From 91d6b94343f05b345db2c8f4dba19b0ef82ef7e6 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 16:54:44 +0800
Subject: [PATCH 01/22] Update README.md

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 923446b..210c22f 100644
--- a/README.md
+++ b/README.md
@@ -1 +1,2 @@
-# DeepCIP
\ No newline at end of file
+# DeepCIP
+DeepCIP is a **D**eep learning method for **C**ircRNA **I**RES **P**rediction.

From 6b205fd52ca4f12e21d20afdcdec1300d876bacb Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 17:09:49 +0800
Subject: [PATCH 02/22] Update README.md

---
 README.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/README.md b/README.md
index 210c22f..b008f47 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,6 @@
 # DeepCIP
 DeepCIP is a **D**eep learning method for **C**ircRNA **I**RES **P**rediction.
+
+## Installation of DeepCIP and its environment
+First, download the repository and create the environment.
+    git clone 

From 0dc21a6c5d2a3e48de23a34696ff2363c765d83b Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 17:11:53 +0800
Subject: [PATCH 03/22] Update README.md

---
 README.md | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index b008f47..1009e00 100644
--- a/README.md
+++ b/README.md
@@ -3,4 +3,7 @@ DeepCIP is a **D**eep learning method for **C**ircRNA **I**RES **P**rediction.
 
 ## Installation of DeepCIP and its environment
 First, download the repository and create the environment.
-    git clone 
+```
+git clone https://github.com/zjupgx/DeepCIP.git
+```
+    

From e93a82bf8085a47e849ba84c6fa4a2d0f5c81aa2 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 17:46:49 +0800
Subject: [PATCH 04/22] Update README.md

---
 README.md | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 1009e00..672b968 100644
--- a/README.md
+++ b/README.md
@@ -5,5 +5,12 @@ DeepCIP is a **D**eep learning method for **C**ircRNA **I**RES **P**rediction.
 First, download the repository and create the environment.
 ```
 git clone https://github.com/zjupgx/DeepCIP.git
+cd ./DeepCIP
+conda env create -f environment.yml
 ```
-    
+Then, activate the "DeepCIP_pytorch" environment.
+```
+conda activate DeepCIP_pytorch
+```
+
+## Usage

From e653f9e71ce4dfc27a260a9cc651a0bc4820f469 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 18:48:59 +0800
Subject: [PATCH 05/22] Update README.md

---
 README.md | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/README.md b/README.md
index 672b968..08e64a7 100644
--- a/README.md
+++ b/README.md
@@ -14,3 +14,12 @@ conda activate DeepCIP_pytorch
 ```
 
 ## Usage
+### Run DeepCIP for circRNA IRES prediction
+Example:
+```
+python DeepCIP.py --data_name example --input_file ./data/human_circires.fa --outfile ./results/predict.out
+```
+For more options:
+```
+python DeepCIP.py --help
+```

From b9e35d86d98aa268b8ad1cc4365e50a9d6bb40b8 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 19:01:58 +0800
Subject: [PATCH 06/22] Update README.md

---
 README.md | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/README.md b/README.md
index 08e64a7..a89f775 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,18 @@
 # DeepCIP
 DeepCIP is a **D**eep learning method for **C**ircRNA **I**RES **P**rediction.
 
+## The ViennaRNA package installation
+First, download the ViennaRNA package from https://www.tbi.univie.ac.at/RNA/download/sourcecode/2_5_x/ViennaRNA-2.5.1.tar.gz
+Then, install ViennaRNA package:
+```
+tar -zxvf ViennaRNA-2.5.1.tar.gz
+cd ViennaRNA-2.5.1
+./configure
+make
+make install
+```
+For more details, see https://github.com/ViennaRNA/ViennaRNA
+
 ## Installation of DeepCIP and its environment
 First, download the repository and create the environment.
 ```
@@ -23,3 +35,21 @@ For more options:
 ```
 python DeepCIP.py --help
 ```
+```
+usage: DeepCIP.py [-h] [--data_name] [--input_file INPUT_FILE] [--outfile OUTFILE] [--bs BS] [--c C] [--mode MODE] [--w W] [--s S]
+
+optional arguments:
+  -h, --help            show this help message and exit
+  --data_name           The name of your input dataset.
+  --input_file
+                        Input file for prediction. (*.fasta or *.fa file)
+  --outfile             Output file storage path.
+  --bs                  Batch size. (default=32) "--bs 32" means every 32 sampels constitute a prediction batch. This parameter affects the speed and results of the 
+                        prediction. The larger the batch size, the faster the prediction, as far as your machine allows. (If the lengths of your input sequences vary 
+                        greatly, it is recommended that you do not use a large batch size, or you can put sequences of similar lengths together for prediction)
+  --c                   Prediction threshold. (default=0.5)
+  --mode                The mode of prediction. (default=0) mode 0: Prediction directly on the input sequence. mode 1: The input sequence is partitioned by length w 
+                        and interval s, and then the partitioned sequence is predicted. (w and s can be set by --w and --s, respectively)
+  --w                   window size (default=174). See --mode description. It can be ignore when mode=0.
+  --s                   step (default=50). See --mode description. It can be ignore when mode=0.
+  ```

From 0a4d3b5f579da0ffbb5d97af645ba065867ff331 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 20:18:11 +0800
Subject: [PATCH 07/22] Update README.md

---
 README.md | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index a89f775..f4ecaec 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,10 @@
 DeepCIP is a **D**eep learning method for **C**ircRNA **I**RES **P**rediction.
 
 ## The ViennaRNA package installation
-First, download the ViennaRNA package from https://www.tbi.univie.ac.at/RNA/download/sourcecode/2_5_x/ViennaRNA-2.5.1.tar.gz
+RNAplfold from ViennaRNA version 2.5.1 is required to predict RNA secondary structure in DeepCIP. You need to install the ViennaRNA package before you start to use DeepCIP.
+
+First, download the ViennaRNA package from https://www.tbi.univie.ac.at/RNA/download/sourcecode/2_5_x/ViennaRNA-2.5.1.tar.gz .
+
 Then, install ViennaRNA package:
 ```
 tar -zxvf ViennaRNA-2.5.1.tar.gz

From dc13e42d8e38151921bfadeec3faf821033af088 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 20:24:11 +0800
Subject: [PATCH 08/22] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index f4ecaec..d191cea 100644
--- a/README.md
+++ b/README.md
@@ -39,7 +39,7 @@ For more options:
 python DeepCIP.py --help
 ```
 ```
-usage: DeepCIP.py [-h] [--data_name] [--input_file INPUT_FILE] [--outfile OUTFILE] [--bs BS] [--c C] [--mode MODE] [--w W] [--s S]
+usage: DeepCIP.py [-h] [--data_name] [--input_file] [--outfile] [--bs] [--c] [--mode] [--w] [--s]
 
 optional arguments:
   -h, --help            show this help message and exit

From 7299723183249a36cc4cbcaaa62828d5b5c9a37b Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 20:36:00 +0800
Subject: [PATCH 09/22] Update README.md

---
 README.md | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index d191cea..f3eb7d4 100644
--- a/README.md
+++ b/README.md
@@ -30,7 +30,10 @@ conda activate DeepCIP_pytorch
 
 ## Usage
 ### Run DeepCIP for circRNA IRES prediction
-Example:
+The file prepared for prediction can be put into folder ./data or any other path. 
+Then, type the following command to start the prediction, with parameters set according to your needs.
+
+For example:
 ```
 python DeepCIP.py --data_name example --input_file ./data/human_circires.fa --outfile ./results/predict.out
 ```

From 3733b3f0615946ef92e6a588c0ed73a6aadc3509 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 20:59:42 +0800
Subject: [PATCH 10/22] Update README.md

---
 README.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/README.md b/README.md
index f3eb7d4..7fe2ca3 100644
--- a/README.md
+++ b/README.md
@@ -59,3 +59,6 @@ optional arguments:
   --w                   window size (default=174). See --mode description. It can be ignore when mode=0.
   --s                   step (default=50). See --mode description. It can be ignore when mode=0.
   ```
+
+## Datasets
+Raw data used in our study can be avaliable in [GSE178718_Oligo_eGFP_expression.xlsx](https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE178718&format=file&file=GSE178718%5FOligo%5FeGFP%5Fexpression%2Exlsx) and [55k_oligos](https://bitbucket.org/alexeyg-com/irespredictor/src/v2/data/)

From 5cce8142edce4a12471c23e24f1ee037b3963df7 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 21:00:12 +0800
Subject: [PATCH 11/22] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 7fe2ca3..3bc40c9 100644
--- a/README.md
+++ b/README.md
@@ -61,4 +61,4 @@ optional arguments:
   ```
 
 ## Datasets
-Raw data used in our study can be avaliable in [GSE178718_Oligo_eGFP_expression.xlsx](https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE178718&format=file&file=GSE178718%5FOligo%5FeGFP%5Fexpression%2Exlsx) and [55k_oligos](https://bitbucket.org/alexeyg-com/irespredictor/src/v2/data/)
+Raw data used in our study can be avaliable in [GSE178718_Oligo_eGFP_expression](https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE178718&format=file&file=GSE178718%5FOligo%5FeGFP%5Fexpression%2Exlsx) and [55k_oligos](https://bitbucket.org/alexeyg-com/irespredictor/src/v2/data/)

From af6614ba03edefb28fff0dd9cc2538b2c03f72ab Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 4 Oct 2022 21:01:55 +0800
Subject: [PATCH 12/22] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 3bc40c9..12840c5 100644
--- a/README.md
+++ b/README.md
@@ -4,7 +4,7 @@ DeepCIP is a **D**eep learning method for **C**ircRNA **I**RES **P**rediction.
 ## The ViennaRNA package installation
 RNAplfold from ViennaRNA version 2.5.1 is required to predict RNA secondary structure in DeepCIP. You need to install the ViennaRNA package before you start to use DeepCIP.
 
-First, download the ViennaRNA package from https://www.tbi.univie.ac.at/RNA/download/sourcecode/2_5_x/ViennaRNA-2.5.1.tar.gz .
+First, download the ViennaRNA package from [ViennaRNA-2.5.1.tar.gz](https://www.tbi.univie.ac.at/RNA/download/sourcecode/2_5_x/ViennaRNA-2.5.1.tar.gz) .
 
 Then, install ViennaRNA package:
 ```

From 662eee1827804ae4f04df416701e2781648779f3 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Wed, 5 Oct 2022 15:55:17 +0800
Subject: [PATCH 13/22] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 12840c5..78c0ab1 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,5 @@
 # DeepCIP
-DeepCIP is a **D**eep learning method for **C**ircRNA **I**RES **P**rediction.
+DeepCIP is a **Deep** learning method for **C**ircRNA **I**RES **P**rediction.
 
 ## The ViennaRNA package installation
 RNAplfold from ViennaRNA version 2.5.1 is required to predict RNA secondary structure in DeepCIP. You need to install the ViennaRNA package before you start to use DeepCIP.

From 6dfe1c40a45cfb620e9b243a56731d5552575a92 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Sun, 9 Oct 2022 14:19:53 +0800
Subject: [PATCH 14/22] Update README.md

---
 README.md | 30 ++++++++++++++----------------
 1 file changed, 14 insertions(+), 16 deletions(-)

diff --git a/README.md b/README.md
index 78c0ab1..fa3089e 100644
--- a/README.md
+++ b/README.md
@@ -30,34 +30,32 @@ conda activate DeepCIP_pytorch
 
 ## Usage
 ### Run DeepCIP for circRNA IRES prediction
-The file prepared for prediction can be put into folder ./data or any other path. 
+The file prepared for prediction should be put into folder ./data. 
 Then, type the following command to start the prediction, with parameters set according to your needs.
 
 For example:
 ```
-python DeepCIP.py --data_name example --input_file ./data/human_circires.fa --outfile ./results/predict.out
+python DeepCIP.py -n example -i human_circires.fa
 ```
 For more options:
 ```
 python DeepCIP.py --help
 ```
 ```
-usage: DeepCIP.py [-h] [--data_name] [--input_file] [--outfile] [--bs] [--c] [--mode] [--w] [--s]
+usage: DeepCIP.py [-h] [-n] [-i] [-b] [-c] [-m] [-w] [-s]
 
 optional arguments:
-  -h, --help            show this help message and exit
-  --data_name           The name of your input dataset.
-  --input_file
-                        Input file for prediction. (*.fasta or *.fa file)
-  --outfile             Output file storage path.
-  --bs                  Batch size. (default=32) "--bs 32" means every 32 sampels constitute a prediction batch. This parameter affects the speed and results of the 
-                        prediction. The larger the batch size, the faster the prediction, as far as your machine allows. (If the lengths of your input sequences vary 
-                        greatly, it is recommended that you do not use a large batch size, or you can put sequences of similar lengths together for prediction)
-  --c                   Prediction threshold. (default=0.5)
-  --mode                The mode of prediction. (default=0) mode 0: Prediction directly on the input sequence. mode 1: The input sequence is partitioned by length w 
-                        and interval s, and then the partitioned sequence is predicted. (w and s can be set by --w and --s, respectively)
-  --w                   window size (default=174). See --mode description. It can be ignore when mode=0.
-  --s                   step (default=50). See --mode description. It can be ignore when mode=0.
+  -h, --help           show this help message and exit
+  -n , --data_name     The name of your input dataset.
+  -i , --input_file    Input file for prediction. (*.fasta or *.fa file)
+  -b , --batch_size    Batch size. (default=32) "--bs 32" means every 32 sampels constitute a prediction batch. This parameter affects the speed and results of the 
+                       prediction. The larger the batch size, the faster the prediction, as far as your machine allows. (If the lengths of your input sequences vary 
+                       greatly, it is recommended that you do not use a large batch size, or you can put sequences of similar lengths together for prediction)
+  -c , --cut_off       Prediction threshold. (default=0.5)
+  -m , --mode          The mode of prediction. (default=0) mode 0: Prediction directly on the input sequence. mode 1: The input sequence is partitioned by length w and
+                       interval s, and then the partitioned sequence is predicted. (w and s can be set by --w and --s, respectively)
+  -w , --window_size   window size (default=174). See --mode description. It can be ignore when mode=0.
+  -s , --step          step (default=50). See --mode description. It can be ignore when mode=0.
   ```
 
 ## Datasets

From 4ca9ea8c8b757047efa64e0bf296211660a6c41a Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Sun, 9 Oct 2022 14:33:01 +0800
Subject: [PATCH 15/22] Update README.md

---
 README.md | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/README.md b/README.md
index fa3089e..7076e39 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,14 @@
 # DeepCIP
 DeepCIP is a **Deep** learning method for **C**ircRNA **I**RES **P**rediction.
 
+## System Requirments
+DeepCIP needs to run on a Linux operating system (e.g. Debian 11.3) with the following software installed.
+### Software Requirments:
+Python3.8
+Perl (Recommended v5.32.1)
+Anaconda
+
+
 ## The ViennaRNA package installation
 RNAplfold from ViennaRNA version 2.5.1 is required to predict RNA secondary structure in DeepCIP. You need to install the ViennaRNA package before you start to use DeepCIP.
 

From 52a830b0606ce084f79adf27f788192d2900d58a Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Sun, 9 Oct 2022 14:35:29 +0800
Subject: [PATCH 16/22] Update README.md

---
 README.md | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 7076e39..bf3a41c 100644
--- a/README.md
+++ b/README.md
@@ -4,9 +4,9 @@ DeepCIP is a **Deep** learning method for **C**ircRNA **I**RES **P**rediction.
 ## System Requirments
 DeepCIP needs to run on a Linux operating system (e.g. Debian 11.3) with the following software installed.
 ### Software Requirments:
-Python3.8
-Perl (Recommended v5.32.1)
-Anaconda
+* Python3.8
+* Perl (Recommended v5.32.1)
+* Anaconda
 
 
 ## The ViennaRNA package installation

From 17a5ad7fe14676c81e341d1dd0560cc47a9c5ef4 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Wed, 22 Feb 2023 11:53:03 +0800
Subject: [PATCH 17/22] Update README.md

---
 README.md | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index bf3a41c..749a944 100644
--- a/README.md
+++ b/README.md
@@ -24,6 +24,10 @@ make install
 ```
 For more details, see https://github.com/ViennaRNA/ViennaRNA
 
+## Seqkit installation
+DeepCIP relies on Seqkit to process RNA sequences (eg. subsequence segmentation)
+You can download Seqkit from https://bioinf.shenwei.me/seqkit/download/
+
 ## Installation of DeepCIP and its environment
 First, download the repository and create the environment.
 ```
@@ -50,20 +54,19 @@ For more options:
 python DeepCIP.py --help
 ```
 ```
-usage: DeepCIP.py [-h] [-n] [-i] [-b] [-c] [-m] [-w] [-s]
+usage: DeepCIP.py [-h] -n  -i  [-b] [-c] [-m] [-w] [-s] [-r ]
 
 optional arguments:
   -h, --help           show this help message and exit
   -n , --data_name     The name of your input dataset.
   -i , --input_file    Input file for prediction. (*.fasta or *.fa file)
-  -b , --batch_size    Batch size. (default=32) "--bs 32" means every 32 sampels constitute a prediction batch. This parameter affects the speed and results of the 
-                       prediction. The larger the batch size, the faster the prediction, as far as your machine allows. (If the lengths of your input sequences vary 
-                       greatly, it is recommended that you do not use a large batch size, or you can put sequences of similar lengths together for prediction)
+  -b , --batch_size    Batch size. (default=16) "--bs 16" means every 32 sampels constitute a prediction batch. This parameter affects the speed and results of the prediction. The larger the batch size, the faster the prediction, as far as your machine allows. (If the lengths of your input sequences vary greatly, it is recommended that you do not use a large batch size, or you can put sequences of similar lengths together for prediction)
   -c , --cut_off       Prediction threshold. (default=0.5)
-  -m , --mode          The mode of prediction. (default=0) mode 0: Prediction directly on the input sequence. mode 1: The input sequence is partitioned by length w and
-                       interval s, and then the partitioned sequence is predicted. (w and s can be set by --w and --s, respectively)
-  -w , --window_size   window size (default=174). See --mode description. It can be ignore when mode=0.
-  -s , --step          step (default=50). See --mode description. It can be ignore when mode=0.
+  -m , --mode          The mode of prediction. (default=0) mode 0: Prediction directly on the input sequence. mode 1: The input sequence is partitioned by length w and interval s, and then the partitioned sequence is predicted. (w and s can be set by --w and --s, respectively)
+                       mode 2:
+  -w , --window_size   window size (default=174). See --mode description. It can be ignore when mode not is 1.
+  -s , --step          step (default=50). See --mode description. It can be ignore when mode not is 1.
+  -r  , --region       region of circRNA detection. e.g -r 1 12 for first 12 bases, -r -12 -1 for last 12 bases, -r 13 -1 for cutting first 12 bases. See --mode description. It can be ignore when mode not is 2.
   ```
 
 ## Datasets

From c83b47a8141c36abdb88d9f5476f000a8cdf2dc7 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Wed, 22 Feb 2023 11:53:26 +0800
Subject: [PATCH 18/22] Update README.md

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 749a944..e51c94d 100644
--- a/README.md
+++ b/README.md
@@ -25,7 +25,8 @@ make install
 For more details, see https://github.com/ViennaRNA/ViennaRNA
 
 ## Seqkit installation
-DeepCIP relies on Seqkit to process RNA sequences (eg. subsequence segmentation)
+DeepCIP relies on Seqkit to process RNA sequences (eg. subsequence segmentation).
+
 You can download Seqkit from https://bioinf.shenwei.me/seqkit/download/
 
 ## Installation of DeepCIP and its environment

From 38744c2b6d922a2270209a1fa09715a4d10fd0a3 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Wed, 22 Feb 2023 12:23:55 +0800
Subject: [PATCH 19/22] Update README.md

---
 README.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/README.md b/README.md
index e51c94d..23c56ef 100644
--- a/README.md
+++ b/README.md
@@ -29,6 +29,8 @@ DeepCIP relies on Seqkit to process RNA sequences (eg. subsequence segmentation)
 
 You can download Seqkit from https://bioinf.shenwei.me/seqkit/download/
 
+Reference: W Shen, S Le, Y Li*, F Hu*. SeqKit: a cross-platform and ultrafast toolkit for FASTA/Q file manipulation. PLOS ONE. doi:10.1371/journal.pone.0163962.
+
 ## Installation of DeepCIP and its environment
 First, download the repository and create the environment.
 ```
@@ -70,5 +72,7 @@ optional arguments:
   -r  , --region       region of circRNA detection. e.g -r 1 12 for first 12 bases, -r -12 -1 for last 12 bases, -r 13 -1 for cutting first 12 bases. See --mode description. It can be ignore when mode not is 2.
   ```
 
+The result will be saved as a csv format file.
+
 ## Datasets
 Raw data used in our study can be avaliable in [GSE178718_Oligo_eGFP_expression](https://www.ncbi.nlm.nih.gov/geo/download/?acc=GSE178718&format=file&file=GSE178718%5FOligo%5FeGFP%5Fexpression%2Exlsx) and [55k_oligos](https://bitbucket.org/alexeyg-com/irespredictor/src/v2/data/)

From f7da5f99fe20eed924694bb60fa57c03e2fdb3a1 Mon Sep 17 00:00:00 2001
From: "PGX@ZJU" <94656251+zjupgx@users.noreply.github.com>
Date: Tue, 13 Jun 2023 16:21:29 +0800
Subject: [PATCH 20/22] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 23c56ef..60d56de 100644
--- a/README.md
+++ b/README.md
@@ -50,7 +50,7 @@ Then, type the following command to start the prediction, with parameters set ac
 
 For example:
 ```
-python DeepCIP.py -n example -i human_circires.fa
+python DeepCIP.py -n example -i circires_case.fa
 ```
 For more options:
 ```

From 9937c48cdcce4b5db3d918e82de4efae35f0aa86 Mon Sep 17 00:00:00 2001
From: Yuxuan Zhou <114974251+zhouyx911@users.noreply.github.com>
Date: Wed, 5 Jul 2023 15:25:16 +0800
Subject: [PATCH 21/22] Update DeepCIP.py

update
---
 DeepCIP.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/DeepCIP.py b/DeepCIP.py
index d7e2bca..ced1d10 100644
--- a/DeepCIP.py
+++ b/DeepCIP.py
@@ -169,6 +169,8 @@ def DeepCIP_predict():
         ires_labels.append(ires_label)
 
     out_dir = './results'
+    if not os.path.exists(out_dir):
+        os.mkdir(out_dir)
     out_name = args.input_file.split('/')[-1].split('.')[0]
     outfile = f'{out_dir}/{out_name}_mode_{args.mode}.csv'
 
@@ -191,4 +193,4 @@ def DeepCIP_predict():
     print('The prediction results were saved in {}'.format(outfile))
 
 if __name__ == "__main__":
-    DeepCIP_predict()
\ No newline at end of file
+    DeepCIP_predict()

From 20d3c53a21e9113c15dd03f646025c1ecf0bf3c5 Mon Sep 17 00:00:00 2001
From: Yuxuan Zhou <114974251+zhouyx911@users.noreply.github.com>
Date: Thu, 6 Mar 2025 12:36:19 +0800
Subject: [PATCH 22/22] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 60d56de..b238805 100644
--- a/README.md
+++ b/README.md
@@ -63,7 +63,7 @@ optional arguments:
   -h, --help           show this help message and exit
   -n , --data_name     The name of your input dataset.
   -i , --input_file    Input file for prediction. (*.fasta or *.fa file)
-  -b , --batch_size    Batch size. (default=16) "--bs 16" means every 32 sampels constitute a prediction batch. This parameter affects the speed and results of the prediction. The larger the batch size, the faster the prediction, as far as your machine allows. (If the lengths of your input sequences vary greatly, it is recommended that you do not use a large batch size, or you can put sequences of similar lengths together for prediction)
+  -b , --batch_size    Batch size. (default=16) "--bs 16" means every 16 sampels constitute a prediction batch. This parameter affects the speed and results of the prediction. The larger the batch size, the faster the prediction, as far as your machine allows. (If the lengths of your input sequences vary greatly, it is recommended that you do not use a large batch size, or you can put sequences of similar lengths together for prediction)
   -c , --cut_off       Prediction threshold. (default=0.5)
   -m , --mode          The mode of prediction. (default=0) mode 0: Prediction directly on the input sequence. mode 1: The input sequence is partitioned by length w and interval s, and then the partitioned sequence is predicted. (w and s can be set by --w and --s, respectively)
                        mode 2: