Pretrained Models

BBB

• BBB-score: The Blood–Brain Barrier (BBB) Score
  

  

CYP450

• D-CyPre: Tool for Accurately Predicting the Site of Metabolism of Human Cytochrome P450 Metabolism
  

  

• GTransCYPs: graph transformer neural network with attention pooling for reliably predicting CYP450 inhibitors
  

  

General

• ADMET_XGBoost: ADMETboost: a web server for accurate ADMET prediction
  

  

• ADMETlab: systematical evaluation of ADMET properties, as well as some physicochemical properties and medicinal chemistry friendliness
  

  

• ADMETlab3.0: systematical evaluation of ADMET properties, as well as some physicochemical properties and medicinal chemistry friendliness

  

• ChemMORT: ChemMORT: an automatic ADMET optimization platform using deep learning and multi-objective particle swarm optimization
  

  

• Computation-ADME:
  

  

• Datagrok Admetica: Datagrok pretrained ADME models
  

• OCHEM:

  

• OPERA:
  

• QIP: Machine learning model that predict the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties of molecules.
  

  

• SwissADME: web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness

  

  

• VEGA:

• admet-ai: ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries
  

  

• vNN-ADMET:

  

Metabolites

• MetaPredictor: in silico prediction of drug metabolites based on deep language models
  

  

PK

• Deep-PK: deep learning for small molecule pharmacokinetic and toxicity prediction

• PKSmart: This work used molecular structural fingerprints, physicochemical properties, and predicted animal PK data as features to model the human PK parameters VDss, CL, t½, fu and MRT for 1,283 unique compounds and developed a webhosted application PKSmart, the first work that publicly releases PK models on par with industry-standard models.
  

  

• pkCSM:

  

Toxicity

• ProTox3: Webserver for toxicity prediction

  

  

Toxicity

• Cyto-Safe: Webserver for toxicity prediction
  

  

  

hERG

• CLOP-hERG: Contrastive Learning Optimized Pretrained Model for Representation Learning in Predicting Drug-Induced hERG Channel Blockers
  

  

• CardioTox: A robust predictor for hERG channel blockade via deep learning meta ensembling approaches
  

  

• hERGdb: web-based cardiotoxicity prediction

  

  

logP

• OWPCP: OWPCP: A Deep Learning Model to Predict Octanol-Water Partition Coefficient
  

  

• rescoss_logp_ml: A repository dedicated to logP prediction using machine learning, offering insights into the solubility and distribution properties of compounds.