Skip to content
Snippets Groups Projects
Commit 144b83c8 authored by Valentina Galata's avatar Valentina Galata
Browse files

rm data and src_SBB in report/

parent e004fdf2
No related branches found
No related tags found
1 merge request!76Merge "cleanup" branch with "master" branch
Hide whitespace changes
Inline Side-by-side
Showing
with 0 additions and 647 deletions
report/data/.gitkeep deleted 100644 → 0
+ 0
− 0
View file @ e004fdf2
report/data/2019_GDB_protein_partial_genes.txt deleted 100644 → 0
+ 0
− 5
View file @ e004fdf2
tool metaspades metaspades_hybrid
prodigal_partial 251907 169318
prodigal_total 365813 341322
cdhit_unique 27526 63911
cdhit_total 365813 341322
report/data/bwa_lr_metaspades_hybrid_HQ_bins.txt deleted 100644 → 0
+ 0
− 11
View file @ e004fdf2
maxbin_output.024 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__Eubacterium_R;s__Eubacterium_R 97.32 2.48 0.00
maxbin_output.021 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Ruminococcaceae;g__Ruminococcus_D;s__Ruminococcus_D 98.63 0.00 0.00
maxbin_output.015 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Acetatifactor;s__Acetatifactor 98.07 3.51 8.33
maxbin_output.020 d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Acidaminococcales;f__Acidaminococcaceae;g__Phascolarctobacterium;s__Phascolarctobacterium 99.98 2.89 0.00
maxbin_output.001 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides;s__Bacteroides 99.18 0.50 0.00
maxbin_output.022 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Barnesiellaceae;g__Barnesiella;s__Barnesiella 95.85 0.38 0.00
maxbin_output.027 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Butyricimonas;s__Butyricimonas 94.98 2.31 33.33
maxbin_output.031 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Odoribacter;s__Odoribacter 88.51 2.69 0.00
maxbin_output.007 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 100.00 5.74 0.00
maxbin_output.012 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Tidjanibacter;s__Tidjanibacter 99.52 1.44 0.00
maxbin_output.023 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__;s__ 95.97 0.67 0.00
report/data/bwa_merged_metaspades_hybrid_HQ_bins.txt deleted 100644 → 0
+ 0
− 27
View file @ e004fdf2
bwa_merged_metaspades_hybrid.metabat.58 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__Eubacterium_R;s__Eubacterium_R 97.32 0.00 0.00
maxbin_output.020 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Ruminococcaceae;g__Ruminococcus_D;s__Ruminococcus_D 98.63 0.48 0.00
bwa_merged_metaspades_hybrid.metabat.26 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Ruminococcaceae;g__Faecalibacterium;s__Faecalibacterium 94.29 0.00 0.00
bwa_merged_metaspades_hybrid.metabat.6 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Oscillospiraceae;g__Oscillibacter;s__Oscillibacter 87.58 1.85 75.00
bwa_merged_metaspades_hybrid.metabat.25 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__TANB77;f__CAG-508;g__CAG-492;s__CAG-492 71.52 5.01 7.69
bwa_merged_metaspades_hybrid.metabat.22 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Acetatifactor;s__Acetatifactor 97.58 1.45 0.00
bwa_merged_metaspades_hybrid.metabat.5_sub d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Faecalicatena;s__Faecalicatena 89.13 1.29 75.00
bwa_merged_metaspades_hybrid.metabat.17 d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Acidaminococcales;f__Acidaminococcaceae;g__Succiniclasticum;s__Succiniclasticum 78.13 0.00 0.00
maxbin_output.024 d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Acidaminococcales;f__Acidaminococcaceae;g__Phascolarctobacterium;s__Phascolarctobacterium 99.98 2.89 0.00
bwa_merged_metaspades_hybrid.metabat.54 d__Bacteria;p__Cyanobacteria;c__Vampirovibrionia;o__Gastranaerophilales;f__Gastranaerophilaceae;g__CAG-196;s__CAG-196 77.34 1.66 0.00
bwa_merged_metaspades_hybrid.metabat.34 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__UBA6398;s__UBA6398 88.41 1.28 33.33
maxbin_output.002 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides;s__Bacteroides 67.71 0.00 0.00
bwa_merged_metaspades_hybrid.metabat.43 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides_A;s__Bacteroides_A 86.91 1.67 40.00
bwa_merged_metaspades_hybrid.metabat.32_sub d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides_B;s__Bacteroides_B 92.95 1.67 50.00
bwa_merged_metaspades_hybrid.metabat.80 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Tannerellaceae;g__Parabacteroides;s__Parabacteroides 78.08 0.13 0.00
bwa_merged_metaspades_hybrid.metabat.55 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Barnesiellaceae;g__Barnesiella;s__Barnesiella 95.85 0.00 0.00
bwa_merged_metaspades_hybrid.metabat.2 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Coprobacteraceae;g__Coprobacter;s__Coprobacter 91.32 0.57 0.00
bwa_merged_metaspades_hybrid.metabat.45 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Butyricimonas;s__Butyricimonas 97.49 1.41 40.00
maxbin_output.038_sub d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Odoribacter;s__Odoribacter 87.97 3.49 0.00
bwa_merged_metaspades_hybrid.metabat.42 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 83.17 0.00 0.00
maxbin_output.029 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 87.67 5.50 27.27
maxbin_output.023 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 98.53 5.53 66.67
maxbin_output.014 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Tidjanibacter;s__Tidjanibacter 99.52 1.44 0.00
bwa_merged_metaspades_hybrid.metabat.73 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes_A;s__Alistipes_A 80.91 1.12 0.00
bwa_merged_metaspades_hybrid.metabat.57 d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Parasutterella;s__Parasutterella 81.43 1.25 40.00
maxbin_output.026 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__;s__ 93.96 0.67 0.00
bwa_merged_metaspades_hybrid.metabat.63 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Oscillospiraceae;g__CAG-103;s__ 79.47 0.75 66.67
report/data/bwa_sr_metaspades_hybrid_HQ_bins.txt deleted 100644 → 0
+ 0
− 26
View file @ e004fdf2
bwa_sr_metaspades_hybrid.metabat.37 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__Eubacterium_R;s__Eubacterium_R 97.32 0.00 0.00
maxbin_output.014 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Ruminococcaceae;g__Ruminococcus_D;s__Ruminococcus_D 98.63 0.00 0.00
bwa_sr_metaspades_hybrid.metabat.14 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Ruminococcaceae;g__Faecalibacterium;s__Faecalibacterium 94.29 0.00 0.00
bwa_sr_metaspades_hybrid.metabat.7 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Oscillospiraceae;g__Oscillibacter;s__Oscillibacter 87.58 1.85 75.00
bwa_sr_metaspades_hybrid.metabat.27 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__TANB77;f__CAG-508;g__CAG-492;s__CAG-492 71.52 6.06 6.25
bwa_sr_metaspades_hybrid.metabat.24 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Acetatifactor;s__Acetatifactor 98.31 1.93 16.67
bwa_sr_metaspades_hybrid.metabat.6 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Faecalicatena;s__Faecalicatena 94.39 1.29 75.00
bwa_sr_metaspades_hybrid.metabat.32_sub d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Acidaminococcales;f__Acidaminococcaceae;g__Succiniclasticum;s__Succiniclasticum 76.94 0.00 0.00
maxbin_output.020 d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Acidaminococcales;f__Acidaminococcaceae;g__Phascolarctobacterium;s__Phascolarctobacterium 99.98 2.89 0.00
bwa_sr_metaspades_hybrid.metabat.33 d__Bacteria;p__Cyanobacteria;c__Vampirovibrionia;o__Gastranaerophilales;f__Gastranaerophilaceae;g__CAG-196;s__CAG-196 77.34 0.38 0.00
bwa_sr_metaspades_hybrid.metabat.42 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__UBA6398;s__UBA6398 88.41 1.28 33.33
maxbin_output.001 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides;s__Bacteroides 99.23 0.50 0.00
maxbin_output.004 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides_B;s__Bacteroides_B 91.91 4.67 21.05
maxbin_output.016 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Tannerellaceae;g__Parabacteroides;s__Parabacteroides 94.94 1.63 0.00
bwa_sr_metaspades_hybrid.metabat.28 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Barnesiellaceae;g__Barnesiella;s__Barnesiella 95.85 0.00 0.00
bwa_sr_metaspades_hybrid.metabat.3 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Coprobacteraceae;g__Coprobacter;s__Coprobacter 91.32 0.38 0.00
bwa_sr_metaspades_hybrid.metabat.46 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Butyricimonas;s__Butyricimonas 97.49 1.41 40.00
maxbin_output.034 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Odoribacter;s__Odoribacter 91.92 7.36 0.00
maxbin_output.005 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 99.52 0.48 0.00
bwa_sr_metaspades_hybrid.metabat.50_sub d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 98.04 1.44 66.67
maxbin_output.011 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Tidjanibacter;s__Tidjanibacter 99.52 1.92 0.00
bwa_sr_metaspades_hybrid.metabat.71 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes_A;s__Alistipes_A 80.91 1.12 0.00
bwa_sr_metaspades_hybrid.metabat.55_sub d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Parasutterella;s__Parasutterella 81.43 1.25 40.00
maxbin_output.022 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__;s__ 95.97 0.67 0.00
bwa_sr_metaspades_hybrid.metabat.53 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Oscillospiraceae;g__CAG-170;s__ 90.71 5.50 25.00
bwa_sr_metaspades_hybrid.metabat.59 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Oscillospiraceae;g__CAG-103;s__ 84.75 0.73 50.00
report/data/flye_HQ_bins.txt deleted 100644 → 0
+ 0
− 1
View file @ e004fdf2
maxbin_output.001 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides;s__Bacteroides 67.45 2.58 55.56
report/data/mappability_over_1000bp.txt deleted 100644 → 0
+ 0
− 11
View file @ e004fdf2
sample mapped_reads total percent_mapped
flye_counts.txt 7144171 8351240 85.5462
hybrid_bwa_lr_counts.txt 7347760 8299732 88.5301
hybrid_bwa_merged_counts.txt 57368285 60114498 95.4317
hybrid_bwa_sr_counts.txt 50020525 51814766 96.5372
hybrid_metaT_sr_counts.txt 48979035 78868203 62.1024
hybrid_mmi_lr_counts.txt 7044114 8402725 83.8313
hybrid_mmi_merged_counts.txt 59404046 63790314 93.1239
hybrid_mmi_sr_counts.txt 52359932 55387589 94.5337
megahit_counts.txt 48800047 51826913 94.1597
megahit_metaT_sr_counts.txt 45584230 78531498 58.0458
report/data/mappability_over_1500bp.txt deleted 100644 → 0
+ 0
− 11
View file @ e004fdf2
sample mapped_reads total percent_mapped
flye_counts.txt 7130256 8351240 85.3796
hybrid_bwa_lr_counts.txt 7265218 8299732 87.5356
hybrid_bwa_merged_counts.txt 56903252 60114498 94.6581
hybrid_bwa_sr_counts.txt 49638034 51814766 95.799
hybrid_metaT_sr_counts.txt 45743715 78868203 58.0002
hybrid_mmi_lr_counts.txt 6953663 8402725 82.7549
hybrid_mmi_merged_counts.txt 58859670 63790314 92.2705
hybrid_mmi_sr_counts.txt 51906007 55387589 93.7141
megahit_counts.txt 47762664 51826913 92.158
megahit_metaT_sr_counts.txt 36898046 78531498 46.985
report/data/mappability_over_2000bp.txt deleted 100644 → 0
+ 0
− 11
View file @ e004fdf2
sample mapped_reads total percent_mapped
flye_counts.txt 7121527 8351240 85.2751
hybrid_bwa_lr_counts.txt 7200635 8299732 86.7574
hybrid_bwa_merged_counts.txt 56512238 60114498 94.0077
hybrid_bwa_sr_counts.txt 49311603 51814766 95.169
hybrid_metaT_sr_counts.txt 42538190 78868203 53.9358
hybrid_mmi_lr_counts.txt 6887067 8402725 81.9623
hybrid_mmi_merged_counts.txt 58426554 63790314 91.5916
hybrid_mmi_sr_counts.txt 51539487 55387589 93.0524
megahit_counts.txt 46946179 51826913 90.5826
megahit_metaT_sr_counts.txt 32506911 78531498 41.3935
report/data/mappability_over_5000bp.txt deleted 100644 → 0
+ 0
− 11
View file @ e004fdf2
sample mapped_reads total percent_mapped
flye_counts.txt 7066935 8351240 84.6214
hybrid_bwa_lr_counts.txt 6934846 8299732 83.5551
hybrid_bwa_merged_counts.txt 54644383 60114498 90.9005
hybrid_bwa_sr_counts.txt 47709537 51814766 92.0771
hybrid_metaT_sr_counts.txt 29346178 78868203 37.2091
hybrid_mmi_lr_counts.txt 6611655 8402725 78.6847
hybrid_mmi_merged_counts.txt 56320978 63790314 88.2908
hybrid_mmi_sr_counts.txt 49709323 55387589 89.7481
megahit_counts.txt 43437290 51826913 83.8122
megahit_metaT_sr_counts.txt 19650549 78531498 25.0225
report/data/megahit_HQ_bins.txt deleted 100644 → 0
+ 0
− 13
View file @ e004fdf2
megahit.metabat.12 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__Eubacterium_R;s__Eubacterium_R 98.66 1.68 0.00
megahit.metabat.38 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Ruminococcaceae;g__Ruminococcus_D;s__Ruminococcus_D 97.26 0.68 100.00
megahit.metabat.31 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Acetatifactor;s__Acetatifactor 98.87 1.81 28.57
megahit.metabat.18 d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Acidaminococcales;f__Acidaminococcaceae;g__Phascolarctobacterium;s__Phascolarctobacterium 98.18 1.70 0.00
maxbin_output.002 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides;s__Bacteroides 83.95 2.11 20.00
megahit.metabat.5 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Tannerellaceae;g__Parabacteroides;s__Parabacteroides 91.15 1.09 75.00
maxbin_output.027 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Barnesiellaceae;g__Barnesiella;s__Barnesiella 92.10 1.57 42.86
megahit.metabat.36 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Coprobacteraceae;g__Coprobacter;s__Coprobacter 98.11 0.77 0.00
megahit.metabat.13_sub d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Butyricimonas;s__Butyricimonas 80.54 2.96 14.29
maxbin_output.009 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 96.10 4.90 52.94
maxbin_output.023 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 92.77 6.96 42.86
megahit.metabat.43 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Tidjanibacter;s__Tidjanibacter 99.52 0.24 100.00
megahit.metabat.45 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__;s__ 93.51 0.67 0.00
report/data/mmi_lr_metaspades_hybrid_HQ_bins.txt deleted 100644 → 0
+ 0
− 12
View file @ e004fdf2
maxbin_output.025 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__Eubacterium_R;s__Eubacterium_R 97.32 1.81 0.00
maxbin_output.022 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Ruminococcaceae;g__Ruminococcus_D;s__Ruminococcus_D 98.63 0.00 0.00
maxbin_output.016 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Acetatifactor;s__Acetatifactor 97.58 4.35 18.18
maxbin_output.021 d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Acidaminococcales;f__Acidaminococcaceae;g__Phascolarctobacterium;s__Phascolarctobacterium 99.98 2.89 0.00
maxbin_output.001 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides;s__Bacteroides 99.23 0.50 0.00
maxbin_output.023 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Barnesiellaceae;g__Barnesiella;s__Barnesiella 95.85 0.38 0.00
maxbin_output.028 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Butyricimonas;s__Butyricimonas 94.98 2.84 28.57
maxbin_output.033 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Odoribacter;s__Odoribacter 88.78 2.15 0.00
maxbin_output.007 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 99.52 0.48 0.00
maxbin_output.020 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 98.53 2.88 33.33
maxbin_output.012 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Tidjanibacter;s__Tidjanibacter 99.52 1.44 0.00
maxbin_output.024 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__;s__ 95.97 0.67 0.00
report/data/mmi_merged_metaspades_hybrid_HQ_bins.txt deleted 100644 → 0
+ 0
− 26
View file @ e004fdf2
mmi_merged_metaspades_hybrid.metabat.59 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__Eubacterium_R;s__Eubacterium_R 97.32 0.00 0.00
maxbin_output.017 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Ruminococcaceae;g__Ruminococcus_D;s__Ruminococcus_D 98.63 0.00 0.00
mmi_merged_metaspades_hybrid.metabat.69 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Ruminococcaceae;g__Faecalibacterium;s__Faecalibacterium 94.29 0.00 0.00
mmi_merged_metaspades_hybrid.metabat.49 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Oscillospiraceae;g__Oscillibacter;s__Oscillibacter 87.58 1.85 75.00
mmi_merged_metaspades_hybrid.metabat.20 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__TANB77;f__CAG-508;g__CAG-492;s__CAG-492 70.94 5.24 8.33
mmi_merged_metaspades_hybrid.metabat.73 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Acetatifactor;s__Acetatifactor 98.31 1.93 16.67
mmi_merged_metaspades_hybrid.metabat.28 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Faecalicatena;s__Faecalicatena 90.88 2.07 37.50
mmi_merged_metaspades_hybrid.metabat.47 d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Acidaminococcales;f__Acidaminococcaceae;g__Succiniclasticum;s__Succiniclasticum 78.13 0.00 0.00
maxbin_output.021 d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Acidaminococcales;f__Acidaminococcaceae;g__Phascolarctobacterium;s__Phascolarctobacterium 100.00 3.19 0.00
mmi_merged_metaspades_hybrid.metabat.17 d__Bacteria;p__Cyanobacteria;c__Vampirovibrionia;o__Gastranaerophilales;f__Gastranaerophilaceae;g__CAG-196;s__CAG-196 76.49 0.38 0.00
mmi_merged_metaspades_hybrid.metabat.65 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__UBA6398;s__UBA6398 87.30 1.28 33.33
mmi_merged_metaspades_hybrid.metabat.19 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides_A;s__Bacteroides_A 86.53 0.56 50.00
mmi_merged_metaspades_hybrid.metabat.82 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides_B;s__Bacteroides_B 93.32 8.74 20.00
mmi_merged_metaspades_hybrid.metabat.46 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Barnesiellaceae;g__Barnesiella;s__Barnesiella 95.85 0.00 0.00
mmi_merged_metaspades_hybrid.metabat.5 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Coprobacteraceae;g__Coprobacter;s__Coprobacter 91.32 0.57 0.00
maxbin_output.029 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Butyricimonas;s__Butyricimonas 92.29 0.69 66.67
mmi_merged_metaspades_hybrid.metabat.72_sub d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Odoribacter;s__Odoribacter 88.78 3.23 0.00
mmi_merged_metaspades_hybrid.metabat.40 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 83.17 0.00 0.00
maxbin_output.025_sub d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 92.51 7.10 26.92
mmi_merged_metaspades_hybrid.metabat.48_sub d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 98.04 1.44 66.67
maxbin_output.012 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Tidjanibacter;s__Tidjanibacter 99.52 1.44 0.00
mmi_merged_metaspades_hybrid.metabat.64 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes_A;s__Alistipes_A 80.91 1.12 0.00
mmi_merged_metaspades_hybrid.metabat.23 d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Parasutterella;s__Parasutterella 81.43 1.25 40.00
maxbin_output.023 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__;s__ 95.97 0.67 0.00
maxbin_output.035_sub d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Oscillospiraceae;g__CAG-170;s__ 85.61 5.61 21.43
mmi_merged_metaspades_hybrid.metabat.56 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Oscillospiraceae;g__CAG-103;s__ 85.42 1.40 33.33
report/data/mmi_sr_metaspades_hybrid_HQ_bins.txt deleted 100644 → 0
+ 0
− 27
View file @ e004fdf2
mmi_sr_metaspades_hybrid.metabat.61 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__Eubacterium_R;s__Eubacterium_R 97.32 0.00 0.00
maxbin_output.016 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Ruminococcaceae;g__Ruminococcus_D;s__Ruminococcus_D 98.63 0.00 0.00
mmi_sr_metaspades_hybrid.metabat.72 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Ruminococcaceae;g__Faecalibacterium;s__Faecalibacterium 94.29 0.00 0.00
mmi_sr_metaspades_hybrid.metabat.50 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Oscillospiraceae;g__Oscillibacter;s__Oscillibacter 87.58 1.85 75.00
mmi_sr_metaspades_hybrid.metabat.82 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__TANB77;f__CAG-508;g__CAG-492;s__CAG-492 71.52 7.11 6.25
mmi_sr_metaspades_hybrid.metabat.57 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Acetatifactor;s__Acetatifactor 98.31 1.45 0.00
mmi_sr_metaspades_hybrid.metabat.10 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Lachnospirales;f__Lachnospiraceae;g__Faecalicatena;s__Faecalicatena 90.88 1.68 50.00
mmi_sr_metaspades_hybrid.metabat.48_sub d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Acidaminococcales;f__Acidaminococcaceae;g__Succiniclasticum;s__Succiniclasticum 77.53 0.00 0.00
maxbin_output.022 d__Bacteria;p__Firmicutes_C;c__Negativicutes;o__Acidaminococcales;f__Acidaminococcaceae;g__Phascolarctobacterium;s__Phascolarctobacterium 99.98 2.89 0.00
mmi_sr_metaspades_hybrid.metabat.45 d__Bacteria;p__Cyanobacteria;c__Vampirovibrionia;o__Gastranaerophilales;f__Gastranaerophilaceae;g__CAG-196;s__CAG-196 77.34 0.81 0.00
mmi_sr_metaspades_hybrid.metabat.67 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__UBA6398;s__UBA6398 87.30 1.28 33.33
maxbin_output.001 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides;s__Bacteroides 99.23 0.50 0.00
mmi_sr_metaspades_hybrid.metabat.41 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides_A;s__Bacteroides_A 86.53 0.56 50.00
mmi_sr_metaspades_hybrid.metabat.80 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Bacteroidaceae;g__Bacteroides_B;s__Bacteroides_B 93.32 9.11 21.62
maxbin_output.019_sub d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Tannerellaceae;g__Parabacteroides;s__Parabacteroides 92.63 4.46 22.22
maxbin_output.025 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Barnesiellaceae;g__Barnesiella;s__Barnesiella 99.25 0.38 0.00
mmi_sr_metaspades_hybrid.metabat.5 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Coprobacteraceae;g__Coprobacter;s__Coprobacter 91.32 0.57 0.00
mmi_sr_metaspades_hybrid.metabat.29 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Butyricimonas;s__Butyricimonas 98.03 1.41 40.00
mmi_sr_metaspades_hybrid.metabat.71 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Marinifilaceae;g__Odoribacter;s__Odoribacter 90.39 2.69 0.00
maxbin_output.006 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 99.52 0.48 0.00
mmi_sr_metaspades_hybrid.metabat.49_sub d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes;s__Alistipes 98.04 1.44 66.67
mmi_sr_metaspades_hybrid.metabat.12 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Tidjanibacter;s__Tidjanibacter 83.65 0.00 0.00
mmi_sr_metaspades_hybrid.metabat.1 d__Bacteria;p__Bacteroidota;c__Bacteroidia;o__Bacteroidales;f__Rikenellaceae;g__Alistipes_A;s__Alistipes_A 80.91 1.12 0.00
mmi_sr_metaspades_hybrid.metabat.26 d__Bacteria;p__Proteobacteria;c__Gammaproteobacteria;o__Burkholderiales;f__Burkholderiaceae;g__Parasutterella;s__Parasutterella 81.43 1.25 40.00
mmi_sr_metaspades_hybrid.metabat.9 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Acutalibacteraceae;g__;s__ 93.96 0.67 0.00
mmi_sr_metaspades_hybrid.metabat.47 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Oscillospiraceae;g__CAG-170;s__ 89.62 4.36 25.00
mmi_sr_metaspades_hybrid.metabat.56 d__Bacteria;p__Firmicutes_A;c__Clostridia;o__Oscillospirales;f__Oscillospiraceae;g__CAG-103;s__ 85.51 0.75 66.67
report/data/overlap_sizes.txt deleted 100644 → 0
+ 0
− 11
View file @ e004fdf2
165287 flye
250742 megahit
365813 metaspades
341322 metaspades_hybrid
109382 flye_megahit
112740 flye_metaspades_hybrid
110600 flye_metaspades
196581 megahit_metaspades_hybrid
214396 megahit_metaspades
326458 metaspades_metaspades_hybrid
101535 flye_megahit_metaspades_hybrid_metaspades
report/data/total.txt deleted 100644 → 0
+ 0
− 4
View file @ e004fdf2
flye 165287
megahit 250742
metaspades 365813
metaspades_hybrid 341322
report/src_SBB/2019_GDB_partial_genes.R deleted 100644 → 0
+ 0
− 33
View file @ e004fdf2
setwd("~/Documents/R_data/nanopore_ONT/")
library(tidyverse)
partial <- read.table("2019_GDB_protein_partial_genes.txt", header = TRUE)
# pivoting the dataset
long_merged <- pivot_longer(partial, cols=c(-tool), names_to = "group", values_to = "counts")
# setting a common theme
theme_set(theme_bw() +
theme(strip.background = element_rect(colour = "black", fill = "white"), strip.text = element_text(size=17, family="Helvetica")) +
theme(axis.text.x = element_text(angle = 90, size = 18, family = "Helvetica", face = "bold", color = "black"),
axis.text.y = element_text(size = 18, family = "Helvetica"),
axis.title.y = element_text(size = 18, face = "bold", family = "Helvetica"),
axis.title.x=element_text(size = 18, face = "bold", family = "Helvetica"),
axis.ticks.x=element_blank()) +
theme(plot.title = element_text(hjust = 0.5)) +
theme(legend.text = element_text(size = 18, family = "Helvetica"),
legend.title = element_text(size = 18, family = "Helvetica", face = "bold"), legend.direction = "vertical", legend.box = "vertical"))
# Basic plots
install.packages("devtools")
library(devtools)
install_github("kassambara/easyGgplot2")
library(easyGgplot2)
data_long <- long_merged
ggplot(data_long) +
geom_bar(aes(fill=group, y=counts, x=tool), stat = "identity", position=position_dodge()) + scale_fill_manual("assembly", values = c("metaspades" = "grey", "metaspades_hybrid" = "dodgerblue2"))
ggplot2.barplot(data=data_long, xName='tool', yName='counts',
groupName='group', position=position_dodge())
report/src_SBB/MAGS_2019_GDB_analyses.R deleted 100644 → 0
+ 0
− 133
View file @ e004fdf2
# Assessing the number and kind of bins found due to the different assembly and mapping methods used for the 2019_GDB ONT analsyes
setwd("~/Documents/R_data/nanopore_ONT/")
library(tidyverse)
# importing files and renaming columns
bwa_lr_MH <- read.table("bwa_lr_metaspades_hybrid_HQ_bins.txt", header = FALSE) %>% rename(bin = V1, taxonomy = V2, completion = V3, contamination = V4, strain_heterogeneity = V5)
bwa_sr_MH <- read.table("bwa_sr_metaspades_hybrid_HQ_bins.txt", header = FALSE) %>% rename(bin = V1, taxonomy = V2, completion = V3, contamination = V4, strain_heterogeneity = V5)
bwa_merged_MH <- read.table("bwa_merged_metaspades_hybrid_HQ_bins.txt", header = FALSE) %>% rename(bin = V1, taxonomy = V2, completion = V3, contamination = V4, strain_heterogeneity = V5)
mmi_lr_MH <- read.table("mmi_lr_metaspades_hybrid_HQ_bins.txt", header = FALSE) %>% rename(bin = V1, taxonomy = V2, completion = V3, contamination = V4, strain_heterogeneity = V5)
mmi_sr_MH <- read.table("mmi_sr_metaspades_hybrid_HQ_bins.txt", header = FALSE) %>% rename(bin = V1, taxonomy = V2, completion = V3, contamination = V4, strain_heterogeneity = V5)
mmi_merged_MH <- read.table("mmi_merged_metaspades_hybrid_HQ_bins.txt", header = FALSE) %>% rename(bin = V1, taxonomy = V2, completion = V3, contamination = V4, strain_heterogeneity = V5)
flye <- read.table("flye_HQ_bins.txt", header = FALSE) %>% rename(bin = V1, taxonomy = V2, completion = V3, contamination = V4, strain_heterogeneity = V5)
megahit <- read.table("megahit_HQ_bins.txt", header = FALSE) %>% rename(bin = V1, taxonomy = V2, completion = V3, contamination = V4, strain_heterogeneity = V5)
# removing the "bin" column and separating taxonomy into individual columns
bwa_lr_MH_edited <- bwa_lr_MH %>% select(-bin) %>%
separate(taxonomy, c("Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species"), sep = ";", remove = FALSE)
bwa_sr_MH_edited <- bwa_sr_MH %>% select(-bin) %>%
separate(taxonomy, c("Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species"), sep = ";", remove = FALSE)
bwa_merged_MH_edited <- bwa_merged_MH %>% select(-bin) %>%
separate(taxonomy, c("Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species"), sep = ";", remove = FALSE)
mmi_lr_MH_edited <- mmi_lr_MH %>% select(-bin) %>%
separate(taxonomy, c("Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species"), sep = ";", remove = FALSE)
mmi_sr_MH_edited <- mmi_sr_MH %>% select(-bin) %>%
separate(taxonomy, c("Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species"), sep = ";", remove = FALSE)
mmi_merged_MH_edited <- mmi_merged_MH %>% select(-bin) %>%
separate(taxonomy, c("Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species"), sep = ";", remove = FALSE)
flye_edited <- flye %>% select(-bin) %>%
separate(taxonomy, c("Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species"), sep = ";", remove = FALSE)
megahit_edited <- megahit %>% select(-bin) %>%
separate(taxonomy, c("Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species"), sep = ";", remove = FALSE)
# Keeping only the Family and Genus columns and adding family if the latter is missing
bwa_lr_tax <- bwa_lr_MH_edited %>% select(Family, Genus, completion, contamination, strain_heterogeneity) %>% mutate(Genus = gsub("g__", "", Genus), Family = gsub("f__", "", Family)) %>% mutate_if(is.character, list(~na_if(.,"")))
bwa_sr_tax <- bwa_sr_MH_edited %>% select(Family, Genus, completion, contamination, strain_heterogeneity) %>% mutate(Genus = gsub("g__", "", Genus), Family = gsub("f__", "", Family)) %>% mutate_if(is.character, list(~na_if(.,"")))
bwa_merged_tax <- bwa_merged_MH_edited %>% select(Family, Genus, completion, contamination, strain_heterogeneity) %>% mutate(Genus = gsub("g__", "", Genus), Family = gsub("f__", "", Family)) %>% mutate_if(is.character, list(~na_if(.,"")))
mmi_lr_tax <- mmi_lr_MH_edited %>% select(Family, Genus, completion, contamination, strain_heterogeneity) %>% mutate(Genus = gsub("g__", "", Genus), Family = gsub("f__", "", Family)) %>% mutate_if(is.character, list(~na_if(.,"")))
mmi_sr_tax <- mmi_sr_MH_edited %>% select(Family, Genus, completion, contamination, strain_heterogeneity) %>% mutate(Genus = gsub("g__", "", Genus), Family = gsub("f__", "", Family)) %>% mutate_if(is.character, list(~na_if(.,"")))
mmi_merged_tax <- mmi_merged_MH_edited %>% select(Family, Genus, completion, contamination, strain_heterogeneity) %>% mutate(Genus = gsub("g__", "", Genus), Family = gsub("f__", "", Family)) %>% mutate_if(is.character, list(~na_if(.,"")))
flye_tax <- flye_edited %>% select(Family, Genus, completion, contamination, strain_heterogeneity) %>% mutate(Genus = gsub("g__", "", Genus), Family = gsub("f__", "", Family)) %>% mutate_if(is.character, list(~na_if(.,"")))
megahit_tax <- megahit_edited %>% select(Family, Genus, completion, contamination, strain_heterogeneity) %>% mutate(Genus = gsub("g__", "", Genus), Family = gsub("f__", "", Family)) %>% mutate_if(is.character, list(~na_if(.,"")))
# code replacing NAs in 'Genus' with the values from adjacent column 'Family'
bwa_lr_tax$Genus[is.na(bwa_lr_tax$Genus)] <- bwa_lr_tax$Family[is.na(bwa_lr_tax$Genus)]
bwa_sr_tax$Genus[is.na(bwa_sr_tax$Genus)] <- bwa_sr_tax$Family[is.na(bwa_sr_tax$Genus)]
bwa_merged_tax$Genus[is.na(bwa_merged_tax$Genus)] <- bwa_merged_tax$Family[is.na(bwa_merged_tax$Genus)]
mmi_lr_tax$Genus[is.na(mmi_lr_tax$Genus)] <- mmi_lr_tax$Family[is.na(mmi_lr_tax$Genus)]
mmi_sr_tax$Genus[is.na(mmi_sr_tax$Genus)] <- mmi_sr_tax$Family[is.na(mmi_sr_tax$Genus)]
mmi_merged_tax$Genus[is.na(mmi_merged_tax$Genus)] <- mmi_merged_tax$Family[is.na(mmi_merged_tax$Genus)]
flye_tax$Genus[is.na(flye_tax$Genus)] <- flye_tax$Family[is.na(flye_tax$Genus)]
megahit_tax$Genus[is.na(megahit_tax$Genus)] <- megahit_tax$Family[is.na(megahit_tax$Genus)]
# making the Genus names unique for easier tracking and merging downstream
bwa_lr_tax <- bwa_lr_tax %>% mutate(Genus = make.unique(Genus)) %>% select(-Family)
bwa_sr_tax <- bwa_sr_tax %>% mutate(Genus = make.unique(Genus)) %>% select(-Family)
bwa_merged_tax <- bwa_merged_tax %>% mutate(Genus = make.unique(Genus)) %>% select(-Family)
mmi_lr_tax <- mmi_lr_tax %>% mutate(Genus = make.unique(Genus)) %>% select(-Family)
mmi_sr_tax <- mmi_sr_tax %>% mutate(Genus = make.unique(Genus)) %>% select(-Family)
mmi_merged_tax <- mmi_merged_tax %>% mutate(Genus = make.unique(Genus)) %>% select(-Family)
flye_tax <- flye_tax %>% mutate(Genus = make.unique(Genus)) %>% select(-Family)
megahit_tax <- megahit_tax %>% mutate(Genus = make.unique(Genus)) %>% select(-Family)
# combining all samples based on the Genus, and making additional column with sample name
bwa_lr_final <- bwa_lr_tax %>% mutate(Genus = make.unique(Genus)) %>% select(Genus) %>% mutate(bwa_lr = Genus)
bwa_sr_final <- bwa_sr_tax %>% mutate(Genus = make.unique(Genus)) %>% select(Genus) %>% mutate(bwa_sr = Genus)
bwa_merged_final <- bwa_merged_tax %>% mutate(Genus = make.unique(Genus)) %>% select(Genus) %>% mutate(bwa_merged = Genus)
mmi_lr_final <- mmi_lr_tax %>% mutate(Genus = make.unique(Genus)) %>% select(Genus) %>% mutate(mmi_lr = Genus)
mmi_sr_final <- mmi_sr_tax %>% mutate(Genus = make.unique(Genus)) %>% select(Genus) %>% mutate(mmi_sr = Genus)
mmi_merged_final <- mmi_merged_tax %>% mutate(Genus = make.unique(Genus)) %>% select(Genus) %>% mutate(mmi_merged = Genus)
flye_final <- flye_tax %>% mutate(Genus = make.unique(Genus)) %>% select(Genus) %>% mutate(flye = Genus)
megahit_final<- megahit_tax %>% mutate(Genus = make.unique(Genus)) %>% select(Genus) %>% mutate(megahit = Genus)
merged_2019_tax <- full_join(x = bwa_lr_final, y = bwa_sr_final,
by = "Genus") %>%
full_join( x = ., y = bwa_merged_final, by = "Genus") %>%
full_join( x = ., y = mmi_lr_final, by = "Genus") %>%
full_join( x = ., y = mmi_sr_final, by = "Genus") %>%
full_join( x = ., y = mmi_merged_final, by = "Genus") %>%
full_join( x = ., y = flye_final, by = "Genus")%>%
full_join( x = ., y = megahit_final, by = "Genus")
# %>% arrange(Genus) %>% replace(is.na(.), 0)
long_tax <- pivot_longer(merged_2019_tax, cols = bwa_lr:megahit, names_to = "samples")
# setting a common theme
theme_set(theme_bw() +
theme(strip.background = element_rect(colour = "black", fill = "white"), strip.text = element_text(size=17, family="Helvetica")) +
theme(axis.text.x = element_text(angle = 90, size = 18, family = "Helvetica"),
axis.text.y = element_text(size = 18, family = "Helvetica"),
axis.title.y = element_text(size = 18, face = "bold", family = "Helvetica"),
axis.title.x=element_text(size = 18, face = "bold", family = "Helvetica"),
axis.ticks.x=element_blank()) +
theme(plot.title = element_text(hjust = 0.5)) +
theme(legend.text = element_text(size = 18, family = "Helvetica"),
legend.title = element_text(size = 18, family = "Helvetica", face = "bold"), legend.direction = "vertical", legend.box = "vertical"))
# plotting
ggplot(long_tax, aes(x = samples, y = value))
long_tax <- long_tax %>% drop_na()
long_tax %>%
# group_by(Genus) %>%
# mutate(rescale = scales::rescale(Sqrt.abundance)) %>%
ggplot(., aes(x = factor(samples), y = value)) +
geom_tile(aes(fill = Genus), color = "white") +
# scale_alpha(range = c(0.1, 1)) +
theme(legend.position = "none") +
# xlab(label = "Library Preparation Method") +
facet_grid(~ samples, switch = "x", scales = "free_x", space = "free_x") +
# scale_fill_gradient(name = "Sqrt(Abundance)",
# low = "#FFFFFF",
# high = "#012345") +
theme(strip.placement = "outside") +
theme(axis.text.x = element_blank(),
axis.text.y = element_text(color = scales::hue_pal()(length(levels(as.factor(long_tax$Genus)))))) +
ggtitle(label = "2019_GDB - MAGs")
# Summary table
View(merged_2019_tax)
ggplot(data.frame(long_tax), aes(x=samples, fill=Genus)) +
geom_bar(position = "fill")
#+ scale_fill_brewer(palette = "Dark2")
report/src_SBB/mappability_index-2020-05-26.R deleted 100644 → 0
+ 0
− 144
View file @ e004fdf2
setwd("~/Documents/R_data/nanopore_ONT/")
library(tidyverse)
map_1000 <- read.delim("mappability_over_1000bp.txt") %>% separate(sample, c("sample", "mapped_reads", "total", "percent_mapped"), sep = " ", remove = FALSE) %>% mutate(sample = str_replace_all(sample, "_counts.txt", ""))
map_1000$mapped_reads = NULL
map_1000$total = NULL
map_1500 <- read.delim("mappability_over_1500bp.txt") %>% separate(sample, c("sample", "mapped_reads", "total", "percent_mapped"), sep = " ", remove = FALSE) %>% mutate(sample = str_replace_all(sample, "_counts.txt", ""))
map_1500$mapped_reads = NULL
map_1500$total = NULL
map_2000 <- read.delim("mappability_over_2000bp.txt") %>% separate(sample, c("sample", "mapped_reads", "total", "percent_mapped"), sep = " ", remove = FALSE) %>% mutate(sample = str_replace_all(sample, "_counts.txt", ""))
map_2000$mapped_reads = NULL
map_2000$total = NULL
map_5000 <- read.delim("mappability_over_5000bp.txt") %>% separate(sample, c("sample", "mapped_reads", "total", "percent_mapped"), sep = " ", remove = FALSE) %>% mutate(sample = str_replace_all(sample, "_counts.txt", ""))
map_5000$mapped_reads = NULL
map_5000$total = NULL
# merging all the files
merged_mappability <- full_join(x = map_1000, y = map_1500,by = "sample") %>%
full_join( x = ., y = map_2000, by = "sample") %>%
full_join( x = ., y = map_5000, by = "sample")
columns <- c("samples", "bp1000", "bp1500", "bp2000", "bp5000")
colnames(merged_mappability) <- columns
write.csv(merged_mappability, "merged_mappability_index.csv", quote = FALSE)
# long format
map_long <- pivot_longer(merged_mappability, cols = bp1000:bp5000, names_to = "cutoff", values_to = "count") %>% mutate(samples = str_replace_all(samples, "_counts.txt", ""))
samps <- c("flye", "megahit", "hybrid_bwa_sr", "hybrid_bwa_lr", "hybrid_bwa_merged",
"hybrid_mmi_sr", "hybrid_mmi_lr", "hybrid_mmi_merged", "megahit_metaT_sr", "hybrid_metaT_sr")
write.csv(map_long, "merged_mappability_long_format.csv", quote = FALSE)
### Plotting ###
# setting a common theme for plotting
theme_set(theme_bw() +
theme(strip.background = element_rect(colour = "black", fill = "white"), strip.text = element_text(size=17, family="Helvetica")) +
theme(axis.text.x = element_text(angle = 90, size = 18, family = "Helvetica"),
axis.text.y = element_text(size = 18, family = "Helvetica"),
axis.title.y = element_text(size = 18, face = "bold", family = "Helvetica"),
axis.title.x=element_text(size = 18, face = "bold", family = "Helvetica"),
axis.ticks.x=element_blank()) +
theme(plot.title = element_text(hjust = 0.5)) +
theme(legend.text = element_text(size = 18, family = "Helvetica"),
legend.title = element_text(size = 18, family = "Helvetica", face = "bold"), legend.direction = "vertical", legend.box = "vertical"))
# Bubble plot
map_long %>%
mutate(samples = factor(samples, levels = samps)) %>%
ggplot(aes(x=samples, y=cutoff, size = as.numeric(count), color = cutoff)) +
geom_point(alpha=0.7) +
scale_size(range = c(.1, 15), name="percent_mapped") +
facet_grid(.~factor(samples, levels = c("flye", "megahit", "hybrid_bwa_sr", "hybrid_bwa_lr", "hybrid_bwa_merged", "hybrid_mmi_sr", "hybrid_mmi_lr", "hybrid_mmi_merged", "megahit_metaT_sr", "hybrid_metaT_sr")), scales = "free_x", space = "free_x") +
guides(color = FALSE)
# without facet
map_long %>%
mutate(samples = factor(samples, levels = c("flye", "megahit", "hybrid_bwa_sr", "hybrid_bwa_lr", "hybrid_bwa_merged", "hybrid_mmi_sr", "hybrid_mmi_lr", "hybrid_mmi_merged", "megahit_metaT_sr", "hybrid_metaT_sr"))) %>%
ggplot(aes(x=samples, y=cutoff, size = as.numeric(count), color = cutoff)) +
geom_point(alpha=0.7) +
scale_size(range = c(.1, 15), name="percent_mapped") +
guides(color = FALSE)
# heatmap
ggplot(data = map_long, mapping = aes(x = samples,
y = cutoff,
fill = as.numeric(count))) +
geom_tile() +
xlab(label = "Sample") +
scale_fill_gradient(name = "percent_mapped",
low = "#FFFFFF",
high = "#012345")
# Color Brewer palette
library(viridis)
ggplot(map_long, aes(x = samples,
y = cutoff,
fill = as.numeric(count))) +
geom_tile() +
scale_fill_viridis(discrete=FALSE) +
theme_ipsum()
###############
# Tables in R #
###############
# Trying tables, from here: https://www.littlemissdata.com/blog/prettytables
library(data.table)
library(dplyr)
# install.packages("formattable")
library(formattable)
library(tidyr)
#Set a few color variables to make our table more visually appealing
customGreen0 = "#DeF7E9"
customGreen = "#71CA97"
customRed = "#ff7f7f"
# working with our "real data"
i1 <- merged_mappability %>% arrange(factor(samples, levels = c("flye", "megahit", "hybrid_bwa_sr", "hybrid_bwa_lr", "hybrid_bwa_merged", "hybrid_mmi_sr", "hybrid_mmi_lr", "hybrid_mmi_merged", "megahit_metaT_sr", "hybrid_metaT_sr")))
formattable(i1)
#1) First Data Table
formattable(i1,
align =c("l","c","c","c","c"),
list(`samples` = formatter(
"span", style = ~ style(color = "darkblue",font.weight = "bold"))
))
#2) Add the color mapping for all 2011 to 2016.
formattable(i1,
align =c("l","c","c","c","c"),
list(`samples` = formatter(
"span", style = ~ style(color = "darkblue",font.weight = "bold")),
`bp1000`= color_tile(customGreen, customGreen0),
`bp1500`= color_tile(customGreen, customGreen0),
`bp2000`= color_tile(customGreen, customGreen0),
`bp5000`= color_tile(customGreen, customGreen0)
))
#4) Add custom formatter to improvement over time
percent_formatter <-
formatter("span",
style = x ~ style(
font.weight = "bold",
color = ifelse(x >= 90, customGreen, ifelse(x < 5, customRed, ifelse(x <= 79,"grey", "blue")))))
formattable(i1,
align =c("l","c","c","c","c"),
list(`samples` = formatter(
"span", style = ~ style(color = "darkblue",font.weight = "bold")),
`bp1000`= percent_formatter,
`bp1500`= percent_formatter,
`bp2000`= percent_formatter,
`bp5000`= percent_formatter
))
#####
# Reactable format table
# https://glin.github.io/reactable/index.html
#install.packages("reactable")
library(reactable)
reactable(merged_mappability)
report/src_SBB/mmseq_upset_plot_w_metaspades.R deleted 100644 → 0
+ 0
− 130
View file @ e004fdf2
library(cowplot)
library(tidyverse)
setwd("~/Documents/R_data/nanopore_ONT/")
overlap_sizes <- read.table("~/Documents/R_data/nanopore_ONT/overlap_sizes.txt")
Total <- read.table("~/Documents/R_data/nanopore_ONT/total.txt")
sets <- c("flye", "megahit", "metaspades", "metaspades_hybrid")
category <- c(
"flye",
"megahit",
"metaspades",
"metaspades_hybrid",
"flye_megahit",
"flye_metaspades",
"flye_metaspades_hybrid",
"megahit_metaspades",
"megahit_metaspades_hybrid",
"metaspades_metaspades_hybrid",
"flye_megahit_metaspades_metaspades_hybrid"
)
Overlap <- expand.grid( #generate all the combinations
"sets" = sets,
"category" = category
) %>%
as.data.frame() %>% #determine the intersection: a character col of Y or N.
mutate(intersect = case_when(
str_detect(category, sets %>% as.character()) ~ "Y",
T ~ "N"
))
Overlap[15,3] = "N"
Overlap[27,3] = "N"
Overlap[35,3] = "N"
# Upper-left plot
upperleft <- Total %>%
ggplot(aes(x = V1, y= V2)) +
geom_hline(yintercept = -Inf, size = 1.5) +
geom_vline(xintercept = -Inf, size = 1.5) +
geom_bar(stat = "identity", aes(fill = V1), alpha = 0.8) +
geom_text(aes(label = as.character(V2)), size = 5, angle = 90, hjust = 0, y = 1, fontface = "bold") +
scale_fill_manual(values = c("orangered3", "seagreen", "grey", "dodgerblue2"), #this is my own custom palette
limits = c("flye", "megahit", "metaspades", "metaspades_hybrid")) + #feel free to use something else
scale_x_discrete(labels = NULL) +
scale_y_continuous(labels = NULL) +
labs(x = NULL,
y = "set size") +
theme_minimal() +
theme(legend.position = "none") +
theme(text = element_text(size= 16, face="bold")) +
theme(axis.text.x=element_text(colour = "black", angle = 45, hjust = 1)) +
theme(axis.text.y=element_text(colour = "black")) +
theme(panel.grid = element_blank())
upperleft
# Lower-left plot
Overlap$category <- factor(Overlap$category)
lowerleft <- Overlap %>%
mutate(category = factor(rev(Overlap$category))) %>% #in the colored matrix the first y value appears in the bottom, so the order need to be reversed
ggplot(aes(x = sets, y = category))+
geom_tile(aes(fill = sets, alpha = intersect), color = "black", size = 1.5) +
scale_fill_manual(values = c("orangered1", "seagreen", "grey", "dodgerblue2"),
limits = c("flye", "megahit", "metaspades", "metaspades_hybrid")) +
scale_alpha_manual(values = c(0.8, 0), #color the grid for Y, don't color for N.
limits = c("Y", "N")) +
scale_y_discrete(labels = NULL) +
scale_x_discrete(labels = rep(" ", length(Overlap$sets))) + #I left white space here for better alignment w/ extended plots
labs(x = " ", #white space for better alignment w/ right side plots
y = "overlap") +
theme_minimal() +
theme(legend.position = "none") +
theme(text = element_text(size= 16, face="bold")) +
theme(axis.text.x=element_text(colour = "black")) +
theme(axis.text.y=element_text(colour = "black")) +
theme(panel.grid = element_blank())
lowerleft
# Upper-right plot
Assembly_method <- c("flye", "megahit", "metaspades", "metaspades_hybrid")
upperright <- get_legend(
Total %>%
ggplot(aes(x = V1, y= V2)) +
geom_hline(yintercept = -Inf, size = 1.5) +
geom_vline(xintercept = -Inf, size = 1.5) +
geom_bar(stat = "identity", aes(fill = Assembly_method), alpha = 0.9) +
geom_text(aes(label = "Assembly method"), size = 40, angle = 90, hjust = 0, y = 1, fontface = "bold") +
scale_fill_manual(values = c("orangered1", "seagreen", "grey", "dodgerblue2"), #this is my own custom palette
limits = c("flye", "megahit", "metaspades", "metaspades_hybrid")) + #feel free to use something else
scale_x_discrete(labels = NULL) +
scale_y_continuous(labels = NULL) +
labs(x = NULL,
y = "set size") +
theme_minimal() +
theme(legend.position = "right") +
theme(text = element_text(size= 16, face="bold")) +
theme(axis.text.x=element_text(colour = "black", angle = 45, hjust = 1)) +
theme(axis.text.y=element_text(colour = "black")) +
theme(panel.grid = element_blank())
)
plot_grid(upperright)
# Lower-right plot
overlap_sizes <- overlap_sizes %>% mutate(V2 = factor(V2, levels = rev(V2))) #the order needs to be reversed for the figure to match
lowerright <- overlap_sizes %>%
ggplot(aes(x = V2, y = V1)) +
geom_hline(yintercept = -Inf, size = 1.5) +
geom_vline(xintercept = -Inf, size = 1.5) +
geom_bar(stat = "identity", fill = "grey80", color = NA, alpha = 0.8) +
geom_text(aes(label = V1, y = 0), size = 5, hjust = 0, vjust = 0.5, fontface = "bold") +
scale_y_continuous(breaks = c(0, max(overlap_sizes$V1)) ,
labels = rep(" ", 2)) + #I left white space here for better alignment w/ extended plots
scale_x_discrete(labels = NULL) +
labs(y = "intersect sizes",
x = NULL) +
theme_minimal() +
theme(text = element_text(size= 15, face="bold")) +
theme(axis.text.x=element_text(colour = "black", angle = 45, hjust = 1)) +
theme(axis.text.y=element_text(colour = "black")) +
theme(panel.grid = element_blank()) +
coord_flip()
lowerright
pdf(file="ONT_protein_assembler_mmseq2_Upset_plot_w_metaspades.pdf")
plot_grid(upperleft, upperright, lowerleft, lowerright,
nrow = 2,
ncol = 2,
rel_heights = c(0.95, 1.5), #the more rows in the lower part, the longer it should be
rel_widths = c(0.95, 0.95))
dev.off()
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment