• Components
• Overview  
  • Server overview
• Modeling process
  • Prepare drugs and targets
  • Prepare the datastes
  • Model training and validation
• Model Performance
  • Performance VS fingerprint type
  • Performance VS target number
• All Targets
  • Models using different types of fingerprints
  • The targets

---

---

---

Preparation of the library drugs and targets

---

We used BindingDB database as our training datasets. BindingDB is a public, web-accessible database of measured binding affinities, focusing chiefly on the interactions of proteins considered to be candidate drug-targets with ligands that are small, drug-like molecules. Activity data were filtered to keep only activity end-point points that had half-maximum inhibitory concentration (IC50), half-maximum effective concentration (EC50) or Ki values. Herein, to ensure that enough number of molecules could be used in model building, we previously selected those targets with larger than 200 biological activity data. Following this procedure, 109061 compounds associated with 623 target proteins remained with 115257 activity end-points, which were used for model building.

---

Preparation of the positive and negative set

---

For those compounds with more than one activity values, we took the mean value of their activity values as the final activity value. A compound was considered active when the mean activity value was below 10 uM. All compounds higher than 10 uM are considered inactive. Following this split, maybe some human proteins have very little number of negative samples. To balance the number between positive samples and negative samples for each human protein, we randomly selected certain number of compounds from other human proteins to generate the negative samples for these human proteins. The number of these selected negative samples together with inactive samples should be basically equal to the number of the active samples for these human proteins. These prepared positive set and negative set were used as the subsequent model building.

---

Model training and validation

---

A series of high confidence QSAR models were built using BindingDB. Naïve Bayes models were built with different fingerprint representations for 623 proteins. The Naïve Bayes method for predicting DTI profiling was chosen as it provided both good performance for noisy data sets and a high speed of calculation. Herein, to obtain the best model performance, we compared 7 types of molecular fingerprints when establishing the prediction models, including FP2, MACCS, Estate, FP4, Daylight, ECFP2-2048, ECFP4-2048, and ECFP6-2048. To obtain the better prediction ability, we also ensemble all fingerprint models to obtain the average output. For each model, we applied five-fold cross validation and external validation to evaluate the prediction performance of models. For 5-fold cross validation, the data set is split into 5 roughly equal-sized parts firstly, and then we fit the model to four parts of the data and calculate the error rate of the other part. The process is repeated 5 times so that every part can be predicted as a validation set. To observe the stability of models, we repeated the cross validation program 10 times to report standard deviations of each statistics. For the external validation, the data were split in two parts for the validation step: compounds were clustered and assigned a cluster number. Clusters with an odd number were assigned to the test set, and the clusters with an even number were assigned to the training set. Models were built with the training set, and the test set was scored. Finally, a model was built with all data and scored against itself – the training set and whole set should provide similar validation statistics. Statistics on the performance of the models were reported, including commonly used ones in classification schemes: accuracy, sensitivity, specificity, AUC, Matthews correlation coefficient (MCC) and F-score values. The cut-off providing the best MCC value was adopted, as they are shown to provide better performance. ROC provides an overall score and does not need to specify a cut-off for distinguishing active from inactive compounds. The area under the receiver operating characteristic (ROC) curve provides an indication of the ability of the model to prioritize active compounds over inactive compounds. The ROC curve is the plot of the true positive versus the false positive rate.

---

---

Performance VS fingerprint type

---

Performance VS target number

click the links below to view all corresponding targets

---

Models using different types of fingerprints

---

The 623 targets