http://abacus.gene.ucl.ac.uk/software/paml4.9j.tgz

http://dambe.bio.uottawa.ca/DAMBE/dambe_install_win.aspx

import re

with open('seven.fas', 'r') as fin:

    sequences = [(m.group(), ''.join(m.group().split()))

                 for m in re.finditer(r'(?m)^>([^ \n]+)[^\n]*([^>]*)', fin.read())]

with open('seven.phy', 'w') as fout:

    fout.write('%d %d\n' % (len(sequences), len(sequences[][])))

    for item in sequences:

        fout.write('%-20s %s\n' % item)

import re

with open(r'seven.phy', 'r') as f:

    content = f.read()

    content = content.replace("TAG","---")

    content = content.replace("TAA", "---")

    content = content.replace("TGA", "---")

    # print(content)

with open('sevenend.phy', 'w') as f:

    f.write(content)

      seqfile = seven.nuc * sequence data filename

     treefile = Newick      * tree structure file name

      outfile = test.txt           * main result file name

        noisy =   * ,,,,: how much rubbish on the screen

      verbose =   * : concise; : detailed, : too much

      runmode = -  * : user tree;  : semi-automatic;  : automatic

                   * : StepwiseAddition; (,):PerturbationNNI; -: pairwise

      seqtype =   * :codons; :AAs; :codons-->AAs

    CodonFreq =   * :/ each, :F1X4, :F3X4, :codon table

*        ndata =

        clock =   * :no clock, :clock; :local clock; :CombinedAnalysis

       aaDist =   * :equal, +:geometric; -:linear, -:G1974,Miyata,c,p,v,a

   aaRatefile = dat/jones.dat  * only used for aa seqs with model=empirical(_F)

                   * dayhoff.dat, jones.dat, wag.dat, mtmam.dat, or your own

        model =

                   * models for codons:

                       * :one, :b, : or more dN/dS ratios for branches

                   * models for AAs or codon-translated AAs:

                       * :poisson, :proportional, :Empirical, :Empirical+F

                       * :FromCodon, :AAClasses, :REVaa_0, :REVaa(nr=)

      NSsites =   * :one w;:neutral;:selection; :discrete;:freqs;

                   * :gamma;:2gamma;:beta;:beta&w;:betaγ

                   * :beta&gamma+; :beta&normal>; :&2normal>;

                   * :3normal>

        icode =   * :universal code; :mammalian mt; -:see below

        Mgene =

                   * codon: :rates, :separate; :diff pi, :diff kapa, :all diff

                   * AA: :rates, :separate

    fix_kappa =   * : kappa fixed, : kappa to be estimated

        kappa =   * initial or fixed kappa

    fix_omega =   * : omega or omega_1 fixed, : estimate

        omega = . * initial or fixed omega, for codons or codon-based AAs

    fix_alpha =   * : estimate gamma shape parameter; : fix it at alpha

        alpha = . * initial or fixed alpha, :infinity (constant rate)

       Malpha =   * different alphas for genes

        ncatG =   * # of categories in dG of NSsites models

        getSE =   * : don't want them, 1: want S.E.s of estimates

 RateAncestor =   * (,,): rates (alpha>) or ancestral states ( or )

   Small_Diff = .5e-

    cleandata =   * remove sites with ambiguity data (:yes, :no)?

*  fix_blength =   * : ignore, -: random, : initial, : fixed, : proportional

       method =   * Optimization method : simultaneous; : one branch a time

* Genetic codes: :universal, :mammalian mt., :yeast mt., :mold mt.,

* : invertebrate mt., : ciliate nuclear, : echinoderm mt.,

* : euplotid mt., : alternative yeast nu. : ascidian mt.,

* : blepharisma nu.

* These codes correspond to transl_table  to  of GENEBANK.

codeml

67 columns are converted into ??? because of stop codons

Error: Error in sequence data file: . in 1st seq.?.

Error: check #seqs and tree: perhaps too many '('?.

Make sure to separate the sequence from its name by 2 or more spaces.