Click the + button on the input table below to create new lines.
For each line, fill in the required information (the compound's name and/or PubChem cid number) about the compounds you want predictions for.
If only the name is inputted, the program does a search for this name and automatically fills the cid if it finds a hit. It is more precise to manually input the cid number, to make sure the desired compound is being used.
Clicking the Make Predictions button will load a result table with the number of valid targets (those with annotations in our source data) and the prediction results for male and female mice.
If any entry has only compound names and no info for targets when clicking Make Predictions, the system will atempt to 'Autofill' the targets for those entries.
The output is the probability for the compound's association with mouse longevity. All values above 50% are positive classifications, with values closer to 100% indicating a stronger association.
Note that the male and female prediction models are different, as discussed in the 'additional details' section of our Help page. In summary, male-mice prediction models have higher predictive accuracy.
Prepare a text file (.txt or .tsv) where each line corresponds to an entry for a compound. Click the Load from File button and select the input file.
Each line should have 2 tab-separated values: The compound's name (tab) The compound's PubChem id number.
Any element of the line can be left blank, as long as the tab separations are present.
If only the name is inputted, the program does a search for this name and automatically fills the cid if it finds a hit. It is more precise to manually input the cid number, to make sure the desired compound is being used.
Clicking the Make Predictions button will load a result table with the number of valid targets (those with annotations in our source data) and the prediction results for male and female mice.
The output is the probability for the compound's association with mouse longevity. All values above 50% are positive classifications, with values closer to 100% indicating a stronger association.