scripts/ folder

@@ -10,9 +10,9 @@ __pycache__/
 errors.txt
 known_issues.txt
 known_issues_reasons.txt
-kill_rnanet.sh
 Dockerfile
 LICENSE
 README.md
-automate.sh
-build_docker_image.sh
\ No newline at end of file
+scripts/automate.sh
+scripts/kill_rnanet.sh
+scripts/build_docker_image.sh
\ No newline at end of file

@@ -23,7 +23,7 @@ RUN apk update && apk add --no-cache \
     \
     mkdir /3D && mkdir /sequences && \
     \
-    mv /RNANet/x3dna-dssr /usr/local/bin/x3dna-dssr && chmod +x /usr/local/bin/x3dna-dssr && \
+    mv /RNANet/scripts/x3dna-dssr /usr/local/bin/x3dna-dssr && chmod +x /usr/local/bin/x3dna-dssr && \
     \
     curl -SL http://eddylab.org/infernal/infernal-1.1.3.tar.gz | tar xz  && cd infernal-1.1.3 && \
     ./configure && make -j 16 && make install && cd easel && make install && cd / && \

@@ -86,7 +86,7 @@ $ docker image import rnanet_v1.2_docker.tar rnanet
 ```
 * Step 3 : Run the container, giving it 3 folders to mount as volumes: a first to store the 3D data, a second to store the sequence data and alignments, and a third to output the results, data and logs:
 ```
-$ docker run -v path/to/3D/data/folder:/3D -v path/to/sequence/data/folder:/sequences -v path/to/experiment/results/folder:/runDir rnanet [ - other options ]
+$ docker run --rm -v path/to/3D/data/folder:/3D -v path/to/sequence/data/folder:/sequences -v path/to/experiment/results/folder:/runDir rnanet [ - other options ]
 ```
 
 The detailed list of options is below:
@@ -124,6 +124,11 @@ The detailed list of options is below:
 ```
 You may not use the --3d-folder and --seq-folder options, they are set by default to the paths you provide with the -v options when running Docker.
 
+Typical usage:
+```
+nohup bash -c 'time docker run --rm -v /path/to/3D/data/folder:/3D -v /path/to/sequence/data/folder:/sequences -v /path/to/experiment/folder:/runDir rnanet -s --no-logs ' &
+```
+
 ## Using classical command line installation
 
 You need to install the dependencies:

@@ -1546,35 +1546,33 @@ class Pipeline:
                                             runDir + f"/data/{f}_counts.csv"])
 
             # Run statistics files
-            subprocess.run(["python3.8", fileDir+"/regression.py"])
+            subprocess.run(["python3.8", fileDir+"/scripts/regression.py", runDir + "/results/RNANet.db"])
             subprocess.run(["python3.8", fileDir+"/statistics.py", "--3d-folder",  path_to_3D_data, 
                             "--seq-folder", path_to_seq_data, "-r", str(self.CRYSTAL_RES)])
 
         # Save additional informations
+        os.makedirs(runDir + "/archive", exist_ok=True)
         with sqlite3.connect(runDir+"/results/RNANet.db") as conn:
             pd.read_sql_query("""SELECT rfam_acc, description, idty_percent, nb_homologs, nb_3d_chains, nb_total_homol, max_len, comput_time, comput_peak_mem 
                                  FROM family ORDER BY nb_3d_chains DESC;""",
-                              conn).to_csv(runDir + f"/results/archive/families_{time_str}.csv", float_format="%.2f", index=False)
+                              conn).to_csv(runDir + f"/archive/families_{time_str}.csv", float_format="%.2f", index=False)
             pd.read_sql_query("""SELECT eq_class, structure_id, chain_name, pdb_start, pdb_end, rfam_acc, inferred, date, exp_method, resolution, issue 
                                  FROM structure 
                                  JOIN chain ON structure.pdb_id = chain.structure_id
                                  ORDER BY structure_id, chain_name, rfam_acc ASC;""",
-                              conn).to_csv(runDir + f"/results/archive/summary_{time_str}.csv", float_format="%.2f", index=False)
+                              conn).to_csv(runDir + f"/archive/summary_{time_str}.csv", float_format="%.2f", index=False)
 
-        # Archive the results
+        # Update shortcuts to latest versions
+        subprocess.run(["rm", "-f", runDir + "/results/RNANET_datapoints_latest.tar.gz",
+                                    runDir + "/results/summary_latest.csv",
+                                    runDir + "/results/families_latest.csv"
+                        ])
         if self.ARCHIVE:
-            os.makedirs(runDir + "/results/archive", exist_ok=True)
             subprocess.run(["tar", "-C", path_to_3D_data + "/datapoints", "-czf",
-                            runDir + f"/results/archive/RNANET_datapoints_{time_str}.tar.gz", "."])
-
-            # Update shortcuts to latest versions
-            subprocess.run(["rm", "-f", runDir + "/results/RNANET_datapoints_latest.tar.gz",
-                            runDir + "/results/summary_latest.csv",
-                            runDir + "/results/families_latest.csv"
-                            ])
-            subprocess.run(['ln', "-s", runDir + f"/results/archive/RNANET_datapoints_{time_str}.tar.gz", runDir + "/results/RNANET_datapoints_latest.tar.gz"])
-            subprocess.run(['ln', "-s", runDir + f"/results/archive/summary_{time_str}.csv", runDir + "/results/summary_latest.csv"])
-            subprocess.run(['ln', "-s", runDir + f"/results/archive/families_{time_str}.csv", runDir + "/results/families_latest.csv"])
+                            runDir + f"/archive/RNANET_datapoints_{time_str}.tar.gz", "."])
+            subprocess.run(['ln', "-s", runDir + f"/archive/RNANET_datapoints_{time_str}.tar.gz", runDir + "/results/RNANET_datapoints_latest.tar.gz"])
+        subprocess.run(['ln', "-s", runDir + f"/archive/summary_{time_str}.csv", runDir + "/results/summary_latest.csv"])
+        subprocess.run(['ln', "-s", runDir + f"/archive/families_{time_str}.csv", runDir + "/results/families_latest.csv"])
 
     def sanitize_database(self):
         """Searches for issues in the database and correct them"""

@@ -15,7 +15,7 @@ cp `which x3dna-dssr` $THISDIR
 
 ######################################################## Build Docker image ######################################################
 # Execute the Dockerfile and build the image
-docker build -t persalteas/rnanet .
+docker build -t persalteas/rnanet ..
 
 ############################################################## Cleaning ##########################################################
 rm x3dna-dssr

@@ -7,15 +7,18 @@ problems = [
     "1k73_1_B"
 ]
 
+# provide the path to your data folders, the RNANet.db file, and the RNANet.py file as arguments to this script
 path_to_3D_data = sys.argv[1]
 path_to_seq_data = sys.argv[2]
+path_to_db = sys.argv[3]
+path_to_RNANet = sys.argv[4]
 
 for p in problems:
     print()
     print()
     print()
     print()
-    homology = ('-' in p)
+    homology = ('-' in p)   # H4cky l1f3
 
     # Remove the datapoints files and 3D files
     subprocess.run(["rm", '-f', path_to_3D_data + f"/rna_mapped_to_Rfam/{p}.cif"])
@@ -31,21 +34,20 @@ for p in problems:
 
         # Delete the chain from the database, and the associated nucleotides and re_mappings, using foreign keys
         for fam in families:
-            command = ["sqlite3", "results/RNANet.db", f"PRAGMA foreign_keys=ON; delete from chain where structure_id=\"{structure}\" and chain_name=\"{chain}\" and rfam_acc=\"{fam}\";"]
+            command = ["sqlite3", path_to_db, f"PRAGMA foreign_keys=ON; delete from chain where structure_id=\"{structure}\" and chain_name=\"{chain}\" and rfam_acc=\"{fam}\";"]
             print(' '.join(command))
             subprocess.run(command)
 
-        command = ["python3.8", "RNAnet.py", "--3d-folder", path_to_3D_data, "--seq-folder", path_to_seq_data, "-r", "20.0", "--extract", "--only", p]
+        command = ["python3.8", path_to_RNANet, "--3d-folder", path_to_3D_data, "--seq-folder", path_to_seq_data, "-r", "20.0", "--extract", "--only", p]
     else:
         # Delete the chain from the database, and the associated nucleotides and re_mappings, using foreign keys
-        command = ["sqlite3", "results/RNANet.db", f"PRAGMA foreign_keys=ON; delete from chain where structure_id=\"{structure}\" and chain_name=\"{chain}\" and rfam_acc is null;"]
+        command = ["sqlite3", path_to_db, f"PRAGMA foreign_keys=ON; delete from chain where structure_id=\"{structure}\" and chain_name=\"{chain}\" and rfam_acc is null;"]
         print(' '.join(command))
         subprocess.run(command)
 
-        command = ["python3.8", "RNAnet.py", "--3d-folder", path_to_3D_data, "--seq-folder", path_to_seq_data, "-r", "20.0", "--no-homology", "--extract", "--only", p]
+        command = ["python3.8", path_to_RNANet, "--3d-folder", path_to_3D_data, "--seq-folder", path_to_seq_data, "-r", "20.0", "--no-homology", "--extract", "--only", p]
 
     # Re-run RNANet
+    os.chdir(os.path.dirname(os.path.realpath(path_to_db)) + '/../')
     print('\n',' '.join(command),'\n')
     subprocess.run(command)
-
-# run statistics

@@ -20,7 +20,7 @@
 import matplotlib.pyplot as plt
 import pandas as pd
 import numpy as np
-import scipy, os, sqlite3
+import scipy, os, sqlite3, sys
 # from sklearn.linear_model import LinearRegression
 from mpl_toolkits.mplot3d import Axes3D
 pd.set_option('display.max_rows', None)
@@ -28,7 +28,10 @@ pd.set_option('display.max_rows', None)
 LSU_set = ["RF00002", "RF02540", "RF02541", "RF02543", "RF02546"]   # From Rfam CLAN 00112
 SSU_set = ["RF00177", "RF02542",  "RF02545", "RF01959", "RF01960"]  # From Rfam CLAN 00111
 
-with sqlite3.connect(os.getcwd()+"/results/RNANet.db") as conn:
+path_to_db = sys.argv[1]    # The RNANet.db file
+runDir = os.path.dirname(os.path.realpath(path_to_db)) + '/../'
+
+with sqlite3.connect(path_to_db) as conn:
     df = pd.read_sql("SELECT rfam_acc, max_len, nb_total_homol, comput_time, comput_peak_mem FROM family;", conn)
 
 to_remove = [ f for f in df.rfam_acc if f in LSU_set+SSU_set ]
@@ -74,7 +77,7 @@ ax.set_ylabel("Maximum length of sequences ")
 ax.set_zlabel("Computation time (s)")
 
 plt.subplots_adjust(wspace=0.4)
-plt.savefig(os.getcwd()+"/results/cmalign_jobs_performance.png")
+plt.savefig(runDir+"/results/cmalign_jobs_performance.png")
 
 # # ========================================================
 # # Linear Regression of max_mem as function of max_length
@@ -110,7 +113,7 @@ plt.savefig(os.getcwd()+"/results/cmalign_jobs_performance.png")
 # plt.plot(x, coeffs[0] + np.exp(coeffs[1]*x), "-g", label="expo fit")
 # plt.plot(x, coeffs_log[0] + coeffs_log[1]*np.log(x), "-b", label="log fit")
 # plt.legend()
-# plt.savefig("results/regression/memory_linear_model.png")
+# plt.savefig(runDir + "/results/regression/memory_linear_model.png")
 
 # # ========================================================
 # # Linear Regression of comp_time as function of n_chains
@@ -131,4 +134,4 @@ plt.savefig(os.getcwd()+"/results/cmalign_jobs_performance.png")
 # plt.ylabel("Computation time (s)")
 # plt.plot(x, b0 + b1*x, "-r", label="linear fit")
 # plt.legend()
-# plt.savefig("results/regression/comp_time_linear_model.png")
+# plt.savefig(runDir + "/results/regression/comp_time_linear_model.png")