转录组数据拼接之应用篇

for i in `ls /projects/zhaofei/wheat_rawdata/LF0*_1.fq.gz`
do
id=`basename $i |sed 's/_1.fq.gz//'`
interleave-reads.py $i /projects/zhaofei/wheat_rawdata/${id}_2.fq.gz -o ${id}_pair.fq.gz --gzip
done

for i in `ls /projects/zhaofei/wheat_rawdata/LF1*_1.fq.gz`
do
id=`basename $i |sed 's/_1.fq.gz//'`
interleave-reads.py $i /projects/zhaofei/wheat_rawdata/${id}_2.fq.gz -o ${id}_pair.fq.gz --gzip
done

normalize-by-median.py -p -k 27 -M 50G -C 20 -R LF01.log \
-o LF01k32c28.fq.gz --gzip LF01_pair.fq.gz > runLF01.log 2>&1 &

filter-abund.py -V -Z 18 normC20k20.ct input.keep.fa && \
  rm input.keep.fa normC20k20.ct

# 我自己使用的时候实际没有执行这一步

extract-paired-reads.py input.keep.fq

split-paired-reads.py input.fq.pe

trinityrnaseq-Trinity-v2.4.0/Trinity \
--seqType fq --max_memory 40G --CPU 4 \
--left left.fq.gz \
--right right.fq.gz \
--output test_trinity --full_cleanup \
--no_version_check > test.log 2>&1 &

---------------------------
Trinity Phase 1: Clustering of RNA-Seq Reads
---------------------------

In silico Read Normalization
-- (Removing Excess Reads Beyond 50 Coverage --

Jellyfish
-- (building a k-mer catalog from reads) --

Inchworm
-- (Linear contig construction from k-mers) --

Chrysalis
-- (Contig Clustering & de Bruijn Graph Construction) --

------------------------
 Trinity Phase 2: Assembling Clusters of Reads
 ---------------------

Butterfly assemblies are written to \
/projects/zhaofei/wheat_assembly/trinity/LF20_1_trinity.Trinity.fasta

#If your data come from SRA, be sure to dump the fastq file like so:
 #SRA_TOOLKIT/fastq-dump --defline-seq '@$sn[_$rn]/$ri' --split-files --gzip file.sra

fastq-dump --defline-seq '@$sn[_$rn]/$ri' --split-files --gzip input.sra

#如果中间有空格，结尾正确

 zcat ERR037683_1.fastq.gz|awk '{ if (NR%4==1) { print $1"_"$2"" } else { print } }'|gzip >ERR037683_new_1.fastq.gz

 #跑循环修改
 for i in ERR037679_2.fastq.gz ERR037681_2.fastq.gz ERR037687_2.fastq.gz
  do
  zcat $i | awk '{ if (NR%4==1) { print $1"_"$2"" } else { print } }'|gzip > ${i/_2.fastq.gz/}_new_2.fastq.gz && rm -f $i
 done

 #如果结尾不正确
 zcat ERR037683_1.fastq.gz|awk '{ if (NR%4==1) { print $1"_"$2"/1" } else { print } }'|gzip >ERR037683_new_1.fastq.gz
 #_2.fq 同理替换

a) download latest boost and unpack it.

        $ tar zxvf boost_1_47_0.tar.gz

     b) change to the boost directory and run ./bootstrap.sh.

        $ cd  boost_1_47_0
        $ ./bootstrap.sh

        $ ./b2 install --prefix=<YOUR_BOOST_INSTALL_DIRECTORY>

        For example,if you want install boost in /home/czheng/local/boost,the commnd is :
        $ ./b2 install --prefix=/home/czheng/local/boost

        If the boost is installed successfully, you would fild two sub-directories in /home/czheng/local/boost/:
        /home/czheng/local/boost/include/
        /home/czheng/local/boost/lib/

       Note: The default Boost installation directory is /usr/local. Take note of the boost installation
        directory, beacuase you need to tell the Bridger installer where to find boost later on.

     d) Set the LD_LIBRARY_PATH enviroment variable:

        The ~/.bash_profile ($HOME/.bash_profile) or ~/.profile file is executed when you login using console or remotely using ssh.
        Append the following command to  ~/.bash_profile or ~/.profile file:
        $ export LD_LIBRARY_PATH=/home/czheng/local/boost/lib:$LD_LIBRARY_PATH

        Save and close the file.

        OR

        just type the command:
        $ export LD_LIBRARY_PATH=/home/czheng/local/boost/lib:$LD_LIBRARY_PATH

        Note: please replace "/home/czheng/local/boost/lib" with your own directory "<YOUR_BOOST_INSTALL_DIRECTORY>/lib"
        If you do not set this variable , you would possible see the follwoing error information:
         "error while loading shared libraries: libboost_serialization.so.1.47.0: cannot open shared object file: No such file or dire    ctory"

Building Bridger [Make sure Boost has been installed successfully]

     a) Unpack the Bridger and change to the Bridger direcotry.

        $ tar zxvf Bridger_r2013-06-02.tar.gz
        $ cd Bridger_r2013-06-02

     b) Configure Bridger. If Boost is installed somewhere other than /usr/local, you will need to tell
        the installer where to find it using --with-boost option.

        $ ./configure --with-boost=/home/czheng/local/boost/
        Note: please replace "/home/czheng/local/boost/" with your own directory "<YOUR_BOOST_INSTALL_DIRECTORY>"


     c) Make Bridger.

        $ make

       note: If you build boost suffessfully without using --prefix option, the following commands may need before "make":
           export LIBS="-L/home/czheng/boost_1_47_0/stage/lib" (replace "/home/czheng/boost_1_47_0/" with your own directory)
           export CPPFLAGS="-I/home/czheng/boost_1_47_0/"

Splicing Graphs Reconstruction
CMD: ~/software/Bridger_r2014-12-01/src/Assemble --reads both.fa -k 25 --pair_end --fr_strand 2 2>Assemble.log
Error, cmd: ~/software/Bridger_r2014-12-01/src/Assemble --reads both.fa -k 25 --pair_end --fr_strand 2 2>Assemble.log died with ret 256 !

Assemble.log:
[Error] Cannot create directory ./RawGraphs/ !

## Assemble step:
print "\n### Splicing Graphs Reconstruction ###\n\n";
my $graphdir = "RawGraphs"; #新加
mkdir "$output_directory/$graphdir"; #新加
my $assemble_cmd = "$SRC_DIR/Assemble --reads $target_fa -k $kmer_length ";

perl Bridger_r2014-12-01/Bridger.pl --seqType fq -k 31 --left left.fq --right right.fq --CPU 6 --debug -o output

cd-hit-est -i input.fasta -o output-cdhit -T 10 -M 200000

cp $PASAHOME/pasa_conf/pasa.CONFIG.template $PASAHOME/pasa_conf/conf.txt
 ##修改conf.txt以下配置
 #MYSQLSERVER=localhost
 #MYSQL_RW_USER=mysql
 #MYSQL_RW_PASSWORD=1234
 #MYSQL_RO_USER=readonly
 #MYSQL_RO_PASSWORD=1234

cp $PASAHOME/pasa_conf/pasa.alignAssembly.Template.txt./alignAssembly.config
#修改alignAssembly.config 的内容
#MYSQLDB=<you_task_name>

/PASApipeline-2.1.0/scripts/Launch_PASA_pipeline.pl-c alignAssembly.config-C-R-g genome.fa-tTrinity.fasta--ALIGNERS gmap--transcribed_is_aligned_orient--stringent_alignment_overlap30.0--CPU5

{name}#.pasa_assemblies.bed/gff3/gtf/described.txt
{name}.assemblie.fasta