MrBayes on XSEDE 3.2.7a Tree Inference Using Bayesian Analysis - run on XSEDE John P. Huelsenbeck and Fred Ronquist Huelsenbeck, J. P. and F. Ronquist. 2001. MRBAYES: Bayesian inference of phylogeny. Bioinformatics 17:754-755. Ronquist, F. and J. P. Huelsenbeck. 2003. MRBAYES 3: Bayesian phylogenetic inference under mixed models. Bioinformatics 19:1572-1574. . Ronquist, F., Teslenko, M., van der Mark, P., Ayres, D.L., Darling, A., Höhna, S., Larget, B., Liu, L., Suchard, M.A., and Huelsenbeck, J.P. 2012 MrBayes 3.2: Efficient Bayesian Phylogenetic Inference and Model Choice Across a Large Model Space Syst Biol 61 (3): 539-542 doi:10.1093/sysbio/sys029 Phylogeny / Alignment mrbayes_xsede_expanse mbmpi_326 perl $run_version eq "6" perl "" 0 mbmpi_327 perl $run_version eq "7" perl "" 0 mpi_processes_conf1 3 scheduler.conf perl $mrbayesblockquery && $run_version eq "6" && !$more_memory perl "jobtype=mpi\\n" . "cpus-per-task=1\\n" . "threads_per_process=1\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/128))) . "G\\n" . "node_exclusive=0\\n" . "mpi_processes=" . $nchains_specified * $nruns_specified . "\\n" mpi_processes_conf1b 3 scheduler.conf perl $mrbayesblockquery && $run_version eq "6" && $more_memory perl "jobtype=mpi\\n" . "cpus-per-task=1\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/32))) . "G\\n" . "threads_per_process=4\\n" . "node_exclusive=0\\n" . "mpi_processes=" . $nchains_specified * $nruns_specified . "\\n" mpi_processes_conf2 3 scheduler.conf perl $mrbayesblockquery && $run_version eq "7" && $set_beagle_params && !$more_memory perl "jobtype=mpi\\n" . "cpus-per-task=2\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/128))) . "G\\n" . "node_exclusive=0\\n" . "threads_per_process=2\\n" . "mpi_processes=" . $nchains_specified * $nruns_specified * 0.5 . "\\n" mpi_processes_conf2b 3 scheduler.conf perl $mrbayesblockquery && $run_version eq "7" && $set_beagle_params && $more_memory perl "jobtype=mpi\\n" . "cpus-per-task=4\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/32))) . "G\\n" . "node_exclusive=0\\n" . "threads_per_process=4\\n" . "mpi_processes=" . $nchains_specified * $nruns_specified . "\\n" mpi_processes_conf2c 3 scheduler.conf perl $mrbayesblockquery && $run_version eq "7" && !$set_beagle_params && !$more_memory perl "jobtype=mpi\\n" . "cpus-per-task=1\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/128))) . "G\\n" . "node_exclusive=0\\n" . "threads_per_process=1\\n" . "mpi_processes=" . $nchains_specified * $nruns_specified . "\\n" mpi_processes_conf2d 3 scheduler.conf perl $mrbayesblockquery && $run_version eq "7" && !$set_beagle_params && $more_memory perl "jobtype=mpi\\n" . "cpus-per-task=1\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/32))) . "G\\n" . "node_exclusive=0\\n" . "threads_per_process=4\\n" . "mpi_processes=" . $nchains_specified * $nruns_specified . "\\n" mpi_processes_conf3 3 scheduler.conf perl !$mrbayesblockquery && $run_version eq "6" && !$more_memory perl "jobtype=mpi\\n" . "cpus-per-task=1\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/128))) . "G\\n" . "node_exclusive=0\\n" . "threads_per_process=1\\n" . "mpi_processes=" . $nchainsval * $nrunsval . "\\n" mpi_processes_conf3b 3 scheduler.conf perl !$mrbayesblockquery && $run_version eq "6" && $more_memory perl "jobtype=mpi\\n" . "cpus-per-task=1\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/32))) . "G\\n" . "threads_per_process=4\\n" . "node_exclusive=0\\n" . "mpi_processes=" . $nchainsval * $nrunsval . "\\n" mpi_processes_conf4 3 scheduler.conf perl !$mrbayesblockquery && $run_version eq "7" && $set_beagle_params && !$more_memory perl "jobtype=mpi\\n" . "cpus-per-task=2\\n" . "threads_per_process=2\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/128))) . "G\\n" . "node_exclusive=0\\n" . "mpi_processes=" . $nchainsval * $nrunsval . "\\n" mpi_processes_conf4b 3 scheduler.conf perl !$mrbayesblockquery && $run_version eq "7" && $set_beagle_params && $more_memory perl "jobtype=mpi\\n" . "cpus-per-task=4\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/32))) . "G\\n" . "threads_per_process=4\\n" . "node_exclusive=0\\n" . "mpi_processes=" . $nchainsval * $nrunsval . "\\n" mpi_processes_conf4c 3 scheduler.conf perl !$mrbayesblockquery && $run_version eq "7" && !$set_beagle_params && !$more_memory perl "jobtype=mpi\\n" . "cpus-per-task=1\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/128))) . "G\\n" . "node_exclusive=0\\n" . "threads_per_process=1\\n" . "mpi_processes=" . $nchains_specified * $nruns_specified . "\\n" mpi_processes_conf4d 3 scheduler.conf perl !$mrbayesblockquery && $run_version eq "7" && !$set_beagle_params && $more_memory perl "jobtype=mpi\\n" . "cpus-per-task=1\\n" . "mem=" . (int($nchains_specified * $nruns_specified*(248/32))) . "G\\n" . "threads_per_process=4\\n" . "node_exclusive=0\\n" . "mpi_processes=" . $nchainsval * $nrunsval . "\\n" infile Input File (must be in Nexus format) (-execute) paramfile.txt perl "execute infile.nex\\n" 2 infile.nex setopts paramfile.txt perl "set autoclose=yes\\n" 1 setwarnopts paramfile.txt perl "set nowarnings=yes\\n" 1 mrbayes_closeout perl "quit\\n" paramfile.txt 99 ALL_FILES * run_version Choose the MB version you wish to run 6 7 7 mrbayesblockquery 1 My Data Contains a MrBayes Data Block (CHECK THIS OR MrBayes BLOCK ENTRIES WILL BE OVERWRITTEN!!!) perl ($value)? "":"" 0 Jobs that do not have a MrBayes block cannot be restarted. We encourage you to use a MrBayes block if possible. perl !$mrbayesblockquery This interface allows you to configure MrBayes from the command line, or from a MrBayes block in your data file. However, you must choose one or the other. So, if you have a MrBayes Block in your data, you should configure the entire run in that block (see the MrBayes manual for help on how to do this). It is our belief that MrBayes is sufficiently complex in its command structure and use that if you want to analyse multiple partitions and multiple datatypes you should do it in the Nexus file structure. The current interface supports multiple data partitions ONLY in the Nexus file. If you need more options than we provide, please let us know: http://www.ngbw.org/ngbugz. Other options are not included in this interface because they (and any complex MrBayes runs) are much better handled in the MrBayes block of your data file, are more useful for interactive running, or are not appropriate for batch runs. These include: Ctype, Link, Unlink, Delete, Include, Restore, Props, Plot, and Comparetree, the prset option Aarevmatpropts is not supported; the lset Ploidy option does not seem to be working in MrBayes 3.1.2. Any parameters requiring printing to the screen are not supported for obvious reasons. Importantly, unlike the command line version, it is not possible to upload a MrBayes block file that calls a separate data file with your matrix. nruns_specified 1 My MrBayes Block specifies nruns= scheduler.conf perl $mrbayesblockquery 2 The values entered for nruns and nchains influence the number of cpu's that can be used in parallel. Please enter the value you specified for nruns in the MrBayes block of the Nexus file. If you didn't specify a value for nruns, please leave this field at its default value of 2. Please enter a value for nruns perl !$nruns_specified The value of nruns must be greater than 0 perl $nruns_specified < 1 nchains_specified 1 My MrBayes Block specifies nchains= scheduler.conf perl $mrbayesblockquery 4 The value entered for nruns and nchains influences the number of cpu's that can be used in parallel. Enter the value you specified for nchains in the MrBayes block of the nexus file. If you didn't specify a value for nchains, please leave this field at its default value of 4. Please enter value for nchains perl !$nchains_specified The value of nchains must be greater than 0 perl $nchains_specified < 1 The value for nchains must be 1 or greater. The recommended value is at least 4. perl $nchains_specified < 1 nruns x nchains must be less than or equal to 16. perl ($nruns_specified * $nchains_specified > 16) nruns x nchains must be a multiple of 2 perl ((($nruns_specified * $nchains_specified) % 2) != 0) Version 3.2.7 is the development version, with an important bug fixed. perl $run_version eq "71" The job will run on 2 processors as configured. If it runs for the entire configured time, it will consume 2 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 2 && !$more_memory The job will run on 4 processors as configured. If it runs for the entire configured time, it will consume 4 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 4 && !$more_memory The job will run on 6 processors as configured. If it runs for the entire configured time, it will consume 6 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 6 && !$more_memory The job will run on 8 processors as configured. If it runs for the entire configured time, it will consume 8 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 8 && !$more_memory The job will run on 10 processors as configured. If it runs for the entire configured time, it will consume 10 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 10 && !$more_memory The job will run on 12 processors as configured. If it runs for the entire configured time, it will consume 12 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 12 && !$more_memory The job will run on 14 processors as configured. If it runs for the entire configured time, it will consume 14 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 14 && !$more_memory The job will run on 16 processors as configured. If it runs for the entire configured time, it will consume 16 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 16 && !$more_memory The job will run on 8 processors as configured. If it runs for the entire configured time, it will consume 8 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 2 && $more_memory The job will run on 16 processors as configured. If it runs for the entire configured time, it will consume 16 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 4 && $more_memory The job will run on 24 processors as configured. If it runs for the entire configured time, it will consume 24 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 6 && $more_memory The job will run on 32 processors as configured. If it runs for the entire configured time, it will consume 32 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 8 && $more_memory The job will run on 40 processors as configured. If it runs for the entire configured time, it will consume 40 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 10 && !$more_memory The job will run on 48 processors as configured. If it runs for the entire configured time, it will consume 48 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 12 && $more_memory The job will run on 52 processors as configured. If it runs for the entire configured time, it will consume 52 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 14 && $more_memory The job will run on 64 processors as configured. If it runs for the entire configured time, it will consume 64 x $runtime cpu hours perl $mrbayesblockquery && $nchains_specified * $nruns_specified == 16 && $more_memory The job will run on 2 processors as configured. If it runs for the entire configured time, it will consume 2 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 2 && !$more_memory The job will run on 4 processors as configured. If it runs for the entire configured time, it will consume 4 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 4 && !$more_memory The job will run on 6 processors as configured. If it runs for the entire configured time, it will consume 6 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 6 && !$more_memory The job will run on 8 processors as configured. If it runs for the entire configured time, it will consume 8 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 8 && !$more_memory The job will run on 10 processors as configured. If it runs for the entire configured time, it will consume 10 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 10 && !$more_memory The job will run on 12 processors as configured. If it runs for the entire configured time, it will consume 12 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 12 && !$more_memory The job will run on 14 processors as configured. If it runs for the entire configured time, it will consume 14 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 14 && !$more_memory The job will run on 16 processors as configured. If it runs for the entire configured time, it will consume 16 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 16 && !$more_memory The job will run on 8 processors as configured. If it runs for the entire configured time, it will consume 8 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 2 && $more_memory The job will run on 16 processors as configured. If it runs for the entire configured time, it will consume 16 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 4 && $more_memory The job will run on 24 processors as configured. If it runs for the entire configured time, it will consume 24 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 6 && $more_memory The job will run on 32 processors as configured. If it runs for the entire configured time, it will consume 32 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 8 && $more_memory The job will run on 40 processors as configured. If it runs for the entire configured time, it will consume 40 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 10 && !$more_memory The job will run on 48 processors as configured. If it runs for the entire configured time, it will consume 48 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 12 && $more_memory The job will run on 52 processors as configured. If it runs for the entire configured time, it will consume 52 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 14 && $more_memory The job will run on 64 processors as configured. If it runs for the entire configured time, it will consume 64 x $runtime cpu hours perl !$mrbayesblockquery && $nrunsval * $nchainsval == 16 && $more_memory runtime 1 scheduler.conf Maximum Hours to Run (click here for help setting this correctly) 168 The maximum hours to run must be less than 168 perl $runtime > 168.0 Please enter a positive number for the maximum runtime perl $runtime < 0 Please specify a maximum runtime perl !defined $runtime perl "runhours=$value\\n" Estimate the maximum time your job will need to run. We recommend testing initially with a < 0.5hr test run because Jobs set for 0.5 h or less depedendably run immediately in the "debug" queue. Once you are sure the configuration is correct, you then increase the time. The reason is that jobs > 0.5 h are submitted to the "normal" queue, where jobs configured for 1 or a few hours times may run sooner than jobs configured for the full 168 hours. zipfilename 1 scheduler.conf perl "zipfilename=$value\\n" flagdatatype My Data Type Is (only one data type can be used through the web form, see help below) perl !$mrbayesblockquery dna dna protein standard other Setting this flag helps us eliminate uneeded options seed Set the Seed Number (set seed=) paramfile.txt perl !$mrbayesblockquery perl (defined $value) ? "set seed=$value\\n":"" 1 Sets the seed number for the random number generator. The random number seed is initialized haphazardly at the beginning of each MrBayes session. This option allows you to set the seed to some specific value, thereby allowing you to exactly repeat an analysis. If the analysis uses swapping between cold and heated chains, you must also set the swap seed (see below) to exactly repeat the analysis. swapseed Set the Swapseed (set swapseed=) paramfile.txt perl !$mrbayesblockquery perl (defined $value) ? "set swapseed=$value\\n":"" 1 Sets the seed used for generating the swapping sequence when Metropolis-coupled heated chains are used. By default, this seed is generated at the beginning of each MrBayes session. This option allows you to set the seed to some specific value, thereby allowing you to exactly repeat a swap sequence. more_memory I need more memory paramfile.txt 0 1 Write output in scientific notation (higher precision). Otherwise, use fixed format (easier for humans to read). scientific Use scientific notation paramfile.txt perl !$mrbayesblockquery 0 perl (defined $value) ? "set scientific=Yes\\n":"set scientific=No\\n" 1 Write output in scientific notation (higher precision). Otherwise, use fixed format (easier for humans to read). precision How many decimals should we print? paramfile.txt perl !$mrbayesblockquery 15 perl (defined $value) ? "set precision = $value\\n":"" 1 Please set the precsion to a number between 3 and 15. 15 is the default. perl $value < 3 Please set the precsion to a number between 3 and 15. 15 is the default. perl $value > 15 Set the number of decimals to print your results in. Values of 3-15 are permitted. set_beagle_params Run BEAGLE paramfile.txt 1 Disabling BEAGLE will slow your run by as much as 20%. You should only do this if a run with BEAGLE fails, or if you believe using BEAGLE gave you unexpected results. perl !$set_beagle_params We have seen examples where MrBayes runs on BEAGLE can produce anomalous topologies. If you see an odd topology, please try the run without BEAGLE perl $set_beagle_params Beagle should speed up runs by about 10-20%. You should only disable this parameter if you have a problem using Beagle. set_beagle_params6 paramfile.txt perl $set_beagle_params && $run_version == "6" perl "set usebeagle=yes beagleprecision=double beaglesse=yes beaglescaling=dynamic beaglethreads=no\\n" set_beagle_params7a paramfile.txt perl $set_beagle_params && $run_version == "7" && !$more_memory perl "set usebeagle=yes beagleprecision=double beaglesse=yes beaglescaling=dynamic beaglethreads=2\\n" set_beagle_params7b paramfile.txt perl $set_beagle_params && $run_version == "7" && $more_memory perl "set usebeagle=yes beagleprecision=double beaglesse=yes beaglescaling=dynamic beaglethreads=4\\n" set_nobeagle7 paramfile.txt perl !$set_beagle_params && $run_version eq "7" perl "set usebeagle=no\\n" set_outgroup Specify (only) one outgroup paramfile.txt perl !$mrbayesblockquery perl (defined $value) ? "outgroup $value\\n":"" 3 With this command, "outgroup 3" assigns the third taxon in the matrix to be the outgroup. Similarly, "outgroup Homo_sapiens" assings the taxon "Homo_sapiens" to be the outgroup (assuming that there is a taxon named "Homo_sapiens" in the matrix). Only a single taxon can be assigned to be the outgroup. lsetopts Likelihood Model Parameters nstopts Set the number of substitution types (Nst=) perl !$mrbayesblockquery paramfile.txt perl "lset Nst= $value\\n" 1 1 2 6 mixed 5 Sets the number of substitution types: "1" constrains all of the rates to be the same (e.g., a JC69 or F81 model); "2" allows transitions and transversions to have potentially different rates (e.g., a K80 or HKY85 model); "6" allows all rates to be different, subject to the constraint of time-reversibility (e.g., a GTR model). nucmodelopts Set the nucleotide substitution model (Nucmodel=) paramfile.txt perl !$mrbayesblockquery perl "lset Nucmodel= $value\\n" 4by4 4by4 doublet codon protein 5 This parameter specifies the general form of the nucleotide substitution model. The options are "4by4" [the standard model of DNA substitution in which there are only four states (A,C,G,T/U)], "doublet" (a model appropriate for modelling the stem regions of ribosomal genes where the state space is the 16 doublets of nucleotides), and "codon" (the substitution model is expanded around triplets of nucleotides--a codon). codonopts Set the Codon translation table (Codon=) paramfile.txt perl "lset Code= $value\\n" perl $nucmodelopts eq "codon" && !$mrbayesblockquery universal universal vertmt mycoplasma ciliates metmt yeast 5 omegavaropts Allow the nonsynonymous/synonymous rate ratio (omega) (Omegavar=) paramfile.txt perl !$mrbayesblockquery && $nucmodelopts eq "codon" perl "lset omegavar= $value\\n" equal equal Ny98 M3 5 Allows the nonsynonymous/synonymous rate ratio (omega) to vary across codons. Ny98 assumes that there are three classes, with potentially different omega values (omega1, omega2, omega3): omega2 = 1; omega1 is less than 1 but greater than 0; and omega3 is greater than 1. Like the Ny98 model, the M3 model has three omega classes. However, their values are less constrained, with omega1 less than omega2, which is less than omega3. The default (omegavar = equal) has no variation on omega across sites. ploidyopts Set the ploidy (Ploidy=) perl "Ploidy= $value\\n" perl $brlenspropts eq "clock:coalescence" Diploid Diploid Haploid zlinked 5 This option is used when a coalescence prior is used on trees. rateopts Set the model for among-site rate variation (Rates=) paramfile.txt perl !$mrbayesblockquery perl "lset Rates= $value\\n" equal equal gamma adgamma propinv invgamma 5 In general, the rate at a site is considered to be an unknown random variable. Valid options are: equal:No rate variation across sites; gamma: The rate at a site is drawn from a gamma distribution. The gamma distribution has a single parameter that describes how much rates vary; adgamma: Autocorrelated rates across sites. The marginal rate distribution is gamma, but adjacent sites have correlated rates; propinv -- A proportion of the sites are invariable; invgamma -- A proportion of the sites are invariable while the rate for the remaining sites are drawn from a gamma distribution.Note that MrBayes versions 2.0 and earlier supported options that allowed site specific rates (e.g., ssgamma). In versions 3.0 and later, site specific rates are allowed, but set using the 'prset ratepr' command for each partition. Ngammacatopts Set number of rate categories for gamma distribution (Ngammacat=) paramfile.txt perl !$mrbayesblockquery && $rateopts eq "gamma" perl "lset Ngammacat= $value\\n" 4 5 The Ngammacat parameter sets the number of rate categories for the gamma distribution. The gamma distribution is continuous. However, it is virtually impossible to calculate likelihoods under the continuous gamma distribution. Hence, an approximation to the continuous gamma is used; the gamma distribution is broken into ncat categories of equal weight (1/ncat). The mean rate for each category represents the rate for the entire cateogry. This option allows you to specify how many rate categories to use when approximating the gamma. The approximation is better as ncat is increased. In practice, "ncat=4" does a reasonable job of approximating the continuous gamma. Nbetacatopts Set number of rate categories for beta distribution (Nbetacat=) paramfile.txt perl !$mrbayesblockquery perl "lset Nbetacat= $value\\n" 5 5 A symmetric beta distribution is used to model the stationary frequencies when morphological data are used. This option specifies how well the beta distribution will be approximated. Covarionopts Force the use of covarion-like model (4X4 dna model, or protein) (Covarion=) paramfile.txt perl !$mrbayesblockquery perl ($value)? "lset Covarion = Yes\\n":"" 0 5 This forces the use of a covarion-like model of substitution for nucleotide or amino acid data (it is not used for other data types).The valid options are "yes" and "no". The covarion model allows the rate at a site to change over its evolutionary history. Specifically, the site is either on or off. When it is off, no substitutions are possible. When the process is on, substitutions occur according to a specified substitution model (specified using the other lset options). codingopts Specify how characters were sampled (Coding=) paramfile.txt perl !$mrbayesblockquery perl "lset coding = $value\\n" all all variable noabsence nopresence 5 The Coding parameter specifies how characters were sampled. If all site patterns had the possibility of being sampled, then "all" should be specified (the default). Otherwise "variable" (only var iable characters had the possibility of being sampled), "noabsence" (characters for which all taxa were coded as absent were not sampled), and "nopresence" (characters for which all taxa were coded as present were not sampled. "All" works for all data types. However, the others only work for morphological (all/variable) or restriction site (all/variable/noabsence/nopresence) data. Parsmodelopts Force calculation under a Parsimony model (Parmodel=) paramfile.txt perl !$mrbayesblockquery 0 perl ($value)? "lset parsmodel = Yes\\n":"" 5 This forces calculation under the so-called parsimony model described by Tuffley and Steel (1998). The options are "yes" or "no". Note that the biological assumptions of this model are anything but parsimonious. In fact, this model assumes many more parameters than the next most complicated model implemented in this program. If you really believe that the parsimony model makes the biological assumptions described by Tuffley and Steel, then the parsimony method is miss-named. prsetparams Configure Priors tratioopts Transition/Transversion Rate Ratio; DNA only (Tratiopr=) paramfile.txt perl !$mrbayesblockquery && $flagdatatype eq "dna" beta beta fixed beta "prset Tratiopr = beta($betameanx, $betavary)\\n" fixed "preset Tratiopr = fixed($tratiofixed)\\n" 10 Tratiopr changes the prior probability of the transition/transversion ratio. It can be fixed (fixed), or set to a beta distribution with mean x and variance y (beta(x,y)).The program assumes that the transition and transversion rates are independent gamma-distributed random variables with the same scale parameter when beta is selected. If you want a diffuse prior that puts equal emphasis on transition/transversion rate ratios above 1.0 and below 1.0, then use a flat Beta, beta(1,1), which is the default. If you wish to concentrate this distribution more in the equal-rates region, then use a prior of the type beta(x,x), where the magnitude of x determines how much the prior is concentrated in the equal rates region. For instance, a beta(20,20) puts more probability on rate ratios close to 1.0 than a beta(1,1). If you think it is likely that the transition/transversion rate ratio is 2.0, you can use a prior of the type beta(2x,x), where x determines how strongly the prior is concentrated on tratio values near 2.0. For instance, a beta(2,1) is much more diffuse than a beta(80,40) but both have the expected tratio 2.0 in the absence of data. The parameters of the Beta can be interpreted as counts: if you have observed x transitions and y transversions, then a beta(x+1,y+1) is a good representation of this information. The fixed option allows you to fix the tratio to a particular value. betameanx Beta mean x perl !$mrbayesblockquery && $tratioopts eq "beta" perl "" 1.0 10 betavary Beta variance y perl "" perl !$mrbayesblockquery && $tratioopts eq "beta" 1.0 10 tratiofixed Fixed Transition/Transversion Ratio perl "" perl !$mrbayesblockquery && $tratioopts eq "fixed" 1.0 10 revmatpropts Substitution Rates of the GTR Model; Nucleic Data only (Revmatpr=) paramfile.txt perl !$mrbayesblockquery && $flagdatatype eq "dna" dirichlet dirichlet fixed dirichlet "prset revmatpr = dirichlet($atocrate,$atograte,$atotrate,$ctograte,$ctotrate,$gtotrate)\\n" fixed "prset revmatpr = fixed($fixedatocrate,$fixedatograte,$fixedatotrate,$fixedctograte,$fixedctotrate,$fixedgtotrat)\\n" 10 Revmatpr sets the prior for the substitution rates of the GTR model for nucleotide data. For Revmatpr=dirichlet, MrBayes assumes that the six substitution rates are independent gamma-distributed random variables with the same scale parameter. The six numbers in brackets each corresponds to a particular substitution type. Together, they determine the shape of the prior. The six rates are in the order A / C, A / G, A / T, C / G, C / T, and G / T. By default, dirichlet(1,1,1,1,1,1) is used, also referred to as a 'flat' Dirichlet. For a prior where the C / T rate is 5 times and the A / G rate 2 times higher, on average, than the transversion rates, which are all the same, then you should use a prior of the form dirichlet(x,2x,x,x,5x,x), where x determines how much the prior is focused on these particular rates. For more information, see Tratiopr. The fixed option allows you to fix the substitution rates to particular values. atocrate A/C rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "dirichlet" 1.0 10 atograte A/G rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "dirichlet" 1.0 10 atotrate A/T rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "dirichlet" 1.0 10 ctograte C/G rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "dirichlet" 1.0 10 ctotrate C/T rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "dirichlet" 1.0 10 gtotrate G/T Rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "dirichlet" 1.0 10 fixedatocrate A/C rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "fixed" 1.0 10 fixedatograte A/G rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "fixed" 1.0 10 fixedatotrate A/T rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "fixed" 1.0 10 fixedctograte C/G rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "fixed" 1.0 10 fixedctotrate C/T rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "fixed" 1.0 10 fixedgtotrate G/T Rate perl "" perl !$mrbayesblockquery && $revmatpropts eq "fixed" 1.0 10 aamodelpropts Set the Rate Matrix for Amino Acids (Aamodelpr=) paramfile.txt perl !$mrbayesblockquery perl ("$value" ne "$vdef")? "prset aamodelpr=$value\\n" : "" fixed(poisson) fixed(blosum) fixed(cprev) fixed(dayhoff) fixed(equalin) fixed(gtr) fixed(jones) mixed fixed(mtmam) fixed(mtrev) fixed(poisson) fixed(rtrev) fixed(vt) fixed(wag) fixed(lg) 10 Aamodelpr sets the rate matrix for amino acid data.You choose a single fixed model, or choose mixed to average over the ten models by specifying "mixed". In the latter case, the Markov chain will sample each model according to its probability. The sampled model is reported as an index: poisson(0), jones(1), dayhoff(2), mtrev(3), mtmam(4), wag(5), rtrev(6), cprev(7), vt(8), or blosum(9). The 'Sump' command summarizes the MCMC samples and calculates the posterior probability estimate for each of these models. omegapropts Nonsynonymous/Synonymous Rate Ratio (Omegapr=) paramfile.txt perl !$mrbayesblockquery && $omegavaropts eq "equal" && $nucmodelopts eq "codon" uniform uniform exponential fixed uniform "prset omegapr = uniform($omegaprdir1,$omegaprdir2)\\n" exponential "prset omegapr = exponential($omegaprexponential)\\n" fixed "prset omegapr = fixed($omegafixed)\\n" 10 This parameter specifies the prior on the nonsynonymous/synonymous rate ratio. The options are:uniform, exponential, and fixed. This parameter is used only when the nucleotide substitution model is set to codon, and there is no variation in omega across sites (i.e. omegavar=equal"). omegaprdir1 Uniform Omega Rate1 perl "" perl !$mrbayesblockquery && $omegapropts eq "uniform" 1.0 10 omegaprdir2 Uniform Omega Rate2 perl !$mrbayesblockquery && $omegapropts eq "uniform" perl "" 1.0 10 omegaprexponential Exponential Omega Rate perl !$mrbayesblockquery && $omegapropts eq "exponential" perl "" 1.0 10 omegafixed Fixed Omega Rate perl "" perl !$mrbayesblockquery && $omegapropts eq "fixed" 1.0 10 ny98omega1propts Nonsynonymous/Synonymous Rate Ratio for sites under purifying selection (Ny98omega1pr=) paramfile.txt perl !$mrbayesblockquery && $omegavaropts eq "Ny98" beta beta fixed beta "prset Ny98omega1pr = beta($ny98omega1prbeta1,$ny98omega1prbeta2)\\n" fixed "prset Ny98omega1pr = fixed($ny98omega1prfix1)\\n" 10 This parameter is only in effect if the nucleotide substitution model is set to "codon" and where omega varies across sites using the model of Nielsen and Yang (1998) (i.e., Ny98). If fixing the parameter, you must specify a number between 0 and 1. ny98omega1prbeta1 Ny98omega1 Beta Rate 1 perl "" perl !$mrbayesblockquery && $ny98omega1propts eq "beta" 1.0 10 ny98omega1prbeta2 Ny98omega1 Beta Rate 2 perl "" perl !$mrbayesblockquery && $ny98omega1propts eq "beta" 1.0 10 ny98omega1prfix1 Fixed Ny98Omega1 Rate perl !$mrbayesblockquery && $ny98omega1propts eq "fixed" perl "" 1.0 10 ny98omega3propts Nonsynonymous/Synonymous Rate Ratio for sites under positive selection (Ny98omega3pr=) paramfile.txt perl !$mrbayesblockquery && $omegavaropts eq "Ny98" perl "" exponential uniform exponential fixed uniform "prset Ny98omega3pr = uniform($ny98omega3pruni1,$ny98omega3pruni2)\\n" exponential "prset Ny98omega3pr = exponential($ny98omega3prexp1)\\n" fixed "prset ny98omega3pr = fixed($ny98omega3prfix1)\\n" 10 This parameter specifies the prior on the nonsynonymous/synonymous rate ratio for positively selected sites. The options are:uniform, exponential, and fixed. This parameter is only in effect if the nucleotide substitution model is set to codon and where omega varies across sites according to the NY98 model. ny98omega3pruni1 Ny98 Uniform Omega Rate 1 for Positive Selection perl "" The value entered must be greater than or equal to 1 perl $ny98omega3pruni1 < 1 perl !$mrbayesblockquery && $ny98omega3propts eq "uniform" 1.0 10 ny98omega3pruni2 Ny98 Uniform Omega Rate 2 for Positive Selection perl "" The value entered must be greater than or equal to 1 perl $ny98omega3pruni2 < 1 perl !$mrbayesblockquery && $ny98omega3propts eq "uniform" 1.0 10 ny98omega3prexp1 Ny98 Exponential Omega Rate for Positive Selection 10 perl !$mrbayesblockquery && $ny98omega3propts eq "exponential" 1.0 perl "" The value entered must be greater than or equal to 1 perl $ny98omega3prexp1 < 1 ny98omega3prfix1 Ny98 Fixed Omega Rate for Positive Selection perl "" perl !$mrbayesblockquery && $ny98omega3pr eq "fixed" 1.0 10 M3omega3propts Nonsynonymous/Synonymous Rate Ratio for sites under the M3 model (M3omega1pr=) paramfile.txt perl !$mrbayesblockquery && $omegavaropts eq "M3" perl "" exponential exponential fixed exponential "prset M3omega3pr = exponential \\n" fixed "prset M3omega3pr = fixed($M3omega3prfix1,$M3omega3prfix2,$M3omega3prfix3)\\n" 10 This parameter specifies the prior on the nonsynonymous/synonymous rate ratio for positively selected sites. The options are:uniform, exponential, and fixed. This parameter is only in effect if the nucleotide substitution model is set to codon and where omega varies across sites according to the NY98 model. M3omega3prfix1 M3 Fixed Omega Rate 1 for M3 Model perl "" perl !$mrbayesblockquery && $M3omega3pr eq "fixed" 1.0 10 M3omega3prfix2 M3 Fixed Omega Rate 2 for M3 Model perl "" perl !$mrbayesblockquery && $M3omega3pr eq "fixed" 1.0 10 M3omega3prfix3 M3 Fixed Omega Rate 3 for M3 Model perl "" perl !$mrbayesblockquery && $M3omega3pr eq "fixed" 1.0 10 codoncatfreqsopts Frequencies of sites under Purifying, Neutral, and Positive Selection (Codoncatfreqs=) paramfile.txt perl $omegavaropts eq "Ny98" || $omegavaropts eq "M3" perl "" dirichlet dirichlet fixed dirichlet "prset Codoncatfreqs = dirichlet($codoncatfreqsdir1,$codoncatfreqsdir2,$codoncatfreqsdir3)\\n" fixed "prset Codoncatfreqs = fixed($codoncatfreqsfix1,$codoncatfreqsfix2,$codoncatfreqsfix3)\\n" 10 Codoncatfreqs specifies the prior on frequencies of sites under purifying, neutral, and positive selection. The options are dirichlet and fixed. This parameter is relevant if the nucleotide substitution model is set to "codon" and where omega varies across sites using the models of Nielsen and Yang (1998), or Yang et al. (2000) i.e. Omegavar=Ny98 or M3. Note that the sum of the three frequencies must be 1. codoncatfreqsdir1 Codoncatfreqs Dirichlet Parameter 1 perl !$mrbayesblockquery && $codoncatfreqsopts eq "dirichlet" perl "" 1.0 10 codoncatfreqsdir2 Codoncatfreqs Dirichlet Parameter 2 perl !$mrbayesblockquery && $codoncatfreqsopts eq "dirichlet" perl "" 1.0 10 codoncatfreqsdir3 Codoncatfreqs Dirichlet Parameter 3 perl "" perl !$mrbayesblockquery && $codoncatfreqsopts eq "dirichlet" 1.0 10 codoncatfreqsfix1 Codoncatfreqs Fixed Parameter 1 perl !$mrbayesblockquery && $codoncatfreqsopts eq "fixed" 10 perl "" codoncatfreqsfix2 Codoncatfreqs Fixed Parameter 2 perl !$mrbayesblockquery && $codoncatfreqsopts eq "fixed" perl "" 10 codoncatfreqsfix3 Codoncatfreqs Fixed Parameter 3 perl !$mrbayesblockquery && $codoncatfreqsopts eq "fixed" 10 perl "" statewfreqpropts State Frequencies (Statefreqpr=); Assigning frequencies to each state is not supported perl !$mrbayesblockquery paramfile.txt dirichlet dirichlet fixed(equal) fixed(empirical) dirichlet "prset statefreqpr = dirichlet($statewfreqprdir1)\\n" fixed (equal) "prset statefreqpr = fixed(equal)\\n" fixed (empirical) "prset statefreqpr = fixed(empirical)\\n" 10 This parameter specifies the prior on the state frequencies. The options are dirichlet, fixed, with equal frequencies, and fixed with empirically determined frequencies. If you specify a single number, then the prior has all states equally probable with a variance related to the single parameter passed. statewfreqprdir1 Statefreqs Dirichlet Parameter (A single number) perl !$mrbayesblockquery && $statewfreqpropts eq "dirichlet" 1.0 10 shapepropts Gamma Shape Parameter (Shapepr=) perl !$mrbayesblockquery paramfile.txt uniform uniform exponential fixed dirichlet "prset shapepr = uniform($shapepruni1,$shapepruni2)\\n" exponential "prset shapepr = exponential($shapeprexp1)\\n" fixed "prset shapepr = fixed($shapeprfix1)\\n" 10 This parameter specifies the prior on the state frequencies. The options are dirichlet, fixed, with equal frequencies, and fixed with emirically determined frequencies. The dirichlet prior has all states equally probable with a variance related to the single parameter passed in. shapepruni1 Gamma Shape Uniform Parameter 1 perl "" perl !$mrbayesblockquery && $shapepropts eq "uniform" 0.0 10 shapeprdir2 Gamma Shape Dirichlet Parameter 2 perl "" perl !$mrbayesblockquery && $shapepropts eq "uniform" 50.0 10 shapeprexp1 Gamma Shape Exponential Parameter perl "" perl !$mrbayesblockquery && $shapepropts eq "exponential" 1.0 10 shapeprfix1 Gamma Shape Fixed Parameter perl "" perl !$mrbayesblockquery && $shapepropts eq "fixed" 1.0 10 pinvarpropts Proportion of Invariable Sites (Pinvarpr=) perl !$mrbayesblockquery paramfile.txt uniform uniform fixed uniform "prset pinvarpr = uniform($pinvarpruni1,$pinvarpruni2)\\n" fixed "prset pinvarpr = fixed($pinvarprfix1)\\n" 10 This parameter specifies the prior for the proportion of invariable sites. The options are uniform and fixed. The valid range for the parameters is between 0 and 1. pinvarpruni1 Invariable Sites, Uniform Parameter 1 perl !$mrbayesblockquery && $pinvarpropts eq "uniform" perl "" 0.0 10 pinvarpruni2 Invariable Sites, Uniform Parameter 2 perl !$mrbayesblockquery && $pinvarpropts eq "uniform" perl "" 1.0 10 pinvarprfix1 Invariable Sites, Fixed Parameter perl !$mrbayesblockquery && $pinvarpropts eq "fixed" perl "" 1.0 10 ratecorrpropts Autocorrelation Parameter for Gamma Distribution for Among SIte Variation (Ratecorrpr=) paramfile.txt perl !$mrbayesblockquery && $flagdatatype eq "dna" uniform uniform fixed uniform "prset ratecorrpr = uniform($ratecorrpruni1,$ratecorrpruni2)\\n" fixed "prset ratecorrpr = fixed($ratecorrprfix1)\\n" 10 This parameter specifies the prior for the autocorrelation parameter of the autocorrelated gamma distribution for among-site rate variation. The options are uniform and fixed The parameter for uniform is between -1 and 1. The default setting is uniform, (-1, 1). ratecorrpruni1 Autocorrelation Uniform Parameter 1 perl "" perl !$mrbayesblockquery && $ratecorrpropts eq "uniform" -1.0 10 ratecorrpruni2 Autocorrelation Uniform Parameter 2 perl "" perl !$mrbayesblockquery && $ratecorrpropts eq "uniform" 1.0 10 ratecorrprfix1 Autocorrelation Fixed Parameter perl !$mrbayesblockquery && $ratecorrpropts eq "fixed" perl "" 1.0 10 covswitchpropts Covrion Switching Rates (Covswitchpr=) perl !$mrbayesblockquery paramfile.txt uniform uniform exponential fixed uniform "prset covswitchpr = uniform($covswitchuni1,$covswitchuni2)\\n" exponential "prset covswitchpr = exponential($covswitchexp1)\\n" fixed "prset covswitchpr = fixed($covswitchfix1,covswitchfix2)\\n" 10 This option sets the prior for the covarion switching rates. The options are uniform, exponential, and fixed, The covarion model has two rates: a rate from on to off and a rate from off to on. The rates are assumed to have independent priors that individually are either uniformly or exponentially distributed. The other option is to fix the switching rates, in which case you must specify both rates. (The first number is off to on and the second is on to off; the first should always be less than the second). covswitchuni1 Covarion Model Off to On Rate (Uniform) perl !$mrbayesblockquery && $covswitchpropts eq "uniform" perl "" 0.0 10 covswitchuni2 Covarion Model On to Off Rate (Uniform) perl !$mrbayesblockquery && $covswitchpropts eq "uniform" perl "" 100.0 10 covswitchexp1 Covarion Model Exponential Parameter perl "" perl !$mrbayesblockquery && $covswitchpropts eq "exponential" 1.0 10 covswitchfix1 Covarion Model Off to On Rate (Fixed) perl "" perl !$mrbayesblockquery && $covswitchpropts eq "fixed" 1.0 10 covswitchfix2 Covarion Model On to Off Rate (Fixed) perl "" perl !$mrbayesblockquery && $covswitchpropts eq "fixed" 1.0 10 symdirihyperpropts Stationary frequencies for states in standard data sets (Symdirihyperpr=) perl !$mrbayesblockquery paramfile.txt fixed(infinity) uniform exponential fixed fixed(infinity) uniform "prset symdirihyperpr = uniform($symdiruni1,$symdiruni2)\\n" exponential "prset symdirihyperpr = exponential($symdirexp1)\\n" fixed "prset symdirihyperpr = fixed($symdirfix1)\\n" fixed (infinity) "prset symdirihyperpr = fixed(infinity)\\n" 10 Symdirihyperpr sets the prior for the stationary frequencies of the states for morphological (standard) data. There can be as many as 10 states for standard data. However, the labelling of the states is somewhat arbitrary. For example, the state "1" for different characters does not have the same meaning. This is not true for DNA characters, for example, where a "G" has the same meaning across characters. The fact that the labelling of morphological characters is arbitrary makes it difficult to allow unequal character state frequencies. MrBayes gets around this problem by assuming that the states have a dirichlet prior, with all states having equal frequency. The variation in the dirichlet can be controlled by this parameter--symdirihyperpr.Symdirihyperpr specifies the distribution on the variance parameter of the dirichlet. Valid options are uniform, exponential, fixed with an explicit rate value, and fixed(infinity). "Fixed(infinity)" fixes the dirichlet prior such that all character states have equal frequency. symdiruni1 Stationary Frequency Uniform Param 1 perl "" perl !$mrbayesblockquery && $symdirihyperpropts eq "uniform" 1.0 10 symdiruni2 Stationary Frequency Uniform Param 2 perl "" perl !$mrbayesblockquery && $symdirihyperpropts eq "uniform" 1.0 10 symdirexp1 Stationary Frequency Exponential Param 1 perl "" perl !$mrbayesblockquery && $symdirihyperpropts eq "exponential" 1.0 10 symdirfix1 Stationary Frequency Fixed Param 1 perl "" perl !$mrbayesblockquery && $symdirihyperpropts eq "fixed" 1.0 10 topologypropts Specify Topological Constraint Types (Topologypr=) paramfile.txt perl !$mrbayesblockquery && $noconstraints >= 1 uniform uniform speciestree constraints uniform "prset topologypr = uniform\\n" constraints "prset topologypr = constraints($constraintnames)\\n" 10 This parameter specifies the prior probabilities of phylogenies. The options are uniform constraints If the prior is selected to be "uniform" all possible trees are considered a priori equally probable. The constraints option allows you to specify complicated prior probabilities on trees (constraints are discussed more fully in "help constraint"). Note that you must specify a list of constraints that you wish to be obeyed. The list can be either the constraint's number or its name. Also, note that the constraints simply tell you how much more (or less) probable individual trees are that possess the constraint than trees not possessing the constraint. constraintnames1 Enter the names or numbers of the constraints to be used, separated by commas perl !$mrbayesblockquery && $topologypropts eq "constraints" perl "" 10 brlenspropts Probability distribution on branch lengths (Brlenspr=) perl !$mrbayesblockquery paramfile.txt unconstrained:exponential unconstrained:uniform unconstrained:exponential clock:uniform clock:birthdeath clock:coalescence unconstrained:uniform "prset brlenspr = unconstrained:uniform(0,$brlenspruni2)\\n" unconstrained:exponential "prset brlenspr = unconstrained:exponential($brlensprexp1)\\n" clock:uniform "prset brlenspr = clock:uniform\\n" clock:birthdeath "prset brlenspr = clock:birthdeath\\n" clock:coalescence "prset brlenspr = clock:coalescence\\n" 10 Brlenspr specifies the prior probability distribution on branch lengths. The options are unconstrained:uniform, unconstrained:exponential, clock:uniform, clock:birthdeath, clock:coalescence. Trees with unconstrained branch lengths are unrooted whereas clock-constrained trees are rooted. The option after the colon specifies the details of the probability density of branch lengths. If you choose a birth-death or coalescence prior, you may want to modify the details of the parameters of those processes. brlenspruni1 Unconstrained Uniform Param 1 is set at 0 perl !$mrbayesblockquery && $brlenspropts eq "uniform" brlenspruni2 Unconstrained Uniform Param 2 perl "" perl !$mrbayesblockquery && $brlenspropts eq "uniform" 1.0 10 brlensprexp1 Unconstrained Exponential Param perl "" perl !$mrbayesblockquery && $brlenspropts eq "unconstrained:exponential" 10.0 10 treeheightpropts Distribution on Tree Height (for Clock Models) (Treeagepr=) perl !$mrbayesblockquery && $brlenspropts eq "clock:uniform" paramfile.txt exponential gamma exponential fixed gamma "prset treeagepr = gamma($treeheightsprgamma1,$treeheightsprgamma2)\\n" exponential "prset treeagepr = exponential($treeheightsprexp1)\\n" fixed "prset treeagepr = fixed($treeheightsprfx1)\\n" 10 Treeagepr specifies the prior probability distribution on the tree height, when a clock model is specified. The options are gamma and exponential. (And, yes, we know the exponential is a special case of the gamma distribution.) The tree height is the expected number of substitutions on a single branch that extends from the root of the tree to the tips. This parameter does not come into play for the coalescence prior. It insures that the prior probability distribution for unconstrained and birth-death models is proper. treeheightsprgamma1 Gamma Param 1 perl "" perl !$mrbayesblockquery && $treeheightpropts eq "gamma" 1.0 10 treeheightsprgamma2 Unconstrained Uniform Param 2 perl !$mrbayesblockquery && $treeheightpropts eq "gamma" perl "" 1.0 10 treeheightsprexp1 Unconstrained Exponential Param perl !$mrbayesblockquery && $treeheightpropts eq "exponential" perl "" 1.0 10 treeheightsprfx1 Treeagepr Fixed Param perl !$mrbayesblockquery && $treeheightpropts eq "exponential" perl "" 1.0 10 ratepropts Site Specific Rates Models (Ratepr=) paramfile.txt perl !$mrbayesblockquery fixed fixed variable fixed "prset ratepr = fixed\\n" variable "prset ratepr = variable\\n" 10 Ratepr specifies the site specific rates model. First, you must have defined a partition of the characters. For example, you may define a partition that divides the characters by codon position, if you have DNA data. Second, you must make that partition the active one using the set command. For example, if your partition is called "by_codon", then you make that the active partition using "set partition=by_codon". Now that you have defined and activated a partition, you can specify the rate multipliers for the various partitions. The options are fixed, variable, and dirichlet. For "fixed" the rate multiplier for that partition is set to 1 (i.e., the rate is fixed to the average rate across partitions). On the other hand, for "variable", the rate is allowed to vary across partitions subject to the constraint that the average rate of substitution across the partitions is 1. You must specify a variable rate prior for at least twopartitions, otherwise the option is not activated when calculating likelihoods. The variable option automatically associates the partition rates with a dirichlet(1,...,1) prior. The dirichlet option is an alternative way of setting a partition rate to be variable, and also gives accurate control of the shape of the prior. The parameters of the Dirichlet are listed in the order of the partitions that the ratepr is applied to. For instance, "prset applyto=(1,3,4)ratepr = dirichlet(10,40,15)" would set the Dirichlet parameter 10 to partition 1, 40 to partition 3, and 15 to partition 4. speciationpropts Speciation Rate (for Birth:Death Clock Models) (Speciationpr=) paramfile.txt perl !$mrbayesblockquery && $brlenspropts eq "clock:birthdeath" uniform uniform exponential fixed uniform "prset speciationpr = uniform($speciationpruni1,$speciationpruni2)\\n" exponential "prset speciationpr = exponential($speciationprexp1)\\n" fixed "prset speciationpr = fixed($speciationprfix1)\\n" 10 Speciationpr sets the prior on the speciation rate. The options are uniform, exponential, and fixed. This parameter is only relevant if the birth-death process is selected as the prior on branch lengths. speciationpruni1 Speciationpr Uniform Param 1 perl "" perl !$mrbayesblockquery && $speciationpropts eq "uniform" 0.0 10 speciationpruni2 Speciationpr Uniform Param 2 perl !$mrbayesblockquery && $speciationpropts eq "uniform" perl "" 10.0 10 speciationprexp1 Speciationpr Exponential Param perl "" perl !$mrbayesblockquery && $speciationpropts eq "exponential" 1.0 10 speciationprfix1 Speciationpr Fixed Param perl "" perl !$mrbayesblockquery && $speciationpropts eq "fixed" 1.0 10 extinctionpropts Extinction Rate (for Birth:Death Clock Models) (Extinctionpr=) paramfile.txt perl !$mrbayesblockquery && $brlenspropts eq "clock:birthdeath" beta beta fixed beta "prset extinctionpr = beta($extinctionpruni1,$extinctionpruni2)\\n" fixed "prset extinctionpr = fixed($extinctionprfix1)\\n" 10 Extinctionpr sets the prior on the extinction rate. Valid options are uniform, exponential, and fixed.This parameter is only relevant if the birth-death process is selected as the prior on branch lengths. extinctionpruni1 Extinctionpr Beta Param 1 perl "" perl !$mrbayesblockquery && $extinctionpropts eq "beta" 1.0 10 extinctionpruni2 Extinctionpr Beta Param 2 perl !$mrbayesblockquery && $extinctionpropts eq "beta" perl "" 1.0 10 extinctionprfix1 Extinctionpr Fixed Param perl "" perl !$mrbayesblockquery && $extinctionpropts eq "fixed" 1.0 10 sampleprobopts Fraction of Species Samples in Birth Death Analysis (SampleprobExtinctionpr=) paramfile.txt perl !$mrbayesblockquery && $brlenspropts eq "clock:birthdeath" perl "prset sampleprob = $value\\n" 1.0 10 Sampleprob sets the fraction of species that are sampled in the analysis. This is used with the birth death prior on trees (see Yang and Rannala, 1997). thetapropts Prior on the coalescence parameter (nucleic acid data) (Thetapr=) paramfile.txt perl !$mrbayesblockquery && $brlenspropts eq "clock:coalescence" uniform uniform exponential fixed uniform "prset thetapr = uniform($thetapruni1,$thetapruni2)\\n" exponential "prset thetapr = exponential($thetaprexp1)\\n" fixed "prset thetapr = fixed($thetaprfix1)\\n" 10 Thetapr sets the prior on the coalescence parameter. This parameter is only relevant if the coalescence process is selected as the prior on branch lengths. thetapruni1 Thetapr Uniform Param 1 perl "" perl !$mrbayesblockquery && $extinctionpropts eq "uniform" 0.0 10 thetapruni2 Thetapr Uniform Param 2 perl !$mrbayesblockquery && $extinctionpropts eq "uniform" perl "" 10.0 10 thetaprexp1 Thetapr Exponential Param perl "" perl !$mrbayesblockquery && $thetapropts eq "exponential" 1.0 10 thetaprfix1 Thetapr Fixed Param perl "" perl !$mrbayesblockquery && $thetapropts eq "fixed" 1.0 10 datamodifications Data Specifications databreaksopts paramfile.txt Specify Breaks in Sequence Data (Protein and Nucleic Acid Data only) perl !$mrbayesblockquery perl "databreaks $value" 20 The Databreaks command is used to specify breaks in the input data matrix. Some of the models (e.g. autocorrelated gamma model) implemented by MrBayes account for nonindependence at adjacent characters. Databreaks option specifies that two sites that are adjacent in the matrix, are actually separated by many kilobases or megabases in the genome. For example, say you have a data matrix of 3204 characters that include nucleotide data from three genes that are physically unlinked. The first gene covers characters 1 to 970, the second gene covers characters 971 to 2567, and the third gene covers characters 2568 to 3204. Just enter the last number of the contiuous sequnce, in this case, 970 and 2567, separated by spaces. pairsopts Specify nucleotide pairs involved in Watson-Crick pairing (pairs nucmodel=doublet only) paramfile.txt perl !$mrbayesblockquery && $nucmodelopts eq "doublet" perl "pairs $value\\n" 20 The Pairs command is used to specify pairs of nucleotides. For example, RNA sequences with a known secondary structure of stems and loops. Substitutions in nucleotides involved in a Watson-Crick pairing in stems are not strictly independent; a change in one changes the probability of a change in the partner. A solution to this problem is to expand the model around the pair of nucleotides in the stem. Pairs allows you to do this. The correct usage is to enter the numbers of a base-pairforming nucleotide pair, separated by a semicolon: for example:30:56. To include multiplepairs, separate the enteredvalues by commas: 31:55, 32:54, 33:53, 34:52, 35:51, 36:50. This specifies pairings between nucleotides 30 and 56, 31 and 55, etc. Onlynucleotide data (DNA or RNA) may be paired using this command. Note that in order for the program to actually implement a "doublet" model involving a 16 X 16 rate matrix, you must specify that the structure of the model is 16 X 16 using "lset nucmodel=doublet". Charset Character Sets perl !$mrbayesblockquery nocharsets How many character sets would you like to define? See the note below. perl !$mrbayesblockquery paramfile.txt perl "" 0 1 2 3 4 5 6 7 8 0 30 You can specify up to 8 character sets here. You can experiment here, but if you get serious, you should really do this in the MrBayes Command block of a Nexus file. For more information see the help section below. charset1 Name for character set 1 paramfile.txt perl !$mrbayesblockquery && $nocharsets >= 1 perl "" 30 Charset defines a character set. You must specify the name of the charset you wish to create, and the first and last positions of that set. Both parameters are entered into the forms provided, for up to 8 charsets. The character set name is entered in the first box; it cannot have any spaces in it. The character range is entered second, you enter the first character position, and last characterer position, separated by a hyphen. You can use "." to indicate the last character. In addition, the forward slash (\) can be used to tell the program to assign every third (or second, or fifth, or whatever) character to the character set. For example, "charset first_pos = 1-720\3" defines a character set called "first_pos" that includes every third site from 1 to 720. charset1range Character set 1 range perl !$mrbayesblockquery && $nocharsets >= 1 paramfile.txt perl (defined $value )? " charset $charset1 = $value\\n": "" 30 charset2 Name for character set 2 paramfile.txt perl !$mrbayesblockquery && $nocharsets >= 2 perl "" 30 charset2range Character set 2 range perl !$mrbayesblockquery && $nocharsets >= 2 paramfile.txt perl (defined $value )? " charset $charset2 = $value\\n" : "" 30 charset3 Name for character set 3 paramfile.txt perl !$mrbayesblockquery && $nocharsets >= 3 perl "" 30 charset3range Character set 3 range perl !$mrbayesblockquery && $nocharsets >= 3 paramfile.txt perl (defined $value )? " charset $charset3 = $value\\n" : "" 30 charset4 Name for character set 4 paramfile.txt perl !$mrbayesblockquery && $nocharsets >= 4 perl "" 30 charset4range Character set 4 range perl !$mrbayesblockquery && $nocharsets >= 4 paramfile.txt perl (defined $value )? " charset $charset4 = $value\\n" : "" 30 charset5 Name for character set 5 perl !$mrbayesblockquery && $nocharsets >= 5 perl "" 30 charset5range Character set 5 range perl !$mrbayesblockquery && $nocharsets >= 5 paramfile.txt perl (defined $value )? " charset $charset5 = $value\\n" : "" 30 charset6 Name for character set 6 perl !$mrbayesblockquery && $nocharsets >= 6 perl "" 30 charset6range Character set 6 range perl !$mrbayesblockquery && $nocharsets >= 6 paramfile.txt perl (defined $value )? " charset $charset6 = $value\\n" : "" 30 charset7 Name for character set 7 perl !$mrbayesblockquery && $nocharsets >= 7 perl "" 30 charset7range Character set 7 range perl !$mrbayesblockquery && $nocharsets >= 7 paramfile.txt perl (defined $value )? " charset $charset7 = $value\\n" : "" 30 charset8 Name for character set 8 perl !$mrbayesblockquery && $nocharsets >= 8 perl "" 30 charset8range Character set 8 range perl !$mrbayesblockquery && $nocharsets >= 8 paramfile.txt perl (defined $value )? " charset $charset8 = $value\\n" : "" 30 excludeopts Exclude these characters from the analysis perl !$mrbayesblockquery paramfile.txt perl "exclude $value\\n" 30 Exclude removes specific character positions from the analysis. Enter one of the following into the form provided : a set of individual character position numbers separated by spaces (2, 3, 10, 11, 12, 13, 14, and 22); a range of numbers, by giving the starting and finishing position, separated by a hyphen ( 1-100 ). Note the backslash can be used to exclude every nth character (1-100\3), the name of a character set, or "all". A mixture is also allowed (2 3 10-14 22). mcmcparams Parameters for MCMC ngenval Number of Generations (Ngen=) perl !$mrbayesblockquery paramfile.txt perl "mcmc ngen=$value filename=infile.nex nruns=$nrunsval nchains=$nchainsval temp=$tempval swapfreq=$swapfreqval nswaps=$nswapsval samplefreq=$samplefreqval $mcmcdiagnval minpartfreq=$minpartfreqval $allchainsval $relburninval burnin=$burninval burninfrac=$burninfracval $stopruleval $startingtreeval stopval=$stopval $sbrlensval nperts=$npertsval $ordertaxaval\\n" 5000 The number of samples you requested is greater than 50,000; this may cause your .t output file to exceed the allowed limit of 500 GB. Please consider editing your input file to request a lower sample frequency. perl $ngenval > 50000 * $samplefreqval Please enter a value for ngen of at least 5000 generations perl $ngenval < 5000 50 Ngen sets the number of cycles for the MCMC algorithm. This should be a big number as you want the chain to first reach stasis, and then remain there for enough time to take lots of samples. nrunsval Number of Runs (nruns=) perl !$mrbayesblockquery paramfile.txt perl " " 2 50 Nruns sets the number of independent analyses started simultaneously. Only values of 2 and 4 are permitted. Please enter a value for nruns (default = 2) perl !$mrbayesblockquery && !defined $nrunsval Please enter a value greater than 0 for nruns (default = 2) perl !$mrbayesblockquery && $nrunsval < 1 nchainsval Number of Chains to Run (nchains=) perl !$mrbayesblockquery paramfile.txt perl "" 4 50 Nchains specifies how many chains are run for each analysis for the MCMCMC variant. The default is 4: 1 cold chain and 3 heated chains. If Nchains is set to 1, MrBayes will use regular MCMC sampling, without heating. The value of nchains must 1 or greater. The default (recommended) is 4. perl $nchainsval < 1 nruns x nchains must be a multiple of 2 perl ((($nrunsval * $nchainsval) % 2) != 0) nruns x nchains must be less than or equal to 24. perl ($nrunsval * $nchainsval > 24) Please enter a value for nchains= (default = 4) perl !defined $nchainsval tempval Temperature parameter (temp=) perl !$mrbayesblockquery paramfile.txt perl " " 0.200 50 Temp is the temperature parameter for heating the chains. The higher the temperature, the more likely the heated chains are tomove between isolated peaks in the posterior distribution. However, excessive heating may lead to very low acceptance rates for swaps between different chains. Before changing the default setting, however, note that the acceptance rates of swaps tend to fluctuate during the burn-in phase of the run. swapfreqval How often should swap of states be attempted perl !$mrbayesblockquery perl "" 1 Swapfreq specifies how often swaps of states between chains are attempted. You must be running at least two chains for this option to be relevant. The default is Swapfreq=1, resulting in Nswaps (see below) swaps being tried each generation of the run. If Swapfreq is set to 10, then Nswaps swaps will be tried every tenth generation of the run. nswapsval How many swaps should be tried per generation perl !$mrbayesblockquery perl "" 1 Nswaps sets the number of swaps tried for each swapping generation of the chain (see also Swapfreq). samplefreqval How often should the Markov chain be sampled? perl !$mrbayesblockquery paramfile.txt perl "" 1000 50 Samplefreq specifies how often the Markov chain is sampled. You can sample the chain every cycle, but this results in very large output files. Thinning the chain is a way of making these files smaller and making the samples more independent. mcmcdiagnval Write acceptance ratios of moves and swaps to file? perl !$mrbayesblockquery mcmcdiagn=Yes mcmcdiagn=Yes mcmcdiagn=No Mcmcdiagn determines whether acceptance ratios of moves and swaps will be printed to file. The file will be named similarly to the .p' and '.t' files, but will have the ending '.mcmc'. If more than one independent analysis is run simultaneously (see Nruns below), convergence diagnostics for tree topology will also be printed to this file. The convergence diagnostic used is the average standard deviation in partition frequency values across independent analyses. The Burnin setting (see below) determines how many samples will be discarded as burnin before calculating the partition frequencies. The Minpartfreq setting (see below) determines the minimum partition frequency required for a partition to be included in the calculation. As the independent analyses approach stationarity (converge), the value of the diagnostic is expected to approach zero. minpartfreqval Minimum frequency for a partition to be included (minpartfreq) perl !$mrbayesblockquery paramfile.txt perl "" 0.1 50 Minpartfreq sets the minimum frequency required for a partition to be included in the calculation of the topology convergence diagnostic. The partition is included if the minimum frequency is reached in at least one of the independent tree samples that are compared. allchainsval paramfile.txt Record acceptance ratios for all chains? perl !$mrbayesblockquery allchains=No allchains=Yes allchains=No Allchains: when set to YES, acceptance ratios for moves are recorded for all chains, cold or heated. By default, only the acceptance ratios for the cold chain are recorded. relburninval Discard a proportion of the sampled values as burnin when calculating the convergence diagnostic? perl !$mrbayesblockquery perl "" relburnin=Yes relburnin=Yes relburnin=No Relburnin: If set to YES, a proportion of the sampled values will be discarded as burnin when calculating the convergence diagnostic. The proportion to be discarded is set with Burninfrac. By default, the Relburnin option is set to NO, resulting in a specific number of samples being discarded instead. This number is set by Burnin (see below). burninfracval Specify the fraction of the sampled values discarded as burnin paramfile.txt perl !$mrbayesblockquery && $relburninval eq "relburnin=Yes" perl "" 0.25 BurninFrac specifies fraction of samples that will be discarded when convergence diagnostics are calculated. The value of this option is only relevant when Relburnin is set to YES. Example: A value for this option of 0.25 means that 25 percent of the samples will be discarded. burninval Specify the number of sampled values discarded as burnin paramfile.txt perl !$mrbayesblockquery && $relburninval eq "relburnin=No" perl "" 0 50 Burnin specifies the number of samples (not generations) that will be discarded when convergence diagnostics are calculated. The value of this option is only relevant when Relburnin is set to NO. stopruleval Stop early if the convergence diagnostic falls below the stop value? perl !$mrbayesblockquery && $mcmcdiagnval eq "mcmcdiagn=Yes" && $nrunsval > 1 stoprule=Yes stoprule=Yes stoprule=No Stoprule: if set to NO, then the chain is run the number of generations determined by Ngen. If it is set to YES, and topological convergence diagnostics are calculated (Mcmcdiagn is set to YES), then the chain will be stopped before the pre-determined number of generations if the convergence diagnostic falls below the stop value. stopval Please enter the stop value paramfile.txt perl !$mrbayesblockquery && $mcmcdiagnval eq "mcmcdiagn=Yes" && $nrunsval > 1 perl "" 0.01 Please enter a value for the stopvalue perl $stopruleval eq "stoprule=Yes" && !defined $stopval 50 Stopval: the critical value for the topological convergence diagnostic. Only used when Stoprule and Mcmcdiagn are set to yes, and more than one analysis is run simultaneously (Nruns greater than 1). startingtreeval perl !$mrbayesblockquery && $Usertreesel paramfile.txt perl "" starttree=random 50 Startingtree specifies whether the starting tree for the chain is randomly selected or user-defined. It might be a good idea to start from randomly chosen trees; convergence seems likely if independently run chains, each of which started from different random trees, converge to the same answer. npertsval Number of random perturbations to apply to user starting tree. perl !$mrbayesblockquery && $startingtreeval eq "startingtree=user" perl "" 0 Nperts is the number of random perturbations to apply to the user starting tree. This allows you to have something between completely random and user-defined trees start the chain. sbrlensval Save branch length information? perl !$mrbayesblockquery paramfile.txt Savebrlens=Yes Savebrlens=Yes Savebrlens=No 50 ordertaxaval Should taxa be ordered before trees are printed to file? perl !$mrbayesblockquery paramfile.txt Ordertaxa=Yes Ordertaxa=Yes Ordertaxa=No perl "" 50 Ordertaxa determines whether taxa should be ordered before trees are printed to file. If set to 'Yes', terminals in the sampled trees will be reordered to match the order of the taxa in thedata matrix as closely as possible. By default, trees will be printed without reordering of taxa. outputopts Output/Reporting Options sumtintro Report parameters Report allows you to control how the posterior distribution is reported. For rate parameters, it allows you to choose among several popular parameterizations. The report command also allows you to request printing of some model aspects that are usually not reported. For instance, if a node is constrained in the analysis, MrBayes can print the probabilities of the ancestral states at that node. Similarly, if there is rate variation in the model, MrBayes can print the inferred site rates, and if there is omega variation, MrBayes can print the inferred omega (positive selection) values foreach codon. In a complex model with several partitions, each partition is controlled separately using the same 'Applyto' mechanism as in the 'Lset' and 'Prset' commands. Options: Applyto allows you to apply the report commands to specific partitions. This command should be the first in the list of commands specified in 'report'. For example, report applyto=(1,2) tratio=ratio report applyto=(3) tratio=dirichlet would result in the transition and transversion rates of the first and second partitions in the model being reported as a ratio and the transition and transversion rates of the third partition being reported as proportions of the rate sum (the Dirichlet parameterization). Tratio -- This specifies the report format for the transition and transversion rates of a nucleotide substitution model with nst=2. If 'ratio' is selected, the rates will be reported as a ratio (transition rate/transversion rate). If 'dirichlet' is selected, the transition and transversion rates will instead be reported as proportions of the rate sum. For example, if the transition rate is three times the transversion rate and 'ratio' is selected, this will reported as a single value, '3.0'. If 'dirichlet' is selected instead, the same rates will be reported using two values, '0.75 0.25'. The sum of the Dirichlet values is always 1. Although the Dirichlet format may be unfamiliar to some users, it is more convenient for specifying priors than the ratio format. Revmat -- This specifies the report format for the substitution rates of a GTR substitution model for nucleotide or amino acid data. If 'ratio' is selected, the rates will be reported scaled to the G-T rate (for nucleotides) or the Y-V rate (for amino acids). If 'dirichlet' is specified instead, the rates are reported as proportions of the rate sum. For instance, assume that the C-T rate is twice the A-G rate and four times the transversion rates, which are equal. If the report format is set to 'ratio', this would be reported as '1.0 2.0 1.0 1.0 4.0 1.0' since the rates are reported in the order rAC, rAG, rAT, rCG, rCT, rGT and scaled relative to the last rate, the G-T rate. If 'dirichlet' is selected instead, the same rates would have been reported as '0.1 0.2 0.1 0.1 0.4 0.1' since the rates are now scaled so that they sumto 1.0. The Dirichlet format is the parameterization used for formulating priors on the rates. Ratemult -- This specifies the report format used for the rate multiplier of different model partitions. Three formats are available. If 'scaled' is selected, then rates are scaled such that the mean rate per site across partitions is 1.0. If 'ratio' is chosen, the rates are scaled relative to the rate of the first partition. Finally, if 'dirichlet' is chosen, the rates are given as proportions of the rate sum. The latter is the format used when formulating priors on the rate multiplier. Ancstates -- If this option is set to 'yes', MrBayes will print the probability of the ancestral states at all constrained nodes. Typically, you are interested in the ancestral states of only a few characters and only at one node in the tree. To perform such an analysis, first define and enforce a topology constraint using 'constraint' and 'prset topologypr = constraints (...)'.Then put the character(s) of interest in a separate partition and set MrBayes to report the ancestral states for that partition. For instance, if the characters of interest are in partition 2, use 'report applyto=(2) ancstates=yes' to force MrBayes to print the probability of the ancestral states of those characters at the constrained node to the '.p' file. Siterates If this option is set to 'yes' and the relevant model has rate variation across sites, the mean site rate in the posterior will be reported for each site to the '.p' file. Possel If this option is set to 'yes' and the relevant model has omega variation across sites, the mean omega value for each model site (codon in this case) will be written to the '.p' file. tratioval Report format for the transition and transversion rates of a nucleotide substitution model with nst=2 paramfile.txt ratio perl !$mrbayesblockquery && $nstopts == 2 perl "report tratio=$value\\n" ratio dirichlet 45 revmatopts Report format for substitution rates of a GTR substitution model for nucleotide or amino acid data perl !$mrbayesblockquery paramfile.txt dirichlet perl "report revmat=$value\\n" ratio dirichlet 45 reportancstateopts Report the probability of ancestral states at all constrained nodes paramfile.txt 0 perl !$mrbayesblockquery && $topologypropts eq "constraint" perl ($value)? "report Ancstates=Yes\\n":"report Ancstates=No\\n" 45 reportsiterateopts Report mean site rate in the posterior perl !$mrbayesblockquery paramfile.txt 0 perl ($value)? "report Siterates=Yes\\n":"report Siterates=No\\n" 45 reportposselopts Write Mean Omega Values paramfile.txt 0 perl !$mrbayesblockquery && $nucmodelopts eq "codon" perl ($value)? "report possel=Yes\\n":"report possel=No\\n" 45 sumtintro Set Sumt parameters Sumt command is used to produce summary statistics for trees sampled during a Bayesian MCMC analysis. You can either summarize trees from one individual analysis, or trees coming from several independent analyses. In either case, all the sampled trees are read in and the proportion of the time any single taxon bipartition is found is counted. The proportion of the time that the bipartition is found is an approximation of the posterior probability of the bipartition. (A taxon bipartition is defined by removing a branch on the tree, dividing the tree into those taxa to the left and right of the removed branch.) The branchlength of the bipartition is also recorded, if branch lengths have been saved to file. The result is a list of taxon bipartitions, the frequency with which they were found, the posterior probability of the bipartition and the mean and variance of the lengthof the branch (if bl's were recorded). The partition information is output to a file with the suffix ".parts" and a consensus tree is also printed to a file with the suffix ".con". The consensus tree is either a 50 percent majority rule tree or a majority rule tree showing all compatible partitions. If branch lengths have been recorded during the run, the ".con" file will contain a consensus tree with branch lengths and interior nodes labelled with support values. This tree can be viewed in a program such as TreeView. Finally, MrBayes produces a file with the ending ".trprobs" that contains a list of all the trees that were found during the MCMC analysis, sorted by their probabilities. This list of trees can be used to construct a credible set of trees. For example, if you want to construct a 95 percent credible set of trees, you include all of those trees whose cumulated probability is less than or equal to 0.95. If you are analyzing a large set of taxa, you may actually want to skip the calculation of tree probabilities entirely by setting "Calctreeprobs" to NO. When calculating summary statistics you probably want to skip those trees that were sampled in the initial part of the run, the so-called burn-in period. The number of skipped samples is controlled by the "burnin" setting. The default is 0 but you typically want to override this setting. If you are summarizing the trees sampled in several independent analyses, such as those resulting from setting the "Nruns" option of the "Mcmc" command to a value larger than 1, MrBayes will also calculate convergence diagnostics for the sampled topologies and branch lengths. These values can help you determine whether it is likely that your chains have converged. The "Sumt" command expands the "Filename" according to the current values of the "Nruns" and "Ntrees" options. For instance, if both "Nruns" and "Ntrees" are set to 1, "Sumt" will try to open a file named "Filename.t". If "Nruns" is set to 2 and "Ntrees" to 1, then "Sumt" will open two files, Filename.run1.t and Filename.run2.t, etc. By default, the "Filename" option will be set such that "Sumt" automatically summarizes all the results from your immediately preceding "Mcmc" command. You can also use the "Sumt" command to summarize tree samples inolder analyses. If you want to do that, remember to first read in a matrix so that MrBayes knows what taxon names to expect in the trees. Then set the "Nruns", "Ntrees" and "Filename" options appropriately. Options: Burnin -- Determines the number of samples that will be discarded from the input file before calculating summary statistics. If there are several input files, the same number of sampleswill be discarded from each. Note that the burnin is set separately for the 'sumt', 'sump', and 'mcmc' commands. Ntrees -- Determines how many trees there are in the sampled model. If 'Ntrees' is greater then 1 then the names of the files are derived from 'Filename' by adding '.tree1.t', '.tree2.t', etc. If Nruns=1 and Ntrees=1 (see below), then only '.t' is added to 'Filename'. Displaygeq -- The minimum probability of partitions to display. Contype -- Type of consensus tree. 'Halfcompat' results in a 50 majority rule tree, 'Allcompat' adds all compatible groups to such a tree. Calctreeprobs -- Determines whether tree probabilities should be calculated. sumtburnin Sumt Burnin Value perl !$mrbayesblockquery paramfile.txt 10 perl "sumt burnin=$value relburnin=$sumt_relburnin burninfrac=$sumt_burninfrac nruns=$sumtnruns ntrees=$sumtntrees minpartfreq=$sumtdisplaygeq $sumtcontype conformat=$sumt_conformat\\n" Please enter a sumt burnin value of 10 or more perl $value < 10 70 sumt_relburnin Discard a specified proportion of samples instead of a specific number(Relburnin=Yes) perl !$mrbayesblockquery paramfile.txt Yes Yes No perl "" 60 Specify the fraction of samples to be discarded. sumt_burninfrac Specify the fraction of samples to be discarded (Burninfrac=) perl !$mrbayesblockquery && $sumt_relburnin eq "Yes" paramfile.txt 0.25 perl "" 60 Specify the fraction of samples to be discarded. sumtnruns How many .t files should be summarized (Sumt nruns=) perl !$mrbayesblockquery paramfile.txt 2 perl "" 70 Sumt Nruns Determines how many '.t' files from independent analyses will be summarized. If Nruns > 1 then the names of the files are derived from 'Filename' by adding '.run1.t', '.run2.t', etc. If Nruns=1 and Ntrees=1 (see below), then only '.t' is added to 'Filename'. sumtntrees How many trees should be in the Sumt model perl !$mrbayesblockquery paramfile.txt 1 perl "" 70 Sumt Ntrees determines how many trees there are in the sampled model. If 'Ntrees' > 1 then the names of the files are derived from 'Filename' by adding '.tree1.t', '.tree2.t', etc. If there are both multiple trees and multiple runs, the filenames will be 'Filename.tree1.run1.t', 'Filename.tree1.run2.t', etc. sumtdisplaygeq Minimum probability of partitions to display in Sumt (0.05 = 95%) perl !$mrbayesblockquery paramfile.txt 0.05 perl "" 70 sumtcontype Type of consensus tree paramfile.txt contype=Halfcompat perl "" 70 perl !$mrbayesblockquery contype=Halfcompat contype=Allcompat Contype sets the type of consensus tree. The choices are 50 per cent majority rule tree, and one where all compatible groups are added to the tree. sumt_conformat Choose the output format for your consensus tree (Conformat=) perl !$mrbayesblockquery paramfile.txt Figtree Figtree Simple perl "" 60 Figtree format is rich and can be read by the program Figtree. Simple format can be read by many programs sumtshowtreeprobs Show Tree Probabilities perl !$mrbayesblockquery paramfile.txt showtreeprobs=No showtreeprobs=Yes showtreeprobs=No perl "" 70 sumpintro Set Sump parameters Sump specifies how information is summarized, and written to a parameter file. During MCMC analysis, MrBayes prints the sampled parameter values to a tab delimited text file. By default, the name of the parameter file is assumed to be the name of the last matrix-containing nexus file, but with a '.p' extension. You can set 'Sump' to summarize the information in any other parameter file by setting the 'filename' option to the appropriate file name. The 'Sump' command does not require a matrix to be read in first. When you invoke the 'Sump' command, three items are output (1) a generation plot of the likelihood values; (2) estimates of the marginal likelihood of the model; and (3) a table with the mean, variance, and 95 percent credible interval for the sampled parameters. Each of these items can be switched on or off using the options 'Plot', 'Marglike', and 'Table'. By default, all three items are output but only to the screen. If output to a file is also desired, set 'Printtofile' to 'Yes'. The name of the output file is specified by setting the 'Outputname' option. When a new matrix is read in or when the 'Mcmc' output filename or 'Sump' input filename is changed, the 'Sump' outputname is changed as well. If you want to output to another file than the default, make sure you specify the outputname every time you invoke 'Sump'. If the specified outputfile already exists, you will be prompted about whether you like to overwrite it or append to it. When you run several independent analyses simultaneously in MrBayes, the 'Nruns' and 'Filename' options are automatically set such that 'Sump' will summarize all the resulting output files. Default settings: Burnin:0; Nruns:1; Filename:temp.p.p; Printtofile:No; Outputname:temp.p.stat; Plot:Yes; Marglike:Yes; Table:Yes sumpburnin Sump Burnin Value perl !$mrbayesblockquery paramfile.txt 10 perl "sump burnin=$value relburnin=$sump_relburnin burninfrac=$sump_burninfrac nruns=$sumpnruns outputname=sumpoutput.out $sumpplot $sumpmarglike $sumptable\\n" Please enter a sump burnin value of 10 or more perl $value < 10 60 Burnin determines the number of samples that will be discarded from the input file before calculating summary statistics. If there are several input files, the same number of samples will be discarded from each. sump_relburnin Discard a specified proportion of samples instead of a specific number(Relburnin=Yes) perl !$mrbayesblockquery paramfile.txt Yes Yes No perl "" 60 Specify the fraction of samples to be discarded. sump_burninfrac Specify the fraction of samples to be discarded (Burninfrac=) perl !$mrbayesblockquery && $sump_relburnin eq "Yes" paramfile.txt 0.25 perl "" 60 Specify the fraction of samples to be discarded. sumpnruns How many '.p' files from independent analyses will be summarized (sump Nruns=) perl !$mrbayesblockquery paramfile.txt 2 perl "" 60 Sump nruns determines how many '.p' files from independent analyses that will be summarized. If Nruns > 1 then the names of the files are derived from 'Filename' by adding '.run1.p', '.run2.p', etc. If Nruns=1, then the single file name is obtained by adding '.p' to 'Filename'.