Merge pull request #253 from joaomcteixeira/2_user_defined_cara_deriv…

…es_pkls Added 3 user peaklist formats
Farseer-NMR · Jun 23, 2018 · 31ebaae · 31ebaae
2 parents 0b3eccd + a2c8019
commit 31ebaae
Show file tree

Hide file tree

Showing 18 changed files with 531 additions and 104 deletions.
diff --git a/Documentation/Accepted_Peaklists_Formats/user_pkl_1.prot b/Documentation/Accepted_Peaklists_Formats/user_pkl_1.prot
@@ -0,0 +1,8 @@
+   1  10.494 0.000 H     3
+   2 130.175 0.000 N     3
+   4   9.965 0.000 H     4
+   5 125.165 0.000 N     4
+   7   9.748 0.000 H     5
+   8 123.874 0.000 N     5
+  10   9.978 0.000 H     1
+  11 121.313 0.000 N     1
diff --git a/Documentation/Accepted_Peaklists_Formats/user_pkl_2.str b/Documentation/Accepted_Peaklists_Formats/user_pkl_2.str
@@ -0,0 +1,34 @@
+   loop_
+      _Atom_shift_assign_ID
+      _Residue_seq_code
+      _Residue_label
+      _Atom_name
+      _Atom_type
+      _Chem_shift_value
+      _Chem_shift_value_error
+      _Chem_shift_ambiguity_code
+
+         1  181   CYS  C     C 174.365 0.3     1  
+         2  181   CYS  CA    C  57.746 0.3     1  
+         3  181   CYS  CB    C  43.369 0.3     1  
+         4  181   CYS  H     H   9.977 0.020   1  
+         5  181   CYS  N     N 121.339 0.3     1  
+         6  183   VAL  C     C 177.016 0.3     1  
+         7  183   VAL  CA    C  65.287 0.3     1  
+         8  183   VAL  CB    C  31.942 0.3     1  
+         9  183   VAL  H     H   8.155 0.020   1  
+        10  183   VAL  N     N 121.041 0.3     1  
+        11  184   ASN  CA    C  57.382 0.3     1  
+        12  184   ASN  H     H   8.944 0.020   1  
+        13  184   ASN  N     N 116.914 0.3     1  
+        14  185   TRP  C     C 176.036 0.3     1  
+        15  185   TRP  CA    C  57.791 0.3     1  
+        16  185   TRP  CB    C  29.590 0.3     1  
+        17  185   TRP  H     H   8.641 0.020   1  
+        18  185   TRP  N     N 121.241 0.3     1  
+        19  186   VAL  C     C 174.765 0.3     1  
+        20  186   VAL  CA    C  61.880 0.3     1  
+        21  186   VAL  CB    C  35.364 0.3     1  
+        22  186   VAL  H     H   9.920 0.020   1  
+        23  186   VAL  N     N 120.580 0.3     1  
+stop_
diff --git a/Documentation/Accepted_Peaklists_Formats/user_pkl_3.csv b/Documentation/Accepted_Peaklists_Formats/user_pkl_3.csv
@@ -0,0 +1,5 @@
+Peak,Region,Type,Index (F2),Index (F1),?(F2) [ppm],?(F1) [ppm],?(F2) [Hz],?(F1) [Hz],Intensity [abs],Annotation,
+35,1,Automatic,339.3,1183.7,8.8003,118.7829,5279.5636,7220.8575,364636.02,A1,
+12,1,Automatic,246.7,464.4,9.3439,126.0890,5605.6855,7664.9981,166196.66,F2,
+16,1,Automatic,363.3,1559.3,8.6594,114.9676,5195.0334,6988.9240,196764.84,V3,
+22,1,Automatic,303.2,160.8,9.0119,129.1727,5406.5087,7852.4574,230523.44,W4,
diff --git a/core/fslibs/parsing_routines/__init__.py b/core/fslibs/parsing_routines/__init__.py
@@ -1,6 +1,11 @@
+# official formats
 from core.fslibs.parsing_routines.ansig import parse_ansig_peaklist as ansig
 from core.fslibs.parsing_routines.ccpnmrv2 import parse_ccpnmrv2_peaklist as ccpnmrv2
 from core.fslibs.parsing_routines.nmrdraw import parse_nmrdraw_peaklist as nmrdraw
 from core.fslibs.parsing_routines.nmrview import parse_nmrview_peaklist as nmrview
 from core.fslibs.parsing_routines.sparky import parse_sparky_peaklist as sparky
+# user defined formats
+from core.fslibs.parsing_routines.user_defined_1 import parse_user_peaklist_1 as user_pkl_1
+from core.fslibs.parsing_routines.user_defined_2 import parse_user_peaklist_2 as user_pkl_2
+from core.fslibs.parsing_routines.user_defined_3 import parse_user_peaklist_3 as user_pkl_3
 #from core.fslibs.parsing_routines.YOUR_FILE import parse_YOUR_FORMAT_peaklist as YOUR_FORMAT
diff --git a/core/fslibs/parsing_routines/parsing_template.py b/core/fslibs/parsing_routines/parsing_template.py
@@ -15,7 +15,7 @@
 """
 from core.fslibs.Peak import Peak
 
-def parse_YOUR_FORMAT_peaklists(peaklist_file):
+def parse_user_peaklist_NUM(peaklist_file):
     """
     Parses YOUR FORMAT peaklist.
     

diff --git a/core/fslibs/parsing_routines/user_defined_1.py b/core/fslibs/parsing_routines/user_defined_1.py
@@ -0,0 +1,111 @@
+"""
+Copyright © 2017-2018 Farseer-NMR
+Teixeira, J.M.C., Skinner, S.P., Arbesú, M. et al. J Biomol NMR (2018).
+https://doi.org/10.1007/s10858-018-0182-5
+
+João M.C. Teixeira and Simon P. Skinner
+
+@ResearchGate https://goo.gl/z8dPJU
+@Twitter https://twitter.com/farseer_nmr
+
+This file is part of Farseer-NMR.
+
+Farseer-NMR is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+Farseer-NMR is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with Farseer-NMR. If not, see <http://www.gnu.org/licenses/>.
+"""
+from core.fslibs.Peak import Peak
+from core.utils import eval_str_to_float
+from core.fslibs import wet as fsw
+
+def parse_user_peaklist_1(peaklist_file):
+    """
+    Parses a user defined CARA-derived peaklist.
+    
+    File extention: *.prot
+    Peaklist format:
+    
+        1  10.494 0.000 H     238
+        2 130.175 0.000 N     238
+        4   9.965 0.000 H     216
+        5 125.165 0.000 N     216
+    
+    In the current version, only H and N atoms are considered.
+    
+    Returns:
+        a list fo Peak objects.
+    """
+
+    fin = open(peaklist_file, 'r')
+    peakList = []
+
+    current_residue = None
+    count_residue = 0
+
+    counter = -1
+
+    eval_elements = [
+        str.isdigit,
+        eval_str_to_float,
+        eval_str_to_float,
+        str.isalpha,
+        str.isdigit
+        ]
+
+    for line in fin:
+        counter += 1
+
+        ls = line.strip().split()
+
+        if not ls:
+            continue
+
+        elif all([f(e) for e, f in zip(ls, eval_elements)]) \
+                and len(ls) == 5:
+            pass
+
+        else:
+            msg = "The peaklist {} contains a wrong line format in line {}."\
+                .format(peaklist_file, counter)
+            print(fsw.gen_wet('ERROR', msg, 29))
+            fsw.abort()
+
+        if ls[3] not in ('N', 'H'):
+            continue
+
+        if ls[-1] != current_residue:
+            current_residue = ls[-1]
+            position = [ls[1]]
+            atom = [ls[3]]
+            count_residue += 1
+
+        elif ls[-1] == current_residue:
+            position.append(ls[1])
+            atom.append(ls[3])
+
+            peak = Peak(
+                peak_number=count_residue,
+                positions=position,
+                residue_number=current_residue,
+                residue_type=None,
+                atoms=atom,
+                linewidths=[0, 0],
+                volume=0,
+                height=0,
+                format_='user_pkl_1'
+                )
+
+            peakList.append(peak)
+
+    fin.close()
+
+    return peakList 
diff --git a/core/fslibs/parsing_routines/user_defined_2.py b/core/fslibs/parsing_routines/user_defined_2.py
@@ -0,0 +1,96 @@
+"""
+Copyright © 2017-2018 Farseer-NMR
+Teixeira, J.M.C., Skinner, S.P., Arbesú, M. et al. J Biomol NMR (2018).
+https://doi.org/10.1007/s10858-018-0182-5
+
+João M.C. Teixeira and Simon P. Skinner
+
+@ResearchGate https://goo.gl/z8dPJU
+@Twitter https://twitter.com/farseer_nmr
+
+This file is part of Farseer-NMR.
+
+Farseer-NMR is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+Farseer-NMR is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with Farseer-NMR. If not, see <http://www.gnu.org/licenses/>.
+"""
+from core.fslibs.Peak import Peak
+
+def parse_user_peaklist_2(peaklist_file):
+    """
+    Parses a CARA peaklist.
+    
+    File extention: *.str
+    Peaklist format:
+    
+           loop_
+      _Atom_shift_assign_ID
+      _Residue_seq_code
+      _Residue_label
+      _Atom_name
+      _Atom_type
+      _Chem_shift_value
+      _Chem_shift_value_error
+      _Chem_shift_ambiguity_code
+         1  181   CYS  C     C 174.365 0.3     1  
+         2  181   CYS  CA    C  57.746 0.3     1  
+         3  181   CYS  CB    C  43.369 0.3     1  
+         4  181   CYS  H     H   9.977 0.020   1 
+    
+    In the current version, only H and N atoms are considered.
+    
+    Returns:
+        a list fo Peak objects.
+    """
+    fin = open(peaklist_file, 'r')
+    peakList = []
+
+    current_residue = None
+    residue_counter = 0
+
+    for line in fin:
+        if not line.strip() \
+                or line.strip().startswith('_') \
+                or line.strip().endswith('_'):
+            continue
+
+        ls = line.strip().split()
+
+        if ls[3] not in ('N', 'H'):
+            continue
+
+        if ls[1] != current_residue:
+            current_residue = ls[1]
+            positions = [ls[5]]
+            atom = [ls[3]]
+            residue_counter += 1
+
+        elif ls[1] == current_residue:
+            positions.append(ls[5])
+            atom.append(ls[3])
+
+            peak = Peak(
+                peak_number=residue_counter,
+                positions=positions,
+                residue_type=ls[2],
+                residue_number=ls[1],
+                atoms=atom,
+                linewidths=[0, 0],
+                volume=0,
+                height=0,
+                format_='user_pkl_2'
+                )
+
+            peakList.append(peak)
+
+    fin.close()
+    return peakList
diff --git a/core/fslibs/parsing_routines/user_defined_3.py b/core/fslibs/parsing_routines/user_defined_3.py
@@ -0,0 +1,62 @@
+"""
+YOUR DESCRIPTION HERE
+
+To add your parsing routine, you sould:
+
+1) code your funcion in this file
+2) add a import statment in the __init__.py file according to the
+    given examples.
+3) code the identification snipet in core.fslibs.parsing.get_peaklist_format()
+    Add, if necessary, a file extention to the list:
+        core.fslibs.parsing.file_extensions
+4) if your peaklist requires a FASTA file to read residue types, add your
+    peaklist format code (defined in 3) in the list:
+        core.fslibs.setup_farseer_calculation.peaklist_format_requires_fasta
+"""
+from core.fslibs.Peak import Peak
+from core.utils import aal1tol3
+
+def parse_user_peaklist_3(peaklist_file):
+    """
+    Parses YOUR FORMAT peaklist.
+    
+    According to the format:
+    
+        * paste an example of your format here*
+    
+    Parameters:
+        - peaklist_file (str): path to peaklist
+    
+    Returns:
+        peakList (list): a list of Peak objects.
+    """
+    fin = open(peaklist_file, 'r')
+    peakList = []
+
+
+    for line in fin:
+
+        ls = line.strip().rstrip(',').split(',')
+
+        if not line.strip() or not ls[0].isdigit():
+            continue
+
+        pk = Peak(
+            peak_number=ls[0],
+            positions=ls[5:7],
+            atoms=['H','N'],
+            residue_type=aal1tol3[ls[-1][0]],
+            residue_number=ls[-1][1:],
+            linewidths=ls[7:9],
+            height=ls[9],
+            volume=ls[9],
+            details=ls[2],
+            format_='user_pkl_3'
+            )
+
+        peakList.append(pk)
+
+    else:
+        fin.close()
+
+    return peakList