[ { "id": "dadi", "name": "dadi", "article": "10.1038\/npre.2010.4594.1", "website": "https:\/\/dadi.readthedocs.io\/en\/latest\/", "git": "https:\/\/bitbucket.org\/gutenkunstlab\/dadi\/src\/master\/", "description": "Fit population genetic models of demography and selection using diffusion approximations to the allele frequency spectrum", "version": "2.3.0", "documentation": "https:\/\/dadi.readthedocs.io\/en\/latest\/", "multiqc": "custom", "commands": [ { "name": "dadi", "cname": "Dadi", "command": "", "category": "genet_pop", "output_dir": "dadi", "inputs": [ { "name": "fs_file_name", "type": "path" } ], "outputs": [ { "name": "full", "type": "txt", "file": "dadi-full.txt", "description": "" }, { "name": "easy", "type": "txt", "file": "dadi-easy.txt", "description": "" }, { "name": "modelsfs", "type": "txt", "file": "dadi-modelsfs.txt", "description": "" }, { "name": "img", "type": "png", "file": "dadi_{model}_mqc.png", "description": "" } ], "options": [ { "name": "dadi_masked", "prefix": "--masked", "type": "checkbox", "value": false, "label": "--masked : If set, mask the singletons in the sfs: [1,0] and [0,1]." }, { "name": "dadi_folded", "prefix": "--folded", "type": "checkbox", "value": false, "label": "--folded : If set, the sfs is folded (i.e. no outgroup to polarize the data)." }, { "name": "dadi_projected", "prefix": "--projected", "type": "checkbox", "value": false, "label": "--projected : If set, the sfs is projected down to n1,n2 (values to be set with option -n). If your data have missing calls for some individuals, projecting down to a smaller sample size will increase the number of SNPs you can use. It will average over all possible re-samplings of the larger sample size data (assuming random mating)." }, { "name": "dadi_datatype", "type": "select", "prefix": "--datatype", "choices": [ { "simul": "simul" }, { "sfs": "sfs" }, { "snp-dadi": "snp-dadi" } ], "value": "simul", "label": "Type of input: 1) simul: ms simulation. 2) sfs: sfs data. 3) snp-dadi: snp data with dadi format; the sample size is required (values to be set with options -j and -n). 4) vcf: vcf data; it requires -c to be provided and it will only include sites without missing data." }, { "name": "dadi_namepop1", "prefix": "--namepop1", "type": "text", "value": "Pop1", "label": "Population 1 name" }, { "name": "dadi_namepop2", "prefix": "--namepop2", "type": "text", "value": "Pop2", "label": "Population 2 name" }, { "name": "dadi_proj_sample", "prefix": "--proj_sample", "type": "text", "value": "10,10 ", "label": "--proj_sample : Sample size of population 1 and 2 in the sfs. Recall that for a diploid organism we get two samples from each individual. These values are ignored if -j is not set." }, { "name": "dadi_grid_points", "prefix": "--grid_points", "type": "text", "value": "10,20,30 ", "label": "--grid_points : Size of the grids for extrapolation. dadi solves a partial differential equation, approximating the solution using a grid of points in population frequency space (diffusion approximation). The grid takes 3 numbers separated by a coma. Good results are obtained by setting the smallest grid size slightly larger than the largest sample size, but this can be altered depending on usage. If you are fitting a complex model, it may speed up the analysis considerably to first run an optimization at small grid sizes. They can then be refined by running another optimization with a finer grid." }, { "name": "dadi_model_list", "type": "select", "prefix": "--model_list", "choices": [ { "SI": "SI" }, { "IM": "IM" }, { "SC": "SC" }, { "AM": "AM" } ], "value": "SI", "label": "--model_list : List the models to include in the inference. All available models are defined in dadi_models_2pop.py." }, { "name": "dadi_maxiterGlobal", "prefix": "", "type": "numeric", "value": 100, "min": 1, "max": "NA", "step": 1, "label": "maximum global search iterations - in each iteration, it explores twice the number of parameters." }, { "name": "dadi_accept", "prefix": "", "type": "numeric", "value": 1, "min": "NA", "max": "NA", "step": "NA", "label": "parameter for acceptance distribution (lower values makes the probability of acceptance smaller)" }, { "name": "dadi_visit", "prefix": "", "type": "numeric", "value": 1.01, "min": "NA", "max": "NA", "step": "NA", "label": "parameter for visiting distribution (higher values makes the algorithm jump to a more distant region)" }, { "name": "dadi_Tini", "prefix": "", "type": "numeric", "value": 50, "min": "NA", "max": "NA", "step": "NA", "label": "initial temperature" }, { "name": "dadi_no_local_search", "prefix": "", "type": "checkbox", "value": false, "label": "If set to True, a Generalized Simulated Annealing will be performed with no local search strategy applied" }, { "name": "dadi_local_method", "prefix": "", "type": "text", "value": "L-BFGS-B", "label": "local search method" }, { "name": "dadi_maxiterLocal", "prefix": "", "type": "numeric", "value": 20, "min": "NA", "max": "NA", "step": 1, "label": "maxiterLocal" } ] } ], "prepare_report_script": "dadi.prepare.report.py", "prepare_report_outputs": [ "dadi-full_mqc.txt" ], "install": [], "citations": { "numpy": [ "S. van der Walt, S. C. Colbert and G. Varoquaux, 'The NumPy Array: A Structure for Efficient Numerical Computation,' in Computing in Science & Engineering, vol. 13, no. 2, pp. 22-30, March-April 2011, doi: 10.1109\/MCSE.2011.37." ], "scipy": [ "Virtanen, P., Gommers, R., Oliphant, T.E. et al. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods 17, 261-272 (2020). https:\/\/doi.org\/10.1038\/s41592-019-0686-2" ], "matplotlib": [ "J. D. Hunter, 'Matplotlib: A 2D Graphics Environment,' in Computing in Science & Engineering, vol. 9, no. 3, pp. 90-95, May-June 2007, doi: 10.1109\/MCSE.2007.55." ], "dadi": [ "Gutenkunst, R., Hernandez, R., Williamson, S. et al. Diffusion Approximations for Demographic Inference: DaDi. Nat Prec (2010). https:\/\/doi.org\/10.1038\/npre.2010.4594.1" ] }, "yaml": "{\n id: dadi,\n name: dadi,\n article: \"10.1038\/npre.2010.4594.1\",\n website: \"https:\/\/dadi.readthedocs.io\/en\/latest\/\",\n git: \"https:\/\/bitbucket.org\/gutenkunstlab\/dadi\/src\/master\/\",\n description: \"Fit population genetic models of demography and selection using diffusion approximations to the allele frequency spectrum\",\n version: \"2.3.0\",\n documentation: \"https:\/\/dadi.readthedocs.io\/en\/latest\/\",\n multiqc: \"custom\",\n commands:\n [\n {\n name: dadi,\n cname: \"Dadi\",\n command: \"\",\n category: \"genet_pop\",\n output_dir: dadi,\n inputs:\n [\n { name: fs_file_name, type: \"path\" }\n #{ pop_file_name: } Path-name to the file describing how individuals map to populations. This file is ignored if datatype is not 'vcf'.\n ],\n outputs: [\n { name: full, type: \"txt\", file: \"dadi-full.txt\", description: \"\" },\n { name: easy, type: \"txt\", file: \"dadi-easy.txt\", description: \"\" },\n { name: modelsfs, type: \"txt\", file: \"dadi-modelsfs.txt\", description: \"\" },\n { name: img, type: \"png\", file: \"dadi_{model}_mqc.png\", description: \"\" }\n ],\n options:\n [\n {\n name: dadi_masked,\n prefix: \"--masked\",\n type: checkbox,\n value: FALSE,\n label: \"--masked : If set, mask the singletons in the sfs: [1,0] and [0,1].\",\n },\n {\n name: dadi_folded,\n prefix: \"--folded\",\n type: checkbox,\n value: FALSE,\n label: \"--folded : If set, the sfs is folded (i.e. no outgroup to polarize the data).\",\n },\n {\n name: dadi_projected,\n prefix: \"--projected\",\n type: checkbox,\n value: FALSE,\n label: \"--projected : If set, the sfs is projected down to n1,n2 (values to be set with option -n). If your data have missing calls for some individuals, projecting down to a smaller sample size will increase the number of SNPs you can use. It will average over all possible re-samplings of the larger sample size data (assuming random mating).\",\n },\n #{\n # name: dadi_nameoutput,\n # prefix: \"--nameoutput\",\n # type: text,\n # value: \"dadi\",\n # label: \"Prefix for output files\"\n #},\n {\n name: dadi_datatype,\n type: select,\n prefix: \"--datatype\",\n choices: [\n simul: \"simul\",\n sfs: \"sfs\",\n snp-dadi: \"snp-dadi\"\n ],\n value: \"simul\",\n label: \"Type of input: 1) simul: ms simulation. 2) sfs: sfs data. 3) snp-dadi: snp data with dadi format; the sample size is required (values to be set with options -j and -n). 4) vcf: vcf data; it requires -c to be provided and it will only include sites without missing data.\"\n },\n {\n name: dadi_namepop1,\n prefix: \"--namepop1\",\n type: text,\n value: \"Pop1\",\n label: \"Population 1 name\"\n },\n {\n name: dadi_namepop2,\n prefix: \"--namepop2\",\n type: text,\n value: \"Pop2\",\n label: \"Population 2 name\"\n },\n\n {\n name: dadi_proj_sample,\n prefix: \"--proj_sample\",\n type: text,\n value: \"10,10 \",\n label: \"--proj_sample : Sample size of population 1 and 2 in the sfs. Recall that for a diploid organism we get two samples from each individual. These values are ignored if -j is not set.\"\n },\n\n {\n name: dadi_grid_points,\n prefix: \"--grid_points\",\n type: text,\n value: \"10,20,30 \",\n label: \"--grid_points : Size of the grids for extrapolation. dadi solves a partial differential equation, approximating the solution using a grid of points in population frequency space (diffusion approximation). The grid takes 3 numbers separated by a coma. Good results are obtained by setting the smallest grid size slightly larger than the largest sample size, but this can be altered depending on usage. If you are fitting a complex model, it may speed up the analysis considerably to first run an optimization at small grid sizes. They can then be refined by running another optimization with a finer grid.\"\n },\n\n {\n name: dadi_model_list,\n type: select,\n prefix: \"--model_list\",\n choices: [\n SI: \"SI\",\n IM: \"IM\",\n SC: \"SC\",\n AM: \"AM\"\n ],\n value: \"SI\",\n label: \"--model_list : List the models to include in the inference. All available models are defined in dadi_models_2pop.py.\"\n },\n\n {\n name: dadi_maxiterGlobal,\n prefix: \"\",\n type: numeric,\n value: 100,\n min: 1,\n max: NA,\n step: 1,\n label: \"maximum global search iterations - in each iteration, it explores twice the number of parameters.\",\n },\n {\n name: dadi_accept,\n prefix: \"\",\n type: numeric,\n value: 1,\n min: NA,\n max: NA,\n step: NA,\n label: \"parameter for acceptance distribution (lower values makes the probability of acceptance smaller)\",\n },\n {\n name: dadi_visit,\n prefix: \"\",\n type: numeric,\n value: 1.01,\n min: NA,\n max: NA,\n step: NA,\n label: \"parameter for visiting distribution (higher values makes the algorithm jump to a more distant region)\",\n },\n {\n name: dadi_Tini,\n prefix: \"\",\n type: numeric,\n value: 50,\n min: NA,\n max: NA,\n step: NA,\n label: \"initial temperature\",\n },\n {\n name: dadi_no_local_search,\n prefix: \"\",\n type: checkbox,\n value: FALSE,\n label: \"If set to True, a Generalized Simulated Annealing will be performed with no local search strategy applied\",\n },\n {\n name: dadi_local_method,\n prefix: \"\",\n type: text,\n value: \"L-BFGS-B\",\n label: \"local search method\"\n },\n {\n name: dadi_maxiterLocal,\n prefix: \"\",\n type: numeric,\n value: 20,\n min: NA,\n max: NA,\n step: 1,\n label: \"maxiterLocal\",\n }, \n ]\n },\n ],\n prepare_report_script: dadi.prepare.report.py,\n prepare_report_outputs: [\n dadi-full_mqc.txt\n ],\n install: {\n # numpy: [\n # \"pip3 install numpy\"\n # ],\n # scipy: [\n # \"pip3 install scipy\"\n # ],\n # matplotlib: [\n # \"pip3 install matplotlib\"\n # ],\n # dadi: [\n # \"cd \/sources\/dadi_sources\",\n # \"tar -xvzf dadi-wrapper.tar.gz\",\n # \"cd \/sources\/dadi_sources\/dadi-wrapper\/dadi-2.0.6_modif\",\n # \"python3 setup.py install\"\n # ],\n },\n citations: {\n numpy: [\n \"S. van der Walt, S. C. Colbert and G. Varoquaux, 'The NumPy Array: A Structure for Efficient Numerical Computation,' in Computing in Science & Engineering, vol. 13, no. 2, pp. 22-30, March-April 2011, doi: 10.1109\/MCSE.2011.37.\"\n ],\n scipy: [\n \"Virtanen, P., Gommers, R., Oliphant, T.E. et al. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods 17, 261-272 (2020). https:\/\/doi.org\/10.1038\/s41592-019-0686-2\"\n ],\n matplotlib: [\n \"J. D. Hunter, 'Matplotlib: A 2D Graphics Environment,' in Computing in Science & Engineering, vol. 9, no. 3, pp. 90-95, May-June 2007, doi: 10.1109\/MCSE.2007.55.\"\n ],\n dadi: [\n \"Gutenkunst, R., Hernandez, R., Williamson, S. et al. Diffusion Approximations for Demographic Inference: DaDi. Nat Prec (2010). https:\/\/doi.org\/10.1038\/npre.2010.4594.1\"\n ],\n }\n}\n" } ]