This paragraph will display the corresponding help that you request. Aiming fetch that information, hover the mouse cursor over the left square that you want to obtain help.

All help paragraphs contained in this page describe general information about how each path works. So, if you need further information about input fields, file format or examples, please navigate to your desired process path and read the specifications there.

The training path read the provided sequences and their assigned genotype to build a classification criteria. The training information can be downloaded locally to use on the next step as many times as desired.

Training needs the following inputs to be run:

1. Strain type (A, B or personalized)
2. Alignment file in fasta format
3. Classification file of alignment in CSV format, and its separator
4. Maximum frequency to filter

You can run the process or check the input specifications of the training here.

The classification path suggest the most probable genotype for each input sequence using the training criteria.
Training files are required, it is not neccesary the training file was made using this tool, as long as the format is the same.
Moreover, you don't need to save a copy of the training file on your local machine, you can run the classifier using the given job id instead.

Classifier needs the following inputs to be run

1. Training file in CSV format separated by ';', or job id if you haven't downloaded it.
2. Alignment file in fasta format. The same file provided in the previous step.
3. New sequences in fasta format. The sequences to classify.

You can run the process or check the input speficiation of the classifier here.

The all process path performs sequentially the training and the classification to obtain the final results. It performs the same steps described previuosly in the training and classification paths from scratch.
If you only need to run one of the two processes, please check the help section related to your needings. You can run the full pipeline or check the input specifications here, or the same but with the training process here and with the classification here.

The all path needs the same inputs that the training and the classifier

1. Strain type (A, B or personalized)
2. Alignment file in fasta format
3. Classification file of alignment in CSV format, and its separator
4. New sequences in fasta format. The sequences to classify.
5. Maximum frequency to filter.

The following flowchart describes how the pipeline works.

Biotechvana - 2025

This work is distributed under the terms of our license.

Full license text is available here, please check it before run any job.

Results path syntax:

/results/( classifier | training )/<JOBID>[?format=raw]

• Pathname: You must specify on the pathname if you want classifier or training results, the path will respond 404 otherwise.
  
• Jobid: You must specify the desired jobid, the path will respond 404 if the jobid is not provided or not found.
  
• Format: The path can display the results graphically as HTML or you can view and/or download them adding ?format=raw as a URL search param. This optional parameter aims to display the file as is.
  You will also be able to download the file by clicking the download button on the navigator.

If you doubt about how to reach your results, here you can specify the parameters, click Go! and the page will refresh automatically with your results: