Update RNAmining according to revisors comments

volumes/rnamining-front/about.php

@@ -14,7 +14,7 @@
  <div class="row">
  <div class="col-md-8 col-md-offset-2 col-xs-12 col-sm-12">
  <h4 class="text-justify text-about" style="line-height:30px;text-indent:50px">
- <p><span class="specialchar">RNAmining</span> is a web tool that allows nucleotides coding potential prediction. It takes a user-defined fasta sequences. This tool was implemented using machine learning algorithms. Machine learning is a subfield of computer science that developed from the study of pattern recognition and computational learning theories in artificial intelligence. This tool operate through a model obtained from training data analyzes and produces an inferred function, which can be used for mapping new examples.
+ <p><span class="specialchar">RNAmining</span> is a web tool that allows nucleotides coding potential prediction. It takes a user-defined fasta sequences. This tool was implemented using XGBoost machine learning algorithm. Machine learning is a subfield of computer science that developed from the study of pattern recognition and computational learning theories in artificial intelligence. This tool operate through a model obtained from training data analyzes and produces an inferred function, which can be used for mapping new examples.
  </p>
  </h4>
 
@@ -27,14 +27,15 @@
 
  <h3 class="portfolio-text">How does the algorithm used work?</h3>
  <h4 class="text-justify text-about" style="line-height:30px;text-indent:50px">
- <p>The algorithm begins by reading the RNA sequences provided in the uploaded file. Thereafter, it is divided into two main parts: the preprocessing and the prediction. In preprocessing, we perfomed a tri-nucleotides frequency of each RNA sequence and then, normalize it according to the sequence's lenght. This process is save in a file, which is going to be used as input for the second part. In prediction, since the user provides the organism type (e.g. Homo sapiens), the tool selects a specific organism model trained by XGBoost and perform the prediction, which is shown in the platform and can be downloaded as a .zip file.</p>
+ <p>The algorithm begins by reading the RNA sequences provided in the uploaded file. Thereafter, it is divided into two main parts: the preprocessing and the prediction. In preprocessing, we perfomed a tri-nucleotides frequency of each RNA sequence and then, we normalized it according to the sequence's lenght. This process is save in a file, which is going to be used as input for the second part. In prediction, since the user provides the organism type (e.g. Homo sapiens), the tool selects a specific organism model trained by XGBoost and perform the prediction, which is shown in the platform and can be downloaded as a .zip file.</p>
  </h4>
 
  <h3 class="portfolio-text">How can RNAmining helps?</h3>
  <h4 class="text-justify text-about" style="line-height:30px;text-indent:50px">
- <p>Non-coding RNAs are untranslated RNA molecules, but are important players in the cellular regulation of organisms from different kingdom. Thus, the research interest on non-coding RNAs has increased dramatically in recent years. Its investigation is routine in every transcriptome or genome project, since any mutations or misregulation on them result in disorders such as: tumor formation (cancerous or other type), cardiovascular, neurological diseases and others human illness. Therefore, exists an important step in ncRNAs research which is the ability to distinguish coding/non-coding sequences. Thus, <span class="specialchar">RNAmining</span> was developed to perform nucleotides coding potential prediction.</p>
+ <p>Non-coding RNAs are untranslated RNA molecules, but are important players in the cellular regulation of organisms from different kingdom. Thus, the research interest on non-coding RNAs has increased dramatically in recent years. Its investigation is routine in every transcriptome or genome project, since any mutations or misregulation on them result in disorders such as: tumor formation (cancerous or other type), cardiovascular, neurological diseases and others human illness. Therefore, exists an important step in ncRNAs research which is the ability to distinguish coding/non-coding sequences.</p>
 
- <p>Thus, <span class="specialchar">RNAmining</span> was built to enable easy access to coding potential prediction for non-programming researchers. Additionally, the results are very easy to interpret.</p>
+ <p>Thus, <span class="specialchar">RNAmining</span> was built to enable easy access to nucleotides coding potential prediction for non-programming researchers. Additionally, the results are very easy to interpret.</p>
+ <p>More information about RNAmining in: Ramos TAR, Galindo NRO, Arias-Carrasco R et al. RNAmining: A machine learning stand-alone and web server tool for RNA coding potential prediction [version 1; peer review: 2 approved with reservations]. F1000Research 2021, 10:323 (<a href= 'https://doi.org/10.12688/f1000research.52350.1'>https://doi.org/10.12688/f1000research.52350.1</a>)</p>
  </h4>
  </div>
  </div>

volumes/rnamining-front/assets/scripts/rnamining.py

@@ -40,7 +40,7 @@ def process_inputfile(filename, organism_name,output_folder):
  return X
 
 
-def process_outputfile(filename_path, predict, organism_name, prediction_type, output_folder):
+def process_outputfile(filename_path, predict, proba, organism_name, prediction_type, output_folder):
  """
  Description: function that generates the output file. First, it converts the predict classes so that the predictions
  with value equal to 1 are renamed to coding and 0 to non-coding. Then, the funciton generates a file with a header for general information
@@ -57,17 +57,21 @@ def process_outputfile(filename_path, predict, organism_name, prediction_type, o
  #The last instance
  if(i==(len(predict)-1)):
  if predict[i]==0:
- out[i] = ids[i] + '\tnon-coding'
- 
+ out[i] = ids[i] + '\tnon-coding\t'
+
  else:
- out[i] = ids[i] + '\tcoding'
+ out[i] = ids[i] + '\tcoding\t'
+ out[i] += str(max(proba[i]))
  else:
  #All instances
  if predict[i]==0:
- out[i] = ids[i] + '\tnon-coding\n'
+ out[i] = ids[i] + '\tnon-coding\t'
 
  else:
- out[i] = ids[i] + '\tcoding\n'
+ out[i] = ids[i] + '\tcoding\t'
+ out[i] += str(max(proba[i])) + '\n'
+
+
 
  output_file = open(output_folder+'/predictions.txt', 'w')
  output_file.writelines("RNAMining Predictions\n")
@@ -105,7 +109,8 @@ def predict(filename_path, organism_name, prediction_type, output_folder):
  X = process_inputfile(filename_path, organism_name, output_folder)
  model = pickle.load(open('models/' + 'coding_prediction/' + organism_name + '.pkl', 'rb'))
  predict = model.predict(X)
- process_outputfile(filename_path, predict, organism_name, prediction_type,output_folder)
+ proba = model.predict_proba(X)
+ process_outputfile(filename_path, predict, proba, organism_name, prediction_type,output_folder)
 
  except NameError:
  print('Please check if organism_name and prediction_type matches RNAMining documentation.')

volumes/rnamining-front/download.php

@@ -14,15 +14,16 @@
  <div class="row">
  <div class="col-md-8 col-md-offset-2 col-xs-12 col-sm-12">
 
- <h3 class="portfolio-text">Used databases</h3>
+ <h3 class="portfolio-text">Used databases</h3>
  <h4 class="text-justify text-about" style="line-height:30px;text-indent:50px">
  <p><span class="specialchar">RNAmining</span> was validated by a series of tests. all the FASTA sequences used in the creation process of this tool can be downloaded <a href = "../examples/Sequences.zip">here.</a></p>
  </h4>
 
 
+
  <h3 class="portfolio-text">Standalone Version</h3>
  <h4 class="text-justify text-about" style="line-height:30px;text-indent:50px">
- <p><span class="specialchar">RNAmining</span> was also developed in a standalone software. A complete tutorial of how to install and use it to perform coding potential prediction and RNA functional assignationis is described below.</p>
+ <p><span class="specialchar">RNAmining</span> was also developed in a standalone software. A complete tutorial of how to install and use it to perform coding potential prediction is described below.</p>
  </h4>
 
  <h3 class="portfolio-text">Dependencies</h3>
@@ -32,31 +33,42 @@
  <li>Pandas Version >= 0.23.3</li>
  <li>Scikit-learn Version >= 0.21.3</li>
  <li>XGBoost Version >= 1.2.0</li>
+ <li>Biopython Version >= 1.78</li>
  </ul> 
  </h4>
 
  <h3 class="portfolio-text">How to run?</h3>
  <h4 class="text-justify text-about" style="line-height:30px;text-indent:50px">
-  <p>Download the <a href="https://gitlab.com/integrativebioinformatics/RNAmining/-/tree/master/volumes/rnamining-front/assets/scripts/">RNAmining</a> files and run the commands explain there to perform files prediction!</p>
+ <p><span class="specialchar">RNAmining</span> is supported in <a href = "https://gitlab.com/integrativebioinformatics/RNAmining"> Docker version </a>and the user also can download the <a href="https://gitlab.com/integrativebioinformatics/RNAmining/-/tree/master/volumes/rnamining-front/assets/scripts/">RNAmining stand-alone version</a> through Gitlab. All the installation and run commands are explained in:</p>
  </h4> 
- 
- <h4 class="text-justify text-about" style="line-height:30px;">
-  <p>Run the following command to display all the parameters available to change in RNAmining:</p>
- </h4>
- <div style="white-space: nowrap; overflow-x: auto;">
-  <table>
-  <th>
-  python3 rnamining.py -h 
- </th>
- </table>
-  </div>
-  </br> 
+ 
+ <div class="container-fluid" style='margin: 20px 0'>
+ <div class="col-md-12 col-sm-12 col-xs-12 vcenter" style="text-align:center">
+ <h4> Docker and stand-alone versions with all commands: </p>
+ <a href="https://gitlab.com/integrativebioinformatics/RNAmining" target=_blank">
+ <img height=70 src="../assets/images/Logos/docker_image.png"/>Docker Version</a>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;
+ <a href="https://gitlab.com/integrativebioinformatics/RNAmining/-/tree/master/volumes/rnamining-front/assets/scripts/" target="_blank">
+ <img height=75 src="../assets/images/Logos/GitLab_Logo.png"/>&nbsp;&nbsp;Stand-alone Version</a>
+
+
+ </div>
+ </div>
 
-
- <h4 class="text-justify text-about" style="line-height:30px;">
- <p>If need more information see the file README.md in the .zip file!</p> 
+
+
+ <h3 class="portfolio-text">Release history</h3>
+ <h4 class="text-justify text-about">
+ <ul style="list-style-type:circle">
+ <li><b>RNAmining v1.0.4</b> (Jun 01, 2021)</li>
+ <p> Inclusion of classification probabilities in the output file </p>
+ <li><b>RNAmining v1.0.3</b> (Dec 17, 2020)</li>
+ <p> Fix inconsistency in sequence's read.</p>
+ <li><b>RNAmining v1.0.2</b> (Nov 13, 2020)</li>
+ <p> New version using XGBoost models.</p>
+ </ul> 
  </h4>
 
+
  </div>
  </div>
 

volumes/rnamining-front/index.php

@@ -31,6 +31,7 @@
  <!-- <img src="/assets/images/MDP_scheme_front.png" alt="MetaVolcano" class="img-responsive center-block"
  style="width:50%; padding-top: 50px; padding-bottom: 50px"> -->
  <p>See more <a href="/about">about</a> RNAmining and follow our <a href="/tutorial">tutorial</a> to learn how to use it.</p>
+ <p>More information about RNAmining in: <a href="https://doi.org/10.12688/f1000research.52350.1">https://doi.org/10.12688/f1000research.52350.1</a></p>
  </div>
  </div>
  </div>

volumes/rnamining-front/pages/footer.php

@@ -2,7 +2,7 @@
  <div style='text-align:center;font-size:11px;'>
  <hr>
  <p> Copyright &copy; <span id='year'></span></p>
- <p>Laboratory of Integrative Bioinformatics - University of Chile</p>
+  <p>Laboratory of Integrative Bioinformatics - Universidad de Chile &amp; Instituto Vandique</p>
  <p>Bioinformatics Multidisciplinary Environment - University of Rio Grande do Norte</p>
  <p>Artificial Intelligence Applications Laboratory - University of Paraiba</p>
  </div>

volumes/rnamining-front/results.php

@@ -5,7 +5,7 @@
  <?php include("pages/head.php"); ?>
 
 
- <script type="text/javascript" src="http://cdn.datatables.net/1.10.19/js/jquery.dataTables.min.js"></script>
+ <script type="text/javascript" src="https://cdn.datatables.net/1.10.24/js/jquery.dataTables.min.js"></script>
  <link rel="stylesheet" type="text/css" href="http://cdn.datatables.net/1.10.19/css/jquery.dataTables.min.css">
 
 
@@ -84,8 +84,8 @@
 
  <?php
  echo '<thead><tr><th style = "text-align:center;">Sequence ID</th>';
- echo '<th style = "text-align:center;">Coding Potential Classification</th></tr></thead>';
-
+ echo '<th style = "text-align:center;">Coding Potential Classification</th>';
+ echo '<th style = "text-align:center;">Classification Probabilities</th></tr></thead>';
  echo '<tbody>';
 
  foreach ($array as $i => $line) {
@@ -96,10 +96,12 @@
 
  $sequence_id = $exploded[0];
  $label = $exploded[1];
+ $probability = $exploded[2];
 
 
  echo '<tr><td>'.$sequence_id .'</td>';
- echo '<td>'.$label .'</td></tr>';
+ echo '<td>'.$label .'</td>';
+ echo '<td>'.$probability .'</td></tr>';
  }
  }