pdb_mmcif 下载特别慢 # 参考网站 https://www.wwpdb.org/ftp/pdb-ftp-sites # 找到合适的链接下载,比如: rsync -rlpt -v -z --delete \ rsync.ebi.ac.uk::pub/databases/pdb/data/structures/divided/mmCIF/ \ ./mmCIF # 脚本中给出的信息: #echo " * rsync.ebi.ac.uk::pub/databases/pdb/data/structures/divided/mmCIF/ (Europe)" #echo " * ftp.pdbj.org::ftp_data/structures/divided/mmCIF/ (Asia)" #echo "or see https://www.wwpdb.org/ftp/pdb-ftp-sites for more download options." #rsync --recursive --links --perms --times --compress --info=progress2 --delete --port=33444 \ # rsync.rcsb.org::ftp_data/structures/divided/mmCIF/ \ # "${RAW_DIR}"

2f0f56d6-98e7-4ade-a941-76870dfa1c34-image.png

Genetics:A Conceptual Approach

fastq-dump --origfmt --split-files SRR7879722.1

@ice-melt

FTP增加删除用户 增加用户 mkdir -p /home/test sudo useradd -g ftp -d /home/test -m test # (注：g：用户所在的组 # d：表示创建用户的自己目录的位置给予指定 # m：不建立默认的自家目录，也就是说在/home下没有自己的目录) # 给用户添加口令 sudo passwd test # 123456 编辑/etc/vsftpd.chroot_list文件，将ftp的帐户名添加进去，保存退出 修改用户权限文件vsftpf.chroot_list文件后一定要重启服务才能生效 删除用户 sudo userdel test

@ice-melt

process_radtags 双端处理格式

// Parse a file name that looks like: lane6_NoIndex_L006_R1_003.fastq // but exclude the paired-end files: lane6_NoIndex_L006_R2_003.fastq // // Another example could be: GfddRAD1_001_ATCACG_L008_R1_001.fastq.gz // and excluding the paired-end file: GfddRAD1_001_ATCACG_L008_R2_001.fastq.gz

@ice-melt

sra数据查询下载

地址： https://www.ncbi.nlm.nih.gov/sra
使用说明： https://www.jianshu.com/p/680e8d720516

RAD-Seq （restriction site-associated DNA Sequencing） GBS（genotyping-by-sequencing）

lefse 1.0.8.post1 报错 # 170 lefse-plot_cladogram.py all_add_groups.res all_add_groups_cladogram.png --format png --clade_sep 0.05 --abrv_stop_lev 7 --dpi 500 # 报错: AttributeError: Unknown property axis_bgcolor

修改：~/miniconda2/envs/lefse/bin/lefse-plot_cladogram.py

def draw_tree(out_file,tree,params): plt_size = 7 nlev = tree['nlev'] pt_scale = (params['min_point_size'],max(1.0,((tree['max_abs']-tree['min_abs']))/(params['max_point_size']-params['min_point_size']))) depth = len(nlev) sep = (2.0*np.pi)/float(nlev[-1]) seps = [params['clade_sep']*sep/float(depth-i+1) for i in range(1,len(tree['nlev'])+1)] totseps = sum([s*nlev[i] for i,s in enumerate(seps[:-1])]) clade_sep_err = True if totseps > np.pi else False while totseps > np.pi: params['clade_sep'] *= 0.75 seps = [params['clade_sep']*sep/(float(depth-i+1)*0.25) for i in range(1,len(tree['nlev'])+1)] totseps = sum([s*nlev[i] for i,s in enumerate(seps[:-1])]) if clade_sep_err: print 'clade_sep parameter too large, lowered to',params['clade_sep'] fig = plt.figure(edgecolor=params['back_color'],facecolor=params['back_color']) ax = fig.add_subplot(111, polar=True, frame_on=False,facecolor=params['back_color'] ) # axis_bgcolor 修改为 facecolor #ax = fig.add_subplot(111, polar=True, frame_on=False, axis_bgcolor=params['back_color'] )

常见文件格式读取 读取 fastq.gz 文件 import gzip import itertools # 参见：q2_demux._dumux.py:function@_read_fastq_seqs def read_fastq_seqs(filepath): fh = gzip.open(filepath, 'rt') for seq_header, seq, qual_header, qual in itertools.zip_longest(*[fh] * 4): yield (seq_header.strip(), seq.strip(), qual_header.strip(), qual.strip()) 读取 biom 文件 def read_biom_file(filepath): table = load_table(filepath) # table 获取数据的常用方法示例 ids = table.ids() otu_ids = table.ids(axis='observation') cnts = table.matrix_data.astype(int).toarray().T 读取进化树 （文本格式，后缀一般为tre|nwk等）文件 def read_tree_node(filepath) -> skbio.TreeNode: # ignore BOM only when reading, do not emit BOM on write with open(filepath, mode='r', encoding='utf-8-sig') as fh: return skbio.TreeNode.read(fh, format='newick', verify=False) 读取距离矩阵(一种tsv格式)文件 def read_distence_matrix(filepath): return skbio.DistanceMatrix.read(filepath, format='lsmat', verify=False) 读取PCoA分析结果文件 # 当前无需读取使用该方法，直接从距离矩阵中计算PCoA结果 # master = skbio.stats.ordination.pcoa(dm, method='eigh', inplace=False) def read_ordination_data(filepath): return skbio.OrdinationResults.read(filepath, format='ordination', verify=False)