abstract={PyHMMER provides Python integration of the popular profile Hidden Markov Model software HMMER via Cython bindings. This allows annotation of protein sequences with profile HMMs and building new ones directly with Python. PyHMMER increases flexibility of use, allowing creating queries directly from Python code, launching searches and obtaining results without I/O, or accessing previously unavailable statistics like uncorrected p-values. A new parallelization model greatly improves performance when running multithreaded searches, while producing the exact same results as HMMER.PyHMMER supports all modern Python versions (Python 3.6+) and similar platforms as HMMER (x86 or PowerPC UNIX systems). Pre-compiled packages are released via PyPI (https://pypi.org/project/pyhmmer/) and Bioconda (https://anaconda.org/bioconda/pyhmmer). The PyHMMER source code is available under the terms of the open-source MIT licence and hosted on GitHub (https://github.com/althonos/pyhmmer); its documentation is available on ReadTheDocs (https://pyhmmer.readthedocs.io).Supplementary data are available at Bioinformatics online.},
urldate={2023-04-30},
journal={Bioinformatics},
author={Larralde, Martin and Zeller, Georg},
month=apr,
year={2023},
pages={btad214},
}
@software{sean_r_eddy_hmmer_nodate,
title={{HMMER}: biosequence analysis using profile hidden {Markov} models},
url={http://hmmer.org/},
abstract={HMMER is used for searching sequence databases for sequence homologs, and for making sequence alignments. It implements methods using probabilistic models called profile hidden Markov models (profile HMMs).
HMMER is often used together with a profile database, such as Pfam or many of the databases that participate in Interpro. But HMMER can also work with query sequences, not just profiles, just like BLAST. For example, you can search a protein query sequence against a database with phmmer, or do an iterative search with jackhmmer.
HMMER is designed to detect remote homologs as sensitively as possible, relying on the strength of its underlying probability models. In the past, this strength came at significant computational expense, but as of the new HMMER3 project, HMMER is now essentially as fast as BLAST.
HMMER can be downloaded and installed as a command line tool on your own hardware, and now it is also more widely accessible to the scientific community via new search servers at the European Bioinformatics Institute.},
urldate={2022-11-28},
author={{Sean R. Eddy} and {Travis Wheeler} and {Nick Carter}},
abstract={Profile hidden Markov models (profile HMMs) and probabilistic inference methods have made important contributions to the theory of sequence database homology search. However, practical use of profile HMM methods has been hindered by the computational expense of existing software implementations. Here I describe an acceleration heuristic for profile HMMs, the “multiple segment Viterbi” (MSV) algorithm. The MSV algorithm computes an optimal sum of multiple ungapped local alignment segments using a striped vector-parallel approach previously described for fast Smith/Waterman alignment. MSV scores follow the same statistical distribution as gapped optimal local alignment scores, allowing rapid evaluation of significance of an MSV score and thus facilitating its use as a heuristic filter. I also describe a 20-fold acceleration of the standard profile HMM Forward/Backward algorithms using a method I call “sparse rescaling”. These methods are assembled in a pipeline in which high-scoring MSV hits are passed on for reanalysis with the full HMM Forward/Backward algorithm. This accelerated pipeline is implemented in the freely available HMMER3 software package. Performance benchmarks show that the use of the heuristic MSV filter sacrifices negligible sensitivity compared to unaccelerated profile HMM searches. HMMER3 is substantially more sensitive and 100- to 1000-fold faster than HMMER2. HMMER3 is now about as fast as BLAST for protein searches.},
