2020 Mtb. analyses.

1 Annotation version: 20200716

The following section loads the microbesonline and genbank annotations for Mycobacterium tuberculosis.

## Looks like it is taxon ID 83332
mtb_annotations <- as.data.frame(load_microbesonline_annotations(species="Mycobacterium tuberculosis H37Rv"))

## Found 1 entry.

##                                Genome         Phylum Paper     Loaded Complete
## 2178 Mycobacterium tuberculosis H37Rv Actinobacteria   yes 2007-05-08      yes
##      #Chr. #Plasmids #Genes tax_id
## 2178     1         0   4047  83332

## The species being downloaded is: Mycobacterium tuberculosis H37Rv

## Downloading: http://www.microbesonline.org/cgi-bin/genomeInfo.cgi?tId=83332;export=tab

knitr::kable(head(mtb_annotations))

locusId	accession	GI	scaffoldId	start	stop	strand	sysName	name	desc	COG	COGFun	COGDesc	TIGRFam	TIGRRoles	GO	EC	ECDesc
31772	NP_214515.1	15607143	7022	1	1524	+	Rv0001	dnaA	chromosomal replication initiation protein (NCBI)	COG593	L	ATPase involved in DNA replication initiation	TIGR00362 chromosomal replication initiator protein DnaA [dnaA]	DNA metabolism:DNA replication, recombination, and repair	GO:0006270,GO:0006275,GO:0003688,GO:0017111,GO:0005524	NA	NA
31773	NP_214516.1	15607144	7022	2052	3260	+	Rv0002	dnaN	DNA polymerase III subunit beta (NCBI)	COG592	L	DNA polymerase sliding clamp subunit (PCNA homolog)	TIGR00663 DNA polymerase III, beta subunit [dnaN]	DNA metabolism:DNA replication, recombination, and repair	GO:0006260,GO:0003677,GO:0003893,GO:0008408,GO:0016449,GO:0019984,GO:0003889,GO:0003894,GO:0015999,GO:0016450,GO:0003890,GO:0003895,GO:0016000,GO:0016451,GO:0003891,GO:0016448,GO:0016452	2.7.7.7	DNA-directed DNA polymerase.
31774	NP_214517.1	15607145	7022	3280	4437	+	Rv0003	recF	recombination protein F (NCBI)	COG1195	L	Recombinational DNA repair ATPase (RecF pathway)	TIGR00611 DNA replication and repair protein RecF [recF]	DNA metabolism:DNA replication, recombination, and repair	GO:0006281,GO:0005694,GO:0003697,GO:0005524	NA	NA
31775	NP_214518.1	15607146	7022	4434	4997	+	Rv0004	Rv0004	hypothetical protein (NCBI)	COG5512	R	Zn-ribbon-containing, possibly RNA-binding protein and truncated derivatives	NA	NA	NA	NA	NA
31776	NP_214519.1	15607147	7022	5123	7267	+	Rv0005	gyrB	DNA topoisomerase IV subunit B (NCBI)	COG187	L	Type IIA topoisomerase (DNA gyrase/topo II, topoisomerase IV), B subunit	TIGR01059 DNA gyrase, B subunit [gyrB]	DNA metabolism:DNA replication, recombination, and repair	GO:0006304,GO:0006265,GO:0005694,GO:0003918,GO:0005524	5.99.1.3	DNA topoisomerase (ATP-hydrolyzing).
31777	NP_214520.1	15607148	7022	7302	9818	+	Rv0006	gyrA	DNA gyrase subunit A (NCBI)	COG188	L	Type IIA topoisomerase (DNA gyrase/topo II, topoisomerase IV), A subunit	TIGR01063 DNA gyrase, A subunit [gyrA]	DNA metabolism:DNA replication, recombination, and repair	GO:0006265,GO:0006268,GO:0005694,GO:0003918,GO:0005509,GO:0005524	5.99.1.3	DNA topoisomerase (ATP-hydrolyzing).

mtb_go <- load_microbesonline_go(species="Mycobacterium tuberculosis H37Rv", id_column="sysName")

## Found 1 entry.

##                                Genome         Phylum Paper     Loaded Complete
## 2178 Mycobacterium tuberculosis H37Rv Actinobacteria   yes 2007-05-08      yes
##      #Chr. #Plasmids #Genes tax_id
## 2178     1         0   4047  83332

## The species being downloaded is: Mycobacterium tuberculosis H37Rv and is being downloaded as 83332.tab.

colnames(mtb_go) <- c("ID", "GO")

mtb_gff <- load_gff_annotations(gff="~/scratch/libraries/genome/mtuberculosis_h37rv.gff")

## Trying attempt: rtracklayer::import.gff3(gff, sequenceRegionsAsSeqinfo=TRUE)

## Trying attempt: rtracklayer::import.gff3(gff, sequenceRegionsAsSeqinfo=FALSE)

## Had a successful gff import with rtracklayer::import.gff3(gff, sequenceRegionsAsSeqinfo=FALSE)

## Returning a df with 15 columns and 4008 rows.

rownames(mtb_gff) <- mtb_gff[["locus_tag"]]

mtb_annot <- merge(mtb_gff, mtb_annotations, by.x="row.names", by.y="sysName", all.x=TRUE)
rownames(mtb_annot) <- mtb_annot[["Row.names"]]
mtb_annot[["Row.names"]] <- NULL

2 Loading all processed samples

There is now a sample sheet on google docs which contains Volker’s samples along with a growing set of downloaded samples.

all_expt <- create_expt(
    metadata=glue::glue("sample_sheets/Mtb_RNAseq_data_sources_{ver}.xlsx"),
    file_column="mtbh37rvhisat2file")

## Reading the sample metadata.

## The sample definitions comprises: 227 rows(samples) and 27 columns(metadata fields).

## Reading count tables.

## Reading count files with read.table().

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0021/outputs/hisat2_mtuberculosis_h37rv/HPGL0021.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0022/outputs/hisat2_mtuberculosis_h37rv/HPGL0022.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0023/outputs/hisat2_mtuberculosis_h37rv/HPGL0023.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0024/outputs/hisat2_mtuberculosis_h37rv/HPGL0024.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0025/outputs/hisat2_mtuberculosis_h37rv/HPGL0025.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0026/outputs/hisat2_mtuberculosis_h37rv/HPGL0026.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0083/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0084/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0085/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0087/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0088/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0089/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0091/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0092/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0093/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0095/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0130/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0131/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0132/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0133/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0134/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0135/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0136/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0137/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0138/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0139/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0140/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0141/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0330/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0331/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0332/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0333/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0334/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0335/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0336/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0511/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0512/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0513/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0514/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0515/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0516/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0517/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0518/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0519/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0520/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/hpgl0521/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214125/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214126/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214127/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214128/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214129/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214130/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214131/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214132/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214133/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214134/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214135/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214136/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214137/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214138/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214139/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214140/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214141/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214142/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214143/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1022493/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1022494/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1022495/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1022496/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1022497/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1022499/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1022501/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1022502/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1022507/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1022513/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198589/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198590/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198591/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198592/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198593/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198594/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198595/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198596/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198597/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198598/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198599/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198600/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198601/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198602/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198603/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198604/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198605/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198606/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198607/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198608/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198609/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198610/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198611/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198612/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198613/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198614/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198615/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198616/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198617/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198618/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198619/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198620/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198621/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198622/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198623/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198624/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198625/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198626/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198627/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198628/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198636/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198637/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198638/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198642/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198643/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198644/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198645/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198647/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198648/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198649/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198650/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198651/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198652/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198653/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198654/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198655/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198656/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198657/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198658/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198659/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198660/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198661/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198662/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198663/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198664/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198665/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198666/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198667/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198668/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198669/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198670/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198671/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198672/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198673/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198674/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198675/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198676/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198677/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR10198678/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR11215146/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR11215147/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR11215148/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR11215149/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR11215150/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR11215151/outputs/hisat2_mtuberculosis_h37rv/r1.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140762/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140763/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140764/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140765/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140766/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140767/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140768/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140769/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140770/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140771/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140772/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140773/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140774/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140775/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140776/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140777/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140778/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140779/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140780/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140781/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140782/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140783/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140784/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140785/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140786/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140787/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140788/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140789/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140790/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140791/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140792/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140793/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140794/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140795/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140796/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140797/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140798/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/ERR1140799/outputs/hisat2_mtuberculosis_h37rv/r1_trimmed.count_mtuberculosis_h37rv_sno_gene_locus_tag.count.xz contains 4013 rows and merges to 4013 rows.

## Finished reading count data.

## Warning in create_expt(metadata = glue::glue("sample_sheets/
## Mtb_RNAseq_data_sources_{ver}.xlsx"), : Some samples were removed when cross
## referencing the samples against the count data.

## Matched 4008 annotations and counts.

## Bringing together the count matrix and gene information.

## Saving the expressionset to 'expt.rda'.

## The final expressionset has 4008 rows and 198 columns.

all_expt <- set_expt_batches(all_expt, fact="experimentname")
all_expt <- set_expt_conditions(all_expt, fact="vitrovivo")

2.1 Testing

all_norm <- normalize_expt(all_expt, transform="log2", convert="cpm",
                           filter="simple", norm="quant")

## This function will replace the expt$expressionset slot with:

## log2(cpm(quant(simple(data))))

## It will save copies of each step along the way
##  in expt$normalized with the corresponding libsizes. Keep libsizes in mind
##  when invoking limma.  The appropriate libsize is non-log(cpm(normalized)).
##  This is most likely kept at:
##  'new_expt$normalized$intermediate_counts$normalization$libsizes'
##  A copy of this may also be found at:
##  new_expt$best_libsize

## Not correcting the count-data for batch effects.  If batch is
##  included in EdgerR/limma's model, then this is probably wise; but in extreme
##  batch effects this is a good parameter to play with.

## Step 1: performing count filter with option: simple

## Removing 9 low-count genes (3999 remaining).

## Step 2: normalizing the data with quant.

## Step 3: converting the data with cpm.

## Step 4: transforming the data with log2.

## transform_counts: Found 2 values equal to 0, adding 1 to the matrix.

## Step 5: not doing batch correction.

plot_nonzero(all_norm)$plot

pp(file="first_pca_test.png", image=plot_pca(all_norm)$plot)

## plot labels was not set and there are more than 100 samples, disabling it.

## Not putting labels on the PC plot.

## Writing the image to: first_pca_test.png and calling dev.off().

## Warning in MASS::cov.trob(data[, vars]): Probable convergence failure

## Warning in MASS::cov.trob(data[, vars]): Probable convergence failure

## Warning in MASS::cov.trob(data[, vars]): Probable convergence failure

## Warning in MASS::cov.trob(data[, vars]): Probable convergence failure

all_nb <- normalize_expt(all_expt, transform="log2", filter="simple",
                         batch="limma", convert="cpm", surrogates=1)

## This function will replace the expt$expressionset slot with:

## log2(limma(cpm(simple(data))))

## It will save copies of each step along the way
##  in expt$normalized with the corresponding libsizes. Keep libsizes in mind
##  when invoking limma.  The appropriate libsize is non-log(cpm(normalized)).
##  This is most likely kept at:
##  'new_expt$normalized$intermediate_counts$normalization$libsizes'
##  A copy of this may also be found at:
##  new_expt$best_libsize

## Leaving the data unnormalized.  This is necessary for DESeq, but
##  EdgeR/limma might benefit from normalization.  Good choices include quantile,
##  size-factor, tmm, etc.

## Step 1: performing count filter with option: simple

## Removing 9 low-count genes (3999 remaining).

## Step 2: not normalizing the data.

## Step 3: converting the data with cpm.

## Step 4: transforming the data with log2.

## transform_counts: Found 86553 values equal to 0, adding 1 to the matrix.

## Step 5: doing batch correction with limma.

## Note to self:  If you get an error like 'x contains missing values' The data has too many 0's and needs a stronger low-count filter applied.

## Passing off to all_adjusters.

## batch_counts: Before batch/surrogate estimation, 702129 entries are x>1: 89%.

## batch_counts: Before batch/surrogate estimation, 86553 entries are x==0: 11%.

## batch_counts: Before batch/surrogate estimation, 3120 entries are 0<x<1: 0%.

## A specific number of surrogate variables was chosen: 1.

## batch_counts: Using limma's removeBatchEffect to remove batch effect.

## If you receive a warning: 'NANs produced', one potential reason is that the data was quantile normalized.

## There are 38385 (5%) elements which are < 0 after batch correction.

## Setting low elements to zero.

nb_pca <- plot_pca(all_nb)

## plot labels was not set and there are more than 100 samples, disabling it.

## Not putting labels on the PC plot.

pp(file="first_pca_batch_test.png", image=nb_pca$plot)

## Writing the image to: first_pca_batch_test.png and calling dev.off().

all_nb <- normalize_expt(all_expt, transform="log2", filter="simple",
                         norm="quant", batch="svaseq", convert="cpm")

## This function will replace the expt$expressionset slot with:

## log2(svaseq(cpm(quant(simple(data)))))

## It will save copies of each step along the way
##  in expt$normalized with the corresponding libsizes. Keep libsizes in mind
##  when invoking limma.  The appropriate libsize is non-log(cpm(normalized)).
##  This is most likely kept at:
##  'new_expt$normalized$intermediate_counts$normalization$libsizes'
##  A copy of this may also be found at:
##  new_expt$best_libsize

## Warning in normalize_expt(all_expt, transform = "log2", filter = "simple", :
## Quantile normalization and sva do not always play well together.

## Step 1: performing count filter with option: simple

## Removing 9 low-count genes (3999 remaining).

## Step 2: normalizing the data with quant.

## Step 3: converting the data with cpm.

## Step 4: transforming the data with log2.

## transform_counts: Found 2 values equal to 0, adding 1 to the matrix.

## Step 5: doing batch correction with svaseq.

## Note to self:  If you get an error like 'x contains missing values' The data has too many 0's and needs a stronger low-count filter applied.

## Passing off to all_adjusters.

## batch_counts: Before batch/surrogate estimation, 788630 entries are x>1: 100%.

## batch_counts: Before batch/surrogate estimation, 2 entries are x==0: 0%.

## batch_counts: Before batch/surrogate estimation, 3170 entries are 0<x<1: 0%.

## The be method chose 16 surrogate variables.

## Attempting svaseq estimation with 16 surrogates.

## There are 76 (0%) elements which are < 0 after batch correction.

## Setting low elements to zero.

nb_pca <- plot_pca(all_nb)

## plot labels was not set and there are more than 100 samples, disabling it.

## Not putting labels on the PC plot.

pp(file="first_pca_batch_test.png", image=nb_pca$plot)

## Writing the image to: first_pca_batch_test.png and calling dev.off().

testing <- plot_3d_pca(nb_pca)

## Warning: `arrange_()` is deprecated as of dplyr 0.7.0.
## Please use `arrange()` instead.
## See vignette('programming') for more help
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.

3 Local Samples Estimation

This is the group of samples which were collected by the Briken lab and previously analyzed by members of the El-Sayed lab.

local_expt <- sm(create_expt(metadata="sample_sheets/Mtb_RNAseq_data_sources_20200618.xlsx",
                             file_column="mtbfile",
                             gene_info=mtb_annot))

## Error in create_expt(metadata = "sample_sheets/Mtb_RNAseq_data_sources_20200618.xlsx", : I could not find your count tables by sample nor type, uppercase nor lowercase.

3.1 Just take the samples of immediate interest

Najib and Volker would like to focus for the moment on only hpgl IDs: 130-132, 330-332.

few_expt <- subset_expt(local_expt, subset="condition=='Rv'")

## Error in sampleNames(expt): object 'local_expt' not found

new_column <- paste0(pData(few_expt)[["condition"]], "_", pData(few_expt)[["vitrovivo"]])

## Error in pData(few_expt): object 'few_expt' not found

few <- set_expt_conditions(few_expt, fact=new_column)

## Error in pData(expt): object 'few_expt' not found

few_norm <- normalize_expt(few, filter=TRUE, convert="cpm", transform="log2", norm="quant")

## Error in normalize_expt(few, filter = TRUE, convert = "cpm", transform = "log2", : object 'few' not found

plot_pca(few_norm)$plot

## Error in plot_pca(few_norm): object 'few_norm' not found

few_filt <- normalize_expt(few_expt, filter=TRUE)

## Error in normalize_expt(few_expt, filter = TRUE): object 'few_expt' not found

few_write <- write_expt(few_expt, excel="excel/few_written.xlsx")

## Error in exprs(expt): object 'few_expt' not found

few_de <- all_pairwise(few_filt)

## Error in normalize_expt(input, filter = TRUE, batch = FALSE, transform = "log2", : object 'few_filt' not found

few_table <- combine_de_tables(few_de, excel="excel/few_samples_table.xlsx")

## Error in combine_de_tables(few_de, excel = "excel/few_samples_table.xlsx"): object 'few_de' not found

few_sig <- extract_significant_genes(few_table,
                                     excel="excel/few_samples_sig.xlsx")

## Error in extract_significant_genes(few_table, excel = "excel/few_samples_sig.xlsx"): object 'few_table' not found

mtb_lengths <- mtb_annot[, c("seqnames", "width")]
mtb_lengths[["seqnames"]] <- rownames(mtb_lengths)
colnames(mtb_lengths) <- c("ID", "length")

up_genes <- few_sig[["deseq"]][["ups"]][[1]]

## Error in eval(expr, envir, enclos): object 'few_sig' not found

up_go <- simple_goseq(sig_genes=up_genes, go_db=mtb_go, length_db=mtb_lengths,
                      excel="excel/up_goseq.xlsx")

## Error in simple_goseq(sig_genes = up_genes, go_db = mtb_go, length_db = mtb_lengths, : object 'up_genes' not found

down_genes <- few_sig[["deseq"]][["downs"]][[1]]

## Error in eval(expr, envir, enclos): object 'few_sig' not found

down <- rownames(down_genes)

## Error in rownames(down_genes): object 'down_genes' not found

down_go <- simple_goseq(sig_genes=down, go_db=mtb_go, length_db=mtb_lengths)

## Error in simple_goseq(sig_genes = down, go_db = mtb_go, length_db = mtb_lengths): object 'down' not found

few_write[["norm_pca"]]

## Error in eval(expr, envir, enclos): object 'few_write' not found

few_table[["plots"]][[1]][["deseq_ma_plots"]][["plot"]]

## Error in eval(expr, envir, enclos): object 'few_table' not found

up_go$pvalue_plots[[1]]

## Error in eval(expr, envir, enclos): object 'up_go' not found

down_go$pvalue_plots[[1]]

## Error in eval(expr, envir, enclos): object 'down_go' not found

4 Exogenous Samples Estimation

In this context, exogenous just means samples which were not created here. E.g. samples I downloaded from SRA.

exo_annot <- mtb_annot
rownames(exo_annot) <- exo_annot[["db_xref"]]
exo_expt <- create_expt(metadata="sample_sheets/exo_samples.xlsx",
                           file_column="mtbfile",
                           gene_info=exo_annot)

## Reading the sample metadata.

## Did not find the batch column in the sample sheet.

## Filling it in as undefined.

## The sample definitions comprises: 19 rows(samples) and 12 columns(metadata fields).

## Reading count tables.

## Reading count files with read.table().

## /mnt/sshfs/cbcbsub01/fs/cbcb-lab/nelsayed/scratch/atb/rnaseq/mycobacterium_tuberculosis_2020/preprocessing/SRR9214125/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows.

## preprocessing/SRR9214126/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214127/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214128/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214129/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214130/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214131/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214132/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214133/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214134/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214135/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214136/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214137/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214138/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214139/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214140/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214141/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214142/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## preprocessing/SRR9214143/outputs/hisat2_mtuberculosis_h37rv/r1.count.xz contains 4013 rows and merges to 4013 rows.

## Finished reading count data.

## Matched 4008 annotations and counts.

## Bringing together the count matrix and gene information.

## Some annotations were lost in merging, setting them to 'undefined'.

## Saving the expressionset to 'expt.rda'.

## The final expressionset has 4008 rows and 19 columns.

4.1 Create some plots of the new data

The following blocks will plot and print a few common metrics of the new data.

exo_plots <- sm(graph_metrics(exo_expt))

exo_norm <- sm(normalize_expt(exo_expt, transform="log2", norm="quant", filter=TRUE))
exon_plots <- sm(graph_metrics(exo_norm))

4.2 Now show some plots!

exo_plots$libsize

exo_plots$density

tn <- normalize_expt(exo_expt, transform="log2")

## This function will replace the expt$expressionset slot with:

## log2(data)

## It will save copies of each step along the way
##  in expt$normalized with the corresponding libsizes. Keep libsizes in mind
##  when invoking limma.  The appropriate libsize is non-log(cpm(normalized)).
##  This is most likely kept at:
##  'new_expt$normalized$intermediate_counts$normalization$libsizes'
##  A copy of this may also be found at:
##  new_expt$best_libsize

## Filter is false, this should likely be set to something, good
##  choices include cbcb, kofa, pofa (anything but FALSE).  If you want this to
##  stay FALSE, keep in mind that if other normalizations are performed, then the
##  resulting libsizes are likely to be strange (potentially negative!)

## Leaving the data unconverted.  It is often advisable to cpm/rpkm
##  the data to normalize for sampling differences, keep in mind though that rpkm
##  has some annoying biases, and voom() by default does a cpm (though hpgl_voom()
##  will try to detect this).

## Leaving the data unnormalized.  This is necessary for DESeq, but
##  EdgeR/limma might benefit from normalization.  Good choices include quantile,
##  size-factor, tmm, etc.

## Not correcting the count-data for batch effects.  If batch is
##  included in EdgerR/limma's model, then this is probably wise; but in extreme
##  batch effects this is a good parameter to play with.

## Step 1: not doing count filtering.

## Step 2: not normalizing the data.

## Step 3: not converting the data.

## Step 4: transforming the data with log2.

## transform_counts: Found 1020 values equal to 0, adding 1 to the matrix.

## Step 5: not doing batch correction.

tnp <- plot_density(tn)

tmp_ggstats <- ggstatsplot::ggbetweenstats(
                                data=tnp$table, x=sample, y=counts,
                                notch=TRUE, mean.ci=TRUE, k=3,
                                pairwise.comparisons=FALSE)

## Registered S3 method overwritten by 'broom.mixed':
##   method      from 
##   tidy.gamlss broom

## Registered S3 methods overwritten by 'car':
##   method                          from
##   influence.merMod                lme4
##   cooks.distance.influence.merMod lme4
##   dfbeta.influence.merMod         lme4
##   dfbetas.influence.merMod        lme4

## Registered S3 method overwritten by 'DescTools':
##   method         from 
##   reorder.factor gdata

## Warning:  Number of labels is greater than default palette color count.
##  Try using another color `palette` (and/or `package`).

## 

tmp_ggstats

tmp_ggstats <- ggstatsplot::grouped_ggbetweenstats(
                                grouping.var=condition,
                                data=tnp$table, x=sample, y=counts,
                                notch=TRUE, mean.ci=TRUE, k=3,
                                pairwise.comparisons=FALSE)
tmp_ggstats

## Quick PCA
exon_pc_expt <- normalize_expt(exo_expt, transform="log2", filter=TRUE, convert="cpm",
                               norm="quant", batch="svaseq")

## This function will replace the expt$expressionset slot with:

## log2(svaseq(cpm(quant(cbcb(data)))))

## It will save copies of each step along the way
##  in expt$normalized with the corresponding libsizes. Keep libsizes in mind
##  when invoking limma.  The appropriate libsize is non-log(cpm(normalized)).
##  This is most likely kept at:
##  'new_expt$normalized$intermediate_counts$normalization$libsizes'
##  A copy of this may also be found at:
##  new_expt$best_libsize

## Warning in normalize_expt(exo_expt, transform = "log2", filter = TRUE, convert =
## "cpm", : Quantile normalization and sva do not always play well together.

## Step 1: performing count filter with option: cbcb

## Removing 20 low-count genes (3988 remaining).

## Step 2: normalizing the data with quant.

## Step 3: converting the data with cpm.

## Step 4: transforming the data with log2.

## transform_counts: Found 11 values equal to 0, adding 1 to the matrix.

## Step 5: doing batch correction with svaseq.

## Note to self:  If you get an error like 'x contains missing values' The data has too many 0's and needs a stronger low-count filter applied.

## Passing off to all_adjusters.

## batch_counts: Before batch/surrogate estimation, 75205 entries are x>1: 99%.

## batch_counts: Before batch/surrogate estimation, 11 entries are x==0: 0%.

## batch_counts: Before batch/surrogate estimation, 556 entries are 0<x<1: 1%.

## The be method chose 2 surrogate variables.

## Attempting svaseq estimation with 2 surrogates.

## There are 13 (0%) elements which are < 0 after batch correction.

## Setting low elements to zero.

pp(file="images/exo_pc.png", image=plot_pca(exon_pc_expt)$plot)

## Writing the image to: images/exo_pc.png and calling dev.off().

pander::pander(sessionInfo())

R version 4.0.0 (2020-04-24)

Platform: x86_64-pc-linux-gnu (64-bit)

locale: LC_CTYPE=en_US.UTF-8, LC_NUMERIC=C, LC_TIME=en_US.UTF-8, LC_COLLATE=en_US.UTF-8, LC_MONETARY=en_US.UTF-8, LC_MESSAGES=en_US.UTF-8, LC_PAPER=en_US.UTF-8, LC_NAME=C, LC_ADDRESS=C, LC_TELEPHONE=C, LC_MEASUREMENT=en_US.UTF-8 and LC_IDENTIFICATION=C

attached base packages: parallel, stats, graphics, grDevices, utils, datasets, methods and base

other attached packages: ruv(v.0.9.7.1), hpgltools(v.1.0), testthat(v.2.3.2), Biobase(v.2.48.0) and BiocGenerics(v.0.34.0)

loaded via a namespace (and not attached): corpcor(v.1.6.9), ps(v.1.3.3), Rsamtools(v.2.4.0), lmtest(v.0.9-37), V8(v.3.2.0), foreach(v.1.5.0), rprojroot(v.1.3-2), crayon(v.1.3.4), MASS(v.7.3-51.6), PMCMRplus(v.1.4.4), nlme(v.3.1-148), backports(v.1.1.8), metafor(v.2.4-0), ggcorrplot(v.0.1.3), sva(v.3.36.0), GOSemSim(v.2.14.0), rlang(v.0.4.7), readxl(v.1.3.1), XVector(v.0.28.0), performance(v.0.4.7), nloptr(v.1.2.2.2), callr(v.3.4.3), limma(v.3.44.3), BiocParallel(v.1.22.0), bit64(v.0.9-7.1), loo(v.2.3.1), glue(v.1.4.1), pbkrtest(v.0.4-8.6), rstan(v.2.21.1), processx(v.3.4.3), AnnotationDbi(v.1.50.1), ggstatsplot(v.0.5.0), DOSE(v.3.14.0), haven(v.2.3.1), tidyselect(v.1.1.0), SummarizedExperiment(v.1.18.2), usethis(v.1.6.1), rio(v.0.5.16), variancePartition(v.1.18.2), XML(v.3.99-0.4), tidyr(v.1.1.0), zoo(v.1.8-8), SuppDists(v.1.1-9.5), GenomicAlignments(v.1.24.0), mc2d(v.0.1-18), xtable(v.1.8-4), MatrixModels(v.0.4-1), magrittr(v.1.5), evaluate(v.0.14), ggplot2(v.3.3.2), cli(v.2.0.2), zlibbioc(v.1.34.0), rstudioapi(v.0.11), miniUI(v.0.1.1.1), fastmatch(v.1.1-0), shiny(v.1.5.0), xfun(v.0.15), askpass(v.1.1), parameters(v.0.8.0), groupedstats(v.1.0.1), inline(v.0.3.15), pkgbuild(v.1.1.0), bridgesampling(v.1.0-0), caTools(v.1.18.0), tidygraph(v.1.2.0), WRS2(v.1.1-0), expm(v.0.999-4), tibble(v.3.0.3), Brobdingnag(v.1.2-6), ggrepel(v.0.8.2), Biostrings(v.2.56.0), reshape(v.0.8.8), rcompanion(v.2.3.25), ez(v.4.4-0), zeallot(v.0.1.0), withr(v.2.2.0), bitops(v.1.0-6), ggforce(v.0.3.2), cellranger(v.1.1.0), plyr(v.1.8.6), coda(v.0.19-3), RcppParallel(v.5.0.2), pillar(v.1.4.6), gplots(v.3.0.4), GenomicFeatures(v.1.40.1), multcomp(v.1.4-13), Rmpfr(v.0.8-1), fs(v.1.4.2), europepmc(v.0.4), paletteer(v.1.2.0), clusterProfiler(v.3.16.0), vctrs(v.0.3.2), ellipsis(v.0.3.1), generics(v.0.0.2), nortest(v.1.0-4), urltools(v.1.7.3), devtools(v.2.3.0), tools(v.4.0.0), foreign(v.0.8-80), munsell(v.0.5.0), tweenr(v.1.0.1), fgsea(v.1.14.0), DelayedArray(v.0.14.1), abind(v.1.4-5), fastmap(v.1.0.1), compiler(v.4.0.0), pkgload(v.1.1.0), httpuv(v.1.5.4), rtracklayer(v.1.48.0), sessioninfo(v.1.1.1), DescTools(v.0.99.37), plotly(v.4.9.2.1), ggExtra(v.0.9), GenomeInfoDbData(v.1.2.3), gridExtra(v.2.3), edgeR(v.3.30.3), lattice(v.0.20-41), later(v.1.1.0.1), dplyr(v.1.0.0), prismatic(v.0.2.0), BiocFileCache(v.1.12.0), jsonlite(v.1.7.0), scales(v.1.1.1), carData(v.3.0-4), pbapply(v.1.4-2), genefilter(v.1.70.0), lazyeval(v.0.2.2), promises(v.1.1.1), car(v.3.0-8), BWStest(v.0.2.2), tidyBF(v.0.2.1), doParallel(v.1.0.15), metaBMA(v.0.6.3), effectsize(v.0.3.1), pairwiseComparisons(v.1.1.2), sandwich(v.2.5-1), rmarkdown(v.2.3), openxlsx(v.4.1.5), cowplot(v.1.0.0), statmod(v.1.4.34), Rtsne(v.0.15), ipmisc(v.3.1.0), forcats(v.0.5.0), pander(v.0.6.3), downloader(v.0.4), selectr(v.0.4-2), logspline(v.2.1.16), igraph(v.1.2.5), numDeriv(v.2016.8-1.1), survival(v.3.2-3), yaml(v.2.2.1), metaplus(v.0.7-11), rstantools(v.2.1.1), htmltools(v.0.5.0), memoise(v.1.1.0), fastGHQuad(v.1.0), modeltools(v.0.2-23), locfit(v.1.5-9.4), graphlayouts(v.0.7.0), IRanges(v.2.22.2), quadprog(v.1.5-8), dunn.test(v.1.3.5), viridisLite(v.0.3.0), gmp(v.0.6-0), digest(v.0.6.25), assertthat(v.0.2.1), mime(v.0.9), rappdirs(v.0.3.1), repr(v.1.1.0), bayestestR(v.0.7.0), RSQLite(v.2.2.0), Exact(v.2.0), LaplacesDemon(v.16.1.4), remotes(v.2.1.1), data.table(v.1.12.8), blob(v.1.2.1), S4Vectors(v.0.26.1), preprocessCore(v.1.50.0), splines(v.4.0.0), labeling(v.0.3), rematch2(v.2.1.2), RCurl(v.1.98-1.2), broom(v.0.7.0), hms(v.0.5.3), colorspace(v.1.4-1), base64enc(v.0.1-3), BiocManager(v.1.30.10), GenomicRanges(v.1.40.0), libcoin(v.1.0-5), broom.mixed(v.0.2.6), coin(v.1.3-1), Rcpp(v.1.0.5), mvtnorm(v.1.1-1), enrichplot(v.1.8.1), multcompView(v.0.1-8), fansi(v.0.4.1), R6(v.2.4.1), grid(v.4.0.0), ggridges(v.0.5.2), lifecycle(v.0.2.0), EMT(v.1.1), statsExpressions(v.0.4.2), StanHeaders(v.2.21.0-5), zip(v.2.0.4), BayesFactor(v.0.9.12-4.2), curl(v.4.3), ggsignif(v.0.6.0), minqa(v.1.2.4), gdata(v.2.18.0), broomExtra(v.4.0.3), fastcluster(v.1.1.25), DO.db(v.2.9), PROPER(v.1.20.0), Matrix(v.1.2-18), skimr(v.2.1.2), qvalue(v.2.20.0), TH.data(v.1.0-10), desc(v.1.2.0), RColorBrewer(v.1.1-2), iterators(v.1.0.12), TMB(v.1.7.16), stringr(v.1.4.0), directlabels(v.2020.6.17), htmlwidgets(v.1.5.1), polyclip(v.1.10-0), triebeard(v.0.3.0), biomaRt(v.2.44.1), purrr(v.0.3.4), crosstalk(v.1.1.0.1), gridGraphics(v.0.5-0), rvest(v.0.3.5), mgcv(v.1.8-31), openssl(v.1.4.2), insight(v.0.8.5), bdsmatrix(v.1.3-4), codetools(v.0.2-16), matrixStats(v.0.56.0), GO.db(v.3.11.4), gtools(v.3.8.2), prettyunits(v.1.1.1), dbplyr(v.1.4.4), GenomeInfoDb(v.1.24.2), correlation(v.0.3.0), gtable(v.0.3.0), DBI(v.1.1.0), stats4(v.4.0.0), httr(v.1.4.1), highr(v.0.8), KernSmooth(v.2.23-17), stringi(v.1.4.6), kSamples(v.1.2-9), progress(v.1.2.2), reshape2(v.1.4.4), farver(v.2.0.3), annotate(v.1.66.0), viridis(v.0.5.1), xml2(v.1.3.2), bbmle(v.1.0.23.1), colorRamps(v.2.3), rvcheck(v.0.1.8), boot(v.1.3-25), lme4(v.1.1-23), readr(v.1.3.1), ggplotify(v.0.0.5), bit(v.1.1-15.2), scatterpie(v.0.1.4), ggraph(v.2.0.3), pkgconfig(v.2.0.3) and knitr(v.1.29)

message(paste0("This is hpgltools commit: ", get_git_commit()))

## If you wish to reproduce this exact build of hpgltools, invoke the following:

## > git clone http://github.com/abelew/hpgltools.git

## > git reset b8af113ae7a9b8582c5d1a9e23febb5a2b2adb58

## This is hpgltools commit: Sun Jul 19 17:08:52 2020 -0400: b8af113ae7a9b8582c5d1a9e23febb5a2b2adb58

this_save <- paste0(gsub(pattern="\\.Rmd", replace="", x=rmd_file), "-v", ver, ".rda.xz")
message(paste0("Saving to ", this_save))

## Saving to 01_mtb_analyses_$20200716-v20200716.rda.xz

tmp <- sm(saveme(filename=this_save))