Online inference
Documentation to run Ersilia models online
Last updated
Was this helpful?
Documentation to run Ersilia models online
Last updated
Was this helpful?
To ensure users from all backgrounds are able to benefit from our tools, we provide a ready-to-use, no-code solution to obtain predictions for your molecules.
We offer a broad range of models, from bioactivity prediction against several pathogens (malaria, tuberculosis, schistosomiasis, ESKAPE pathogens...) to ADME endpoints and toxicity predictions. Use our to browse models according to your needs and take note of the model identifier you wish to use!
Please ensure you understand the output of each model before using it. For example, a classifier will output the probability of being active in a particular assay, e.g. probability that a molecule kills the malaria parasite in an in vitro assay, and a regressor might output the predicted IC50 value at which the molecule inhibits the growth of the parasite.
The molecules must be displayed in SMILES notation. You can use to find the SMILES notation of a given compound: simply introduce the compound name on the search bar (for example, aspirin), select the best result and scroll to the SMILES section within "Name and Identifiers" (in this case; CC(=O)OC1=CC=CC=C1C(=O)O). If your starting input data is an .sdf
file, use your preferred visualiser, like ChemDraw, to open the molecule and obtain its SMILES representation. To deal with multiple molecular file formats, including SDF, you can use to convert them into SMILES notation. Alternatively, you can also use free software like to draw a molecule and then simply click on save 💾 it as a SMILES.
Collect your list of SMILES in a .csv
or .txt
file.
Go to our and select your model of choice from the drop down list. Copy the list of SMILES (maximum allowed 100 molecules) and click on "Run Predictions!". Wait a few minutes to download your results!
By default, Ersilia will provide a downloadable .csv
file summarizing the results, containing the following columns:
SMILES: the input SMILES (please note that these might have been standardised if they were not provided in the standard format).
InChIKey: 27-character unique identifier of the molecule based on the International Chemical Identifier (InChI).
Model output: one or several columns containing the predictions of the selected model. Make sure to read about the model in the literature or in the Ersilia documentation to appropriately interpret the model's results.
Posting to this free online service will make your molecules public. Please consider if you are working with IP-protected molecules.