Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix to pdb stream #116

Merged
merged 2 commits into from
Mar 27, 2023
Merged

Fix to pdb stream #116

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ba8f414
Fix to_pdb_stream return statement and default argument
Mar 26, 2023
d3e25b0
Update changelog and fix README link
Mar 26, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,7 @@
- Documentation: [https://BioPandas.github.io/biopandas/](https://BioPandas.github.io/biopandas/)
- Source code repository: [https://github.com/rasbt/biopandas](https://github.com/rasbt/biopandas)
- PyPI: [https://pypi.python.org/pypi/biopandas](https://pypi.python.org/pypi/biopandas)
- How to contribute: [https://BioPandas.github.io/biopandas//contributing/](https://BioPandas.github.io/biopandas/contributing/)
- How to contribute: [https://biopandas.github.io/biopandas/CONTRIBUTING/](https://biopandas.github.io/biopandas/CONTRIBUTING/)
- Changelog: [./docs/sources/CHANGELOG.md](./docs/sources/CHANGELOG.md)

<br>
Expand Down
40 changes: 21 additions & 19 deletions biopandas/pdb/pandas_pdb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ def __init__(self):

@property
def df(self):
"""Acccess dictionary of pandas DataFrames for PDB record sections."""
"""Access dictionary of pandas DataFrames for PDB record sections."""
return self._df

@df.setter
Expand Down Expand Up @@ -115,22 +115,25 @@ def read_pdb_from_list(self, pdb_lines):
self.header, self.code = self._parse_header_code()
return self


def fetch_pdb(self, pdb_code: Optional[str] = None, uniprot_id: Optional[str] = None, source: str = "pdb"):
"""Fetches PDB file contents from the Protein Databank at rcsb.org or AlphaFold database at https://alphafold.ebi.ac.uk/.
"""Fetches PDB file contents from the Protein Databank at rcsb.org or AlphaFold database
at https://alphafold.ebi.ac.uk/.
.
Parameters
----------
pdb_code : str, optional
A 4-letter PDB code, e.g., `"3eiy"` to retrieve structures from the PDB. Defaults to `None`.
A 4-letter PDB code, e.g., `"3eiy"` to retrieve structures from the PDB.
Defaults to `None`.
uniprot_id : str, optional
A UniProt Identifier, e.g., `"Q5VSL9"` to retrieve structures from the AF2 database. Defaults to `None`.
A UniProt Identifier, e.g., `"Q5VSL9"` to retrieve structures from the AF2 database.
Defaults to `None`.
source : str
The source to retrieve the structure from
(`"pdb"`, `"alphafold2-v1"`, `"alphafold2-v2"`, `"alphafold2-v3"` (latest)). Defaults to `"pdb"`.
(`"pdb"`, `"alphafold2-v1"`, `"alphafold2-v2"`, `"alphafold2-v3"` (latest)).
Defaults to `"pdb"`.
Returns
---------
Expand All @@ -144,13 +147,12 @@ def fetch_pdb(self, pdb_code: Optional[str] = None, uniprot_id: Optional[str] =
invalid_input_combination_2 = pdb_code is not None and source in {
"alphafold2-v1", "alphafold2-v2", "alphafold2-v3"}


if invalid_input_identifier_1 or invalid_input_identifier_2:
raise ValueError("Please provide either a PDB code or a UniProt ID.")

if invalid_input_combination_1 :
if invalid_input_combination_1:
raise ValueError("Please use a 'pdb_code' instead of 'uniprot_id' for source='pdb'.")
elif invalid_input_combination_2 :
elif invalid_input_combination_2:
raise ValueError(f"Please use a 'uniprot_id' instead of 'pdb_code' for source={source}.")

if source == "alphafold2-v1":
Expand Down Expand Up @@ -364,7 +366,6 @@ def _fetch_af2(uniprot_id: str, af2_version: int = 3):
print('URL Error %s' % e.args)
return url, txt


def _parse_header_code(self):
"""Extract header information and PDB code."""
code, header = "", ""
Expand Down Expand Up @@ -441,7 +442,7 @@ def _construct_df(pdb_lines):
record = line[:6].rstrip()
line_ele = ["" for _ in range(len(pdb_records[record]) + 1)]
for idx, ele in enumerate(pdb_records[record]):
line_ele[idx] = line[ele["line"][0] : ele["line"][1]].strip()
line_ele[idx] = line[ele["line"][0]: ele["line"][1]].strip()
line_ele[-1] = line_num
line_lists[record].append(line_ele)
else:
Expand Down Expand Up @@ -486,7 +487,7 @@ def amino3to1(self, record="ATOM", residue_col="residue_name", fillna="?"):
Parameters
----------
record : str, default: 'ATOM'
Specfies the record DataFrame.
Specifies the record DataFrame.
residue_col : str, default: 'residue_name'
Column in `record` DataFrame to look for 3-letter amino acid
codes for the conversion.
Expand Down Expand Up @@ -786,8 +787,8 @@ def get_models(self, model_indices: List[int]) -> PandasPdb:
Parameters
----------
model_index : int
An integer representing the model index to subset to.
model_indices : List[int]
A list representing the model indexes to subset to.
Returns
---------
Expand All @@ -812,14 +813,14 @@ def get_models(self, model_indices: List[int]) -> PandasPdb:
]
return df

def to_pdb_stream(self, records: List[str] = ["ATOM", "HETATM"]) -> StringIO:
def to_pdb_stream(self, records: tuple[str] = ("ATOM", "HETATM")) -> StringIO:
"""Writes a PDB dataframe to a stream.
Parameters
------------
records : List[str]
List of record names to save to stream. Any of `["ATOM", "HETATM", "OTHERS"]`.
records : iterable, default: ('ATOM', 'HETATM')
Iterable of record names to save to stream. Any of `["ATOM", "HETATM", "OTHERS"]`.
Returns
--------
io.StringIO : Filestream of PDB file.
Expand Down Expand Up @@ -861,4 +862,5 @@ def to_pdb_stream(self, records: List[str] = ["ATOM", "HETATM"]) -> StringIO:
to_write = "\n".join(s)
output.write(to_write)
output.write("\n")
return output.seek(0)
output.seek(0)
return output
15 changes: 15 additions & 0 deletions docs/CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,21 @@ The CHANGELOG for the current development version is available at
[https://github.com/rasbt/biopandas/blob/main/docs/sources/CHANGELOG.md](https://github.com/rasbt/biopandas/blob/main/docs/sources/CHANGELOG.md).


### 0.5.1 (26-03-2023)

##### Downloads

- [Source code (zip)](https://github.com/rasbt/biopandas/archive/v0.5.1.zip)
- [Source code (tar.gz)](https://github.com/rasbt/biopandas/archive/v0.5.1.tar.gz)

##### Bug Fixes

- Fix the `return` statement in `PandasPdb.to_pdb_stream()` to return `output` instead of `output.seek(0)`. (via [goniochromatic](https://github.com/github.com/goniochromatic/), PR #[116](https://github.com/rasbt/biopandas/pull/116/files))
- Change the `records` default argument in `PandasPdb.to_pdb_stream()` to be immutable. (via [goniochromatic](https://github.com/github.com/goniochromatic/), PR #[116](https://github.com/rasbt/biopandas/pull/116/files))
- Fix some typos and general style issues. (via [goniochromatic](https://github.com/github.com/goniochromatic/), PR #[116](https://github.com/rasbt/biopandas/pull/116/files))
- Fix link for "How to contribute" in `README.md`. (via [goniochromatic](https://github.com/github.com/goniochromatic/), PR #[116](https://github.com/rasbt/biopandas/pull/116/files))


### 0.5.0dev (UNRELEASED)


Expand Down