From 89c73638cc3d2e5b2a6faa400870e8b3639416e2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Mon, 7 Feb 2022 18:49:00 +0100
Subject: [PATCH 01/30] Extended mdanalysis to accept other attributes as well.

---
 package/MDAnalysis/coordinates/LAMMPS.py | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 0cd3874997b..ef6dd695fcd 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -509,7 +509,8 @@ class DumpReader(base.ReaderBase):
     """
     format = 'LAMMPSDUMP'
     _conventions = ["auto", "unscaled", "scaled", "unwrapped",
-                    "scaled_unwrapped"]
+                    "charge", "scaled_unwrapped"]
+
     _coordtype_column_names = {
         "unscaled": ["x", "y", "z"],
         "scaled": ["xs", "ys", "zs"],
@@ -518,7 +519,7 @@ class DumpReader(base.ReaderBase):
     }
 
     @store_init_arguments
-    def __init__(self, filename, 
+    def __init__(self, filename,
                  lammps_coordinate_convention="auto",
                  unwrap_images=False,
                  **kwargs):
@@ -681,6 +682,14 @@ def _read_next_timestep(self):
             coord_cols.extend(image_cols)
 
         ids = "id" in attr_to_col_ix
+
+        # Create the data arrays for additional attributes which will be saved 
+        # under ts.data
+        if len(attrs) > 3:
+            for attribute_key in attrs[3:]:
+                ts.data[attribute_key] = np.empty(self.n_atoms)
+
+        # Parse all the atoms
         for i in range(self.n_atoms):
             fields = f.readline().split()
             if ids:
@@ -701,6 +710,11 @@ def _read_next_timestep(self):
             if self._has_forces:
                 ts.forces[i] = [fields[dim] for dim in force_cols]
 
+            # Add the capability to also collect other data
+            if len(attrs) > 3: # Then there is also more than just the positional data
+                for attribute_key in attrs[3:]:
+                    ts.data[attribute_key][i] = fields[attr_to_col_ix[attribute_key]]
+
         order = np.argsort(indices)
         ts.positions = ts.positions[order]
         if self._has_vels:

From 99b7875dc72c80aee5166afa48e0a05b2c2ad91c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Wed, 6 Apr 2022 14:24:34 +0200
Subject: [PATCH 02/30] Able to parse arbitrary columns now.

---
 package/MDAnalysis/coordinates/LAMMPS.py | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index ef6dd695fcd..291073a6d72 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -685,9 +685,15 @@ def _read_next_timestep(self):
 
         # Create the data arrays for additional attributes which will be saved 
         # under ts.data
+        additional_keys = []
         if len(attrs) > 3:
-            for attribute_key in attrs[3:]:
+            for attribute_key in attrs:
+                # Skip the normal columns
+                if attribute_key == "id" or attribute_key in self._coordtype_column_names[self.lammps_coordinate_convention]: 
+                    continue
+                # Else this is an additional field
                 ts.data[attribute_key] = np.empty(self.n_atoms)
+                additional_keys.append(attribute_key)
 
         # Parse all the atoms
         for i in range(self.n_atoms):
@@ -711,8 +717,8 @@ def _read_next_timestep(self):
                 ts.forces[i] = [fields[dim] for dim in force_cols]
 
             # Add the capability to also collect other data
-            if len(attrs) > 3: # Then there is also more than just the positional data
-                for attribute_key in attrs[3:]:
+            if len(additional_keys) != 0: # Then there is also more than just the positional data
+                for attribute_key in additional_keys:
                     ts.data[attribute_key][i] = fields[attr_to_col_ix[attribute_key]]
 
         order = np.argsort(indices)
@@ -721,6 +727,11 @@ def _read_next_timestep(self):
             ts.velocities = ts.velocities[order]
         if self._has_forces:
             ts.forces = ts.forces[order]
+
+        # Also need to sort the additional keys
+        for attribute_key in additional_keys:
+            ts.data[attribute_key] = ts.data[attribute_key][order]
+
         if (self.lammps_coordinate_convention.startswith("scaled")):
             # if coordinates are given in scaled format, undo that
             ts.positions = distances.transform_StoR(ts.positions,

From 36e9bb6bdf70777913929ab1c7d118c0a8797737 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Fri, 6 May 2022 11:57:25 +0200
Subject: [PATCH 03/30] Tried to fix most of the pep8 problems.

---
 package/MDAnalysis/coordinates/LAMMPS.py | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 291073a6d72..ca914d464fa 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -508,8 +508,8 @@ class DumpReader(base.ReaderBase):
     .. versionadded:: 0.19.0
     """
     format = 'LAMMPSDUMP'
-    _conventions = ["auto", "unscaled", "scaled", "unwrapped",
-                    "charge", "scaled_unwrapped"]
+    _conventions = ["auto", "unscaled", "scaled", "unwrapped", 
+            "scaled_unwrapped"]
 
     _coordtype_column_names = {
         "unscaled": ["x", "y", "z"],
@@ -522,7 +522,7 @@ class DumpReader(base.ReaderBase):
     def __init__(self, filename,
                  lammps_coordinate_convention="auto",
                  unwrap_images=False,
-                 **kwargs):
+                 additional_columns=False, **kwargs):
         super(DumpReader, self).__init__(filename, **kwargs)
 
         root, ext = os.path.splitext(self.filename)
@@ -537,6 +537,9 @@ def __init__(self, filename,
 
         self._unwrap = unwrap_images
 
+        if additional_columns:
+            self._additional_columns = additional_columns
+
         self._cache = {}
 
         self._reopen()
@@ -683,13 +686,17 @@ def _read_next_timestep(self):
 
         ids = "id" in attr_to_col_ix
 
-        # Create the data arrays for additional attributes which will be saved 
+        # Create the data arrays for additional attributes which will be saved
         # under ts.data
         additional_keys = []
         if len(attrs) > 3:
             for attribute_key in attrs:
                 # Skip the normal columns
-                if attribute_key == "id" or attribute_key in self._coordtype_column_names[self.lammps_coordinate_convention]: 
+                if attribute_key == "id" or \
+                        attribute_key in \
+                        self._coordtype_column_names[
+                        self.lammps_coordinate_convention] \
+                        or attribute_key not in self._additional_columns:
                     continue
                 # Else this is an additional field
                 ts.data[attribute_key] = np.empty(self.n_atoms)
@@ -717,9 +724,11 @@ def _read_next_timestep(self):
                 ts.forces[i] = [fields[dim] for dim in force_cols]
 
             # Add the capability to also collect other data
-            if len(additional_keys) != 0: # Then there is also more than just the positional data
+            # Then there is also more than just the positional data
+            if len(additional_keys) != 0:
                 for attribute_key in additional_keys:
-                    ts.data[attribute_key][i] = fields[attr_to_col_ix[attribute_key]]
+                    ts.data[attribute_key][i] = \
+                            fields[attr_to_col_ix[attribute_key]]
 
         order = np.argsort(indices)
         ts.positions = ts.positions[order]

From 3406e5b691a7dd01463900912e7235906b59eed6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Fri, 6 May 2022 12:47:06 +0200
Subject: [PATCH 04/30] First try at testing the additional column part.

---
 .../MDAnalysisTests/coordinates/reference.py  | 10 +++++--
 .../coordinates/test_lammps.py                | 24 ++++++++++++++-
 .../data/lammps/additional_columns.data       | 29 +++++++++++++++++++
 .../data/lammps/additional_columns.lammpstrj  | 19 ++++++++++++
 testsuite/MDAnalysisTests/datafiles.py        |  4 +++
 5 files changed, 82 insertions(+), 4 deletions(-)
 create mode 100644 testsuite/MDAnalysisTests/data/lammps/additional_columns.data
 create mode 100644 testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj

diff --git a/testsuite/MDAnalysisTests/coordinates/reference.py b/testsuite/MDAnalysisTests/coordinates/reference.py
index 2d2ec036bb5..15306769142 100644
--- a/testsuite/MDAnalysisTests/coordinates/reference.py
+++ b/testsuite/MDAnalysisTests/coordinates/reference.py
@@ -25,9 +25,9 @@
 from MDAnalysisTests import datafiles
 from MDAnalysisTests.datafiles import (PDB_small, PDB, LAMMPSdata,
                                        LAMMPSdata2, LAMMPSdcd2,
-                                       LAMMPSdata_mini, PSF_TRICLINIC,
-                                       DCD_TRICLINIC, PSF_NAMD_TRICLINIC,
-                                       DCD_NAMD_TRICLINIC)
+                                       LAMMPSdata_mini, LAMMPSdata_additional_columns,
+                                       PSF_TRICLINIC, DCD_TRICLINIC, 
+                                       PSF_NAMD_TRICLINIC, DCD_NAMD_TRICLINIC)
 
 
 class RefAdKSmall(object):
@@ -227,3 +227,7 @@ class RefLAMMPSDataMini(object):
                          dtype=np.float32)
     dimensions = np.array([60., 50., 30., 90., 90., 90.], dtype=np.float32)
 
+
+class RefLAMMPSDataAdditionalColumns(object):
+    filename = LAMMPSdata_additional_columns
+    n_atoms = 10
diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index c8afb286fb7..0b561ba05ff 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -34,11 +34,13 @@
 from MDAnalysisTests import make_Universe
 from MDAnalysisTests.coordinates.reference import (
     RefLAMMPSData, RefLAMMPSDataMini, RefLAMMPSDataDCD,
+    RefLAMMPSDataAdditionalColumns
 )
 from MDAnalysisTests.datafiles import (
     LAMMPScnt, LAMMPShyd, LAMMPSdata, LAMMPSdata_mini, LAMMPSdata_triclinic,
     LAMMPSDUMP, LAMMPSDUMP_allcoords, LAMMPSDUMP_nocoords, LAMMPSDUMP_triclinic,
-    LAMMPSDUMP_image_vf, LAMMPS_image_vf
+    LAMMPSDUMP_image_vf, LAMMPS_image_vf, LAMMPSdata_additional_columns,
+    LAMMPSDUMP_additional_columns
 )
 
 
@@ -498,6 +500,7 @@ def u(self, tmpdir, request):
             # no conversion needed
             f = LAMMPSDUMP
         else:
+            # Select if one wants to use the additional column format
             f = str(tmpdir.join('lammps.' + trjtype))
             with bz2.BZ2File(LAMMPSDUMP, 'rb') as datain:
                 data = datain.read()
@@ -511,6 +514,21 @@ def u(self, tmpdir, request):
         yield mda.Universe(f, format='LAMMPSDUMP',
                            lammps_coordinate_convention="auto")
 
+    @pytest.fixture()
+    def u_add(self):
+        f = LAMMPSDUMP_additional_columns
+        top = LAMMPSdata_additional_columns
+        yield mda.Universe(top, f, format='LAMMPSDUMP',
+                           lammps_coordinate_convention="auto",
+                           additional_columns=['q'])
+
+    @pytest.fixture()
+    def reference_additional_columns(self):
+        data['charges'] = np.array([2.58855e-03,  6.91952e-05,  1.05548e-02,  4.20319e-03,
+                        9.19172e-03,  4.79777e-03,  6.36864e-04,  5.87125e-03,
+                       -2.18125e-03,  6.88910e-03])
+        return data
+
     @pytest.fixture()
     def reference_positions(self):
         # manually copied from traj file
@@ -592,6 +610,10 @@ def test_atom_reordering(self, u, reference_positions):
             assert_allclose(atom1.position, atom1_pos-bmin, atol=1e-5)
             assert_allclose(atom13.position, atom13_pos-bmin, atol=1e-5)
 
+    def test_additional_colunmns(self, u_add, reference_additional_columns):
+        charges = u.trajectory[0].data['q']
+        assert_almost_equal(charges, reference_additional_columns['charges'])
+
 
 @pytest.mark.parametrize("convention",
                          ["unscaled", "unwrapped", "scaled_unwrapped"])
diff --git a/testsuite/MDAnalysisTests/data/lammps/additional_columns.data b/testsuite/MDAnalysisTests/data/lammps/additional_columns.data
new file mode 100644
index 00000000000..80b9a57bb7d
--- /dev/null
+++ b/testsuite/MDAnalysisTests/data/lammps/additional_columns.data
@@ -0,0 +1,29 @@
+LAMMPS data file via write_data, version 24 Mar 2022, timestep = 500
+
+10 atoms
+1 atom types
+
+0 42.6 xlo xhi
+0 44.2712 ylo yhi
+-25.1 25.1 zlo zhi
+
+Masses
+
+1 12.011
+
+Pair Coeffs # lj/cut/coul/long/omp
+
+1 0.0663 3.5812
+
+Atoms # full
+
+1 2 1 -0.00706800004577013 2.84 8.17 -25 0 0 0
+2 2 1 0.004078816788554217 7.1 8.17 -25 0 0 0
+3 2 1 -0.005824512619752745 2.13 6.94 -25 0 0 0
+4 2 1 0.002812345167059992 6.39 6.94 -25 0 0 0
+5 2 1 -0.004070019151543417 2.84 5.71 -25 0 0 0
+6 2 1 0.004796116641855679 7.1 5.71 -25 0 0 0
+7 2 1 -0.003217742434809291 2.13 4.48 -25 0 0 0
+8 2 1 0.0008273956785370801 6.39 4.48 -25 0 0 0
+9 2 1 -0.0003942558636157474 2.84 3.25 -25 0 0 0
+10 2 1 0.001288716009147968 7.1 3.25 -25 0 0 0
diff --git a/testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj b/testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj
new file mode 100644
index 00000000000..703e5d248db
--- /dev/null
+++ b/testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj
@@ -0,0 +1,19 @@
+ITEM: TIMESTEP
+0
+ITEM: NUMBER OF ATOMS
+10
+ITEM: BOX BOUNDS pp pp ff
+0.0000000000000000e+00 4.2600000000000001e+01
+0.0000000000000000e+00 4.4271200000000000e+01
+-2.5100000000000001e+01 2.5100000000000001e+01
+ITEM: ATOMS id x y z q
+1 2.84 8.17 -25 0.00258855
+2 7.1 8.17 -25 6.91952e-05
+3 2.13 6.94 -25 0.0105548
+4 6.39 6.94 -25 0.00420319
+5 2.84 5.71 -25 0.00919172
+6 7.1 5.71 -25 0.00479777
+7 2.13 4.48 -25 0.000636864
+8 6.39 4.48 -25 0.00587125
+9 2.84 3.25 -25 -0.00218125
+10 7.1 3.25 -25 0.0068891
diff --git a/testsuite/MDAnalysisTests/datafiles.py b/testsuite/MDAnalysisTests/datafiles.py
index 25e85618afe..223d52fa6bb 100644
--- a/testsuite/MDAnalysisTests/datafiles.py
+++ b/testsuite/MDAnalysisTests/datafiles.py
@@ -155,6 +155,7 @@
     "LAMMPSdata_deletedatoms",  # with deleted atoms
     "LAMMPSdata_triclinic",  # lammpsdata file to test triclinic dimension parsing, albite with most atoms deleted
     "LAMMPSdata_PairIJ",  # lammps datafile with a PairIJ Coeffs section
+    "LAMMPSdata_additional_columns",  # structure for the additional column lammpstrj
     "LAMMPSDUMP",
     "LAMMPSDUMP_long",  # lammpsdump file with a few zeros sprinkled in the first column first frame
     "LAMMPSDUMP_allcoords",  # lammpsdump file with all coordinate conventions (x,xs,xu,xsu) present, from LAMMPS rdf example
@@ -165,6 +166,7 @@
     "LAMMPSDUMP_chain1", # Lammps dump file with chain reader
     "LAMMPSDUMP_chain2", # Lammps dump file with chain reader
     "LAMMPS_chain", # Lammps data file with chain reader
+    "LAMMPSDUMP_additional_columns",  # lammpsdump file with additional data (an additional charge column)
     "unordered_res",  # pdb file with resids non sequential
     "GMS_ASYMOPT",  # GAMESS C1  optimization
     "GMS_SYMOPT",   # GAMESS D4h optimization
@@ -544,6 +546,8 @@
 LAMMPSDUMP_chain2 = (_data_ref / "lammps/chain_dump_2.lammpstrj").as_posix()
 LAMMPS_chain = (_data_ref / "lammps/chain_initial.data").as_posix()
 LAMMPSdata_many_bonds = (_data_ref / "lammps/a_lot_of_bond_types.data").as_posix()
+LAMMPSdata_additional_columns = (_data_ref / "lammps/additional_columns.data").as_posix()
+LAMMPSDUMP_additional_columns = (_data_ref / "lammps/additional_columns.lammpstrj").as_posix()
 
 unordered_res = (_data_ref / "unordered_res.pdb").as_posix()
 

From 87ed9cea5660a8c03debf9b968734b14e0d95b30 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Fri, 13 May 2022 11:08:11 +0200
Subject: [PATCH 05/30] Testing multi read columns as well.

---
 .../coordinates/test_lammps.py                | 12 +++++++---
 .../data/lammps/additional_columns.lammpstrj  | 22 +++++++++----------
 2 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index 0b561ba05ff..f57e2a9ad60 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -518,15 +518,19 @@ def u(self, tmpdir, request):
     def u_add(self):
         f = LAMMPSDUMP_additional_columns
         top = LAMMPSdata_additional_columns
-        yield mda.Universe(top, f, format='LAMMPSDUMP',
+        yield (mda.Universe(top, f, format='LAMMPSDUMP',
                            lammps_coordinate_convention="auto",
-                           additional_columns=['q'])
+                           additional_columns=['q']), 
+              mda.Universe(top, f, format='LAMMPSDUMP',
+                           lammps_coordinate_convention="auto",
+                           additional_columns=['q', 'l']))
 
     @pytest.fixture()
     def reference_additional_columns(self):
         data['charges'] = np.array([2.58855e-03,  6.91952e-05,  1.05548e-02,  4.20319e-03,
                         9.19172e-03,  4.79777e-03,  6.36864e-04,  5.87125e-03,
                        -2.18125e-03,  6.88910e-03])
+        data['l'] = np.array([1.1,  1.2]*5) # random test data
         return data
 
     @pytest.fixture()
@@ -611,8 +615,10 @@ def test_atom_reordering(self, u, reference_positions):
             assert_allclose(atom13.position, atom13_pos-bmin, atol=1e-5)
 
     def test_additional_colunmns(self, u_add, reference_additional_columns):
-        charges = u.trajectory[0].data['q']
+        charges = u_add[0].trajectory[0].data['q'] # this is the universe with just q
+        second  = u_add[1].trajectory[0].data['l'] # this is the universe with both
         assert_almost_equal(charges, reference_additional_columns['charges'])
+        assert_almost_equal(second, reference_additional_columns['l'])
 
 
 @pytest.mark.parametrize("convention",
diff --git a/testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj b/testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj
index 703e5d248db..b2d59267968 100644
--- a/testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj
+++ b/testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj
@@ -6,14 +6,14 @@ ITEM: BOX BOUNDS pp pp ff
 0.0000000000000000e+00 4.2600000000000001e+01
 0.0000000000000000e+00 4.4271200000000000e+01
 -2.5100000000000001e+01 2.5100000000000001e+01
-ITEM: ATOMS id x y z q
-1 2.84 8.17 -25 0.00258855
-2 7.1 8.17 -25 6.91952e-05
-3 2.13 6.94 -25 0.0105548
-4 6.39 6.94 -25 0.00420319
-5 2.84 5.71 -25 0.00919172
-6 7.1 5.71 -25 0.00479777
-7 2.13 4.48 -25 0.000636864
-8 6.39 4.48 -25 0.00587125
-9 2.84 3.25 -25 -0.00218125
-10 7.1 3.25 -25 0.0068891
+ITEM: ATOMS id x y z q l
+1 2.84 8.17 -25 0.00258855 1.1
+2 7.1 8.17 -25 6.91952e-05 1.2
+3 2.13 6.94 -25 0.0105548  1.1
+4 6.39 6.94 -25 0.00420319 1.2
+5 2.84 5.71 -25 0.00919172 1.1
+6 7.1 5.71 -25 0.00479777 1.2
+7 2.13 4.48 -25 0.000636864 1.1
+8 6.39 4.48 -25 0.00587125 1.2
+9 2.84 3.25 -25 -0.00218125 1.1
+10 7.1 3.25 -25 0.0068891 1.2

From efca264b68e2238fd8a207dbc25f97e0afefdca8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Fri, 20 May 2022 10:21:15 +0200
Subject: [PATCH 06/30] Fix the no additional columns case.

---
 package/MDAnalysis/coordinates/LAMMPS.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index ca914d464fa..3ed4477ce70 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -539,6 +539,8 @@ def __init__(self, filename,
 
         if additional_columns:
             self._additional_columns = additional_columns
+        else:
+            self._additional_columns = []
 
         self._cache = {}
 

From 2f023953cc9ae841495451ce9b8edf48ac0946ce Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Tue, 28 Jun 2022 16:47:25 +0200
Subject: [PATCH 07/30] Implemented requested changes to docs.

---
 package/MDAnalysis/coordinates/LAMMPS.py | 38 ++++++++++++++++++++----
 1 file changed, 33 insertions(+), 5 deletions(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 3ed4477ce70..342869befa5 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -465,6 +465,35 @@ class DumpReader(base.ReaderBase):
     *gamma*)`` to represent the unit cell. Lengths *A*, *B*, *C* are in the 
     MDAnalysis length unit (Å), and angles are in degrees.
 
+    By using the keyword `additional_columns`, you can specify arbitrary data to be
+    read alongside the coordinates. If specified, the keyword expects a list of the
+    names of the columns that you want to have read. The results of the parsing are
+    saved to the time step `data` dictionary alongside the name of the data column.
+    For instance, if you have time-dependent charges saved in a LAMMPS dump such as
+
+    ```
+    ITEM: ATOMS id x y z q l
+    1 2.84 8.17 -25 0.00258855 1.1
+    2 7.1 8.17 -25 6.91952e-05 1.2
+    ```
+
+    Then you may parse the additional columns `q` and `l` via.
+
+    ```
+    u = mda.Universe('path_to_data', 'path_to_lammpsdump', 
+                     additional_columns=['q', 'l'])
+    ```
+
+    The additional data is then available for each time step via (as the value of
+    the `data` dictionary, sorted by the ids of the atoms).
+
+    ```
+    for ts in u.trajectory:
+        charges = ts.data['q'] # Access the additional data, sorted by the id
+        ls = ts.data['l']
+        ...
+    ```
+
     Parameters
     ----------
     filename : str
@@ -508,8 +537,7 @@ class DumpReader(base.ReaderBase):
     .. versionadded:: 0.19.0
     """
     format = 'LAMMPSDUMP'
-    _conventions = ["auto", "unscaled", "scaled", "unwrapped", 
-            "scaled_unwrapped"]
+    _conventions = ["auto", "unscaled", "scaled", "unwrapped", "scaled_unwrapped"]
 
     _coordtype_column_names = {
         "unscaled": ["x", "y", "z"],
@@ -694,10 +722,10 @@ def _read_next_timestep(self):
         if len(attrs) > 3:
             for attribute_key in attrs:
                 # Skip the normal columns
-                if attribute_key == "id" or \
-                        attribute_key in \
+                if attribute_key == "id" or 
+                        attribute_key in 
                         self._coordtype_column_names[
-                        self.lammps_coordinate_convention] \
+                        self.lammps_coordinate_convention]
                         or attribute_key not in self._additional_columns:
                     continue
                 # Else this is an additional field

From c8f61dbd0f3abdf066e849f966bbc782ce070e8c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Tue, 28 Jun 2022 16:48:12 +0200
Subject: [PATCH 08/30] Implemented the requested changes to the tests.

---
 .../MDAnalysisTests/coordinates/reference.py     |  6 ++++--
 .../MDAnalysisTests/coordinates/test_lammps.py   | 16 ++++------------
 2 files changed, 8 insertions(+), 14 deletions(-)

diff --git a/testsuite/MDAnalysisTests/coordinates/reference.py b/testsuite/MDAnalysisTests/coordinates/reference.py
index 15306769142..5792aeaa129 100644
--- a/testsuite/MDAnalysisTests/coordinates/reference.py
+++ b/testsuite/MDAnalysisTests/coordinates/reference.py
@@ -229,5 +229,7 @@ class RefLAMMPSDataMini(object):
 
 
 class RefLAMMPSDataAdditionalColumns(object):
-    filename = LAMMPSdata_additional_columns
-    n_atoms = 10
+    charges = np.array([2.58855e-03, 6.91952e-05, 1.05548e-02, 4.20319e-03,
+                         9.19172e-03, 4.79777e-03, 6.36864e-04, 5.87125e-03,
+                        -2.18125e-03, 6.88910e-03])
+    additional_data = np.array(5 * [1.1, 1.2])
diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index f57e2a9ad60..bf47efa96ed 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -515,7 +515,7 @@ def u(self, tmpdir, request):
                            lammps_coordinate_convention="auto")
 
     @pytest.fixture()
-    def u_add(self):
+    def u_additional_columns(self):
         f = LAMMPSDUMP_additional_columns
         top = LAMMPSdata_additional_columns
         yield (mda.Universe(top, f, format='LAMMPSDUMP',
@@ -525,14 +525,6 @@ def u_add(self):
                            lammps_coordinate_convention="auto",
                            additional_columns=['q', 'l']))
 
-    @pytest.fixture()
-    def reference_additional_columns(self):
-        data['charges'] = np.array([2.58855e-03,  6.91952e-05,  1.05548e-02,  4.20319e-03,
-                        9.19172e-03,  4.79777e-03,  6.36864e-04,  5.87125e-03,
-                       -2.18125e-03,  6.88910e-03])
-        data['l'] = np.array([1.1,  1.2]*5) # random test data
-        return data
-
     @pytest.fixture()
     def reference_positions(self):
         # manually copied from traj file
@@ -614,11 +606,11 @@ def test_atom_reordering(self, u, reference_positions):
             assert_allclose(atom1.position, atom1_pos-bmin, atol=1e-5)
             assert_allclose(atom13.position, atom13_pos-bmin, atol=1e-5)
 
-    def test_additional_colunmns(self, u_add, reference_additional_columns):
+    def test_additional_columns(self, u_add, reference_additional_columns):
         charges = u_add[0].trajectory[0].data['q'] # this is the universe with just q
         second  = u_add[1].trajectory[0].data['l'] # this is the universe with both
-        assert_almost_equal(charges, reference_additional_columns['charges'])
-        assert_almost_equal(second, reference_additional_columns['l'])
+        assert_almost_equal(charges, RefLAMMPSDataAdditionalColumns.charges)
+        assert_almost_equal(second, RefLAMMPSDataAdditionalColumns.additional_data)
 
 
 @pytest.mark.parametrize("convention",

From 140b0627ebdae905b0088dc7f906ec21f7995643 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Tue, 28 Jun 2022 17:14:51 +0200
Subject: [PATCH 09/30] Incorporated the PEP8 comments.

---
 package/MDAnalysis/coordinates/LAMMPS.py      | 50 ++++++++++++-------
 .../MDAnalysisTests/coordinates/reference.py  |  7 +--
 .../coordinates/test_lammps.py                | 22 ++++----
 3 files changed, 48 insertions(+), 31 deletions(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 342869befa5..41e6dcbecfb 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -458,18 +458,30 @@ class DumpReader(base.ReaderBase):
     """Reads the default `LAMMPS dump format 
     <https://docs.lammps.org/dump.html>`__
 
-    Supports coordinates in various LAMMPS coordinate conventions and both 
-    orthogonal and triclinic simulation box dimensions (for more details see 
-    `documentation <https://docs.lammps.org/Howto_triclinic.html>`__). In 
-    either case, MDAnalysis will always use ``(*A*, *B*, *C*, *alpha*, *beta*,
-    *gamma*)`` to represent the unit cell. Lengths *A*, *B*, *C* are in the 
-    MDAnalysis length unit (Å), and angles are in degrees.
-
-    By using the keyword `additional_columns`, you can specify arbitrary data to be
-    read alongside the coordinates. If specified, the keyword expects a list of the
-    names of the columns that you want to have read. The results of the parsing are
-    saved to the time step `data` dictionary alongside the name of the data column.
-    For instance, if you have time-dependent charges saved in a LAMMPS dump such as
+    Supports coordinates in the LAMMPS "unscaled" (x,y,z), "scaled" (xs,ys,zs),
+    "unwrapped" (xu,yu,zu) and "scaled_unwrapped" (xsu,ysu,zsu) coordinate
+    conventions (see https://docs.lammps.org/dump.html for more details).
+    If `lammps_coordinate_convention='auto'` (default),
+    one will be guessed. Guessing checks whether the coordinates fit each
+    convention in the order "unscaled", "scaled", "unwrapped",
+    "scaled_unwrapped" and whichever set of coordinates is detected first will
+    be used. If coordinates are given in the scaled coordinate convention
+    (xs,ys,zs) or scaled unwrapped coordinate convention (xsu,ysu,zsu) they
+    will automatically be converted from their scaled/fractional representation
+    to their real values.
+
+    Supports both orthogonal and triclinic simulation box dimensions (for more
+    details see https://docs.lammps.org/Howto_triclinic.html). In either case,
+    MDAnalysis will always use ``(*A*, *B*, *C*, *alpha*, *beta*, *gamma*)``
+    to represent the unit cell. Lengths *A*, *B*, *C* are in the MDAnalysis
+    length unit (Å), and angles are in degrees.
+
+    By using the keyword `additional_columns`, you can specify arbitrary data
+    to be read alongside the coordinates. If specified, the keyword expects a
+    list of the names of the columns that you want to have read. The results
+    of the parsing are saved to the time step `data` dictionary alongside the
+    name of the data column. For instance, if you have time-dependent charges
+    saved in a LAMMPS dump such as
 
     ```
     ITEM: ATOMS id x y z q l
@@ -484,8 +496,8 @@ class DumpReader(base.ReaderBase):
                      additional_columns=['q', 'l'])
     ```
 
-    The additional data is then available for each time step via (as the value of
-    the `data` dictionary, sorted by the ids of the atoms).
+    The additional data is then available for each time step via
+    (as the value of the `data` dictionary, sorted by the ids of the atoms).
 
     ```
     for ts in u.trajectory:
@@ -722,11 +734,11 @@ def _read_next_timestep(self):
         if len(attrs) > 3:
             for attribute_key in attrs:
                 # Skip the normal columns
-                if attribute_key == "id" or 
-                        attribute_key in 
-                        self._coordtype_column_names[
-                        self.lammps_coordinate_convention]
-                        or attribute_key not in self._additional_columns:
+                if (attribute_key == "id" or
+                    attribute_key in
+                    self._coordtype_column_names[
+                    self.lammps_coordinate_convention]
+                    or attribute_key not in self._additional_columns):
                     continue
                 # Else this is an additional field
                 ts.data[attribute_key] = np.empty(self.n_atoms)
diff --git a/testsuite/MDAnalysisTests/coordinates/reference.py b/testsuite/MDAnalysisTests/coordinates/reference.py
index 5792aeaa129..dc65d8c2af2 100644
--- a/testsuite/MDAnalysisTests/coordinates/reference.py
+++ b/testsuite/MDAnalysisTests/coordinates/reference.py
@@ -25,8 +25,9 @@
 from MDAnalysisTests import datafiles
 from MDAnalysisTests.datafiles import (PDB_small, PDB, LAMMPSdata,
                                        LAMMPSdata2, LAMMPSdcd2,
-                                       LAMMPSdata_mini, LAMMPSdata_additional_columns,
-                                       PSF_TRICLINIC, DCD_TRICLINIC, 
+                                       LAMMPSdata_mini,
+                                       LAMMPSdata_additional_columns,
+                                       PSF_TRICLINIC, DCD_TRICLINIC,
                                        PSF_NAMD_TRICLINIC, DCD_NAMD_TRICLINIC)
 
 
@@ -230,6 +231,6 @@ class RefLAMMPSDataMini(object):
 
 class RefLAMMPSDataAdditionalColumns(object):
     charges = np.array([2.58855e-03, 6.91952e-05, 1.05548e-02, 4.20319e-03,
-                         9.19172e-03, 4.79777e-03, 6.36864e-04, 5.87125e-03,
+                        9.19172e-03, 4.79777e-03, 6.36864e-04, 5.87125e-03,
                         -2.18125e-03, 6.88910e-03])
     additional_data = np.array(5 * [1.1, 1.2])
diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index bf47efa96ed..b33a1c6f587 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -519,11 +519,11 @@ def u_additional_columns(self):
         f = LAMMPSDUMP_additional_columns
         top = LAMMPSdata_additional_columns
         yield (mda.Universe(top, f, format='LAMMPSDUMP',
-                           lammps_coordinate_convention="auto",
-                           additional_columns=['q']), 
-              mda.Universe(top, f, format='LAMMPSDUMP',
-                           lammps_coordinate_convention="auto",
-                           additional_columns=['q', 'l']))
+                            lammps_coordinate_convention="auto",
+                            additional_columns=['q']),
+               mda.Universe(top, f, format='LAMMPSDUMP',
+                            lammps_coordinate_convention="auto",
+                            additional_columns=['q', 'l']))
 
     @pytest.fixture()
     def reference_positions(self):
@@ -607,10 +607,14 @@ def test_atom_reordering(self, u, reference_positions):
             assert_allclose(atom13.position, atom13_pos-bmin, atol=1e-5)
 
     def test_additional_columns(self, u_add, reference_additional_columns):
-        charges = u_add[0].trajectory[0].data['q'] # this is the universe with just q
-        second  = u_add[1].trajectory[0].data['l'] # this is the universe with both
-        assert_almost_equal(charges, RefLAMMPSDataAdditionalColumns.charges)
-        assert_almost_equal(second, RefLAMMPSDataAdditionalColumns.additional_data)
+        # this is the universe with just q
+        charges = u_add[0].trajectory[0].data['q']  
+        # this is the universe with both
+        second = u_add[1].trajectory[0].data['l']
+        assert_almost_equal(charges, 
+                            RefLAMMPSDataAdditionalColumns.charges)
+        assert_almost_equal(second, 
+                            RefLAMMPSDataAdditionalColumns.additional_data)
 
 
 @pytest.mark.parametrize("convention",

From 03654040c94134920134bdc19705589564a9253b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Tue, 28 Jun 2022 17:19:56 +0200
Subject: [PATCH 10/30] Third round of PEP...

---
 package/MDAnalysis/coordinates/LAMMPS.py             | 10 ++++++----
 testsuite/MDAnalysisTests/coordinates/test_lammps.py |  6 +++---
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 41e6dcbecfb..4264b00e379 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -492,7 +492,7 @@ class DumpReader(base.ReaderBase):
     Then you may parse the additional columns `q` and `l` via.
 
     ```
-    u = mda.Universe('path_to_data', 'path_to_lammpsdump', 
+    u = mda.Universe('path_to_data', 'path_to_lammpsdump',
                      additional_columns=['q', 'l'])
     ```
 
@@ -549,7 +549,8 @@ class DumpReader(base.ReaderBase):
     .. versionadded:: 0.19.0
     """
     format = 'LAMMPSDUMP'
-    _conventions = ["auto", "unscaled", "scaled", "unwrapped", "scaled_unwrapped"]
+    _conventions = ["auto", "unscaled", "scaled", "unwrapped",
+                    "scaled_unwrapped"]
 
     _coordtype_column_names = {
         "unscaled": ["x", "y", "z"],
@@ -737,8 +738,9 @@ def _read_next_timestep(self):
                 if (attribute_key == "id" or
                     attribute_key in
                     self._coordtype_column_names[
-                    self.lammps_coordinate_convention]
-                    or attribute_key not in self._additional_columns):
+                        self.lammps_coordinate_convention
+                    ] or 
+                    attribute_key not in self._additional_columns):
                     continue
                 # Else this is an additional field
                 ts.data[attribute_key] = np.empty(self.n_atoms)
diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index b33a1c6f587..187c2513c97 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -608,12 +608,12 @@ def test_atom_reordering(self, u, reference_positions):
 
     def test_additional_columns(self, u_add, reference_additional_columns):
         # this is the universe with just q
-        charges = u_add[0].trajectory[0].data['q']  
+        charges = u_add[0].trajectory[0].data['q']
         # this is the universe with both
         second = u_add[1].trajectory[0].data['l']
-        assert_almost_equal(charges, 
+        assert_almost_equal(charges,
                             RefLAMMPSDataAdditionalColumns.charges)
-        assert_almost_equal(second, 
+        assert_almost_equal(second,
                             RefLAMMPSDataAdditionalColumns.additional_data)
 
 

From 138d5694e286abadaac42a7f3234fd00013c0f70 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Tue, 28 Jun 2022 17:24:25 +0200
Subject: [PATCH 11/30] PEP8 ...

---
 package/MDAnalysis/coordinates/LAMMPS.py | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 4264b00e379..38aafe51e91 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -736,11 +736,10 @@ def _read_next_timestep(self):
             for attribute_key in attrs:
                 # Skip the normal columns
                 if (attribute_key == "id" or
-                    attribute_key in
-                    self._coordtype_column_names[
-                        self.lammps_coordinate_convention
-                    ] or 
-                    attribute_key not in self._additional_columns):
+                        attribute_key in
+                        self._coordtype_column_names[
+                            self.lammps_coordinate_convention
+                        ] or attribute_key not in self._additional_columns):
                     continue
                 # Else this is an additional field
                 ts.data[attribute_key] = np.empty(self.n_atoms)

From 5ab661a80a451958e8c3447790ccf03a7064dd00 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Tue, 28 Jun 2022 17:30:37 +0200
Subject: [PATCH 12/30] Authors and changelog.

---
 package/AUTHORS   | 1 +
 package/CHANGELOG | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/package/AUTHORS b/package/AUTHORS
index c413c90462d..e53fd78cafe 100644
--- a/package/AUTHORS
+++ b/package/AUTHORS
@@ -222,6 +222,7 @@ Chronological list of authors
   - Shubham Kumar
   - Zaheer Timol
   - Geongi Moon
+  - Philipp Stärk
 
 External code
 -------------
diff --git a/package/CHANGELOG b/package/CHANGELOG
index bca8cc647ad..0fe870bc440 100644
--- a/package/CHANGELOG
+++ b/package/CHANGELOG
@@ -15,7 +15,7 @@ The rules for this file:
 
 -------------------------------------------------------------------------------
 ??/??/?? IAlibay, ianmkenney, PicoCentauri, pgbarletta, p-j-smith, 
-         richardjgowers, lilyminium
+         richardjgowers, lilyminium, pstaerk
 
  * 2.7.0
 
@@ -29,6 +29,7 @@ Fixes
   * Fixes hydrogenbonds tutorial path to point to hbonds (Issue #4285, PR #4286)
 
 Enhancements
+  * Added parsing of arbitrary columns of the LAMMPS dump parser.
   * Adds external sidebar links (Issue #4296)
   * Updated lib.qcprot.CalcRMSDRotationalMatrix to accept either float32 or float64
     inputs (PR #4273, part of #3927)

From a785ceccdac7ba91238098b04dced165f514349a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Wed, 29 Jun 2022 11:00:02 +0200
Subject: [PATCH 13/30] Variable renaming issue.

---
 testsuite/MDAnalysisTests/coordinates/test_lammps.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index 187c2513c97..ee4361fe203 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -606,11 +606,11 @@ def test_atom_reordering(self, u, reference_positions):
             assert_allclose(atom1.position, atom1_pos-bmin, atol=1e-5)
             assert_allclose(atom13.position, atom13_pos-bmin, atol=1e-5)
 
-    def test_additional_columns(self, u_add, reference_additional_columns):
+    def test_additional_columns(self, u_additional_columns, reference_additional_columns):
         # this is the universe with just q
-        charges = u_add[0].trajectory[0].data['q']
+        charges = u_additional_columns[0].trajectory[0].data['q']
         # this is the universe with both
-        second = u_add[1].trajectory[0].data['l']
+        second = u_additional_columns[1].trajectory[0].data['l']
         assert_almost_equal(charges,
                             RefLAMMPSDataAdditionalColumns.charges)
         assert_almost_equal(second,

From ade564780061a4f851087a78386240b9687fac19 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Wed, 29 Jun 2022 14:17:36 +0200
Subject: [PATCH 14/30] Hopefully fixed documentation.

---
 package/MDAnalysis/coordinates/LAMMPS.py | 25 +++++++++++-------------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 38aafe51e91..05867732f01 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -483,28 +483,25 @@ class DumpReader(base.ReaderBase):
     name of the data column. For instance, if you have time-dependent charges
     saved in a LAMMPS dump such as
 
-    ```
-    ITEM: ATOMS id x y z q l
-    1 2.84 8.17 -25 0.00258855 1.1
-    2 7.1 8.17 -25 6.91952e-05 1.2
-    ```
+    .. code-block:: python
+        ITEM: ATOMS id x y z q l
+        1 2.84 8.17 -25 0.00258855 1.1
+        2 7.1 8.17 -25 6.91952e-05 1.2
 
     Then you may parse the additional columns `q` and `l` via.
 
-    ```
-    u = mda.Universe('path_to_data', 'path_to_lammpsdump',
-                     additional_columns=['q', 'l'])
-    ```
+    .. code-block:: python
+        u = mda.Universe('path_to_data', 'path_to_lammpsdump',
+                         additional_columns=['q', 'l'])
 
     The additional data is then available for each time step via
     (as the value of the `data` dictionary, sorted by the ids of the atoms).
 
-    ```
-    for ts in u.trajectory:
-        charges = ts.data['q'] # Access the additional data, sorted by the id
-        ls = ts.data['l']
+    .. code-block:: python
+        for ts in u.trajectory:
+            charges = ts.data['q'] # Access the additional data, sorted by the id
+            ls = ts.data['l']
         ...
-    ```
 
     Parameters
     ----------

From 603116a708d129736fbd2aefff23369d26e1579d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Wed, 29 Jun 2022 14:50:01 +0200
Subject: [PATCH 15/30] Sphinx

---
 package/MDAnalysis/coordinates/LAMMPS.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 05867732f01..e637289f7d9 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -484,6 +484,7 @@ class DumpReader(base.ReaderBase):
     saved in a LAMMPS dump such as
 
     .. code-block:: python
+
         ITEM: ATOMS id x y z q l
         1 2.84 8.17 -25 0.00258855 1.1
         2 7.1 8.17 -25 6.91952e-05 1.2
@@ -491,6 +492,7 @@ class DumpReader(base.ReaderBase):
     Then you may parse the additional columns `q` and `l` via.
 
     .. code-block:: python
+
         u = mda.Universe('path_to_data', 'path_to_lammpsdump',
                          additional_columns=['q', 'l'])
 
@@ -498,6 +500,7 @@ class DumpReader(base.ReaderBase):
     (as the value of the `data` dictionary, sorted by the ids of the atoms).
 
     .. code-block:: python
+
         for ts in u.trajectory:
             charges = ts.data['q'] # Access the additional data, sorted by the id
             ls = ts.data['l']

From bc9296ce6b8d63d5ffdf2d86089d7b9a242e4760 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Tue, 8 Nov 2022 10:39:10 +0100
Subject: [PATCH 16/30] Hopefully fixed the tests

---
 testsuite/MDAnalysisTests/coordinates/test_lammps.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index ee4361fe203..ca533aa937b 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -606,7 +606,7 @@ def test_atom_reordering(self, u, reference_positions):
             assert_allclose(atom1.position, atom1_pos-bmin, atol=1e-5)
             assert_allclose(atom13.position, atom13_pos-bmin, atol=1e-5)
 
-    def test_additional_columns(self, u_additional_columns, reference_additional_columns):
+    def test_additional_columns(self, u_additional_columns):
         # this is the universe with just q
         charges = u_additional_columns[0].trajectory[0].data['q']
         # this is the universe with both

From d6d54263259d6968b0d03d3f488126de7d59df21 Mon Sep 17 00:00:00 2001
From: hejamu <info@jaegerhenrik.de>
Date: Fri, 29 Sep 2023 18:22:11 +0100
Subject: [PATCH 17/30] Implement input from UGM23

---
 package/MDAnalysis/coordinates/LAMMPS.py | 61 +++++++++++++-----------
 1 file changed, 34 insertions(+), 27 deletions(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index e637289f7d9..14781229158 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -479,11 +479,11 @@ class DumpReader(base.ReaderBase):
     By using the keyword `additional_columns`, you can specify arbitrary data
     to be read alongside the coordinates. If specified, the keyword expects a
     list of the names of the columns that you want to have read. The results
-    of the parsing are saved to the time step `data` dictionary alongside the
-    name of the data column. For instance, if you have time-dependent charges
-    saved in a LAMMPS dump such as
+    of the parsing are saved to the time step :attr:`Timestep.data` dictionary
+    alongside the name of the data column. For instance, if you have time-dependent
+    charges saved in a LAMMPS dump such as
 
-    .. code-block:: python
+    .. code-block::
 
         ITEM: ATOMS id x y z q l
         1 2.84 8.17 -25 0.00258855 1.1
@@ -497,7 +497,8 @@ class DumpReader(base.ReaderBase):
                          additional_columns=['q', 'l'])
 
     The additional data is then available for each time step via
-    (as the value of the `data` dictionary, sorted by the ids of the atoms).
+    (as the value of the :attr:`Timestep.data` dictionary, sorted by the ids of the
+    atoms).
 
     .. code-block:: python
 
@@ -538,6 +539,9 @@ class DumpReader(base.ReaderBase):
     **kwargs
        Other keyword arguments used in :class:`~MDAnalysis.coordinates.base.ReaderBase`
 
+    .. versionchanged:: 2.7.0
+       Reading of arbitrary, additional columns is now supported.
+       (Issue `#3608 <https://github.com/MDAnalysis/mdanalysis/pull/3608>`__)
     .. versionchanged:: 2.4.0
        Now imports velocities and forces, translates the box to the origin,
        and optionally unwraps trajectories with image flags upon loading.
@@ -559,11 +563,15 @@ class DumpReader(base.ReaderBase):
         "scaled_unwrapped": ["xsu", "ysu", "zsu"]
     }
 
+    _parsable_columns = ["id", "vx", "vy", "vz", "fx", "fy", "fz"]
+    for key in _coordtype_column_names.keys():
+        _parsable_columns += _coordtype_column_names[key]
+
     @store_init_arguments
     def __init__(self, filename,
                  lammps_coordinate_convention="auto",
                  unwrap_images=False,
-                 additional_columns=False, **kwargs):
+                 additional_columns=None, **kwargs):
         super(DumpReader, self).__init__(filename, **kwargs)
 
         root, ext = os.path.splitext(self.filename)
@@ -578,10 +586,15 @@ def __init__(self, filename,
 
         self._unwrap = unwrap_images
 
-        if additional_columns:
+        if (util.iterable(additional_columns)
+                or additional_columns is None 
+                or additional_columns is True):
             self._additional_columns = additional_columns
         else:
-            self._additional_columns = []
+            raise ValueError(f"additional_columns={additional_columns} "
+                             "is not a valid option. Pleae provide an"
+                             "iterable containing the additional"
+                             "coloum headers.")
 
         self._cache = {}
 
@@ -731,19 +744,15 @@ def _read_next_timestep(self):
 
         # Create the data arrays for additional attributes which will be saved
         # under ts.data
-        additional_keys = []
-        if len(attrs) > 3:
-            for attribute_key in attrs:
-                # Skip the normal columns
-                if (attribute_key == "id" or
-                        attribute_key in
-                        self._coordtype_column_names[
-                            self.lammps_coordinate_convention
-                        ] or attribute_key not in self._additional_columns):
-                    continue
-                # Else this is an additional field
-                ts.data[attribute_key] = np.empty(self.n_atoms)
-                additional_keys.append(attribute_key)
+        if self._additional_columns is True:
+            # Parse every column that is not already parsed elsewhere (total \ parsable)
+            additional_keys = set(attrs).difference(self._parsable_columns)
+        elif self._additional_columns:
+            additional_keys = [key for key in self._additional_columns if key in attrs]
+        else:
+            additional_keys = []
+        for key in additional_keys:
+            ts.data[key] = np.empty(self.n_atoms)
 
         # Parse all the atoms
         for i in range(self.n_atoms):
@@ -766,12 +775,10 @@ def _read_next_timestep(self):
             if self._has_forces:
                 ts.forces[i] = [fields[dim] for dim in force_cols]
 
-            # Add the capability to also collect other data
-            # Then there is also more than just the positional data
-            if len(additional_keys) != 0:
-                for attribute_key in additional_keys:
-                    ts.data[attribute_key][i] = \
-                            fields[attr_to_col_ix[attribute_key]]
+            # Collect additional cols
+            for attribute_key in additional_keys:
+                ts.data[attribute_key][i] = \
+                    fields[attr_to_col_ix[attribute_key]]
 
         order = np.argsort(indices)
         ts.positions = ts.positions[order]

From 27cb7beec246447f776ea57b5d1d2ecb2a9c768e Mon Sep 17 00:00:00 2001
From: hejamu <info@jaegerhenrik.de>
Date: Fri, 29 Sep 2023 18:22:39 +0100
Subject: [PATCH 18/30] refine tests

---
 package/CHANGELOG                             |  2 +-
 package/MDAnalysis/coordinates/LAMMPS.py      | 22 +++++----
 .../MDAnalysisTests/coordinates/reference.py  |  8 ++--
 .../coordinates/test_lammps.py                | 45 ++++++++++++-------
 4 files changed, 45 insertions(+), 32 deletions(-)

diff --git a/package/CHANGELOG b/package/CHANGELOG
index 0fe870bc440..0401c85f794 100644
--- a/package/CHANGELOG
+++ b/package/CHANGELOG
@@ -29,7 +29,7 @@ Fixes
   * Fixes hydrogenbonds tutorial path to point to hbonds (Issue #4285, PR #4286)
 
 Enhancements
-  * Added parsing of arbitrary columns of the LAMMPS dump parser.
+  * Added parsing of arbitrary columns of the LAMMPS dump parser. (Issue #3504)
   * Adds external sidebar links (Issue #4296)
   * Updated lib.qcprot.CalcRMSDRotationalMatrix to accept either float32 or float64
     inputs (PR #4273, part of #3927)
diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 14781229158..6de4a8833d2 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -477,11 +477,9 @@ class DumpReader(base.ReaderBase):
     length unit (Å), and angles are in degrees.
 
     By using the keyword `additional_columns`, you can specify arbitrary data
-    to be read alongside the coordinates. If specified, the keyword expects a
-    list of the names of the columns that you want to have read. The results
-    of the parsing are saved to the time step :attr:`Timestep.data` dictionary
-    alongside the name of the data column. For instance, if you have time-dependent
-    charges saved in a LAMMPS dump such as
+    to be read. The keyword expects a list of the names of the columns or `True` to read
+    all additional columns. The results are saved to :attr:`Timestep.data`. 
+    For example, if your LAMMPS dump looks like this
 
     .. code-block::
 
@@ -489,16 +487,14 @@ class DumpReader(base.ReaderBase):
         1 2.84 8.17 -25 0.00258855 1.1
         2 7.1 8.17 -25 6.91952e-05 1.2
 
-    Then you may parse the additional columns `q` and `l` via.
+    Then you may parse the additional columns `q` and `l` via:
 
     .. code-block:: python
 
         u = mda.Universe('path_to_data', 'path_to_lammpsdump',
                          additional_columns=['q', 'l'])
 
-    The additional data is then available for each time step via
-    (as the value of the :attr:`Timestep.data` dictionary, sorted by the ids of the
-    atoms).
+    The additional data is then available for each time step via:
 
     .. code-block:: python
 
@@ -587,7 +583,7 @@ def __init__(self, filename,
         self._unwrap = unwrap_images
 
         if (util.iterable(additional_columns)
-                or additional_columns is None 
+                or additional_columns is None
                 or additional_columns is True):
             self._additional_columns = additional_columns
         else:
@@ -745,10 +741,12 @@ def _read_next_timestep(self):
         # Create the data arrays for additional attributes which will be saved
         # under ts.data
         if self._additional_columns is True:
-            # Parse every column that is not already parsed elsewhere (total \ parsable)
+            # Parse every column that is not already parsed
+            # elsewhere (total \ parsable)
             additional_keys = set(attrs).difference(self._parsable_columns)
         elif self._additional_columns:
-            additional_keys = [key for key in self._additional_columns if key in attrs]
+            additional_keys = \
+                [key for key in self._additional_columns if key in attrs]
         else:
             additional_keys = []
         for key in additional_keys:
diff --git a/testsuite/MDAnalysisTests/coordinates/reference.py b/testsuite/MDAnalysisTests/coordinates/reference.py
index dc65d8c2af2..5f18cf23166 100644
--- a/testsuite/MDAnalysisTests/coordinates/reference.py
+++ b/testsuite/MDAnalysisTests/coordinates/reference.py
@@ -230,7 +230,7 @@ class RefLAMMPSDataMini(object):
 
 
 class RefLAMMPSDataAdditionalColumns(object):
-    charges = np.array([2.58855e-03, 6.91952e-05, 1.05548e-02, 4.20319e-03,
-                        9.19172e-03, 4.79777e-03, 6.36864e-04, 5.87125e-03,
-                        -2.18125e-03, 6.88910e-03])
-    additional_data = np.array(5 * [1.1, 1.2])
+    q = np.array([2.58855e-03, 6.91952e-05, 1.05548e-02, 4.20319e-03,
+                  9.19172e-03, 4.79777e-03, 6.36864e-04, 5.87125e-03,
+                  -2.18125e-03, 6.88910e-03])
+    l = np.array(5 * [1.1, 1.2])
diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index ca533aa937b..8a2a3b8bf93 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -29,7 +29,7 @@
 import MDAnalysis as mda
 from MDAnalysis import NoDataError
 
-from numpy.testing import (assert_equal, assert_allclose, assert_allclose)
+from numpy.testing import (assert_equal, assert_allclose)
 
 from MDAnalysisTests import make_Universe
 from MDAnalysisTests.coordinates.reference import (
@@ -515,15 +515,28 @@ def u(self, tmpdir, request):
                            lammps_coordinate_convention="auto")
 
     @pytest.fixture()
-    def u_additional_columns(self):
+    def u_additional_columns_true(self):
         f = LAMMPSDUMP_additional_columns
         top = LAMMPSdata_additional_columns
-        yield (mda.Universe(top, f, format='LAMMPSDUMP',
+        return mda.Universe(top, f, format='LAMMPSDUMP',
                             lammps_coordinate_convention="auto",
-                            additional_columns=['q']),
-               mda.Universe(top, f, format='LAMMPSDUMP',
+                            additional_columns=True)
+
+    @pytest.fixture()
+    def u_additional_columns_single(self):
+        f = LAMMPSDUMP_additional_columns
+        top = LAMMPSdata_additional_columns
+        return mda.Universe(top, f, format='LAMMPSDUMP',
+                            lammps_coordinate_convention="auto",
+                            additional_columns=['q'])
+
+    @pytest.fixture()
+    def u_additional_columns_multiple(self):
+        f = LAMMPSDUMP_additional_columns
+        top = LAMMPSdata_additional_columns
+        return mda.Universe(top, f, format='LAMMPSDUMP',
                             lammps_coordinate_convention="auto",
-                            additional_columns=['q', 'l']))
+                            additional_columns=['q', 'l'])
 
     @pytest.fixture()
     def reference_positions(self):
@@ -606,15 +619,17 @@ def test_atom_reordering(self, u, reference_positions):
             assert_allclose(atom1.position, atom1_pos-bmin, atol=1e-5)
             assert_allclose(atom13.position, atom13_pos-bmin, atol=1e-5)
 
-    def test_additional_columns(self, u_additional_columns):
-        # this is the universe with just q
-        charges = u_additional_columns[0].trajectory[0].data['q']
-        # this is the universe with both
-        second = u_additional_columns[1].trajectory[0].data['l']
-        assert_almost_equal(charges,
-                            RefLAMMPSDataAdditionalColumns.charges)
-        assert_almost_equal(second,
-                            RefLAMMPSDataAdditionalColumns.additional_data)
+    @pytest.mark.parametrize("system, fields", [
+        ('u_additional_columns_true', ['q', 'l']),
+        ('u_additional_columns_single', ['q']),
+        ('u_additional_columns_multiple', ['q', 'l']),
+    ])
+    def test_additional_columns(self, system, fields, request):
+        u = request.getfixturevalue(system)
+        for field in fields:
+            data = u.trajectory[0].data[field]
+            assert_allclose(data,
+                            getattr(RefLAMMPSDataAdditionalColumns, field))
 
 
 @pytest.mark.parametrize("convention",

From 1e8557bfea318b531af45ae6a6c35cb0b81acbde Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?PSt=C3=A4rk?= <franz-duck@gmx.de>
Date: Mon, 26 Feb 2024 14:42:38 +0100
Subject: [PATCH 19/30] Small typo

Co-authored-by: Hugo MacDermott-Opeskin <hugomacdermott@gmail.com>
---
 package/MDAnalysis/coordinates/LAMMPS.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 6de4a8833d2..f16c0da780d 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -590,7 +590,7 @@ def __init__(self, filename,
             raise ValueError(f"additional_columns={additional_columns} "
                              "is not a valid option. Pleae provide an"
                              "iterable containing the additional"
-                             "coloum headers.")
+                             "column headers.")
 
         self._cache = {}
 

From 07d0c18c950d50941ece87d33da8f3c9994b68b8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?PSt=C3=A4rk?= <franz-duck@gmx.de>
Date: Mon, 26 Feb 2024 14:45:18 +0100
Subject: [PATCH 20/30] Removed comment

---
 testsuite/MDAnalysisTests/coordinates/test_lammps.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index 8a2a3b8bf93..83a212590a7 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -500,7 +500,6 @@ def u(self, tmpdir, request):
             # no conversion needed
             f = LAMMPSDUMP
         else:
-            # Select if one wants to use the additional column format
             f = str(tmpdir.join('lammps.' + trjtype))
             with bz2.BZ2File(LAMMPSDUMP, 'rb') as datain:
                 data = datain.read()

From 5f36ff49becac589de27ffd097af0e4f601878e3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Mon, 26 Feb 2024 15:04:41 +0100
Subject: [PATCH 21/30] Addressed hmacdope's comments regarding issue link

---
 package/MDAnalysis/coordinates/LAMMPS.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index f16c0da780d..4476c7a4582 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -537,7 +537,7 @@ class DumpReader(base.ReaderBase):
 
     .. versionchanged:: 2.7.0
        Reading of arbitrary, additional columns is now supported.
-       (Issue `#3608 <https://github.com/MDAnalysis/mdanalysis/pull/3608>`__)
+       (Issue #3608)
     .. versionchanged:: 2.4.0
        Now imports velocities and forces, translates the box to the origin,
        and optionally unwraps trajectories with image flags upon loading.

From e45e764527c1a95a452b5a09c211819a43ad2fd8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Mon, 26 Feb 2024 15:07:14 +0100
Subject: [PATCH 22/30] Addressed hmacdope's comments regarding file paths.

---
 package/MDAnalysis/coordinates/LAMMPS.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 4476c7a4582..facf6c17038 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -491,7 +491,7 @@ class DumpReader(base.ReaderBase):
 
     .. code-block:: python
 
-        u = mda.Universe('path_to_data', 'path_to_lammpsdump',
+        u = mda.Universe('structure.data', 'traj.lammpsdump',
                          additional_columns=['q', 'l'])
 
     The additional data is then available for each time step via:

From 546dd43bfc5d29aa25e67fb37465bbe1cfce5f62 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Mon, 26 Feb 2024 15:15:13 +0100
Subject: [PATCH 23/30] Added warning if keys are not in lammpsdump file.

---
 package/MDAnalysis/coordinates/LAMMPS.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index facf6c17038..bc125232e12 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -135,6 +135,7 @@
 from ..topology.LAMMPSParser import DATAParser
 from ..exceptions import NoDataError
 from . import base
+import warnings
 
 btype_sections = {'bond':'Bonds', 'angle':'Angles',
                   'dihedral':'Dihedrals', 'improper':'Impropers'}
@@ -745,6 +746,9 @@ def _read_next_timestep(self):
             # elsewhere (total \ parsable)
             additional_keys = set(attrs).difference(self._parsable_columns)
         elif self._additional_columns:
+            if not all([key in attrs for key in self._additional_columns]):
+                warnings.warn("Some of the additional columns are not present "
+                              "in the file, they will be ignored")
             additional_keys = \
                 [key for key in self._additional_columns if key in attrs]
         else:

From adec7943a620d40cc7beea5657b619c389f69751 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Mon, 26 Feb 2024 15:30:59 +0100
Subject: [PATCH 24/30] Tested the formatting error of additional_columns.

---
 package/MDAnalysis/coordinates/LAMMPS.py          |  2 +-
 .../MDAnalysisTests/coordinates/test_lammps.py    | 15 +++++++++++++++
 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index bc125232e12..516ebb96062 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -589,7 +589,7 @@ def __init__(self, filename,
             self._additional_columns = additional_columns
         else:
             raise ValueError(f"additional_columns={additional_columns} "
-                             "is not a valid option. Pleae provide an"
+                             "is not a valid option. Please provide an "
                              "iterable containing the additional"
                              "column headers.")
 
diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index 83a212590a7..5aef48e6aa4 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -537,6 +537,14 @@ def u_additional_columns_multiple(self):
                             lammps_coordinate_convention="auto",
                             additional_columns=['q', 'l'])
 
+    @pytest.fixture()
+    def u_additional_columns_wrong_format(self):
+        f = LAMMPSDUMP_additional_columns
+        top = LAMMPSdata_additional_columns
+        return mda.Universe(top, f, format='LAMMPSDUMP',
+                            lammps_coordinate_convention="auto",
+                            additional_columns='q')
+
     @pytest.fixture()
     def reference_positions(self):
         # manually copied from traj file
@@ -630,6 +638,13 @@ def test_additional_columns(self, system, fields, request):
             assert_allclose(data,
                             getattr(RefLAMMPSDataAdditionalColumns, field))
 
+    @pytest.mark.parametrize("system", [
+        ('u_additional_columns_wrong_format'),
+    ])
+    def test_wrong_format_additional_colums(self, system, request):
+        with pytest.raises(ValueError,
+                           match="Please provide an iterable containing"):
+            request.getfixturevalue(system)
 
 @pytest.mark.parametrize("convention",
                          ["unscaled", "unwrapped", "scaled_unwrapped"])

From 57b895d6d882e1e2e4cd7aada745e7db59176db6 Mon Sep 17 00:00:00 2001
From: hejamu <info@jaegerhenrik.de>
Date: Tue, 27 Feb 2024 22:27:06 +0100
Subject: [PATCH 25/30] Make changed lines comply with pep8

---
 package/MDAnalysis/coordinates/LAMMPS.py           |  8 ++++----
 testsuite/MDAnalysisTests/coordinates/reference.py |  2 +-
 .../MDAnalysisTests/coordinates/test_lammps.py     |  4 ++--
 testsuite/MDAnalysisTests/datafiles.py             | 14 ++++++++++----
 4 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 516ebb96062..77040033414 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -478,9 +478,9 @@ class DumpReader(base.ReaderBase):
     length unit (Å), and angles are in degrees.
 
     By using the keyword `additional_columns`, you can specify arbitrary data
-    to be read. The keyword expects a list of the names of the columns or `True` to read
-    all additional columns. The results are saved to :attr:`Timestep.data`. 
-    For example, if your LAMMPS dump looks like this
+    to be read. The keyword expects a list of the names of the columns or `True`
+    to read all additional columns. The results are saved to
+    :attr:`Timestep.data`. For example, if your LAMMPS dump looks like this
 
     .. code-block::
 
@@ -500,7 +500,7 @@ class DumpReader(base.ReaderBase):
     .. code-block:: python
 
         for ts in u.trajectory:
-            charges = ts.data['q'] # Access the additional data, sorted by the id
+            charges = ts.data['q'] # Access additional data, sorted by the id
             ls = ts.data['l']
         ...
 
diff --git a/testsuite/MDAnalysisTests/coordinates/reference.py b/testsuite/MDAnalysisTests/coordinates/reference.py
index 5f18cf23166..8c523c639e1 100644
--- a/testsuite/MDAnalysisTests/coordinates/reference.py
+++ b/testsuite/MDAnalysisTests/coordinates/reference.py
@@ -233,4 +233,4 @@ class RefLAMMPSDataAdditionalColumns(object):
     q = np.array([2.58855e-03, 6.91952e-05, 1.05548e-02, 4.20319e-03,
                   9.19172e-03, 4.79777e-03, 6.36864e-04, 5.87125e-03,
                   -2.18125e-03, 6.88910e-03])
-    l = np.array(5 * [1.1, 1.2])
+    p = np.array(5 * [1.1, 1.2])
diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index 5aef48e6aa4..424c179f75f 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -627,9 +627,9 @@ def test_atom_reordering(self, u, reference_positions):
             assert_allclose(atom13.position, atom13_pos-bmin, atol=1e-5)
 
     @pytest.mark.parametrize("system, fields", [
-        ('u_additional_columns_true', ['q', 'l']),
+        ('u_additional_columns_true', ['q', 'p']),
         ('u_additional_columns_single', ['q']),
-        ('u_additional_columns_multiple', ['q', 'l']),
+        ('u_additional_columns_multiple', ['q', 'p']),
     ])
     def test_additional_columns(self, system, fields, request):
         u = request.getfixturevalue(system)
diff --git a/testsuite/MDAnalysisTests/datafiles.py b/testsuite/MDAnalysisTests/datafiles.py
index 223d52fa6bb..e060ce66f69 100644
--- a/testsuite/MDAnalysisTests/datafiles.py
+++ b/testsuite/MDAnalysisTests/datafiles.py
@@ -155,7 +155,8 @@
     "LAMMPSdata_deletedatoms",  # with deleted atoms
     "LAMMPSdata_triclinic",  # lammpsdata file to test triclinic dimension parsing, albite with most atoms deleted
     "LAMMPSdata_PairIJ",  # lammps datafile with a PairIJ Coeffs section
-    "LAMMPSdata_additional_columns",  # structure for the additional column lammpstrj
+    # structure for the additional column lammpstrj
+    "LAMMPSdata_additional_columns",
     "LAMMPSDUMP",
     "LAMMPSDUMP_long",  # lammpsdump file with a few zeros sprinkled in the first column first frame
     "LAMMPSDUMP_allcoords",  # lammpsdump file with all coordinate conventions (x,xs,xu,xsu) present, from LAMMPS rdf example
@@ -166,7 +167,8 @@
     "LAMMPSDUMP_chain1", # Lammps dump file with chain reader
     "LAMMPSDUMP_chain2", # Lammps dump file with chain reader
     "LAMMPS_chain", # Lammps data file with chain reader
-    "LAMMPSDUMP_additional_columns",  # lammpsdump file with additional data (an additional charge column)
+    # lammpsdump file with additional data (an additional charge column)
+    "LAMMPSDUMP_additional_columns",
     "unordered_res",  # pdb file with resids non sequential
     "GMS_ASYMOPT",  # GAMESS C1  optimization
     "GMS_SYMOPT",   # GAMESS D4h optimization
@@ -546,8 +548,12 @@
 LAMMPSDUMP_chain2 = (_data_ref / "lammps/chain_dump_2.lammpstrj").as_posix()
 LAMMPS_chain = (_data_ref / "lammps/chain_initial.data").as_posix()
 LAMMPSdata_many_bonds = (_data_ref / "lammps/a_lot_of_bond_types.data").as_posix()
-LAMMPSdata_additional_columns = (_data_ref / "lammps/additional_columns.data").as_posix()
-LAMMPSDUMP_additional_columns = (_data_ref / "lammps/additional_columns.lammpstrj").as_posix()
+LAMMPSdata_additional_columns = (
+    _data_ref / "lammps/additional_columns.data"
+).as_posix()
+LAMMPSDUMP_additional_columns = (
+    _data_ref / "lammps/additional_columns.lammpstrj"
+).as_posix()
 
 unordered_res = (_data_ref / "unordered_res.pdb").as_posix()
 

From d054946342ab0124d79eacb5e52f6fdb47125d24 Mon Sep 17 00:00:00 2001
From: hejamu <info@jaegerhenrik.de>
Date: Tue, 27 Feb 2024 22:28:51 +0100
Subject: [PATCH 26/30] 80 is indeed longer than 79...

---
 package/MDAnalysis/coordinates/LAMMPS.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/package/MDAnalysis/coordinates/LAMMPS.py b/package/MDAnalysis/coordinates/LAMMPS.py
index 77040033414..0227ed742cd 100644
--- a/package/MDAnalysis/coordinates/LAMMPS.py
+++ b/package/MDAnalysis/coordinates/LAMMPS.py
@@ -478,8 +478,8 @@ class DumpReader(base.ReaderBase):
     length unit (Å), and angles are in degrees.
 
     By using the keyword `additional_columns`, you can specify arbitrary data
-    to be read. The keyword expects a list of the names of the columns or `True`
-    to read all additional columns. The results are saved to
+    to be read. The keyword expects a list of the names of the columns or
+    `True` to read all additional columns. The results are saved to
     :attr:`Timestep.data`. For example, if your LAMMPS dump looks like this
 
     .. code-block::

From 9f14a8a50ada2e044e4835d1d39b3a4d63cea86a Mon Sep 17 00:00:00 2001
From: hejamu <info@jaegerhenrik.de>
Date: Tue, 27 Feb 2024 23:00:18 +0100
Subject: [PATCH 27/30] Fix test

---
 .../MDAnalysisTests/data/lammps/additional_columns.lammpstrj    | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj b/testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj
index b2d59267968..79ad9a6fb74 100644
--- a/testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj
+++ b/testsuite/MDAnalysisTests/data/lammps/additional_columns.lammpstrj
@@ -6,7 +6,7 @@ ITEM: BOX BOUNDS pp pp ff
 0.0000000000000000e+00 4.2600000000000001e+01
 0.0000000000000000e+00 4.4271200000000000e+01
 -2.5100000000000001e+01 2.5100000000000001e+01
-ITEM: ATOMS id x y z q l
+ITEM: ATOMS id x y z q p
 1 2.84 8.17 -25 0.00258855 1.1
 2 7.1 8.17 -25 6.91952e-05 1.2
 3 2.13 6.94 -25 0.0105548  1.1

From bcb044fd4870a30535fadaa15791fc1207140b26 Mon Sep 17 00:00:00 2001
From: hejamu <info@jaegerhenrik.de>
Date: Tue, 27 Feb 2024 23:18:17 +0100
Subject: [PATCH 28/30] Fix test

---
 testsuite/MDAnalysisTests/coordinates/test_lammps.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index 424c179f75f..7c1da50f4ae 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -535,7 +535,7 @@ def u_additional_columns_multiple(self):
         top = LAMMPSdata_additional_columns
         return mda.Universe(top, f, format='LAMMPSDUMP',
                             lammps_coordinate_convention="auto",
-                            additional_columns=['q', 'l'])
+                            additional_columns=['q', 'p'])
 
     @pytest.fixture()
     def u_additional_columns_wrong_format(self):

From 8ef649c524a57bd760eac583c83b23ad098aac0f Mon Sep 17 00:00:00 2001
From: hejamu <info@jaegerhenrik.de>
Date: Tue, 27 Feb 2024 23:55:52 +0100
Subject: [PATCH 29/30] Don't format `datafiles.py`

---
 testsuite/MDAnalysisTests/datafiles.py | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/testsuite/MDAnalysisTests/datafiles.py b/testsuite/MDAnalysisTests/datafiles.py
index e1a51f39510..3fb17695de6 100644
--- a/testsuite/MDAnalysisTests/datafiles.py
+++ b/testsuite/MDAnalysisTests/datafiles.py
@@ -156,8 +156,7 @@
     "LAMMPSdata_deletedatoms",  # with deleted atoms
     "LAMMPSdata_triclinic",  # lammpsdata file to test triclinic dimension parsing, albite with most atoms deleted
     "LAMMPSdata_PairIJ",  # lammps datafile with a PairIJ Coeffs section
-    # structure for the additional column lammpstrj
-    "LAMMPSdata_additional_columns",
+    "LAMMPSdata_additional_columns",  # structure for the additional column lammpstrj
     "LAMMPSDUMP",
     "LAMMPSDUMP_long",  # lammpsdump file with a few zeros sprinkled in the first column first frame
     "LAMMPSDUMP_allcoords",  # lammpsdump file with all coordinate conventions (x,xs,xu,xsu) present, from LAMMPS rdf example
@@ -168,8 +167,7 @@
     "LAMMPSDUMP_chain1", # Lammps dump file with chain reader
     "LAMMPSDUMP_chain2", # Lammps dump file with chain reader
     "LAMMPS_chain", # Lammps data file with chain reader
-    # lammpsdump file with additional data (an additional charge column)
-    "LAMMPSDUMP_additional_columns",
+    "LAMMPSDUMP_additional_columns",  # lammpsdump file with additional data (an additional charge column)
     "unordered_res",  # pdb file with resids non sequential
     "GMS_ASYMOPT",  # GAMESS C1  optimization
     "GMS_SYMOPT",   # GAMESS D4h optimization
@@ -556,12 +554,8 @@
 LAMMPSDUMP_chain2 = (_data_ref / "lammps/chain_dump_2.lammpstrj").as_posix()
 LAMMPS_chain = (_data_ref / "lammps/chain_initial.data").as_posix()
 LAMMPSdata_many_bonds = (_data_ref / "lammps/a_lot_of_bond_types.data").as_posix()
-LAMMPSdata_additional_columns = (
-    _data_ref / "lammps/additional_columns.data"
-).as_posix()
-LAMMPSDUMP_additional_columns = (
-    _data_ref / "lammps/additional_columns.lammpstrj"
-).as_posix()
+LAMMPSdata_additional_columns = (_data_ref / "lammps/additional_columns.data").as_posix()
+LAMMPSDUMP_additional_columns = (_data_ref / "lammps/additional_columns.lammpstrj").as_posix()
 
 unordered_res = (_data_ref / "unordered_res.pdb").as_posix()
 

From bac1f4c85099d7b8173f77972c64075920f60cae Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Philipp=20St=C3=A4rk?= <philipp.staerk@t-online.de>
Date: Thu, 29 Feb 2024 14:51:45 +0100
Subject: [PATCH 30/30] Added test of warning.

---
 .../MDAnalysisTests/coordinates/test_lammps.py    | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/testsuite/MDAnalysisTests/coordinates/test_lammps.py b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
index 7c1da50f4ae..88b4b8c35ee 100644
--- a/testsuite/MDAnalysisTests/coordinates/test_lammps.py
+++ b/testsuite/MDAnalysisTests/coordinates/test_lammps.py
@@ -545,6 +545,14 @@ def u_additional_columns_wrong_format(self):
                             lammps_coordinate_convention="auto",
                             additional_columns='q')
 
+    @pytest.fixture()
+    def u_additional_columns_not_present(self):
+        f = LAMMPSDUMP_additional_columns
+        top = LAMMPSdata_additional_columns
+        return mda.Universe(top, f, format='LAMMPSDUMP',
+                            lammps_coordinate_convention="auto",
+                            additional_columns=['q', 'w'])
+
     @pytest.fixture()
     def reference_positions(self):
         # manually copied from traj file
@@ -646,6 +654,13 @@ def test_wrong_format_additional_colums(self, system, request):
                            match="Please provide an iterable containing"):
             request.getfixturevalue(system)
 
+    @pytest.mark.parametrize("system", [
+        ('u_additional_columns_not_present'),
+    ])
+    def test_warning(self, system, request):
+        with pytest.warns(match="Some of the additional"):
+            request.getfixturevalue(system)
+
 @pytest.mark.parametrize("convention",
                          ["unscaled", "unwrapped", "scaled_unwrapped"])
 def test_open_absent_convention_fails(convention):