Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Code Block
languagejavascript

{
  "status"       "taskId": "success0",

		// Array of predictions (for each input molecule)
        "predictions" : [ {
    "depictionID" : 1000618459,      "moleculeID" : 7868"1002136505",
            
            // Array of predictions for a given molecule. Normally, contains only one prediction. 
            // Can contain multiple predictions for multi-models
            "predictions" : [ {
                "unit": "-log(mmol/L)",
                // Name of the predicted class for classification models. Same as "value" : 1.2020000219345093for regression models.                
                "predictedValueString": "2.7139999866485596", 
     "accuracy" : 0.5011452764639881,
      "dm" : 0.28780001401901245,
                 "value": "2.7139999866485596", // Prediction value (round it as you find necessary)
                "dm": "0.8611000180244446", // The "distance to model" used for the accuracy estimation
				"insideAD" : true, // is this molecule inside the "unit" : "Log unitmodel's applicability domain?
 				"property": "log(IGC50-1)", // The predicted property
  "property"               "accuracy": "BCF0.7065203028344436", // The prediction accuracy (RMSE)
                "realValue" : "0.0"
            }],
      "predictedValueString"       "depictionID": "1.20200002193450931000651576"
    } ]   } ],
  "modelDescriptionUrl"       "metaserverTaskId": "http://ochem.eu/model/231203920",
  "taskId" : 0      "status": "success",
  "metaserverTaskId" : 0
      "modelDescriptionUrl": "http://ochem.eu/model/3"
}

 

Way 2: Using task IDs

Since a prediction is not instantaneous and can take several seconds to minutes, the prediction is performed asynchronously, that is in two steps:

...