Skip to content
Python wrapper for MaxEntScan to calculate splice site strength.
Python Perl MATLAB
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.


Build Status Coverage Status install with bioconda download

maxentpy is a python wrapper for MaxEntScan to calculate splice site strength.

It contains two functions. score5 is adapt from MaxEntScan::score5ss to score 5' splice sites. score3 is adapt from MaxEntScan::score3ss to score 3' splice sites. They only use Maximum Entropy Model to score.


  • Cython
  • msgpack-python


>>> from maxentpy import maxent  # use normal version of maxent
>>> maxent.score5('cagGTAAGT')  # 3 bases in exon and 6 bases in intron
>>> maxent.score3('ttccaaacgaacttttgtAGgga')  # 20 bases in the intron and 3 base in the exon
>>> from maxentpy.maxent import load_matrix5, load_matrix3  # preloading matrix will speed up
>>> timeit maxent.score5('cagGTAAGT')
10 loops, best of 3: 23.5 ms per loop
>>> matrix5 = load_matrix5()
>>> timeit maxent.score5('cagGTAAGT', matrix=matrix5)
100000 loops, best of 3: 3.27 µs per loop
>>> timeit maxent.score3('ttccaaacgaacttttgtAGgga')
1 loop, best of 3: 259 ms per loop
>>> matrix3 = load_matrix3()
>>> timeit maxent.score3('ttccaaacgaacttttgtAGgga', matrix=matrix3)
10000 loops, best of 3: 103 µs per loop
>>> from maxentpy import maxent_fast  # fast version could further speed up
>>> timeit maxent_fast.score5('cagGTAAGT')
100 loops, best of 3: 5.04 ms per loop
>>> timeit maxent_fast.score3('ttccaaacgaacttttgtAGgga')
100 loops, best of 3: 9.3 ms per loop
>>> from maxentpy.maxent_fast import load_matrix  # support preloading matrix
>>> matrix5 = load_matrix(5)
>>> timeit maxent_fast.score5('cagGTAAGT', matrix=matrix5)
100000 loops, best of 3: 3.61 µs per loop
>>> matrix3 = load_matrix(3)
>>> timeit maxent_fast.score3('ttccaaacgaacttttgtAGgga', matrix=matrix3)
100000 loops, best of 3: 7.76 µs per loop



score5 maxentpy.maxent maxentpy.maxent_fast
without matrix 23.5 ms 5.04 ms
with matrix 3.27 µs 3.61 µs


score3 maxentpy.maxent maxentpy.maxent_fast
without matrix 259 ms 9.3 ms
with matrix 103 µs 7.76 µs


Yeo G, Burge CB. Maximum entropy modeling of short sequence motifs with applications to RNA splicing signals. Journal of Computational Biology. 2004, 11:377-94.


The original algorithm and perl scripts are under license described in The python version of maxent is under the MIT License.

You can’t perform that action at this time.