Merge branch 'testCases' into combine_wip_db_and_MoleculeClass

                                 Apache License

                           Version 2.0, January 2004

                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,

      and distribution as defined by Sections 1 through 9 of this document.

      "Licensor" shall mean the copyright owner or entity authorized by

      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all

      other entities that control, are controlled by, or are under common

      control with that entity. For the purposes of this definition,

      "control" means (i) the power, direct or indirect, to cause the

      direction or management of such entity, whether by contract or

      otherwise, or (ii) ownership of fifty percent (50%) or more of the

      outstanding shares, or (iii) beneficial ownership of such entity.

      "You" (or "Your") shall mean an individual or Legal Entity

      exercising permissions granted by this License.

      "Source" form shall mean the preferred form for making modifications,

      including but not limited to software source code, documentation

      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical

      transformation or translation of a Source form, including but

      not limited to compiled object code, generated documentation,

      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or

      Object form, made available under the License, as indicated by a

      copyright notice that is included in or attached to the work

      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object

      form, that is based on (or derived from) the Work and for which the

      editorial revisions, annotations, elaborations, or other modifications

      represent, as a whole, an original work of authorship. For the purposes

      of this License, Derivative Works shall not include works that remain

      separable from, or merely link (or bind by name) to the interfaces of,

      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including

      the original version of the Work and any modifications or additions

      to that Work or Derivative Works thereof, that is intentionally

      submitted to Licensor for inclusion in the Work by the copyright owner

      or by an individual or Legal Entity authorized to submit on behalf of

      the copyright owner. For the purposes of this definition, "submitted"

      means any form of electronic, verbal, or written communication sent

      to the Licensor or its representatives, including but not limited to

      communication on electronic mailing lists, source code control systems,

      and issue tracking systems that are managed by, or on behalf of, the

      Licensor for the purpose of discussing and improving the Work, but

      excluding communication that is conspicuously marked or otherwise

      designated in writing by the copyright owner as "Not a Contribution."

      "Contributor" shall mean Licensor and any individual or Legal Entity

      on behalf of whom a Contribution has been received by Licensor and

      subsequently incorporated within the Work.

   2. Grant of Copyright License. Subject to the terms and conditions of

      this License, each Contributor hereby grants to You a perpetual,

      worldwide, non-exclusive, no-charge, royalty-free, irrevocable

      copyright license to reproduce, prepare Derivative Works of,

      publicly display, publicly perform, sublicense, and distribute the

      Work and such Derivative Works in Source or Object form.

   3. Grant of Patent License. Subject to the terms and conditions of

      this License, each Contributor hereby grants to You a perpetual,

      worldwide, non-exclusive, no-charge, royalty-free, irrevocable

      (except as stated in this section) patent license to make, have made,

      use, offer to sell, sell, import, and otherwise transfer the Work,

      where such license applies only to those patent claims licensable

      by such Contributor that are necessarily infringed by their

      Contribution(s) alone or by combination of their Contribution(s)

      with the Work to which such Contribution(s) was submitted. If You

      institute patent litigation against any entity (including a

      cross-claim or counterclaim in a lawsuit) alleging that the Work

      or a Contribution incorporated within the Work constitutes direct

      or contributory patent infringement, then any patent licenses

      granted to You under this License for that Work shall terminate

      as of the date such litigation is filed.

   4. Redistribution. You may reproduce and distribute copies of the

      Work or Derivative Works thereof in any medium, with or without

      modifications, and in Source or Object form, provided that You

      meet the following conditions:

      (a) You must give any other recipients of the Work or

          Derivative Works a copy of this License; and

      (b) You must cause any modified files to carry prominent notices

          stating that You changed the files; and

      (c) You must retain, in the Source form of any Derivative Works

          that You distribute, all copyright, patent, trademark, and

          attribution notices from the Source form of the Work,

          excluding those notices that do not pertain to any part of

          the Derivative Works; and

      (d) If the Work includes a "NOTICE" text file as part of its

          distribution, then any Derivative Works that You distribute must

          include a readable copy of the attribution notices contained

          within such NOTICE file, excluding those notices that do not

          pertain to any part of the Derivative Works, in at least one

          of the following places: within a NOTICE text file distributed

          as part of the Derivative Works; within the Source form or

          documentation, if provided along with the Derivative Works; or,

          within a display generated by the Derivative Works, if and

          wherever such third-party notices normally appear. The contents

          of the NOTICE file are for informational purposes only and

          do not modify the License. You may add Your own attribution

          notices within Derivative Works that You distribute, alongside

          or as an addendum to the NOTICE text from the Work, provided

          that such additional attribution notices cannot be construed

          as modifying the License.

      You may add Your own copyright statement to Your modifications and

      may provide additional or different license terms and conditions

      for use, reproduction, or distribution of Your modifications, or

      for any such Derivative Works as a whole, provided Your use,

      reproduction, and distribution of the Work otherwise complies with

      the conditions stated in this License.

   5. Submission of Contributions. Unless You explicitly state otherwise,

      any Contribution intentionally submitted for inclusion in the Work

      by You to the Licensor shall be under the terms and conditions of

      this License, without any additional terms or conditions.

      Notwithstanding the above, nothing herein shall supersede or modify

      the terms of any separate license agreement you may have executed

      with Licensor regarding such Contributions.

   6. Trademarks. This License does not grant permission to use the trade

      names, trademarks, service marks, or product names of the Licensor,

      except as required for reasonable and customary use in describing the

      origin of the Work and reproducing the content of the NOTICE file.

   7. Disclaimer of Warranty. Unless required by applicable law or

      agreed to in writing, Licensor provides the Work (and each

      Contributor provides its Contributions) on an "AS IS" BASIS,

      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or

      implied, including, without limitation, any warranties or conditions

      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A

      PARTICULAR PURPOSE. You are solely responsible for determining the

      appropriateness of using or redistributing the Work and assume any

      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,

      whether in tort (including negligence), contract, or otherwise,

      unless required by applicable law (such as deliberate and grossly

      negligent acts) or agreed to in writing, shall any Contributor be

      liable to You for damages, including any direct, indirect, special,

      incidental, or consequential damages of any character arising as a

      result of this License or out of the use or inability to use the

      Work (including but not limited to damages for loss of goodwill,

      work stoppage, computer failure or malfunction, or any and all

      other commercial damages or losses), even if such Contributor

      has been advised of the possibility of such damages.

   9. Accepting Warranty or Additional Liability. While redistributing

      the Work or Derivative Works thereof, You may choose to offer,

      and charge a fee for, acceptance of support, warranty, indemnity,

      or other liability obligations and/or rights consistent with this

      License. However, in accepting such obligations, You may act only

      on Your own behalf and on Your sole responsibility, not on behalf

      of any other Contributor, and only if You agree to indemnify,

      defend, and hold each Contributor harmless for any liability

      incurred by, or claims asserted against, such Contributor by reason

      of your accepting any such warranty or additional liability.

   END OF TERMS AND CONDITIONS

   APPENDIX: How to apply the Apache License to your work.

      To apply the Apache License to your work, attach the following

      boilerplate notice, with the fields enclosed by brackets "{}"

      replaced with your own identifying information. (Don't include

      the brackets!)  The text should be enclosed in the appropriate

      comment syntax for the file format. We also recommend that a

      file or class name and description of purpose be included on the

      same "printed page" as the copyright notice for easier

      identification within third-party archives.

   Copyright {yyyy} {name of copyright owner}

   Licensed under the Apache License, Version 2.0 (the "License");

   you may not use this file except in compliance with the License.

   You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software

   distributed under the License is distributed on an "AS IS" BASIS,

   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

   See the License for the specific language governing permissions and

   limitations under the License.

[![Build Status](https://travis-ci.org/pckroon/pysmiles.svg?branch=master)](https://travis-ci.org/pckroon/pysmiles)

[![Coverage Status](https://coveralls.io/repos/github/pckroon/pysmiles/badge.svg?branch=master)](https://coveralls.io/github/pckroon/pysmiles?branch=master)

# pysmiles: The lightweight and pure-python SMILES reader and writer

This is a small project I started because I couldn't find any SMILES reader or

writer that was easy to install (read: Python only). Currently, the writer is

extremely basic, and although it should produce valid SMILES they won't be

pretty, but see also issue #17. The reader is in a better state, and should be usable.

SMILES strings are assumed to be as specified by the

[OpenSmiles standard][opensmiles].

## Molecules

Molecules are depicted as [Networkx][networkx] graphs. Atoms are the nodes of

the graph, and bonds are the edges. Nodes can have the following attributes:

- element: str. This describes the element of the atom. Defaults to '\*'

    meaning unknown.

- aromatic: bool. Whether the atom is part of an (anti)-aromatic system. 

    Defaults to False.

- isotope: float. The mass of the atom. Defaults to unknown.

- hcount: int. The number of implicit hydrogens attached to this atom.

    Defaults to 0.

- charge: int. The charge of this atom. Defaults to 0.

- class: int. The "class" of this atom. Defaults to 0.

Edges have the following attributes:

- order: Number. The bond order. 1.5 is used for aromatic bonds. Defaults to 1.

There is currently no way of specifying stereo chemical information, and this

is discarded upon reading. Somewhere in the future this will probably be

stored in the "stereo" attribute of nodes.

## Reading SMILES

The function `read_smiles(smiles, explicit_hydrogen=False,

zero_order_bonds=True, reinterpret_aromatic=True)` can be used to parse a

SMILES string. It should not be used to validate whether a string is a valid

SMILES string --- the function does very little validation whether your SMILES string makes chemical sense.

Edges in the created molecule will always have an 'order'

attribute. Nodes will have the relevant attributes in so far they are

specified. Atoms for which the element is not known (\*) will not have an

element attribute.

- `explicit_hydrogen` determines whether hydrogen atoms should be

    represented as explicit nodes in the created molecule, or implicit in the

    'hcount' attribute.

- `zero_order_bonds` determines whether zero-order bonds (.) in the SMILES

    string should result in edges in the produced molecule.

- `reinterpret_aromatic` determines whether aromaticity should be 

    reinterpreted, and determined from the constructed molecule, or whether

    the aromaticity specifications from the SMILES string (lower case 

    elements) should be taken as leading. If `True`, will also set bond orders 

    to 1 for bonds that are not part of an aromatic ring and have a bond order 

    of 1.5. If `False`, will create a molecule using *only* the information in 

    the SMILES string.

### Stereochemical information

Currently the library cannot handle stereochemical information, neither E/Z nor

R/S. Any stereochemical information that was in the SMILES string will be

*discarded* upon parsing. This means there will be no difference between

parsing *e.g.* `N[C@](Br)(O)C`, `N[C@@](Br)(O)C` and `NC(Br)(O)C`. Parsing

these *will result in the same molecule*. The same holds for *e.g.* `F/C=C/F`

and `FC=CF`. These will result in the same molecule.

Whenever stereochemical information is being discarded a warning will be

logged using the built-in `logging` module. If you want to disable all the

messages logged by `pysmiles` you can add the following snippet to your code,

without interfering with any logging by your own code:

```python

import logging

logging.getLogger('pysmiles').setLevel(logging.CRITICAL)  # Anything higher than warning

```

## Writing SMILES

The function `write_smiles(molecule, default_element='*', start=None)` can be

used to write SMILES strings from a molecule. The function does *not* check 

whether your molecule makes chemical sense. Instead, it writes a SMILES 

representation of the molecule you provided, and nothing else.

- `default_element` is the element to use for nodes that do not have an 

    'element' attribute.

- `start` is the key of the node where the depth first traversal should be 

    started. Something clever is done if not specified.

## Additional functions

In addition to these two core functions, four more functions are exposed that

can help in creating chemically relevant molecules with minimal work.

- `fill_valence(mol, respect_hcount=True, respect_bond_order=True,

                 max_bond_order=3)`

    This function will fill the valence of all atoms in your molecule by 

    incrementing the 'hcount' and, if specified, bond orders. Note that it does

    not use 'charge' attribute to find the correct valence.

    - `repect_hcount`: bool. Whether existing hcounts can be overwritten.

    - `respect_bond_order`: bool. Whether bond orders can be changed

    - `max_bond_order`: int. The maximum bond order that will be set.

- `add_explicit_hydrogens(mol)`

    This function transforms implicit hydrogens, specified by 'hcount' 

    attributes, to explicit nodes.

- `remove_explicit_hydrogens(mol)`

    This function does the inverse of `add_explicit_hydrogens`: it will remove

    explicit hydrogen nodes and add them to the relevant 'hcount' attributes.

- `correct_aromatic_rings(mol)`

    This function marks all (anti)-aromatic atoms in your molecule, and sets 

    all bonds between (anti)-aromatic atoms to order 1.5.

    It fills the valence of all atoms (see also `fill_valence`) before trying

    to figure our which atoms are aromatic. It works by first finding all 

    atoms that are in a ring. Next, for every atom in every ring it is checked

    whether the atoms are sp2 hybridized (note that this is a vague term. 

    Strictly speaking we check whether their element is something that *could*

    be aromatic, and whether they have 2 or 3 bonds.). Finally, the number of 

    electrons per ring is counted, and if this is even, the atoms in the ring

    are said to be aromatic.

    This function is the most fragile in the whole library, and I expect it to

    produce wrong answers in some cases. In particular for fused (aromatic)

    ring systems (such as indole) and rings with extracyclic heteroatoms

    (O=C1C=CC=C1). Buyer beware.

## Examples

### Reading

```python

from pysmiles import read_smiles

smiles = 'C1CC[13CH2]CC1C1CCCCC1'

mol = read_smiles(smiles)

print(mol.nodes(data='element'))

# [(0, 'C'),

#  (1, 'C'),

#  (2, 'C'),

#  (3, 'C'),

#  (4, 'C'),

#  (5, 'C'),

#  (6, 'C'),

#  (7, 'C'),

#  (8, 'C'),

#  (9, 'C'),

#  (10, 'C'),

#  (11, 'C')]

print(mol.nodes(data='hcount'))

# [(0, 2),

#  (1, 2),

#  (2, 2),

#  (3, 2),

#  (4, 2),

#  (5, 1),

#  (6, 1),

#  (7, 2),

#  (8, 2),

#  (9, 2),

#  (10, 2),

#  (11, 2)]

mol_with_H = read_smiles(smiles, explicit_hydrogen=True)

print(mol_with_H.nodes(data='element'))

# [(0, 'C'),

#  (1, 'C'),

#  (2, 'C'),

#  (3, 'C'),

#  (4, 'C'),

#  (5, 'C'),

#  (6, 'C'),

#  (7, 'C'),

#  (8, 'C'),

#  (9, 'C'),

#  (10, 'C'),

#  (11, 'C'),

#  (12, 'H'),

#  (13, 'H'),

#  (14, 'H'),

#  (15, 'H'),

#  (16, 'H'),

#  (17, 'H'),

#  (18, 'H'),

#  (19, 'H'),

#  (20, 'H'),

#  (21, 'H'),

#  (22, 'H'),

#  (23, 'H'),

#  (24, 'H'),

#  (25, 'H'),

#  (26, 'H'),

#  (27, 'H'),

#  (28, 'H'),

#  (29, 'H'),

#  (30, 'H'),

#  (31, 'H'),

#  (32, 'H'),

# (33, 'H')]

```

### Writing

```python

import networkx as nx

from pysmiles import write_smiles, fill_valence

mol = nx.Graph()

mol.add_edges_from([(0, 1), (1, 2), (1, 3), (3, 4), (1, 5), (3, 6)])

for idx, ele in enumerate('CCCCOCO'):

    mol.nodes[idx]['element'] = ele

mol.nodes[4]['charge'] = -1

mol.nodes[4]['hcount'] = 0

mol.edges[3, 6]['order'] = 2

print(write_smiles(mol))

# [O-]C(=O)C([C])([C])[C]

fill_valence(mol, respect_hcount=True)

print(write_smiles(mol))

# [O-]C(=O)C(C)(C)C

```

## Limitations

- The writer produces non-recommended SMILES strings (as per OpenSmiles).

- The writer is better described as a "serializer": if the graph provided

    doesn't make chemical sense the produced "SMILES" string will be an

    exact representation of that graph. Because of this, the SMILES string

    will be invalid though.

- `fill_valence` does not use 'charge' to find the correct valence.

- `correct_aromatic_rings` is fragile.

- There is currently no way of specifying stereo chemical information. The 

    parser can deal with it, but it will be discarded.

- It only processes SMILES. This might later be extended to e.g. InChi, SLN,

    SMARTS, etc.

## Requirements

- [networkx][networkx]

## Similar projects

There are more python projects that deal with SMILES, and I try to list at 

least some of them here. If yours is missing, feel free to open up a PR.

- [PySMILE](https://github.com/jhosmer/PySmile): A similar named project, 

    capable of encoding/decoding SMILE format objects. Doesn't deal with 

    SMILES.

- [RDKit](https://github.com/rdkit/rdkit): A collection of cheminformatics and 

    machine-learning software, capable of reading and writing SMILES, InChi, 

    and others.

- [OpenEye Chem toolkit](https://www.eyesopen.com/oechem-tk): The OpenEye 

    chemistry toolkit is a programming library for chemistry and 

    cheminformatics. It is capable of dealing with (canonical) SMILES and 

    InChi.

## License

PySmiles is distributed under the Apache 2.0 license.

    Copyright 2018 Peter C Kroon

    Licensed under the Apache License, Version 2.0 (the "License");

    you may not use this file except in compliance with the License.

    You may obtain a copy of the License at

        http://www.apache.org/licenses/LICENSE-2.0

    Unless required by applicable law or agreed to in writing, software

    distributed under the License is distributed on an "AS IS" BASIS,

    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

    See the License for the specific language governing permissions and

    limitations under the License.

[opensmiles]: http://opensmiles.org/

[networkx]: https://networkx.github.io/

from pysmiles import read_smiles

import networkx as nx

# returns the order number of the edge that appears using nx.edge_list

def get_bond_order(line):

     return int(line.split("{'order': ")[1].rstrip('}\n'))

# multiplies the edge pair by the order number

def process_content(content):

    new_content = ""

    for line in content:

        # Check if the line contains bond order information

        if "{'order':" in line:

            bond_order = get_bond_order(line)

            vertex_pair = ' '.join(line.split()[:2])

            for i in range(bond_order):

             new_content += vertex_pair + '\n'

        else:

            new_content += line

    return new_content

if __name__ == "__main__":

    # replace with name of molecule

    mol_name = "Vitamin-C"

    # replace with smiles string of molecule

    smiles = 'C([C@@H]([C@@H]1C(=C(C(=O)O1)O)O)O)O'

    mol_with_H = read_smiles(smiles, explicit_hydrogen=True)

    file_path = "./molecules/" + mol_name + ".txt"

    nx.write_edgelist(mol_with_H, file_path)

    nodes = mol_with_H.nodes(data='element')

    mol_data = mol_name + '\n'

    mol_data += str(len(nodes)) + '\n'

    for a in nodes:

      mol_data += a[1] + '\n'

    # Read the existing contents of the file

    with open(file_path, 'r') as file:

        edgelist = file.read()

    modified_edgelist = process_content(edgelist.split('\n'))

    # Write the new content at the beginning and the original content

    with open(file_path, 'w') as file:

        file.write(mol_data + modified_edgelist)

L-Theanine

26

C

C

N

C

O

C

C

C

C

O

O

N

H

H

H

H

H

H

H

H

H

H

H

H

H

H

0 1

0 12

0 13

0 14

1 2

1 15

1 16

2 3

2 17

3 4

3 4

3 5

5 6

5 18

5 19

6 7

6 20

6 21

7 8

7 11

7 22

8 9

8 9

8 10

10 23

11 24

11 25