SYNPRED

Welcome to SYNPRED: Prediction of Drug Combinatory Effects in Cancer using Full-Agreement Synergy Metrics and Deep Learning. This webserver allows the user to input two drugs, in the form of two distinct SMILE files and attain the prediction of their synergistic effects on specific cancer cell lines. Please cite A.J. Preto et al. 2021.

Submit

Input your drugs in the upload boxes, in the form of a SMILE file, then click submit. You will be directly sent to your results page, which might take some time to finish. Please, also fill your email address and an appropriate name for the run. An email will be sent to you with the results link. All fields are mandatory for the prediction to be run.


Select the primary body site of the tested cell lines.




Input SMILE for the first drug: Input SMILE for the second drug:




Example File

The submitted files must be SMILE files, thus, they need to have the ".smiles" termination. An example of the content of a SMILE file can be downloaded below.

Database

Due to the high volume of the plots, these are only loaded upon click on the respective button, please feel free to explore our results and hover over the plots to discover additional information.


Methods Summary

High-throughput screening technologies used in the development of omics data continue to produce large amounts of data from different populations and cell types for a variety of diseases. Analysis of such data produced promising results in genomic biomedicine but encounters difficulties due to the heterogeneity of a large percentage of diseases, which is further exacerbated by human biological complexity and genomic variability. Now is the time to redefine the approach to drug discovery, bringing an Artificial Intelligence (AI)-powered informational view that integrates the relevant scientific fields and explores new territories.

Here, we implemented, SynPred, which leverages state-of-the-art AI advances, specifically designed ensembles of ML and DL algorithms to link in an interdisciplinary approach omics and biophysical traits to predict anticancer drug synergy. The final prediction model, when evaluating an independent test set achieved state-of-the-art metrics: accuracy – 0.85, precision – 0.77, recall – 0.75, AUC – 0.82, and F1-score - 0.76. Moreover, data interpretability was achieved by deploying the most current and robust feature importance approaches allowing us to highlight the most relevant omics features and pinpoint specific gene profiles.

Stand-alone deployment

To access our stand-alone version, you can access our SynPred GitHub repository. To use this version of SynPred, it will be required the download and unpacking of our models, which is available in the button bellow. Please follow the instructions for environment setup and model development as indicated in the GitHub page as it is the proper way to get SynPred running on the stand-alone version.

Contact Us