Welcome to BioKlustering!

BioKlustering is a web app for learning and visualization of genomic data. You can choose from a variety of supervised, unsupervised and semi-supervised machine-learning methods to cluster genomic sequences.

There is no programming requirement! Our models will return predicted labels from unaligned/aligned sequences. For example, the input data can be a collection of bacterial sequences. A label of 1 can indicate that a specific strain is resistant to antibiotics and a label of 0 that it is susceptible. In general, our web app allows for missing labels (coded as -1), and for more than two classes.

Learn more


Required. 150 characters or fewer. Letters, digits and @/./+/-/_ only.
  • Your password can’t be too similar to your other personal information.
  • Your password must contain at least 8 characters.
  • Your password can’t be a commonly used password.
  • Your password can’t be entirely numeric.
Enter the same password as before, for verification.
Already have an account? Login here.