Please paste up to 20000 FASTA-formatted sequences in the textarea below:

Select mode: MSA-version (1 sequence)   Single-sequence version (up to 20000 sequences)

Select algorithm to use: HMM (original version)   HMM + dipeptides   HNN

Prior information (constrained prediction):

Enter your email address to get notification of results:

Note: If you wish to perform a batch submission of more than 20000 sequences, please contact pbagoscompgen.org directly.

---

- If you find HMM-TM useful in your research, please consider citing the reference that describes this work:
Algorithms for incorporating prior topological information in HMMs: application to transmembrane proteins
PMID: 16597327

- If you used HMM-TM with the dipepetide mode, please also cite the reference that describes this work:
Extending hidden Markov models to allow conditioning on previous observations
PMID: 30353782

- If you used HMM-TM + HNN, please also cite the reference that describes this work:
Hidden Neural Networks for biological sequence analysis
PMID: 34849210

- HMM-TM can be run locally, using the JUCHMME Java package:
JUCHMME: a Java Utility for Class Hidden Markov Models and Extensions for biological sequence analysis.
PMID: 31250907

---