Models can be saved to and uploaded from excel sheets. The model upload = is only supported for linear (MLRA) models.
Sample file for the linear model upload
In order to upload a model, one needs to make sure first that have the c= ompounds and their respective properties used to develop the model are stor= ed in the database. If you have not done so already, use the "Database= ->Batch upload" feature to upload the compound and property data. C= licking on the batch upload title will lead you to the help on how to use i= t.
It is strongly suggested that you verify the uploaded data against the d= atabase. One can use the 'Select similar compounds" feature to check f= or duplicates, deviant measurements and typing errors.
In order to upload a model, although it is not strictly necessary, i sug= gest that one creates a linear model by the modeling capabilities of the da= tabase. To do so, follow the Models->Create a model help. Having success= fully create such a model, use the 'export to xls' function (Models->App= ly a model->Export to XLS) to create an excel sheet with containing the = model data.
In this file, there will be a sheet named "Linear regression data&q= uot;, which will also be searched for and used for model upload. If there i= s no such sheet the first sheet will be used. The first column will hold th= e descriptor names and be titled 'DESCRIPTORS', the second column holds the= respective linear regression coefficients. The reserved descriptor name 'B= IAS' is used for the model bias.
If you want to upload your model coefficients, preferably just replace t= hem in this excel file. It is, of course, also possible to create a similar= excel file 'from scratch'.
After the data is filled in, proceed to (Models->Upload your mo=
del). Select the training and validation set which will be used to display =
model statistics only, then select all the descriptor types that you have u=
sed. The descriptors will be recalculated for your compounds to ensure comp=
atibility with the other compounds in the database and therefore applicabil=
ity of your model to compounds other than used during model development. No=
te that using 3D/Structure optimization parameters will require you to wait=
for the structural optimization and its verification of the molecules used=
for modeling which is usually a matter of days, not minutes.
You will be asked to verify the model parameters read from the excel she= et. After that, you can verify your model statistics and save your model.