+          reasonably practicable.
+
+       4. If You Share Adapted Material You produce, the Adapter's
+          License You apply must not prevent recipients of the Adapted
+          Material from complying with this Public License.
+
+
+Section 4 -- Sui Generis Database Rights.
+
+Where the Licensed Rights include Sui Generis Database Rights that
+apply to Your use of the Licensed Material:
+
+  a. for the avoidance of doubt, Section 2(a)(1) grants You the right
+     to extract, reuse, reproduce, and Share all or a substantial
+     portion of the contents of the database for NonCommercial purposes
+     only;
+
+  b. if You include all or a substantial portion of the database
+     contents in a database in which You have Sui Generis Database
+     Rights, then the database in which You have Sui Generis Database
+     Rights (but not its individual contents) is Adapted Material; and
+
+  c. You must comply with the conditions in Section 3(a) if You Share
+     all or a substantial portion of the contents of the database.
+
+For the avoidance of doubt, this Section 4 supplements and does not
+replace Your obligations under this Public License where the Licensed
+Rights include other Copyright and Similar Rights.
+
+
+Section 5 -- Disclaimer of Warranties and Limitation of Liability.
+
+  a. UNLESS OTHERWISE SEPARATELY UNDERTAKEN BY THE LICENSOR, TO THE
+     EXTENT POSSIBLE, THE LICENSOR OFFERS THE LICENSED MATERIAL AS-IS
+     AND AS-AVAILABLE, AND MAKES NO REPRESENTATIONS OR WARRANTIES OF
+     ANY KIND CONCERNING THE LICENSED MATERIAL, WHETHER EXPRESS,
+     IMPLIED, STATUTORY, OR OTHER. THIS INCLUDES, WITHOUT LIMITATION,
+     WARRANTIES OF TITLE, MERCHANTABILITY, FITNESS FOR A PARTICULAR
+     PURPOSE, NON-INFRINGEMENT, ABSENCE OF LATENT OR OTHER DEFECTS,
+     ACCURACY, OR THE PRESENCE OR ABSENCE OF ERRORS, WHETHER OR NOT
+     KNOWN OR DISCOVERABLE. WHERE DISCLAIMERS OF WARRANTIES ARE NOT
+     ALLOWED IN FULL OR IN PART, THIS DISCLAIMER MAY NOT APPLY TO YOU.
+
+  b. TO THE EXTENT POSSIBLE, IN NO EVENT WILL THE LICENSOR BE LIABLE
+     TO YOU ON ANY LEGAL THEORY (INCLUDING, WITHOUT LIMITATION,
+     NEGLIGENCE) OR OTHERWISE FOR ANY DIRECT, SPECIAL, INDIRECT,
+     INCIDENTAL, CONSEQUENTIAL, PUNITIVE, EXEMPLARY, OR OTHER LOSSES,
+     COSTS, EXPENSES, OR DAMAGES ARISING OUT OF THIS PUBLIC LICENSE OR
+     USE OF THE LICENSED MATERIAL, EVEN IF THE LICENSOR HAS BEEN
+     ADVISED OF THE POSSIBILITY OF SUCH LOSSES, COSTS, EXPENSES, OR
+     DAMAGES. WHERE A LIMITATION OF LIABILITY IS NOT ALLOWED IN FULL OR
+     IN PART, THIS LIMITATION MAY NOT APPLY TO YOU.
+
+  c. The disclaimer of warranties and limitation of liability provided
+     above shall be interpreted in a manner that, to the extent
+     possible, most closely approximates an absolute disclaimer and
+     waiver of all liability.
+
+
+Section 6 -- Term and Termination.
+
+  a. This Public License applies for the term of the Copyright and
+     Similar Rights licensed here. However, if You fail to comply with
+     this Public License, then Your rights under this Public License
+     terminate automatically.
+
+  b. Where Your right to use the Licensed Material has terminated under
+     Section 6(a), it reinstates:
+
+       1. automatically as of the date the violation is cured, provided
+          it is cured within 30 days of Your discovery of the
+          violation; or
+
+       2. upon express reinstatement by the Licensor.
+
+     For the avoidance of doubt, this Section 6(b) does not affect any
+     right the Licensor may have to seek remedies for Your violations
+     of this Public License.
+
+  c. For the avoidance of doubt, the Licensor may also offer the
+     Licensed Material under separate terms or conditions or stop
+     distributing the Licensed Material at any time; however, doing so
+     will not terminate this Public License.
+
+  d. Sections 1, 5, 6, 7, and 8 survive termination of this Public
+     License.
+
+
+Section 7 -- Other Terms and Conditions.
+
+  a. The Licensor shall not be bound by any additional or different
+     terms or conditions communicated by You unless expressly agreed.
+
+  b. Any arrangements, understandings, or agreements regarding the
+     Licensed Material not stated herein are separate from and
+     independent of the terms and conditions of this Public License.
+
+
+Section 8 -- Interpretation.
+
+  a. For the avoidance of doubt, this Public License does not, and
+     shall not be interpreted to, reduce, limit, restrict, or impose
+     conditions on any use of the Licensed Material that could lawfully
+     be made without permission under this Public License.
+
+  b. To the extent possible, if any provision of this Public License is
+     deemed unenforceable, it shall be automatically reformed to the
+     minimum extent necessary to make it enforceable. If the provision
+     cannot be reformed, it shall be severed from this Public License
+     without affecting the enforceability of the remaining terms and
+     conditions.
+
+  c. No term or condition of this Public License will be waived and no
+     failure to comply consented to unless expressly agreed to by the
+     Licensor.
+
+  d. Nothing in this Public License constitutes or may be interpreted
+     as a limitation upon, or waiver of, any privileges and immunities
+     that apply to the Licensor or You, including from the legal
+     processes of any jurisdiction or authority.
+
+=======================================================================
+
+Creative Commons is not a party to its public
+licenses. Notwithstanding, Creative Commons may elect to apply one of
+its public licenses to material it publishes and in those instances
+will be considered the “Licensor.” The text of the Creative Commons
+public licenses is dedicated to the public domain under the CC0 Public
+Domain Dedication. Except for the limited purpose of indicating that
+material is shared under a Creative Commons public license or as
+otherwise permitted by the Creative Commons policies published at
+creativecommons.org/policies, Creative Commons does not authorize the
+use of the trademark "Creative Commons" or any other trademark or logo
+of Creative Commons without its prior written consent including,
+without limitation, in connection with any unauthorized modifications
+to any of its public licenses or any other arrangements,
+understandings, or agreements concerning use of licensed material. For
+the avoidance of doubt, this paragraph does not form part of the
+public licenses.
+
+Creative Commons may be contacted at creativecommons.org.

README.md

@@ -13,16 +13,31 @@ short_description: Chemprop Baseline Classifier for Tox21
 
 This repository hosts a Hugging Face Space that provides an examplary API for submitting models to the [Tox21 Leaderboard](https://huggingface.co/spaces/tschouis/tox21_leaderboard).
 
-In this example, we trained a Chemprop classifier on the Tox21 targets and saved the trained model in the `assets/` folder.
+In this example, we trained a Chemprop classifier on the Tox21 targets and saved the trained model in the `checkpoints/` folder.
 
-**Important:** For leaderboard submission, your Space does not need to include training code. It only needs to implement inference in the `predict()` function inside `predict.py`. The `predict()` function must keep the provided skeleton: it should take a list of SMILES strings as input and return a nested prediction dictionary as output, with SMILES as keys and dictionaries containing targetname-prediction pairs as values. Therefore, any preprocessing of SMILES strings must be executed on-the-fly during inference.
+**Important:** For leaderboard submission, your Space needs to include training code. The file `train.py` should train the model using the config specified inside the `config/` folder and save the final model parameters into a file inside the `checkpoints/` folder. The model should be trained using the [Tox21_dataset](https://huggingface.co/datasets/tschouis/tox21) provided on Hugging Face. The datasets can be loaded like this:
+```python
+from datasets import load_dataset
+ds = load_dataset("tschouis/tox21", token=token)
+train_df = ds["train"].to_pandas()
+val_df = ds["validation"].to_pandas()
+```
+
+Additionally, the Space needs to implement inference in the `predict()` function inside `predict.py`. The `predict()` function must keep the provided skeleton: it should take a list of SMILES strings as input and return a nested prediction dictionary as output, with SMILES as keys and dictionaries containing targetname-prediction pairs as values. Therefore, any preprocessing of SMILES strings must be executed on-the-fly during inference.
 
 # Repository Structure
 - `predict.py` - Defines the `predict()` function required by the leaderboard (entry point for inference).
 - `app.py` - FastAPI application wrapper (can be used as-is).
+- `train.py` - trains and saves a model using the config in the `config/` folder.
+- `config/` - the config file used by `train.py`. 
+- `logs/` - all the logs of `train.py`, the saved model, and predictions on the validation set.
+- `data/` - chemprop uses data in csv form. During preprocessing in `train.py` two csv files are created and saved here.
+- `checkpoints/` - the saved model that is used in `predict.py` is here.
 
 - `src/` - Core model & preprocessing logic:
-    - `preprocess.py` - SMILES preprocessing pipeline
+    - `data.py` - SMILES preprocessing pipeline
+    - `evaluation.py` - compute ROC AUC metric from a csv
+    - `train_model.py` - trains a single model
 
 # Quickstart with Spaces
 
@@ -32,10 +47,16 @@ You can easily adapt this project in your own Hugging Face account:
 
 - Click "Duplicate this Space" (top-right corner).
 
+- Create a `.env` according to `.example.env`.
+
 - Modify `src/` for your preprocessing pipeline and model class
 
 - Modify `predict()` inside `predict.py` to perform model inference while keeping the function skeleton unchanged to remain compatible with the leaderboard.
 
+- Modify `train.py` according to your model and preprocessing pipeline.
+
+- Modify the file inside `config/` to contain all hyperparameters that are set in `train.py`.
+
 That’s it, your model will be available as an API endpoint for the Tox21 Leaderboard.
 
 # Installation
@@ -75,6 +96,6 @@ The output will be a nested dictionary in the format:
 
 # Notes
 
-- Only adapting `predict.py` for your model inference is required for leaderboard submission.
+- Adapting `predict.py`, `train.py`, `config/`, and `checkpoints/` is required for leaderboard submission.
 
-- Preprocessing (here inside `src/preprocess.py`) must be applied at inference time, not just predicting.
+- Preprocessing (here inside `src/data.py`) must be done inside `predict.py` not just `train.py`.

checkpoints/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:409e15603b089e53efb7358cc3383a1b590c599299754daf2d59a700046e9c0b
+size 2844412

config/config.toml

@@ -0,0 +1,48 @@
+config-path = train\config.toml
+data-path = tox21_data\combined_with_testset.csv
+output-dir = train
+target-columns = [NR-AhR, NR-AR, NR-AR-LBD, NR-Aromatase, NR-ER, NR-ER-LBD, NR-PPAR-gamma, SR-ARE, SR-ATAD5, SR-HSE, SR-MMP, SR-p53]
+splits-column = split
+task-type = classification
+patience = 8
+depth = 3
+dropout = 0.3
+ffn-hidden-dim = 400
+ffn-num-layers = 2
+message-hidden-dim = 400
+batch-size = 32
+epochs = 50
+init-lr = 0.0007
+max-lr = 0.0015
+final-lr = 0.01
+aggregation = mean
+num-workers = 0
+accelerator = auto
+devices = auto
+rxn-mode = REAC_DIFF
+multi-hot-atom-featurizer-mode = V2
+frzn-ffn-layers = 0
+ensemble-size = 1
+aggregation-norm = 100
+activation = RELU
+multiclass-num-classes = 3
+atom-ffn-hidden-dim = 300
+atom-ffn-num-layers = 1
+atom-multiclass-num-classes = 3
+bond-ffn-hidden-dim = 300
+bond-ffn-num-layers = 1
+bond-multiclass-num-classes = 3
+atom-constrainer-ffn-hidden-dim = 300
+atom-constrainer-ffn-num-layers = 1
+bond-constrainer-ffn-hidden-dim = 300
+bond-constrainer-ffn-num-layers = 1
+v-kl = 0.0
+eps = 1e-08
+alpha = 0.1
+tracking-metric = val_loss
+warmup-epochs = 2
+split = RANDOM
+split-sizes = [0.8, 0.1, 0.1]
+split-key-molecule = 0
+num-replicates = 1
+data-seed = 0

predict.py

@@ -2,7 +2,7 @@ import torch
 import csv
 import subprocess
 
-from src.preprocess import create_clean_smiles
+from data import create_clean_smiles
 
 def predict(smiles_list):
     """
@@ -37,7 +37,7 @@ def predict(smiles_list):
     print(f"Received {len(smiles_list)} SMILES strings")
 
     # put smiles into csv
-    with open("./src/smiles.csv", "w", newline="") as f:
+    with open("./data/smiles.csv", "w", newline="") as f:
         writer = csv.writer(f)
         writer.writerow(["smiles"])  # header
         for smi in clean_smiles:
@@ -45,10 +45,9 @@ def predict(smiles_list):
     # predict
     command = [
         "chemprop", "predict",
-        "--test-path", "src/smiles.csv",
-        "--model-path", "assets/best1.pt",
-        "--smiles-columns", "smiles",
-        "--preds-path", "src/preds.csv"
+        "--test-path", "data/smiles.csv",
+        "--model-path", "checkpoints/best.pt",
+        "--smiles-columns", "smiles"
     ]
 
     # Run the command
@@ -56,10 +55,10 @@ def predict(smiles_list):
 
     # create results dictionary from predictions
 
-    csv_path = "./src/preds.csv"
+    csv_path = "./assets/preds.csv"
 
     predictions = {}
-    with open("./src/preds.csv", "r", newline="") as f:
+    with open(csv_path, "r", newline="") as f:
         reader = csv.DictReader(f)
         rows = list(reader)
         target_names = [col for col in reader.fieldnames if col != "smiles"]
@@ -78,6 +77,3 @@ def predict(smiles_list):
 
     return predictions
 
-# smiles = pd.read_csv("tox21_test.csv")["smiles"].tolist()
-# predict(smiles)
-

requirements.txt

@@ -1,10 +1,11 @@
 fastapi
 uvicorn[standard]
+python-dotenv
 torch==2.3.0
-torch-geometric==2.6.1
-numpy==1.26.2
-pandas==2.2.2
-rdkit==2024.3.6
 pydantic
-typing-extensions
-chemprop>=2.2.1
+pandas==2.2.2
+numpy==1.26.2
+scikit-learn==1.7.1
+rdkit-pypi
+datasets
+

src/{preprocess.py → data.py}

@@ -1,9 +1,9 @@
-import numpy as np
-
 from rdkit import Chem
 from rdkit.Chem.MolStandardize import rdMolStandardize
 from rdkit import Chem
 import numpy as np
+import pandas as pd
+from datasets import load_dataset
 
 def create_clean_smiles(smiles_list: list[str]) -> tuple[list[str], np.ndarray]:
     """
@@ -36,4 +36,77 @@ def create_clean_smiles(smiles_list: list[str]) -> tuple[list[str], np.ndarray]:
             print(f"Failed to clean {smi}: {e}")
             valid_mask.append(False)
 
-    return clean_smis, np.array(valid_mask, dtype=bool)
+    return clean_smis, np.array(valid_mask, dtype=bool)
+
+
+def clean_smiles_in_csv(input_csv: str, output_csv: str, smiles_col: str = "smiles", target_cols: list[str] | None = None):
+    """
+    Reads a CSV, cleans SMILES, and saves only valid cleaned rows with all target columns to a new CSV.
+    """
+    # Load dataset
+    df = pd.read_csv(input_csv)
+    if smiles_col not in df.columns:
+        raise ValueError(f"'{smiles_col}' column not found in CSV.")
+
+    # Infer target columns if not specified
+    if target_cols is None:
+        target_cols = [c for c in df.columns if c != smiles_col]
+    keep_cols = target_cols + ["split"]
+    # Validate target columns
+    missing_targets = [c for c in target_cols if c not in df.columns]
+    if missing_targets:
+        raise ValueError(f"Missing target columns in CSV: {missing_targets}")
+
+    # Clean SMILES
+    clean_smis, valid_mask = create_clean_smiles(df[smiles_col].tolist())
+
+    # Keep only valid rows
+    df_clean = df.loc[valid_mask, keep_cols].copy()
+    df_clean.insert(0, smiles_col, clean_smis)  # smiles first column
+
+    # Save cleaned dataset
+    df_clean.to_csv(output_csv, index=False)
+    print(f"✅ Cleaned dataset saved to '{output_csv}' ({len(df_clean)} valid molecules).")
+
+
+def get_tox21_split(token, cvfold=None):
+    ds = load_dataset("tschouis/tox21", token=token)
+    
+    train_df = ds["train"].to_pandas()
+    val_df = ds["validation"].to_pandas()
+
+    if cvfold is None:
+        return {
+            "train": train_df,
+            "validation": val_df
+        }
+    
+    combined_df = pd.concat([train_df, val_df], ignore_index=True)
+    cvfold = float(cvfold)
+
+    # create new splits
+    cvfold = float(cvfold)
+    train_df = combined_df[combined_df.CVfold != cvfold]
+    val_df = combined_df[combined_df.CVfold == cvfold]
+
+    # exclude train mols that occur in the validation split
+    val_inchikeys = set(val_df["inchikey"])
+    train_df = train_df[~train_df["inchikey"].isin(val_inchikeys)]
+
+    return {"train": train_df.reset_index(drop=True), "validation": val_df.reset_index(drop=True)}
+
+
+def get_combined_dataset_csv(token, save_path):
+    datasets = get_tox21_split(token, cvfold=4)
+    train_df, val_df = datasets["train"], datasets["validation"]
+    test_df = val_df.copy()
+    # Add split column
+    train_df["split"] = "train"
+    val_df["split"] = "val"
+    test_df["split"] = "test"
+
+    # Combine all into one DataFrame
+    combined_df = pd.concat([train_df, val_df, test_df], ignore_index=True)
+
+    # Save to a new CSV
+    combined_df.to_csv(save_path, index=False)

src/evaluation.py

@@ -0,0 +1,43 @@
+import pandas as pd
+import numpy as np
+from sklearn.metrics import roc_auc_score
+
+def compute_roc_auc_from_csv(preds_csv: str, labels_csv: str):
+    """
+    Compute ROC AUC per class and overall mean, similar to the PyTorch-style function.
+    Handles missing labels (NaN) like y_mask.
+    """
+    preds = pd.read_csv(preds_csv)
+    labels = pd.read_csv(labels_csv)
+
+    smiles_cols = [c for c in preds.columns if "smiles" in c.lower()]
+    if smiles_cols:
+        print(f"🧪 Dropping SMILES columns: {smiles_cols}")
+        preds = preds.drop(columns=smiles_cols, errors="ignore")
+        labels = labels.drop(columns=smiles_cols, errors="ignore")
+
+    shared_cols = [c for c in preds.columns if c in labels.columns]
+    preds = preds[shared_cols].apply(pd.to_numeric, errors="coerce")
+    labels = labels[shared_cols].apply(pd.to_numeric, errors="coerce")
+
+    y_pred = preds.to_numpy(dtype=float)
+    y_true = labels.to_numpy(dtype=float)
+
+    y_mask = ~np.isnan(y_true)  
+
+    auc_list = []
+    for i in range(y_true.shape[1]):
+        mask_i = y_mask[:, i]
+        if mask_i.sum() > 0:
+            try:
+                auc = roc_auc_score(y_true[mask_i, i], y_pred[mask_i, i])
+            except ValueError:
+                auc = np.nan 
+        else:
+            auc = np.nan
+        auc_list.append(auc)
+
+    auc_array = np.array(auc_list, dtype=np.float32)
+    mean_auc = np.nanmean(auc_array)  
+
+    return auc_array, mean_auc

src/smiles.csv

@@ -1,646 +0,0 @@
-smiles
-C[C@]12C=CC(=O)C=C1CC[C@@H]1C2=CC[C@]2(C)C(C(=O)CN3CCN(c4cc(N5CCCC5)nc(N5CCCC5)n4)CC3)CC[C@@H]12.O=C(O)/C=C\C(=O)O
-Nc1ncnc2c1nc(Br)n2C1OC2CO[P@@](=O)([O-])O[C@@H]2C1O.[Na+]
-O=c1c2ccccc2nc2n1CCc1c-2[nH]c2ccccc12
-Cl.Fc1ccc(C(OCCCc2c[nH]cn2)c2ccc(F)cc2)cc1
-Cc1ccc(S(=O)(=O)NC(Cc2ccccc2)C(=O)CCl)cc1
-Cl.Nc1ccc(-c2ccc3ccccc3n2)cc1
-O=C1NC(=O)/C(=C/c2ccc3c(c2)OC(F)(F)O3)S1
-CCc1ccc(/C=C2/SC(=S)NC2=O)cc1
-C=CCc1cccc(C=NNC(=O)CN2CCN(Cc3ccccc3)CC2)c1O
-CCN1/C(=C/C(C)=O)Sc2ccc(OC)cc21
-O=C1NC(=O)c2cc(Nc3ccccc3)c(Nc3ccccc3)cc21
-CCn1c(=O)[nH]c2cc(Cl)c(Cl)cc21
-Clc1ccc(C(c2ccc(Cl)cc2)[n+]2ccn(CC(OCc3ccc(Cl)cc3Cl)c3ccc(Cl)cc3Cl)c2)cc1.[Cl-]
-COc1cc2ncnc(Nc3cccc(Cl)c3)c2cc1OC
-O=Nc1c(-c2c(O)[nH]c3ccccc23)[nH]c2ccccc12
-CCCCCCCCCCC(C)(C)C(=O)Nc1c(OC)cc(OC)cc1OC
-Cn1cc(C2=C(c3ccc(Cl)cc3Cl)C(=O)NC2=O)c2ccccc21
-CCCCCCCCCCCCCCCC(=O)OC(CC(=O)O)C[N+](C)(C)C.[Cl-]
-Cl.O=c1cc(N2CCOCC2)oc2c(-c3ccccc3)cccc12
-CCCCCCCCCCCCCC(=O)O[C@@H]1[C@@H](C)[C@]2(O)C3=CC(C)C(=O)[C@]3(O)CC(CO)=C[C@H]2[C@@H]2C(C)(C)[C@]12OC(C)=O
-C/C=C(/C)C(=O)O[C@H]1C(C)=C2[C@H]([C@@H]1OC(=O)CCCCCCC)[C@@](C)(OC(C)=O)C[C@H](OC(=O)CCC)[C@@]1(O)[C@H]2OC(=O)[C@@]1(C)O
-COc1cc2c(cc1O)CC[C@@H]1[C@@H]2CC[C@]2(C)[C@@H](O)CC[C@@H]12
-C/C(=C\c1ccc(C(=O)O)cc1)c1ccc2c(c1)C(C)(C)CCC2(C)C
-CCCCCCCCc1ccc(-c2ccc(C(=O)O)cc2)cc1
-[Cl-].c1ccc2c(c1)[I+]c1ccccc1-2
-CS(=O)(=O)O.N=C(NC(=O)c1nc(Cl)c(N)nc1N)Nc1ccccc1
-CC[C@@]1(O)C(=O)OCc2c1cc1n(c2=O)Cc2cc3ccccc3nc2-1
-CC(C)(C)NCC(O)COc1cccc2[nH]c(=O)[nH]c12.Cl
-COC1(C2=NCCN2)COc2ccccc2O1.Cl
-CC(=N)NCCCCC(N)C(=O)O.Cl
-N=C(NCCCC(N)C(=O)O)N[N+](=O)[O-]
-NC(CCCCCP(=O)(O)O)C(=O)O
-NC(CCCP(=O)(O)O)C(=O)O
-Cl.NCCCCC(=O)O
-N[C@@]1(C(=O)O)CCC(C(=O)O)C1
-Cl.NC1(C(=O)O)CCCCC1
-C#CC(N)CCC(=O)O
-CCCCCC(O)CCCC(=O)[O-].[Na+]
-Cl.NC1(C(=O)O)CC1
-C=CCC(N)C(=O)O
-N=C(N)NOCCC(N)C(=O)O.O=S(=O)(O)O
-C[C@H](Cc1ccc2c(c1)OC(C(=O)[O-])(C(=O)[O-])O2)NC[C@H](O)c1cccc(Cl)c1.[Na+].[Na+]
-CCc1ccccc1OC[C@@H](O)CN[C@H]1CCc2ccccc2C1.O=C(O)C(=O)O
-CN(CC[C@@H](Oc1ccc(C(F)(F)F)cc1)c1ccccc1)CC(=O)[O-].[Li+]
-CCCCOc1cc(CC2CNC(=O)N2)ccc1OC
-CN1C2CCC1CC(OC(c1ccccc1)c1ccccc1N)C2
-CC(C)CC(NC(=O)C1OC1C(=O)O)C(=O)NCCCCN=C(N)N
-CC(C)[C@H]1CNC(C(=O)O)[C@H]1CC(=O)O
-CC(=O)NC(C(=O)O)C(C)(C)SN=O
-O=C(O)C1CCCNC1C(=O)O
-COc1ccc2c(c1O)-c1cccc3c1[C@@H](C2)N(C)CC3.Cl
-Br.CN1CCc2cc(O)cc3c2[C@H]1Cc1ccc(O)c(O)c1-3
-O=[N+]([O-])c1cccc2c(Br)[nH]nc12
-O=c1[nH]c2cc([N+](=O)[O-])c([N+](=O)[O-])cc2[nH]c1=O
-O=[N+]([O-])c1cc(O)c(O)c([N+](=O)[O-])c1
-Oc1cc2c(cc1O)CN(C(=S)NCCc1ccc(Cl)cc1)CCC2
-Cl.c1ccc(CN2CCC3(CCCc4ccccc43)CC2)cc1
-Cc1cccc(C#Cc2ccccc2)n1.Cl
-Cc1cccc(/C=C/c2ccccc2)n1
-COc1ccc2c(c1)CCC1C2CC[C@@]2(C)C1CC[C@@H]2NCCCCCCn1c(O)ccc1O
-N=S(=O)([O-])Cc1noc2ccccc12.[Na+]
-N#Cc1cc2nc([O-])c([O-])nc2cc1[N+](=O)[O-].[Na+].[Na+]
-COc1ccc(CCn2nnnc2C2(c3ccc(C)cc3)CC2)cc1
-C[C@@H](Cc1ccc(C=O)cc1)NC[C@@H](O)c1ccc(O)c(NCO)c1.C[C@@H](Cc1ccc(C=O)cc1)NC[C@@H](O)c1ccc(O)c(NCO)c1.O=C(O)/C=C/C(=O)O
-CCCCCCCCCC(=O)NC(CN1CCOCC1)[C@H](O)c1ccccc1.Cl
-CCCCCCCCCC[Si](C)(C)CCC(=O)NC(Cc1ccc(C)cc1)c1ccccc1
-CC(C)N(CCC(=O)c1ccc2ccccc2c1)Cc1ccccc1.Cl
-c1ccc(C(NCc2cccnc2)(c2ccccc2)c2ccccc2)cc1
-Cl.O=C(O)C1=CCCN(CCON=C(c2ccccc2)c2ccccc2)C1
-O=c1cc(-c2ccccc2)[nH]c2nc(Cl)ccc12
-O=c1[nH]ccc2c(O)cccc12
-O=C(c1ccc2c(c1)OCCO2)N1CCCCC1
-CN(C(=O)Cc1ccc(Cl)c(Cl)c1)C(CN1CCCC1)c1cccc(OCC(=O)O)c1.Cl
-CC1CCN(CC[C@H]2CCCN2S(=O)(=O)c2cccc(O)c2)CC1.Cl
-Cn1ncc(S(=O)(=O)Cc2ccccc2)c(Br)c1=O
-CC(C)(Sc1ccc(CCN(CCCCC2CCCCC2)C(=O)NC2CCCCC2)cc1)C(=O)O
-Cl.O=C(Cc1ccc(Cl)c(Cl)c1)N1CCCCC1CN1CCCC1
-Brc1ccc([C@H]2CN3CCSC3=N2)cc1.O=C(O)C(=O)O
-O=C(O)c1cc(=O)c2c(Cl)cc(Cl)cc2[nH]1
-CC1CNCCN1S(=O)(=O)c1cccc2cnccc12.Cl.Cl
-CNCCNS(=O)(=O)c1cccc2cnccc12.Cl.Cl
-CCc1cc(Cl)c(OC)c(C(=O)NC[C@@H]2CCN(CC)C2)c1O.Cl
-CNc1cc(NS(=O)(=O)c2ccc(N)cc2)nc(NC)n1.Cl.Cl
-Cl.O=C(N[C@H]1CN2CCC1CC2)c1ccc(Cl)cc1
-O=C(O)CCC(C(=O)O)N1C(=O)c2ccccc2C1=O
-N#CC(=Cc1ccc(O)c(O)c1)C(=O)NCCc1ccccc1
-Cl.c1ccc2sc(C3(N4CCCCC4)CCCCC3)cc2c1
-C=CCc1ccc([N+](C)(C)CCC(=O)CC[N+](C)(C)c2ccc(CC=C)cc2)cc1.[Br-].[Br-]
-CN1CCc2ccccc2Cc2[nH]c3ccccc3c2CC1
-CC[C@H](NC(=O)c1c(C)c(-c2ccccc2)nc2ccccc12)c1ccccc1
-[NH-]S(=O)(=O)c1cccc2c1c([N+](=O)[O-])cc1nc([O-])c(=O)[nH]c12.[Na+].[Na+]
-CCC(=O)N1CCN(C(=O)c2ccccc2)CC1
-N=C(N)NC(=O)c1nc(Cl)c(N2CCCCCC2)nc1N
-Nc1nc(OCc2ccccc2)c2[nH]cnc2n1
-CCCCCC[C@@H]([C@@H](C)O)n1cnc2c(N)ncnc21.Cl
-Oc1ccc(Cn2cc[nH]c2=S)cc1
-CSc1ccccc1N1CCN(CCCCCC(=O)NC2CCCc3ccccc32)CC1.Cl
-CC[n+]1c(/C=C/C=C2/N(C)c3ccccc3C2(C)C)sc2ccccc21.[I-]
-C[N+]1(C)CCN(c2ccccc2)CC1.[I-]
-Nc1ccc(CCN2CCN(c3cccc(C(F)(F)F)c3)CC2)cc1
-Cl.c1ccc2c(N3CCNCC3)cccc2c1
-Cl.c1ccc2nc(C3=NCCN3)ccc2c1
-Cc1nccc2c1[nH]c1ccccc12
-O=C(c1ccc(Cl)cc1)N1CCN(c2ccc([N+](=O)[O-])c3ncccc23)CC1
-C=CCNc1ncnc2ccc(Br)cc12
-COc1ccccc1N1CCN(CCCCNC(=O)c2ccc3ccccc3c2)CC1
-COc1cccc(C(=O)NCCN2CCN(c3ccc(Cl)cc3)CC2)c1
-CC[N+](CC)(CC)CC(=O)Nc1c(C)cccc1C.[Br-]
-Cc1cc(NC2CCCCC2)nc(-n2nc(C)cc2C)n1
-O=c1onc2cnc3ccccc3n12
-Cc1c(=O)n(C)c(O)c2[nH]cnc12
-CC(O)C(O)c1cnc2[nH]c(N)nc(=O)c2n1
-Cl.c1ccc(CN(Cc2ncc[nH]2)c2ccccc2)cc1
-Cc1cc(NC(=O)Nc2ccc3c(ccn3C)c2)sn1
-Cc1nn(-c2ccccc2)c(C)c1C=NN1CCN(Cc2ccccc2)CC1
-Cc1cc2c(cc1Cl)N(C(=O)Nc1ccnc3ccccc13)CC2
-Clc1ccc2c(c1)N=C(N1CCNCC1)c1ccccc1N2
-Cc1cccc(-c2[nH]c(C(C)(C)C)nc2-c2ccc3nccnc3c2)n1
-O=C(O)c1ccccc1Nc1ccccc1
-CC(C)(C)c1ccc(/C=C/C(=O)Nc2ccc3c(c2)OCCO3)cc1
-CCCN(CC1CC1)c1nc(C)nc(Nc2c(Cl)cc(Cl)cc2Cl)c1Cl
-Cn1cnc2c(NCc3ccccc3)nc(NCCO)nc21
-CCCn1c(=O)c2[nH]c(-c3ccc(S(=O)(=O)O)cc3)nc2n(CCC)c1=O
-C#CCn1c(=O)c2c(ncn2C)n(C)c1=O
-CC(C)Cn1c(=O)n(C)c(=O)c2[nH]cnc21
-Cn1c(=O)c2[nH]c(-c3ccccc3)nc2n(C)c1=O
-Oc1ccc(-c2nc(-c3ccc(F)cc3)c(-c3ccncc3)[nH]2)cc1
-OC[C@H]1O[C@@H](c2nc3cc(Cl)c(Cl)cc3[nH]2)[C@H](O)[C@@H]1O
-Cn1c(=O)c2[nH]c(C3CCCC3)nc2n(C)c1=O
-CCCn1c(=O)c2[nH]c(C3CCCC3)nc2n(CCCOC(=O)c2ccc(S(=O)(=O)F)cc2)c1=O
-O=C(Nc1cccc(C(=O)Nc2ccc(S(=O)(=O)[O-])c3cc(S(=O)(=O)[O-])cc(S(=O)(=O)[O-])c23)c1)Nc1cccc(C(=O)Nc2ccc(S(=O)(=O)[O-])c3cc(S(=O)(=O)[O-])cc(S(=O)(=O)[O-])c23)c1.[Na+].[Na+].[Na+].[Na+].[Na+].[Na+]
-O=c1[nH]c2cc(C(F)(F)F)ccc2n1-c1cc(C(F)(F)F)ccc1O
-COc1ccccc1N1CCN(CCN(C(=O)c2ccc(F)cc2)c2ccccn2)CC1.Cl.Cl
-O=c1[nH]c2ccccc2c2ccccc12
-Nc1ncnc2[nH]nc(Nc3ccc(F)cc3)c12
-CC1(C)C(=O)N(CCN2CCC(C(=O)c3ccc(F)cc3)CC2)c2ccccc21.Cl
-O=c1onc2n1-c1cc(Br)ccc1OC2
-CC(=O)NNC(=O)N1Cc2ccccc2Oc2ccc(Cl)cc21
-COc1ccccc1N1CCN(CCN(C(=O)C2CCCCC2)c2ccccn2)CC1.O=C(O)/C=C\C(=O)O
-COc1ccc(NC(=O)c2ccc(-c3ccc(-c4noc(C)n4)cc3C)cc2)cc1N1CCN(C)CC1.Cl
-O=C(O)c1ccccc1Nc1cccc(OCc2ccc3ccccc3n2)c1
-N#C/C(=C\c1ccc(-c2cc(Cl)ccc2Cl)o1)C(=O)Nc1cccc2ncccc12
-COc1cc2nc(N3CCCN(C)CC3)nc(NC3CCN(Cc4ccccc4)CC3)c2cc1OC.Cl.Cl.Cl
-COc1ccc2c(c1)c(CC(=O)O)c(C)n2C(=O)c1ccccc1
-O=c1[nH]c2cc(Cl)ccc2c(O)c1-c1ccc(Oc2ccccc2)cc1
-Nc1nc2ccc(Cl)cc2c2nc(-c3ccco3)nn12
-Nc1nc2c(cnn2CCc2ccccc2)c2nc(-c3ccco3)nn12
-O=C1NC(=O)C(c2ccccc2[N+](=O)[O-])C1=Nc1ccc(O)c(Cl)c1
-O=C1Cc2c([nH]c3ccc(Br)cc23)-c2ccccc2N1
-O=S1(=O)N(CCN2CC=C(c3c[nH]c4cc(F)ccc34)CC2)c2cccc3c2N1CCC3
-CCCc1c(-c2ccc(O)cc2)nn(-c2ccc(O)cc2)c1-c1ccc(O)cc1
-OCc1ccc(-c2nn(Cc3ccccc3)c3ccccc23)o1
-CN1CC[C@@]2(C)c3cc(O)ccc3N(C)C12.O=C(O)/C=C\C(=O)O
-CCOC(=O)C(C)Oc1cccc2c(=O)n(CC(=O)Nc3ccc4c(c3)OCCO4)ccc12
-CS(=O)(=O)O.Cn1cc(C(F)(F)F)nc1-c1ccc(OCC(O)CNCCOc2ccc(O)c(C(N)=O)c2)cc1
-COc1cccc(OC)c1OCCNCC1CSc2ccccc2O1.Cl
-N#CSc1ccc2oc(C3=NCCN3)cc2c1
-O=C(O)C1CCN1
-O=C(O)C1CCNCC1
-NC(CS(=O)O)C(=O)O
-CCCCCCCCCCCCCCSCC(=O)O
-C[N+](C)(C)CCOC(=O)CBr.[Br-]
-Br.CO[C@H]1CC=C2CCN3CCC4=C(CC(=O)OC4)[C@]23C1
-CCCCCCC(=O)OC1CC(C)(C)NC(C)(C)C1.Cl
-CN1CC(O)C(O)C(O)C1CO
-Cl.OCC1NCC(O)C(O)C1O
-CCCC(=O)NCCc1c2n(c3ccc(OC)cc13)CCCc1ccccc1-2
-O=c1cc(-c2ccccc2F)[nH]c2cc3c(cc12)OCO3
-Nc1nc(Cl)nc2c1ncn2[C@@H]1O[C@H](CO)C(O)[C@H]1O
-OC[C@H]1O[C@@H](n2cnc3c(NC4CCCC4)ncnc32)[C@H](O)C1O
-OC[C@H]1O[C@@H](n2cnc3cncnc32)[C@H](O)[C@@H]1O
-CNc1ncnc2c1ncn2[C@H]1C[C@H](OP(=O)([O-])O)[C@@H](COP(=O)([O-])O)O1.[NH4+].[NH4+]
-Nc1ncnc2c1ncn2C1CCCO1
-Nc1nc(=O)c2nc(Br)n(C3OC4CO[P@@](=O)([O-])O[C@@H]4C3O)c2[nH]1.[Na+]
-O=C(O)c1cc([N+](=O)[O-])ccc1NCCCc1ccccc1
-C[N+]1(C)C2CCC1CC(OC(=O)c1c[nH]c3ccccc13)C2.[I-]
-CC(=O)O[C@H]1Cc2ccccc2N(C(N)=O)c2ccccc21
-O=c1[nH]c(=S)[nH]c(-c2ccccc2)c1Cc1c(O)ccc2ccccc12
-CC#CCOC(=O)c1c(C)nc2sc3c(c2c1N)CCC(O)C3
-N#Cc1cc([N+](=O)[O-])c2sc(C(N)=O)[n+]([O-])c2c1
-Cc1cnc(NC(=O)C2=C([O-])c3ccccc3S(=O)(=O)N2C)s1.[Na+]
-Nc1c(S(=O)(=O)[O-])cc(Nc2ccc(Nc3nc(Cl)nc(Nc4ccc(S(=O)(=O)[O-])cc4)n3)c(S(=O)(=O)[O-])c2)c2c1C(=O)c1ccccc1C2=O.[Na+].[Na+].[Na+]
-COc1cc(/C=C(\C#N)C(=O)Nc2nnc(C(F)(F)F)s2)ccc1OCc1ccc(C(F)(F)F)cc1C(F)(F)F
-CCCCOC(=O)NS(=O)(=O)c1sc(CC(C)C)cc1-c1ccc(Cn2c(CC)nc3c(C)cc(C)nc32)cc1
-Cc1nc(N=Nc2ccc(S(=O)(=O)[O-])cc2S(=O)(=O)[O-])c(COP(=O)([O-])[O-])c(C=O)c1O.[Na+].[Na+].[Na+].[Na+]
-CN1CCC(c2c[nH]c3ccc(O)cc23)CC1.O=C(O)/C=C\C(=O)O
-COc1cc2c(CCNC(C)=O)c[nH]c2cc1O
-O=C(O)Cc1c[nH]c2ccc(O)cc12
-CC(N)Cc1c[nH]c2ccc(OCc3cccs3)cc12.Cl
-COc1ccc2[nH]cc(CCN)c2c1.Cl
-CCN(CC)c1ncnc2c1ncn2[C@@H]1O[C@H](COP(=O)([O-])OP(=O)([O-])C(Br)(Br)P(=O)([O-])O)[C@@H](O)[C@H]1O.[Na+].[Na+].[Na+]
-CSc1nc(N)c2ncn([C@@H]3O[C@H](COP(=O)([O-])OP(=O)([O-])OP(=O)([O-])[O-])C(O)[C@H]3O)c2n1.[Na+].[Na+].[Na+].[Na+]
-Nc1ncnc2c1nc(Sc1ccc(Cl)cc1)n2[C@H]1OC2CO[P@@](=O)([O-])O[C@@H]2C1O.[Na+]
-Nc1ncnc2c1ncn2[C@@H]1O[C@H](COP(=O)([O-])OP(=O)([O-])OP(=O)([O-])OP(=O)(O)OC[C@@H]2O[C@H](n3cnc4c(N)ncnc43)[C@@H](O)C2O)C(O)[C@H]1O.[NH4+].[NH4+].[NH4+]
-NC(=O)C1=CN(C2OC(COP(=O)([O-])OP(=O)([O-])OC[C@H]3O[C@@H](n4cnc5c(N)ncnc54)[C@H](OP(=O)([O-])[O-])C3O)C(O)C2O)C=CC1.[Na+].[Na+].[Na+].[Na+]
-NC(=S)c1ccc[n+]([C@@H]2O[C@@H](COP(=O)([O-])OP(=O)(O)OC[C@H]3O[C@@H](n4cnc5c(N)ncnc54)[C@H](OP(=O)([O-])O)C3O)C(O)C2O)c1.[Na+]
-Nc1ccc(CCNc2ncnc3c2ncn3C2OC(CO)C(O)C2O)cc1
-CNC(=O)C1O[C@@H](n2cnc3c(NCc4ccc(N)cc4)ncnc32)[C@H](O)C1O
-CCNC(=O)C1O[C@@H](n2cnc3c(N)nc(NCCc4ccc(CCC(=O)O)cc4)nc32)[C@H](O)C1O.Cl
-CCNC(=O)C1O[C@@H](n2cnc3c(N)ncnc32)[C@H](O)C1O
-C[C@H](Cc1ccccc1)Nc1ncnc2c1ncn2[C@@H]1O[C@H](CO)C(O)[C@H]1O
-NCCc1c[nH]c2ccc(C(N)=O)cc12.O=C(O)/C=C\C(=O)O
-O=C([O-])Cc1ccccc1Nc1c(Cl)cccc1Cl.[Na+]
-COC(=O)C1=C(C)N=C(C)C([N+](=O)[O-])C1c1ccccc1C(F)(F)F
-CC(=O)NC(Cc1c[nH]c2ccccc12)C(=O)OCc1cc(C(F)(F)F)cc(C(F)(F)F)c1
-CC(C)C1C(=O)C(C(N)=O)C(=O)[C@@]2(O)C(=O)C3C(=O)c4c(O)ccc(N(C)C)c4C[C@H]3C[C@@H]12.Cl
-Cl.Oc1ccc2c3c1O[C@H]1c4[nH]c5ccccc5c4C[C@@]4(O)C(C2)N(CC2CC2)CCC314
-COc1cc(N)c(Cl)cc1C(=O)OCCN1CCCCC1
-CCN(CC)CCOC(=O)c1cc(Cl)c(N)cc1OC.Cl
-CCCCCCCC/C=C\CCCCCCCC(=O)NCCO
-C[N+](C)(C)CC#CCN1CCCC1=O.[I-]
-CCN1C(=O)C=CC1=O
-Cl.NOCC(=O)O.NOCC(=O)O
-CC(=O)C(C)=NO
-CC(=O)NBr
-NC(=O)C(=O)[O-].[Na+]
-CCN(CC)CCCCCCCCOC(=O)c1cc(OC)c(OC)c(OC)c1.Cl
-O=Nc1ccc2oc(=O)ccc2c1
-COc1cccc(-c2cc(=O)c3ccccc3o2)c1N
-CC(=O)c1c(O)c(C)c(O)c(Cc2c(O)c3c(c(C(=O)/C=C/c4ccccc4)c2O)OC(C)(C)C=C3)c1O
-O=C1C(O)c2c(O)cc(O)cc2OC1c1ccc(O)c(O)c1
-COC[C@H]1OC(=O)c2coc3c2[C@@]1(C)C1=C(C3=O)C2CCC(=O)[C@@]2(C)C[C@H]1OC(C)=O
-COC(=O)C1=CO[C@@H](O)[C@@H]2C(CO)=CC[C@H]12
-C=C1C[C@@]23CC[C@H]4[C@@](C)(CCC[C@@]4(C)C(=O)OC4OC(CO)C(O)C(O)C4O)[C@@H]2CC[C@]1(OC1OC(CO)C(O)C(O)C1OC1OC(CO)C(O)C(O)C1O)C3
-C=C(C)[C@H]1C2C(=O)O[C@H]1[C@H]1OC(=O)[C@@]34O[C@@H]3C[C@]2(O)[C@@]14C.CC(C)(O)[C@H]1C2C(=O)O[C@H]1[C@H]1OC(=O)[C@@]34O[C@@H]3C[C@]2(O)[C@@]14C
-CC1(C(=O)O)C2CCC(O2)C1(C)C(=O)O
-OCC1O[C@H](O)C(Cl)C(O)C1O
-Cl.Cl.Cl.NCCC1CCCC(CCN)N1
-Cl.Cl.Cl.NCCCCNCCCN
-S=C([S-])N1CCCC1.[NH4+]
-CC(=O)SCC[N+](C)(C)C.[Cl-]
-NCCCS(=O)(=O)[O-].[Na+]
-C[N+](C)(C)CC=O.[Cl-]
-Cl.Cl.NCCSSCCN
-Br.CCSC(=N)N
-[Li]Cl
-CSC(=N)N.CSC(=N)N.O=S(=O)(O)O
-Cl.Cl.NCCCCN
-O=c1ccc2c(OCCCCc3ccccc3)c3ccoc3cc2o1
-CCCC[C@@]1(C2CCCC2)Cc2cc(OCC(=O)O)c(Cl)c(Cl)c2C1=O
-C[C@]12CCC3C(CC[C@H]4C[C@H](O)CC[C@]34C)C1CCC2C(=O)CO
-N#CC(=Cc1ccc(O)cc1)C(=N)C(C#N)C#N
-N#CC(=Cc1ccc(O)c(O)c1)C(=O)NCCCNC(=O)C(C#N)=Cc1ccc(O)c(O)c1
-COc1ccc(C=C(C#N)C#N)cc1
-CC(C)(C)c1cc(C=C(C#N)C(N)=S)cc(C(C)(C)C)c1O
-N#CC(=Cc1ccc(O)c(O)c1)C(N)=S
-N#CC(C#N)=CC(=N)C(C#N)c1cc(O)c(O)c(O)c1
-CC(C)(C)c1cc(C=C(C#N)C#N)cc(C(C)(C)C)c1O
-CC(C)NP(=O)(NC(C)C)OP(=O)(NC(C)C)NC(C)C
-O=C(O)CCC/C=C\C[C@@H]1[C@@H](/C=C/[C@H](O)C2Cc3ccccc3C2)[C@@H](F)C[C@@H]1O
-CC(=O)C1CCC2C3CC=C4C[C@@H](OS(=O)(=O)[O-])CC[C@]4(C)C3CC[C@]12C.[Na+]
-C1CNCCN1.COc1cc(C(O)CO)ccc1O.COc1cc(C(O)CO)ccc1O
-CC1CCN=C(N)S1.Cl
-NC(C(=O)O)c1cc(O)cc(O)c1
-O=C1/C(=C/c2ccsc2)CC/C1=C\c1cccs1
-C=C(C)C1CC=C(C(=O)O)CC1
-CCCCCCCCCCC/C=C\C(C)(C)/C=C\CCCC(=O)O
-CCCCCCC/C=C\CCCCCCCCC(=O)O
-NC(C(=O)O)c1cc(=O)[nH]o1
-C=C/C(C)=C/[C@@]1(C)SC(=O)C(C)C1=O
-Br.C#CCOC(=O)C1=CCCN(C)C1
-O=C(O)C1CN(CCCP(=O)(O)O)CCN1
-Cl.O=C(O)C1=CCNCC1
-CP(=O)([O-])C1=CC[NH2+]CC1
-Cl.NCC(O)c1cc(O)c(O)cc1F
-Cl.O=C(O)Cc1c[nH]cn1
-Br.Br.N=C(N)SCCc1c[nH]cn1
-COC(=O)C(C)(N)Cc1ccc(O)cc1.Cl
-Cl.NC1C=CC=C(C(=O)O)C1
-NC(Cc1cccc(-c2ccccc2CP(=O)(O)O)c1)C(=O)O
-Cl.O[Si](CCCN1CCCCC1)(c1ccc(F)cc1)C1CCCCC1
-C[C@@H](N)C1CCC(C(=O)Nc2ccncc2)CC1.Cl.Cl
-CNCCc1ccc(O)c(O)c1.Cl
-Br.CCCN(CCC)CCc1ccc(O)c(O)c1
-C[C@@H](CN1CCC(Cc2ccccc2)CC1)[C@@H](O)c1ccc(O)cc1.Cl
-O=C(O)CNC(=O)C(CS)Cc1ccccc1
-C#CCN[C@H](C)Cc1ccccc1.Cl
-Cl.NCCc1ccc(S(=O)(=O)F)cc1
-CC(N)c1cccc(Cl)c1Cl.Cl
-NC(=O)c1cccc(N)c1
-CC(=O)O.N=C(N)N/N=C/c1c(Cl)cccc1Cl
-Br.CCCN(CCC)[C@@H]1CCc2ccc(O)cc2C1
-Br.CCCN(CCC)C1CCc2cccc(O)c2C1
-CCCN(CCc1ccccc1)C1CCc2c(O)cccc2C1.Cl
-CCCN(CCC)[C@H]1CCc2c(F)ccc(O)c2C1.Cl
-C[N+](C)(C)CC#CCOC(=O)Nc1cccc(Cl)c1.[Cl-]
-Cl.N=C(N)N=C(N)Nc1cccc(Cl)c1
-Cl.Clc1cc(I)cc(Cl)c1NC1=NCCN1
-S=C(Nc1ccccc1)Nc1nccs1
-N=C(N)N=C(N)Nc1ccccc1
-Brc1c(Br)c(Br)c2[nH]nnc2c1Br
-CN1CCc2cc(Cl)c(O)cc2C(c2ccccc2)C1.Cl
-Br.Cc1cccc(C2CN(C)CCc3c2cc(O)c(O)c3Cl)c1
-Br.C=CCN1CCc2cc(O)c(O)cc2C(c2ccccc2)C1
-Cl.OC1CCCCC1N1CCC(c2ccccc2)CC1
-Cc1ccccc1/C=C/C1=NCCN1.O=C(O)C(=O)O
-O=C([O-])C[C@H](O)CC(O)/C=C/c1c(C2CC2)nc2ccccc2c1-c1ccc(F)cc1.O=C([O-])C[C@H](O)C[C@H](O)/C=C/c1c(C2CC2)nc2ccccc2c1-c1ccc(F)cc1.[Ca+2]
-C[N+](C)(C)CCCCCC[N+](C)(C)C.[Cl-].[Cl-]
-[Cl-].c1ccc(C[P+](c2ccccc2)(c2ccccc2)c2ccccc2)cc1
-CN(C)c1ccc(C(=C2C=CC(=[N+](C)C)C=C2)c2ccccc2)cc1.[Cl-]
-CCCCCCCCCCCCCC[N+](C)(C)Cc1ccccc1.[Cl-]
-CC[N+](CC)(CC)Cc1ccccc1.[Cl-]
-CCc1c(C(=O)[O-])c(=O)cnn1-c1ccc(Cl)cc1.[K+]
-O=P([O-])([O-])CN(CP(=O)([O-])[O-])CP(=O)([O-])O.[Na+].[Na+].[Na+].[Na+].[Na+]
-O=S(=O)([O-])c1cc(S(=O)(=O)[O-])c2ccc3c(S(=O)(=O)[O-])cc(S(=O)(=O)[O-])c4ccc1c2c43.[Na+].[Na+].[Na+].[Na+]
-COc1ccc([N+](=O)[O-])cc1[O-].[Na+]
-CCc1cccc(CC)c1N(COC)C(=O)CS(=O)(=O)[O-].[Na+]
-O=S([O-])O.[Na+]
-COCc1c(-c2ccc(F)cc2)c(=CC[C@@H](O)C[C@@H](O)CC(=O)[O-])c(C(C)C)nc1=C(C)C.[Na+]
-[Na+].[O-]c1c(Cl)c(Cl)c(Cl)c(Cl)c1Cl
-CCc1cccc(CC)c1NC(=O)C(=O)[O-].[Na+]
-Nc1ccc(S(=O)(=O)[N-]c2nccs2)cc1.[Na+]
-Nc1ccc2c(S(=O)(=O)O)cccc2c1S(=O)(=O)[O-].[Na+]
-CCN(CCC#N)c1ccc(/N=N/c2ccc([N+](=O)[O-])cc2)cc1
-B.C1COCCN1
-N#CBr
-C=CC(=O)OCC(Br)CBr
-CCc1c(Br)c(Br)c(Br)c(Br)c1Br
-Brc1cc(Br)cc(Br)c1
-Nc1c(Br)cc([N+](=O)[O-])cc1Br
-Brc1ccccn1
-Brc1c(Br)c(Br)c(Oc2c(Br)c(Br)c(Br)c(Br)c2Br)c(Br)c1Br
-O=C1OC2(c3ccccc31)c1ccc(O)c(Br)c1Oc1c2ccc(O)c1Br
-BrCC(Br)c1ccccc1
-CCCCCCCCCCBr
-C#CC(O)CCC
-CN(C)c1ccc(C(=C2C=CC(=[N+](C)C)C=C2)c2ccccc2)cc1.O=C([O-])C(=O)O
-C=CC(=C)CC/C=C(\C)CCC=C(C)C
-CC(C)=CCCC(C)O
-CC(C)=NNC(N)=S
-C[As+](C)(C)CC(=O)[O-]
-COCC(=O)N(c1c(C)cccc1C)C(C)C(=O)OC
-CCOC(=O)C(C)O
-C/C(=N/[Si](C)(C)C)O[Si](C)(C)C
-CCO[Si](C)(C)OCC
-C[SiH](C)O[SiH](C)C
-CC(=O)[CH-]C(C)=O.CC(=O)[CH-]C(C)=O.[AlH3].[CH2-]C(=O)CC(C)=O
-CC(=O)[CH-]C(C)=O.CC(=O)[CH-]C(C)=O.[CH2-]C(=O)CC(C)=O.[Cr]
-CC(=O)[CH-]C(C)=O.CC(=O)[CH-]C(C)=O.[CH2-]C(=O)CC(C)=O.[Fe]
-CC(C)=CCC[C@H](C)CC=O
-CCC(=O)OC/C=C(\C)CCC=C(C)C
-CC(C)=CCCC(C)CCOC(=O)C(C)C
-C=CC/C=C/C/C=C/C/C=C/C
-C=C(C)CCCC
-C=C(C)CCO
-C=C[Si](C)(C)Cl
-C=C1CC[C@H]2O[C@]2(C)CC[C@@H]2[C@@H]1CC2(C)C
-C=CC(=O)O[C@@H]1C[C@H]2CC[C@]1(C)C2(C)C
-C=CC(=O)OCCOC1C2CCC1C1CC=CC12
-C=CC(C)(C)O
-C=CC(C)C#N
-C=CC=CC=CCCCCC
-C=Cc1ccncc1
-C=COCCCC
-C=COCCCl
-C1=CCCC1
-c1ccc(-c2ccccc2-c2ccccc2)cc1
-c1ccc2c(c1)CCC2
-c1ccc([Sb](c2ccccc2)c2ccccc2)cc1
-c1cc[nH]c1
-C1CCSC1
-c1ccc2c(c1)-c1ccc3ccc4cccc5cc-2c1c3c45
-C=C(C)C1CCC(C)CC1O
-CCC=C(C)C=O
-CC(=O)CC(N)=O
-CCCC(C)CCC(C)=O
-CCCCCCCCC(C)=O
-CC(=O)O[C@@H]1C[C@@H]2CC[C@@]1(C)C2(C)C
-CC(=O)OCC=C(C)CCC=C(C)CCC=C(C)C
-CCc1cc(C)cc(CC)c1-c1c(OC(=O)C(C)(C)C)n2n(c1=O)CCOCC2
-CC(C)(C)C(O)C(Oc1ccc(-c2ccccc2)cc1)n1cncn1
-CC(C)(C)C1=CC(=O)C(C(C)(C)C)=CC1=O
-CSc1nc(=O)c(C(C)(C)C)n[nH]1
-CCC(C)c1cc(C(C)(C)C)cc(-n2nc3ccccc3n2)c1O
-Cc1cc(C)c(O)c(C(C)(C)C)c1
-CC(C)(C)c1cc(CCC(=O)NCCCCCCNC(=O)CCc2cc(C(C)(C)C)c(O)c(C(C)(C)C)c2)cc(C(C)(C)C)c1O
-CC(C)(C)c1cc(CCC(=O)OCCSCCOC(=O)CCc2cc(C(C)(C)C)c(O)c(C(C)(C)C)c2)cc(C(C)(C)C)c1O
-CC(C)(C)c1ccc(OC2CCCCC2O)cc1
-CC(c1cc(C(C)(C)C)cc(C(C)(C)C)c1O)c1cc(C(C)(C)C)cc(C(C)(C)C)c1O
-CC(CC(C)(C)C)CC(C)(C)CC(C)(C)C
-CC(C)(C)N.CCCC(NC(C)C(=O)N1C(C(=O)O)C[C@@H]2CCCC[C@@H]21)C(=O)OCC
-CCC(C)(OOC(C)(C)C)OOC(C)(C)C
-CC(C)(COCC1CO1)COCC1CO1
-CC(C)C(=O)C(C)C
-CC(C)C(=O)OCc1ccccc1
-CC(C)C(=O)Cl
-CC(C)c1ccccc1N
-CC(C)CBr
-CC(C)CCOCCC(C)C
-CC=CC(=O)OCC(C)C
-COCCc1ccc(OCC(O)CNC(C)C)cc1
-CC(C)OP(OC(C)C)OC(C)C
-CC(C=O)c1ccccc1
-CC(c1ccccc1)(c1ccc(O)cc1)c1ccc(O)cc1
-CC(c1ccc(O)cc1)c1ccc(O)cc1
-CCC(C)C(=O)OC
-CCC(=O)CC(C)CC
-CCCC(C)C=O
-CCOC(=O)CC(C)O
-CCSC(C)CC1CC(=O)C(C(CC)=NOC/C=C/Cl)C(=O)C1
-CC=CC(=O)C1=C(C)C=CCC1(C)C
-C=C(/C=C/C)C1=C(C)CCCC1(C)C
-CC=CCO
-CC1(C)C(=O)N(CO)C(=O)N1CO
-CC1(C)COCN1
-CCC1(C)C(=O)N(Cl)C(=O)N1Cl
-Cc1cc(C)[nH]c(=O)n1.O=C(Nc1ccc([N+](=O)[O-])cc1)Nc1ccc([N+](=O)[O-])cc1
-CC1=CC[C@@H](C(C)(C)O)CC1
-Cc1ccc(O)o1
-Cc1c[nH]c(=O)[nH]c1=O
-Cc1cc(C)c(C=O)c(C)c1
-CC(C)=CC1CC(C)CCO1
-CNC(=O)Oc1cc(C)c(SC)c(C)c1
-Cc1cccc(N(C)C)c1
-Cc1cccc(OP(=O)(Oc2cccc(C)c2)Oc2cccc(C)c2)c1
-CSc1ccc(O)cc1C
-Cc1ccc2[nH]nnc2c1
-Cc1ccc(C=O)cc1
-Cc1ccc(C(=O)Cl)cc1
-CC1CCC(C(C)(C)O)CC1
-Cc1ccc(S(=O)(=O)C(I)I)cc1
-COc1cc(C(C)C)ccc1C
-Cc1ccc(CCl)cc1
-Cc1ccc2nc3sc(=O)sc3nc2c1
-Cc1cccc(C)c1C
-Cc1cccc(C)n1
-C=Cc1cccc(C)c1
-CC1CCCCC1
-CCc1ccccc1C
-Cc1cncc(C)c1
-CC1CNCC(C)O1
-Cc1cnccn1
-COC[C@H](C)N(C(=O)CCl)c1c(C)csc1C
-CC1(C)[C@H]2CC[C@]1(C)C(=O)C2
-Cc1ccc(N=Nc2c(O)ccc3ccccc23)c(C)c1
-Cc1cccc2c1ccc1ccccc12
-Cc1ccc2sc3cccc(C)c3c2c1
-CCC(=O)O
-CCC(=O)OCC=Cc1ccccc1
-CCC(C)c1ccccc1
-CCC(O)CO
-CCc1c(C)cc(N)c(CC)c1N
-CCc1cccc(CC)c1
-CCC1CCCCC1
-CCc1ccc(C)nc1
-CCCC(O)C(O)CO
-CCCCCCCC(C)=O
-CCCCCCCCc1ccc(Nc2ccc(CCCCCCCC)cc2)cc1
-CCCCCCCCCCc1ccccc1
-CCCCCCCCCCCCCc1ccccc1
-CCCCCCCCCCCCCCCCCO
-CCCCCCS
-CCCCN(C)C
-CCCCOP(=O)(CCCC)OCCCC
-CCCCOP(OCCCC)OCCCC
-CCN(CC)C(=O)Cl
-CCN(CC)c1cccc(C)c1
-CCN(CC)c1ccc(/N=N/c2ccccc2)cc1
-CCN(CC)c1ccc(C=O)cc1
-CCN(CC)c1ccc2c(c1)Oc1cc(N(CC)CC)ccc1C21OC(=O)c2ccccc21
-CCn1c2ccccc2c2ccccc21
-CCOB(OCC)OCC
-CCOC(/C=C(\C)CCC=C(C)C)OCC
-CCOC(=O)OC(=O)OCC
-CC=Cc1ccc(OCC)c(O)c1
-CCCCOCC
-CCOCOCC
-CCOP(=O)(OCC)SCCSCC
-CCOP(=S)(OCC)SCS(=O)(=O)C(C)(C)C
-CCOP(=S)(OCC)SCS(=O)(=O)CC
-CC(Cl)CN(C)C.Cl
-Cl.Cl.Nc1ccc(N)cc1
-CN(C)CCCl.Cl
-Cl.ClCCN1CCOCC1
-Cl.ClCCNCCCl
-CCOC(=O)CN.Cl
-CC1(C)C(C(=O)OCc2cccc(Oc3ccccc3)c2)[C@@H]1C=C(Cl)Cl
-Cl[C@H]1[C@H](Cl)[C@@H](Cl)[C@H](Cl)[C@@H](Cl)[C@H]1Cl
-Cl[Sn](c1ccccc1)(c1ccccc1)c1ccccc1
-CC1(C)C(C(=O)O[C@H](C#N)c2cccc(Oc3ccccc3)c2)[C@@H]1/C=C(\Cl)C(F)(F)F
-Cl/C=C\CCl
-CCCCCCCCCCCC(=O)Cl
-O=C(Cl)OCCOC(=O)Cl
-ClC(c1ccccc1)(c1ccccc1)c1ccccc1
-O=S(=O)(C(Cl)(Cl)Cl)C(Cl)(Cl)Cl
-C#CC1=C(C#C)C(=O)C(Cl)=C(Cl)C1=O
-Cc1cc(Cl)ccc1OC(C)C(=O)O
-CC(Oc1ccc(Cl)cc1Cl)C(=O)O
-CC(C)N.O=C(O)COc1ccc(Cl)cc1Cl
-Clc1ccc2c(Cl)ccnc2c1
-N#CCc1ccc(Cl)cc1
-Clc1ccc(-c2ccccc2)cc1
-COc1cc2ncnc(Nc3cccc(Cl)c3)c2cc1OC
-Clc1cccc(Cl)n1
-Clc1cccnc1
-Clc1nc2ccccc2s1
-ClC1=C(Cl)[C@]2(Cl)[C@H]3C[C@@H](Cl)C(Cl)[C@H]3[C@@]1(Cl)C2(Cl)Cl
-ClC1=C(Cl)[C@]2(Cl)[C@H]3C[C@H](Cl)C(Cl)[C@H]3[C@@]1(Cl)C2(Cl)Cl
-CC[Hg+].Oc1[n-]c(O)c2c1C1(Cl)C(Cl)=C(Cl)C2(Cl)C1(Cl)Cl
-Clc1cc(Cl)c(-c2c(Cl)c(Cl)cc(Cl)c2Cl)cc1Cl
-Clc1ccc(Oc2ccccc2)cc1
-O=C(NCc1ncc(C(F)(F)F)cc1Cl)c1c(Cl)cccc1Cl
-ClC(Cl)=C(c1ccc(Cl)cc1)c1ccccc1Cl
-NC(=O)CCl
-ClCc1ccccc1CCl
-OCCCCl
-CCCCCCCCCCCCS(=O)(=O)Cl
-C=CC(=O)N(C)C
-CN(C)CCN1CCOCC1
-Cn1cccc1
-CN1CCN(C)CC1
-Cn1ccnc1
-CN1CN(C)CN(C)C1
-CO[Si](CCC1CCC2OC2C1)(OC)OC
-CO[Si](CCCNCCNCCN)(OC)OC
-CO[Si](OC)(c1ccccc1)c1ccccc1
-CCCCCCCC(OC)OC
-CC=Cc1ccc(OC)c(OC)c1
-COc1ccc(C#N)cc1
-COc1ccc(OC)c(C=O)c1
-COc1cccc(OC)c1O
-COc1ccccc1C=O
-CCNc1nc(NC(C)(C)C)nc(OC)n1
-COc1nccnc1CC(C)C
-COc1ccc(OC)c(N=Nc2c(O)ccc3ccccc23)c1
-COS(=O)(=O)c1ccc(C)cc1
-CS(C)(=O)=O
-COC(=O)N(C(=O)N1COC2(C(=O)OC)Cc3cc(Cl)ccc3C2=N1)c1ccc(OC(F)(F)F)cc1
-N#Cc1ccc(C/C(=N\NC(=O)Nc2ccc(OC(F)(F)F)cc2)c2cccc(C(F)(F)F)c2)cc1
-CC(=NNC(=O)Nc1cc(F)cc(F)c1)c1ncccc1C(=O)O
-O=C(O)c1cn(-c2ccc(F)cc2)c2cc(N3CCNCC3)c(F)cc2c1=O
-Oc1c(I)cc(I)cc1I
-Oc1ccc(I)cc1
-N#C/C=C/c1ccccc1
-CC(O)C#N
-N#Cc1cc([N+](=O)[O-])ccc1N
-N#Cc1ccc(O)cc1
-N#Cc1ccccc1Cl
-N#Cc1ccccc1N
-N#CCCO
-N#CCCOCCC#N
-NC(=O)C1CO1
-C=CCOC(N)=O
-Nc1cc([N+](=O)[O-])cc(Cl)c1O
-Nc1cc([N+](=O)[O-])ccc1Cl
-CC(C)(c1ccc(Oc2ccc(N)cc2)cc1)c1ccc(Oc2ccc(N)cc2)cc1
-Nc1ccc(Oc2cccc(Oc3ccc(N)cc3)c2)cc1
-Nc1ccc([N+](=O)[O-])cc1Cl
-Nc1cccnc1N
-Nc1ccc(Cl)cc1C(=O)c1ccccc1
-NCc1ccco1
-COP(N)(=S)OC
-Cl[Dy](Cl)Cl.O.O.O.O.O.O
-Cl[Eu](Cl)Cl.O.O.O.O.O.O
-O.O.O.O.O.O.[Cl-].[Cl-].[Cl-].[Sc+3]
-O=C(C(O)CO)C(O)CO
-C[C@]12CC[C@H](O)C[C@H]1CC[C@@H]1[C@@H]2C[C@@H](O)[C@]2(C)[C@@H](C3=CC(=O)OC3)CC[C@]12O
-CCOC(=O)C(O)C(O)C(=O)OCC
-O[Si](c1ccccc1)(c1ccccc1)c1ccccc1
-O=[N+]([O-])c1cc(Cl)ccc1Cl
-Nc1ccc(Cl)c([N+](=O)[O-])c1
-Nc1ccc(F)c([N+](=O)[O-])c1
-O=[N+]([O-])c1ccc([N+](=O)[O-])cc1
-COC(=O)c1ccc([N+](=O)[O-])cc1
-O=[N+]([O-])c1ccc(CO)cc1
-O=C(c1ccccc1)C(Cl)Cl
-CCOC(OCC)C(=O)c1ccccc1
-CC(=O)c1ccc(-c2ccccc2)cc1
-CC(=O)c1ccccc1N
-CC(=O)OC1CCCCC1
-C=CC(=O)OCCN(CC)CC
-COC(=O)C=Cc1ccccc1
-O=C(c1ccccc1)c1ccc(Cl)cc1
-CCCC(=O)OC(OC(=O)CCC)OC(=O)CCC
-CCCCCCCC(=O)OCC
-CC/C=C\C/C=C\C/C=C\CCCCCCCC(=O)OC
-CN(CCCC(=O)c1cccnc1)N=O
-O=C(Cl)c1ccc(Cl)cc1
-O=C(Cl)c1ccc(Cl)cc1Cl
-O=C(Cl)Oc1ccccc1
-NC(=O)c1ccccc1Cl
-NC(=O)c1ccc(N)nc1
-CCOC(=O)c1ccccc1S(=O)(=O)NC(=O)Nc1nc(Cl)cc(OC)n1
-COc1cc(OC)nc(NC(=O)NS(=O)(=O)Nc2ccccc2C(=O)N(C)C)n1
-CCc1cccc(C)c1N(C(=O)C(=O)O)C(C)COC
-C/C(=C\c1ccc(C(=O)O)cc1)c1ccc2c(c1)C(C)(C)CCC2(C)C
-O=C(O)CN(CCCN(CC(=O)O)CC(=O)O)CC(=O)O
-CCOc1nc(F)cc2nc(S(=O)(=O)Nc3c(Cl)cccc3C(=O)OC)nn12
-COCCC(=O)OC
-CCOC=C(C(=O)OCC)C(=O)OCC
-CCOC(=O)C1=NN(c2ccc(Cl)cc2Cl)C(C)(C(=O)OCC)C1
-CCCCCCCOC(=O)c1ccccc1C(=O)OCCCCCCC
-O=C=NCc1cccc(CN=C=O)c1
-Cc1cc(=O)[nH]c(=O)[nH]1
-O=c1cccc[nH]1
-Cn1sccc1=O
-Cn1c(=O)[nH]c2ncn(C)c2c1=O
-O=C1Cc2ccccc2C1
-Oc1ccc(O)[nH]1
-CC(C)(C)c1n[nH]c(=O)n(N)c1=O
-O=C1OCc2ccccc21
-O=C1C=CC(=O)c2ccccc21
-CCCCNc1ccc(NCCCC)c2c1C(=O)c1ccccc1C2=O
-Nc1c(Oc2ccccc2)cc(O)c2c1C(=O)c1ccccc1C2=O
-O=C1C=CC(=O)N1c1cccc(N2C(=O)C=CC2=O)c1
-O=C1c2ccccc2C(=O)c2c(Cl)cccc21
-C[C@]12CC[C@@H](O)C[C@@H]1CC[C@@H]1[C@@H]2CC[C@]2(C)C(=O)CC[C@@H]12
-O=C1OC(=O)c2ccc3c4c(ccc1c24)C(=O)OC3=O
-CC(=O)C=O
-O=CC1CC1
-CCN(CC)c1ccc(C=O)c(O)c1
-Cc1cc(C)c(C(=O)P(=O)(c2ccccc2)c2ccccc2)c(C)c1
-COP(=O)(CCC(=O)NCO)OC
-CC1=CP(=O)(c2ccccc2)CC1
-CCOP(=S)(OCC)SCCS(=O)(=O)CC
-CCS(=O)(=O)c1cccnc1S(=O)(=O)NC(=O)Nc1nc(OC)cc(OC)n1
-CCc1cccc(C)c1N(C(=O)CS(=O)(=O)O)C(C)COC
-CCOCN(C(=O)CS(=O)(=O)O)c1c(C)cccc1CC
-CN(CCCC(O)c1cccnc1)N=O
-OC(Cc1ccccc1Cl)(Cn1cncn1)C1(Cl)CC1
-Cc1ccc(C2OC[C@@H]3OC(c4ccc(C)cc4)O[C@H]([C@H](O)CO)[C@@H]3O2)cc1
-O=c1[nH]cccc1O
-CCCCCCCCSCc1cc(C)c(O)c(CSCCCCCCCC)c1
-Oc1cccc(-c2ccccc2)c1
-Oc1cc2ccccc2cc1O
-C=Cc1ccc(O)c(OC)c1
-CCCCCc1ccc(O)cc1
-Cc1c(Cl)c(=O)oc2cc(O)ccc12
-Oc1ccc2c(c1)CCC2
-COc1cccc(O)c1
-Oc1ccccc1Br
-O=S(=O)(c1ccc(OCc2ccccc2)cc1)c1ccccc1O
-O=c1cc[nH]cc1
-Cc1ccc(O)cn1
-CC(=O)Nc1ccc(N=Nc2cc(C)ccc2O)cc1
-CC(C)(c1ccc(O)c(-c2ccccc2)c1)c1ccc(O)c(-c2ccccc2)c1
-Oc1ccc(C2(c3ccc(O)c(C4CCCCC4)c3)CCCCC2)cc1C1CCCCC1
-Oc1cccc2c(O)cccc12
-OCCC(O)CO
-OCCCc1cccnc1
-OCCCS
-OCCN1CN(CCO)CN(CCO)C1
-Cn1[nH]nnc1=S
-OC(Cc1ccccc1Cl)(Cn1[nH]cnc1=S)C1(Cl)CC1
-SCc1ccco1

src/train_model.py

@@ -0,0 +1,18 @@
+import subprocess
+from datetime import datetime
+
+def train_model(data_path: str, config_path: str, save_model_path: str):
+    timestamp = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
+    command = [
+        "chemprop", "train",
+        "--data-path", data_path,
+        "--config-path", config_path,
+        "--splits-column", "split",
+        "--logfile", save_model_path + f"/train_{timestamp}.log",
+        "--task-type", "classification",
+        "--target-columns", "NR-AhR","NR-AR","NR-AR-LBD","NR-Aromatase","NR-ER","NR-ER-LBD","NR-PPAR-gamma","SR-ARE","SR-ATAD5","SR-HSE","SR-MMP","SR-p53",
+        "--save-dir", save_model_path
+    ]
+
+    # Run the command
+    subprocess.run(command, check=True)

train.py

@@ -0,0 +1,22 @@
+import os
+from dotenv import load_dotenv
+
+from src.data import clean_smiles_in_csv, get_combined_dataset_csv
+from src.train_model import train_model
+
+
+data_path = "./data/combined_clean.csv"
+config_path = "./config/config.toml"
+save_model_path = "./logs"
+
+# load and clean data
+print("Loading Datasets...")
+load_dotenv()
+token = os.getenv("TOKEN")
+target_cols = ["NR-AhR","NR-AR","NR-AR-LBD","NR-Aromatase","NR-ER","NR-ER-LBD","NR-PPAR-gamma","SR-ARE","SR-ATAD5","SR-HSE","SR-MMP","SR-p53"]
+get_combined_dataset_csv(token, save_path="./data/combined_not_clean.csv")
+clean_smiles_in_csv("./data/combined_not_clean.csv", data_path, "smiles", target_cols)
+
+# train model
+print("Starting Training...")
+train_model(data_path, config_path, save_model_path)