Pacbio Data

Revision as of 12 November 2013 23:58 by admin (Comments | Contribs) | (→Randomly Selected Four SMRT cells)
Contents

Dataset1

All Data

The eight SMRT cells of Ecoli MG1655 were downloaded from HGAP. We used all SMRT cells and randomly selected four and six SMRT cells three times for each in our study.

m121023_202553_42178_c100389662550000001523034410251200_s1_p0.bas.h5
m121023_224605_42178_c100389662550000001523034410251201_s1_p0.bas.h5
m121024_010654_42178_c100389662550000001523034410251202_s1_p0.bas.h5
m121024_032737_42178_c100389662550000001523034410251203_s1_p0.bas.h5
m121024_074656_42178_c100389662550000001523034410251204_s1_p0.bas.h5
m121024_100442_42178_c100389662550000001523034410251205_s1_p0.bas.h5
m121024_122509_42178_c100389662550000001523034410251206_s1_p0.bas.h5
m121024_144608_42178_c100389662550000001523034410251207_s1_p0.bas.h5

We have run smrtpipe.py (SMRT analysis) with the following params.xml to get filtered subreads of continuous long reads (CLR).

 <param name="minLength">
   <value>50</value>
 </param>
 <param name="readScore">
   <value>0.75</value>
 </param>
 <param name="minSubReadLength">
   <value>50</value>

Randomly Selected Four SMRT cells

First Set

m121024_100442_42178_c100389662550000001523034410251205_s1_p0
m121024_122509_42178_c100389662550000001523034410251206_s1_p0
m121023_202553_42178_c100389662550000001523034410251200_s1_p0
m121024_010654_42178_c100389662550000001523034410251202_s1_p0

Second Set

m121024_122509_42178_c100389662550000001523034410251206_s1_p0
m121023_202553_42178_c100389662550000001523034410251200_s1_p0
m121024_032737_42178_c100389662550000001523034410251203_s1_p0
m121024_144608_42178_c100389662550000001523034410251207_s1_p0

Third Set

m121024_032737_42178_c100389662550000001523034410251203_s1_p0
m121024_010654_42178_c100389662550000001523034410251202_s1_p0
m121023_224605_42178_c100389662550000001523034410251201_s1_p0
m121024_074656_42178_c100389662550000001523034410251204_s1_p0

Randomly Selected Six SMRT cells

First Set

m121024_100442_42178_c100389662550000001523034410251205_s1_p0
m121023_224605_42178_c100389662550000001523034410251201_s1_p0
m121023_202553_42178_c100389662550000001523034410251200_s1_p0
m121024_032737_42178_c100389662550000001523034410251203_s1_p0
m121024_074656_42178_c100389662550000001523034410251204_s1_p0
m121024_144608_42178_c100389662550000001523034410251207_s1_p0

Second Set

m121024_074656_42178_c100389662550000001523034410251204_s1_p0
m121023_224605_42178_c100389662550000001523034410251201_s1_p0
m121024_032737_42178_c100389662550000001523034410251203_s1_p0
m121024_144608_42178_c100389662550000001523034410251207_s1_p0
m121024_010654_42178_c100389662550000001523034410251202_s1_p0
m121024_100442_42178_c100389662550000001523034410251205_s1_p0

Third Set

m121023_224605_42178_c100389662550000001523034410251201_s1_p0
m121023_202553_42178_c100389662550000001523034410251200_s1_p0
m121024_032737_42178_c100389662550000001523034410251203_s1_p0
m121024_122509_42178_c100389662550000001523034410251206_s1_p0
m121024_010654_42178_c100389662550000001523034410251202_s1_p0
m121024_144608_42178_c100389662550000001523034410251207_s1_p0

Dataset2

Th four SMRT cells of Mruber were downloaded from HGAP.

m120803_022519_42141_c100388772550000001523034210251234_s1_p0.bas.h5
m120803_041200_42141_c100388772550000001523034210251235_s1_p0.bas.h5
m120803_055858_42141_c100388772550000001523034210251236_s1_p0.bas.h5
m120803_074648_42141_c100388772550000001523034210251237_s1_p0.bas.h5

Dataset3

The seven SMRT cells of Phep were downloaded from HGAP. We used all SMRT cells and randomly selected four SMRT cells three times for each in our study.
m120802_210418_42142_c100388622550000001523034210251211_s1_p0.bas.h5
m120802_225401_42142_c100388622550000001523034210251212_s1_p0.bas.h5
m120803_004251_42142_c100388622550000001523034210251213_s1_p0.bas.h5
m120803_023226_42142_c100388622550000001523034210251214_s1_p0.bas.h5
m120803_041958_42142_c100388622550000001523034210251215_s1_p0.bas.h5
m120803_060809_42142_c100388622550000001523034210251216_s1_p0.bas.h5
m120803_075818_42142_c100388622550000001523034210251217_s1_p0.bas.h5

Randomly Selected Four SMRT cell

First Set

m120802_225401_42142_c100388622550000001523034210251212_s1_p0
m120803_060809_42142_c100388622550000001523034210251216_s1_p0
m120803_004251_42142_c100388622550000001523034210251213_s1_p0
m120802_210418_42142_c100388622550000001523034210251211_s1_p0

Second Set

m120803_023226_42142_c100388622550000001523034210251214_s1_p0
m120803_075818_42142_c100388622550000001523034210251217_s1_p0
m120802_210418_42142_c100388622550000001523034210251211_s1_p0
m120803_060809_42142_c100388622550000001523034210251216_s1_p0

Third Set

m120803_041958_42142_c100388622550000001523034210251215_s1_p0
m120803_075818_42142_c100388622550000001523034210251217_s1_p0
m120803_023226_42142_c100388622550000001523034210251214_s1_p0
m120802_210418_42142_c100388622550000001523034210251211_s1_p0

Dataset4

Alldata

The 17 SMRT cells of Ecoli MG 1655 were downloaded from NCBI SRA, as described in Data.
m120208_071634_42139_c100288480630000001523009507231245_s1_p0.bas.h5
m120228_190630_42139_c100301722550000001523012308061206_s1_p0.bas.h5
m120208_122534_42139_c100290260310000001523009507231262_s1_p0.bas.h5
m120228_192221_42129_c100298890010000001523009207231260_s1_p0.bas.h5
m120208_160812_42139_c100290260310000001523009507231264_s1_p0.bas.h5
m120228_205404_42139_c100301722550000001523012308061207_s1_p0.bas.h5
m120228_082105_42139_c100301722550000001523012308061200_s1_p0.bas.h5
m120228_210845_42129_c000304152550000001500000112311370_s1_p0.bas.h5
m120228_100807_42139_c100301722550000001523012308061201_s1_p0.bas.h5
m120228_223624_richard_c001202352550000001500000112311330_s1_p0.bas.h5
m120228_115504_42139_c100301722550000001523012308061202_s1_p0.bas.h5
m120229_004752_42129_c000304192550000001500000112311350_s1_p0.bas.h5
m120228_134222_42139_c100301722550000001523012308061203_s1_p0.bas.h5
m120229_012852_42139_c000301732550000001500000112311360_s1_p0.bas.h5
m120228_152936_42139_c100301722550000001523012308061204_s1_p0.bas.h5
m120229_193409_42129_c000304212550000001500000112311380_s1_p0.bas.h5
m120228_171636_42139_c100301722550000001523012308061205_s1_p0.bas.h5

Randomly Selected Four SMRT cells

First set

Random Get @m120208_122534_42139_c100290260310000001523009507231262_s1_p0
Random Get @m120228_205404_42139_c100301722550000001523012308061207_s1_p0
Random Get @m120228_210845_42129_c000304152550000001500000112311370_s1_p0
Random Get @m120228_152936_42139_c100301722550000001523012308061204_s1_p0

Second set

Random Get @m120229_012852_42139_c000301732550000001500000112311360_s1_p0
Random Get @m120228_152936_42139_c100301722550000001523012308061204_s1_p0
Random Get @m120228_192221_42129_c100298890010000001523009207231260_s1_p0
Random Get @m120228_100807_42139_c100301722550000001523012308061201_s1_p0

Third set

Random Get @m120228_192221_42129_c100298890010000001523009207231260_s1_p0
Random Get @m120228_223624_richard_c001202352550000001500000112311330_s1_p0
Random Get @m120228_082105_42139_c100301722550000001523012308061200_s1_p0
Random Get @m120229_193409_42129_c000304212550000001500000112311380_s1_p0

Randomly Selected Six SMRT cells

Randomly Selected eight SMRT cells