Our result page is divided into 4 individual sections:
Query Summary
Result Summary
Results
Text Files
The query summary provides these 4 information about your request. These include total number of sequences, number of invalid sequences, server assigned job ID, and ensemble approach.
The total number of sequences displays the user number of sequences entered by them into the server.
Based on the earlier informed restrictions some sequences cannot be interpreted by our application and these sequences are ignored.
The job ID is created by the server uniquely for each submitted request for store and trace your results.
The ensemble approach tells the user of the approach selected by the user , there are two options available to the user by the server :
Ensemble by consensus (without confidence score)
Ensemble by average (with confidence score)
To provide broad overview of our analysis, result summary provides you the following informations number of vaccine candidate predicted and number of non-vaccine candidates predicted.
This section contains a single table consisting following information:
Sequence ID which was extracted from your given FASTA input.
Predicted class is assigned to each sequence ID based on our analysis done by our Deep learning model on that protein sequence.
Probability (%) is assigned to each sequence ID based on our analysis done by our Deep learning model on that protein sequence. It is shows that how much percentage that our Deep learning model is certain that it belongs to that classification.
Example, XP_123456 is classified as a vaccine candidate with Probability (%) 88.44%, it means that our model is saying that XP_123456 is a vaccine candidate with 0.8844 probability and 0.1156 probability for non-vaccine candidate. We display the classification with maximum probability.
(See how we obtain this https://sites.google.com/view/vaxidl/3-results/probability-optimization) [Optional - only available when ensemble by average is selected]
This section contains the 3 downloadable text files. These includes:
Query Summary CSV File : Contains the combined data of Query Summary and Result Summary in CSV format.
Prediction CSV File : Contains the data of Result section in CSV format.
Sequences Excluded File : Contains the sequence IDs of ignored sequences that doesn't meet the criteria.