data_structure_overview.Rmd

```{r include=FALSE}
rm(list = ls(all = TRUE))
gc()
setwd("~/polybox/MSc_ACLS/swissrepeat/results/")
source("helpers.R")
```

# get overview of available data 

## swissrepeat/data/

```{r}
swissprot_annotations <- load_swissprot("data/swissprot_annotations.tsv")
str(swissprot_annotations)
```

```{r}
pfam_annotations <- read.delim("data/pfam_annotations.tab", header = TRUE, sep='\t')
str(pfam_annotations)
```

```{r}
pfam_clans=read.delim("data/Pfam-A.clans.tsv", header = TRUE, sep='\t')
str(pfam_clans)
```
```{r}
scales_and_slopes <- read.delim("data/scales_and_slopes.csv", header = TRUE, sep = '\t')
str(scales_and_slopes)
```


## swissrepeat/results
```{r}
aa_freqs <- read.csv("results/aa_freqs.csv", header = TRUE)
str(aa_freqs)
```

```{r}
virus_host_pairs_host_taxname_in_sp <- read.csv("results/virus_host_pairs_host_taxname_in_sp.csv", header = TRUE)
str(virus_host_pairs_host_taxname_in_sp)
```

### swissrepeat/results/amino_acid_frequencies
```{r}
Archea <- read.csv("results/amino_acid_frequencies/Archaea.csv", header = T)
str(Archea)
head(Archea)
```

```{r}
summary_aa_freqs <- read.csv("results/amino_acid_frequencies/summary.csv", header = T)
str(summary_aa_freqs)
head(summary_aa_freqs)
```

#### swissrepeat/results/amino_acid_frequencies/mobidb_consensus
```{r}
Archea_mobidb_consensus <- read.csv("results/amino_acid_frequencies/mobidb_consensus/Archaea.csv", header = T)
str(Archea_mobidb_consensus)
```

#### swissrepeat/results/amino_acid_frequencies/mobidb_consensus_inverse
```{r}
Archea_mobidb_consensus_inverse <- read.csv("results/amino_acid_frequencies/mobidb_consensus_inverse/Archaea.csv", header = T)
str(Archea_mobidb_consensus_inverse)
```

#### swissrepeat/results/amino_acid_frequencies/mobidb_regions_inverse
```{r}
Archea_mobidb_regions_inverted <- read.csv("results/amino_acid_frequencies/mobidb_regions_inverted/Archaea.csv", header = T)
str(Archea_mobidb_regions_inverted)
```

### swissrepeat/results/disorder_annotations
```{r}
disorder_annotations_mobidb_annotations <- read.csv("results/disorder_annotations/mobidb_annotations.csv", header = T)
str(disorder_annotations_mobidb_annotations)
```

```{r}
disorder_annotations_mobidb_coordinates <- read.csv("results/disorder_annotations/mobidb_coordinates.csv", header = T)
str(disorder_annotations_mobidb_coordinates)
```

```{r}
disorder_annotations_mobidb_regions <- read.csv("results/disorder_annotations/mobidb_regions.csv", header = T)
str(disorder_annotations_mobidb_regions)
```

### swissrepeat/results/empirical_an_expected_homorepeat_counts
emtpy subdirectories...

### swissrepeat/results/tr_annotions
```{r}
tr_annotations <- read.csv("results/tr_annotations/tr_annotations.csv", header = T)
str(tr_annotations)
```

### swissrepeat/results/tr_idr_overlap
```{r}
repeat_disorder_overlap_regions <- read.csv("results/tr_idr_overlap/repeat_disorder_overlap_regions.csv", header = T)
str(repeat_disorder_overlap_regions)
```