README.md 2.87 KB
Newer Older
Midoux Cedric's avatar
Midoux Cedric committed
1
2
# DIGESTOMIC

Midoux Cedric's avatar
Midoux Cedric committed
3
4
5
6
7
8
9
10
11
12
13
## link to DATA

```bash
ln -s ~/DIGESTOMIC/DATA/DIGESTOMIC_J177_A_02_03_16_S3_all_R1_001.fastq.gz DATA/raw/J177_A_R1.fastq.gz
ln -s ~/DIGESTOMIC/DATA/DIGESTOMIC_J177_A_02_03_16_S3_all_R2_001.fastq.gz DATA/raw/J177_A_R2.fastq.gz
ln -s ~/DIGESTOMIC/DATA/DIGESTOMIC_J177_B_02_03_16_S4_all_R1_001.fastq.gz DATA/raw/J177_B_R1.fastq.gz
ln -s ~/DIGESTOMIC/DATA/DIGESTOMIC_J177_B_02_03_16_S4_all_R2_001.fastq.gz DATA/raw/J177_B_R2.fastq.gz
ln -s ~/DIGESTOMIC/DATA/DIGESTOMIC_J80_A_26_11_15_S1_all_R1_001.fastq.gz DATA/raw/J80_A_R1.fastq.gz
ln -s ~/DIGESTOMIC/DATA/DIGESTOMIC_J80_A_26_11_15_S1_all_R2_001.fastq.gz DATA/raw/J80_A_R2.fastq.gz
ln -s ~/DIGESTOMIC/DATA/DIGESTOMIC_J80_B_26_11_15_S2_all_R1_001.fastq.gz DATA/raw/J80_B_R1.fastq.gz
ln -s ~/DIGESTOMIC/DATA/DIGESTOMIC_J80_B_26_11_15_S2_all_R2_001.fastq.gz DATA/raw/J80_B_R2.fastq.gz
Midoux Cedric's avatar
Midoux Cedric committed
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
```

## ghostKOALA

### Submit analysis

```bash
awk 'NR<=2000000' work/FGS/coassembly_FGS.faa > work/FGS/coassembly_FGS-1.faa 
awk 'NR>=2000001&&NR<=4000000' work/FGS/coassembly_FGS.faa > work/FGS/coassembly_FGS-2.faa 
awk 'NR>=4000001&&NR<=6000000' work/FGS/coassembly_FGS.faa > work/FGS/coassembly_FGS-3.faa 
awk 'NR>=6000001&&NR<=8000000' work/FGS/coassembly_FGS.faa > work/FGS/coassembly_FGS-4.faa 
awk 'NR>=8000001&&NR<=10000000' work/FGS/coassembly_FGS.faa > work/FGS/coassembly_FGS-5.faa 
awk 'NR>=10000001' work/FGS/coassembly_FGS.faa  > work/FGS/coassembly_FGS-6.faa 
```

* Download files
* Upload on [GhostKOALA webserver](https://www.kegg.jp/ghostkoala/) with `genus_prokaryotes + family_eukaryotes + viruses ` database option
* Submit
* Download from webserver and group in order annotation files `user_ko.txt`
* Join with other tables

### KEGG orthology table

[source](http://merenlab.org/2018/01/17/importing-ghostkoala-annotations/)

```bash
cd work/ghostKOALA
wget 'https://www.genome.jp/kegg-bin/download_htext?htext=ko00001&format=htext&filedir=' -O ko00001.keg

kegfile="ko00001.keg"

while read -r prefix content
do
    case "$prefix" in A) col1="$content";; \
                      B) col2="$content" ;; \
                      C) col3="$content";; \
                      D) echo -e "$col1\t$col2\t$col3\t$content";;
    esac 
done < <(sed '/^[#!+]/d;s/<[^>]*>//g;s/^./& /' < "$kegfile") > KO_Orthology_ko00001.txt

rm ko00001.keg
Midoux Cedric's avatar
Midoux Cedric committed
55
56

cut -f4 KO_Orthology_ko00001.txt | sort -n | uniq | sed 's/  /\t/' > KO_name.txt
Midoux Cedric's avatar
Midoux Cedric committed
57
58
```

59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
### Combine duplicates lines with comma

```python
import csv
import os

os.system("sort -k1,1 user_ko.txt > user_ko-sort.txt")

with open("user_ko-sort.txt", "r") as f:
	with open("user_ko-uniq.txt", "w") as out:
		reader=csv.reader(f, delimiter='\t')
		old_gene=""
		old_ko=""
		for row in reader:
			gene=row[0]
			try:
				ko=row[1]
			except IndexError:
				ko="NA"
			if(gene==old_gene):
				old_ko=old_ko+","+ko
			else:
				out.write("%s\t%s\n"%(old_gene, old_ko))
				old_gene=gene
				old_ko=ko
		out.write("%s\t%s\n"%(gene, ko))
```