###Install: wget http://ceiba.biosci.arizona.edu/r8s/r8s1.81.tar.gz tar -xzvfr8s1.81.tar.gz cd r8s1.81/src make -f Makefile.linux

__author__ = "Fabio H. K. Mendes" import os import argparse def r8s_prep(path_tree_file, sites_n, list_of_spp_tuples, list_of_spp_cal_points, path_output_file): tree_str = str() with open(path_tree_file, "r") as tree_file: tree_str = tree_file.readline().rstrip() fixage_lines = list() with open(path_output_file, "w") as output_file: output_file.write( "#NEXUS\nbegin trees; \ntree nj_tree = [&R] " + tree_str + "\nEnd; \nbegin rates; \nblformat nsites=" + \ sites_n + " lengths=persite ultrametric=no; \ncollapse; \n") for idx, pair in enumerate(list_of_spp_tuples): node_name = pair[0][-3:] + pair[1][-3:] output_file.write( "mrca " + node_name + " " + pair[0] + " " + pair[1] + "; \n") fixage_lines.append("fixage taxon=" + node_name + " age=" + list_of_cal_points[idx] + "; \n") for line in fixage_lines: output_file.write(line) output_file.write( "divtime method=pl algorithm=tn cvStart=0 cvInc=0.5 cvNum=8 crossv=yes; \ndescribe plot=chronogram; \ndescribe plot=tree_description; \nend; " ) if __name__ == "__main__": parser = argparse.ArgumentParser(description=__doc__, prog="mcl2rawcafe.py") parser.add_argument("-i", "--input-file", action="store", dest="input_file", required=True, type=str, help="full path to .txt file containing tree in NEWICK format") parser.add_argument("-o", "--output-file", action="store", dest="output_file", required=True, type=str, help="full path to file to be written (r8s input file)") parser.add_argument("-s", "--sites-n", action="store", dest="sites_n", required=True, type=str, help="number of sites in alignment used to estimate species tree") parser.add_argument("-p", "--pairs-species", action="store", dest="spp_pairs", required=True, type=str, help="") parser.add_argument("-c", "--calibration-points", action="store", dest="cal_points", required=True, type=str, help="") args = parser.parse_args() list_of_spp_tuples = list() for pair in args.spp_pairs.split(" "): list_of_spp_tuples.append(tuple(pair.split(","))) list_of_cal_points = args.cal_points.split(",") print "\nRunning cafetutorial_clade_and_size_filter.py as a standalone...\n" r8s_prep(args.input_file, args.sites_n, list_of_spp_tuples, list_of_cal_points, args.output_file)

/home/Tools/r8s1.81/src/r8s -b -f r8s_ctl_file.txt > r8s_tmp.txt #提取超度量树 $tail -n 1 r8s_tmp.txt | cut -c 16- > twelve_spp_r8s_ultrametric.txt

awk -F"\t" '{print "Desc""\t"$1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$10"\t"$11"\t"$12"\t"$13}' Orthogroups.GeneCount.tsv > cafe-input.data sed -e '1 s/(null)/Desc/' -e '1 s/Orthogroup/Family/' -i cafe-input.data python cafetutorial_clade_and_size_filter.py -i cafe-input.data -o filtered_cafe_input.txt -s 2> filtered.log

__author__ = "Fabio H. K. Mendes" import os import argparse def clade_filter(mcl_dump, clade_str): lines_to_keep_list = list() spp_idx_dict = dict() clades_list = list() if clade_str: # if clade filter was specified clades_list = clade_str.split(" ") with open(mcl_dump, "r") as input_file: for line_n, line in enumerate(input_file): line = line.rstrip() tokens = line.split("\t") spp_info = tokens[2:] if line.startswith("Desc"): spp_idx_dict = dict((sp, idx) for idx,sp in enumerate(spp_info)) continue if clades_list: clades_ok_list = list() for clade in clades_list: spp_list = clade.split(",") clade_count = sum(1 for sp in spp_list if int(spp_info[spp_idx_dict[sp]]) >= 1) if clade_count >= 2: clades_ok_list.append(1) if sum(clades_ok_list) == len(clades_list): lines_to_keep_list.append(line_n) # just keeping lines where >=2 species (among all of them) have gene copies clade_count = sum(1 for sp_count in spp_info if int(sp_count) >= 1) if clade_count >= 2: lines_to_keep_list.append(line_n) return set(lines_to_keep_list) def size_filter(mcl_dump, lines_to_keep_set): lines_to_remove_set = set() size_cutoff = 100 fam_size = int() with open(mcl_dump, "r") as input_file: for line_n, line in enumerate(input_file): line = line.rstrip() if line.startswith("Desc"): continue elif line_n not in lines_to_keep_set and len(lines_to_keep_set) > 0: continue tokens = line.split("\t") spp_info = tokens[2:] for gene_count in spp_info: if int(gene_count) >= size_cutoff: lines_to_separate_set.add(line_n) lines_to_keep_set -= lines_to_separate_set return lines_to_keep_set, lines_to_separate_set def filter_print(mcl_dump, lines_to_keep_set, lines_to_separate_set, output_file_name): if len(lines_to_keep_set) == 0 and len(lines_to_separate_set) == 0: exit("No filtering was done! Exiting...\n") with open(output_file_name, "w") as output_file: with open("large_"+output_file_name, "w") as output_file2: with open(mcl_dump, "r") as input_file: for line_n, line in enumerate(input_file): line = line.rstrip() + "\n" if line_n == 0: output_file.write(line) output_file2.write(line) elif line_n in lines_to_keep_set and len(lines_to_keep_set) >= 1: output_file.write(line) elif line_n not in lines_to_separate_set and len(lines_to_keep_set) == 0: output_file.write(line) # has to be if, not elif if line_n in lines_to_separate_set: output_file2.write(line) # cleaning up in case size filtering was not done if len(lines_to_separate_set) == 0: os.unlink("large_"+output_file_name) if __name__ == "__main__": parser = argparse.ArgumentParser(description=__doc__, prog="cafetutorial_clade_and_size_filter.py") parser.add_argument("-i", "--input-file", action="store", dest="input_file", required=True, type=str, help="full path to mcl's output dump file") parser.add_argument("-o", "--output-file", action="store", dest="output_file", required=True, type=str, help="full path to file to be written") parser.add_argument("-cl", "--clade-filter", action="store", dest="clade_str", default=None, required=False, type=str, help="list of clades (separated by white spaces) comprised of species identifiers (separated by comma) that must have at least two species with gene copies for a given gene family") parser.add_argument("-s", "--size-filter", action="store_true", dest="size_filter", required=False, help="option to perform size filtering") args = parser.parse_args() lines_to_keep_set, lines_to_separate_set = set(), set() # applying size filter (if no groups are specified, just the lines where just 1 species has gene counts are removed lines_to_keep_set = clade_filter(args.input_file, args.clade_str) if args.size_filter: lines_to_keep_set, lines_to_separate = size_filter(args.input_file, lines_to_keep_set) filter_print(args.input_file, lines_to_keep_set, lines_to_separate_set, args.output_file) # .add(0) to get header back

mkdir -p reports cafe cafetutorial_run.sh

推荐阅读

• 

  椰子油的生活小妙用 椰子油有什么用途和功效
• 

  庆东锅炉故障代码是什么如何解决
• 

  教学教务管理人员是干什么的
• 

  联想yoga2
• 

  如何选择抗体稀释液？ 抗体稀释液
• 

  下载导航地图，导航地图下载
• 

  流媒体后视镜可以当行车记录仪吗 行车记录仪有必要买流媒体吗
• 

  炒苔菜用不用焯水，苔菜用不用焯水再炒
• 

  昆明工业职业技术学院怎么样
• 

  （152）感赏女儿|（152）感赏女儿 2020-12-4
• 

  桃子核发霉外面是好的还能吃吗
• 

  离散傅立叶分析,origin怎么进行傅立叶分析
• 

  次密接触者的一般接触者需要隔离吗
• 

  海带炖土豆的做法 海带炖土豆的做法窍门
• 

  大概的近义词 大概的近义词是什么 标准答案
• 

  合金筷子是塑料还是金属 合金筷子是什么材质
• 

  真我与假我
• 

  钢材包括哪些 钢材怎么分类
• 

  heos,黑色素瘤
• 

  【家事】节如流水

• 2月2日日课总结（基因技术）
• 写在《小偷家族》二刷后
• 信控学院“阳光少年心向党，红色基因代代传”教育关爱服务队前往灵璧县灵光小学走访调研
• 商业装饰领导品牌大红点牵手和道和咨询集团正式引入阿米巴基因工程项目
• 基因决定你是否患肥胖症和糖尿病（）
• AI开发平台系列1（AI开发平台“家族”概览）
• protocol-使用CRISPR-Cas9系统进行基因编辑（一）
• 【王者荣耀】大乔-自戏
• 《基因传》---读书笔记（1）
• Nature Genetics（微生物基因组如何适应植物（(news & views)））