From 8bababd2e2ec2169eb11eb7ddd9b7bbe21425803 Mon Sep 17 00:00:00 2001
From: Remi Planel <rplanel@pasteur.fr>
Date: Wed, 26 Feb 2020 12:50:31 +0100
Subject: [PATCH] Update the readme
---
README.md | 57 ++++++++++++++++++++++++++++++++++++-------------------
1 file changed, 38 insertions(+), 19 deletions(-)
diff --git a/README.md b/README.md
index 0a6acf8..c5c5bde 100644
--- a/README.md
+++ b/README.md
@@ -46,10 +46,10 @@ for guide_rna in guide_rnas:
_output :_
```
-{'target': 'TCATCACGGGCCTTCGCCACGCGCG', 'guide': 'TCATCACGGGCCTTCGCCAC', 'start': 82, 'stop': 102, 'pam': 80, 'ori': '-', 'pred': -0.4719254873780802}
-{'target': 'CATCACGGGCCTTCGCCACGCGCGC', 'guide': 'CATCACGGGCCTTCGCCACG', 'start': 81, 'stop': 101, 'pam': 79, 'ori': '-', 'pred': 1.0491308060379676}
-{'target': 'CGCGCGCGGCAAACAATCACAAACA', 'guide': 'CGCGCGCGGCAAACAATCAC', 'start': 63, 'stop': 83, 'pam': 61, 'ori': '-', 'pred': -0.9021152826078697}
-{'target': 'CCTGATCGGTATTGAACAGCATCTG', 'guide': 'CCTGATCGGTATTGAACAGC', 'start': 29, 'stop': 49, 'pam': 27, 'ori': '-', 'pred': 0.23853258873311955}
+{'target': 'TCATCACGGGCCTTCGCCACGCGCG', 'guide': 'TCATCACGGGCCTTCGCCAC', 'start': 82, 'stop': 102, 'pam': 80, 'ori': '-', 'target_id': 1, 'pred': -0.4719254873780802, 'off_targets_per_seed': []}
+{'target': 'CATCACGGGCCTTCGCCACGCGCGC', 'guide': 'CATCACGGGCCTTCGCCACG', 'start': 81, 'stop': 101, 'pam': 79, 'ori': '-', 'target_id': 2, 'pred': 1.0491308060379676, 'off_targets_per_seed': []}
+{'target': 'CGCGCGCGGCAAACAATCACAAACA', 'guide': 'CGCGCGCGGCAAACAATCAC', 'start': 63, 'stop': 83, 'pam': 61, 'ori': '-', 'target_id': 3, 'pred': -0.9021152826078697, 'off_targets_per_seed': []}
+{'target': 'CCTGATCGGTATTGAACAGCATCTG', 'guide': 'CCTGATCGGTATTGAACAGC', 'start': 29, 'stop': 49, 'pam': 27, 'ori': '-', 'target_id': 4, 'pred': 0.23853258873311955, 'off_targets_per_seed': []}
```
### Command line interface
@@ -82,7 +82,7 @@ $ crisprbact predict from-str --help
```
```
-Usage: crisprbact predict from-str [OPTIONS] [OUTPUT_FILE]
+Usage: cli.py predict from-str [OPTIONS] [OUTPUT_FILE]
Outputs candidate guide RNAs for the S. pyogenes dCas9 with predicted on-
target activity from a target gene.
@@ -91,8 +91,15 @@ Usage: crisprbact predict from-str [OPTIONS] [OUTPUT_FILE]
"stdout"
Options:
- -t, --target TEXT [required]
- --help Show this message and exit.
+ -t, --target TEXT Sequence file to target [required]
+ -s, --off-target-sequence FILENAME
+ Sequence in which you want to find off-
+ targets
+ -w, --off-target-sequence-format [fasta|gb|genbank]
+ Sequence in which you want to find off-
+ targets format [default: genbank]
+ --help Show this message and exit.
+
```
```console
@@ -124,7 +131,7 @@ $ crisprbact predict from-seq --help
```
```
-Usage: crisprbact predict from-seq [OPTIONS] [OUTPUT_FILE]
+Usage: cli.py predict from-seq [OPTIONS] [OUTPUT_FILE]
Outputs candidate guide RNAs for the S. pyogenes dCas9 with predicted on-
target activity from a target gene.
@@ -133,9 +140,16 @@ Usage: crisprbact predict from-seq [OPTIONS] [OUTPUT_FILE]
"stdout"
Options:
- -t, --target FILENAME Sequence file [required]
- -f, --seq-format [fasta|fa|gb|genbank]
- Sequence file format [default: fasta]
+ -t, --target FILENAME Sequence file to target [required]
+ -f, --seq-format [fasta|gb|genbank]
+ Sequence file to target format [default:
+ fasta]
+ -s, --off-target-sequence FILENAME
+ Sequence in which you want to find off-
+ targets
+ -w, --off-target-sequence-format [fasta|gb|genbank]
+ Sequence in which you want to find off-
+ targets format [default: genbank]
--help Show this message and exit.
```
@@ -151,17 +165,22 @@ $ crisprbact predict from-seq -t /tmp/seq.fasta guide-rnas.tsv
$ crisprbact predict from-seq -t /tmp/seq.gb -f gb guide-rnas.tsv
```
+- Off-targets
+
+```console
+predict from-seq -t data-test/sequence.fasta -s data-test/sequence.gb guide-rnas.tsv
+```
+
##### Output file
```
-target PAM position prediction input_id
-ATTTGTTGGCAACCCAGCCAGCCTT 855 -0.7310112260341689 CP027060.1
-CACGTCCGGCAATATTTCCGCGAAC 830 0.14773859036983505 CP027060.1
-TCCGAGCGGCAACGTCTCTGATAAC 799 -0.4922487382950619 CP027060.1
-GCTTAAAGGGCAAAATGTCACGCCT 769 -1.814666749464254 CP027060.1
-CTTAAAGGGCAAAATGTCACGCCTT 768 -0.4285147731290152 CP027060.1
-CGTTTGAGGAGATCCACAAAATTAT 732 -1.2437430146548256 CP027060.1
-CATGAATGGTATAAACCGGCGTGCC 680 -0.8043242669169294 CP027060.1
+target_id target PAM position prediction target_seq_id seed_size off_target_recid off_target_start off_target_end off_target_pampos off_target_strand off_target_feat_type off_target_feat_start off_target_feat_end off_target_feat_strand off_target_locus_tag off_target_gene off_target_note off_target_product off_target_protein_id
+1 TGATCCAGGCATTTTTTAGCTTCAT 835 0.47949500169043713 NC_017634.1:2547433-2548329 8 NC_017634.1 1388198 1388209 1388209 +
+1 TGATCCAGGCATTTTTTAGCTTCAT 835 0.47949500169043713 NC_017634.1:2547433-2548329 8 NC_017634.1 2244514 2244525 2244525 + CDS 2243562 2244720 -1 NRG857_10810 COG1174 ABC-type proline/glycine betaine transport systems, permease component putative transport system permease YP_006120510.1
+1 TGATCCAGGCATTTTTTAGCTTCAT 835 0.47949500169043713 NC_017634.1:2547433-2548329 8 NC_017634.1 4160984 4160995 4160995 + CDS 4160074 4161406 -1 NRG857_19625 hslU COG1220 ATP-dependent protease HslVU (ClpYQ), ATPase subunit ATP-dependent protease ATP-binding subunit HslU YP_006122267.1
+1 TGATCCAGGCATTTTTTAGCTTCAT 835 0.47949500169043713 NC_017634.1:2547433-2548329 8 NC_017634.1 4534189 4534200 4534200 +
+1 TGATCCAGGCATTTTTTAGCTTCAT 835 0.47949500169043713 NC_017634.1:2547433-2548329 8 NC_017634.1 548804 548815 548804 -
+1 TGATCCAGGCATTTTTTAGCTTCAT 835 0.47949500169043713 NC_017634.1:2547433-2548329 8 NC_017634.1 786462 786473 786462 - CDS 785384 786470 1 NRG857_03580 COG2055 Malate/L-lactate dehydrogenases hypothetical protein YP_006119079.1
```
--
GitLab