add readme

milescsmith · Feb 3, 2022 · c142343 · c142343
1 parent 1f4d345
commit c142343
Show file tree

Hide file tree

Showing 7 changed files with 94 additions and 80 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,24 +1,43 @@
 # Changelog
+
 All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.0] - 2021-02-02
+
+### Added
+
+- A real README.md
+
+### Changed
+
+- Removed conditional requirement of `import_metadata` as a version of Python >=3.8 is required
+
+## [0.1.11] - 2021-02-02
+
+### Changed
+
+- updated dependency versions
 
 ## [0.1.10] - 2021-12-20
 
 ### Changed
+
 - updated dependency versions
 
 
 ## [0.1.9] - 2021-04-20
 
 ### Changed
+
 - updated dependency versions
 
 ## [0.1.8] - 2021
 
 ### Changed
+
 - renamed `logging.py` to `logger.py` to avoid colliding with the standard module name
 - alter how the PED file is written to: for whatever reason, `Path().write_text()` was not working
   but using a open file context manager with `writelines()` does.
@@ -27,19 +46,24 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [0.1.7] - 2021-02-22
 
 ### Added
+
 - CHANGELOG.md
 - more logging info
 
 ### Fixed
+
 - add missing import of liftPed to plinkliftover.__main__ from plinkliftover.liftover
 - if the liftOver executable cannot be found, raise an error
 
 ## [0.1.6] - 2021-02-22
 
 ### Fixed
-- replace `set` and `tuple` in type hints with their `typing.Set` and `typing.Tuple` counterparts
 
+- replace `set` and `tuple` in type hints with their `typing.Set` and `typing.Tuple` counterparts
 
+[0.2.0]: https://github.com/olivierlacan/keep-a-changelog/compare/0.1.11...0.2.0
+[0.1.11]: https://github.com/olivierlacan/keep-a-changelog/compare/0.1.10...0.1.11
+[0.1.10]: https://github.com/olivierlacan/keep-a-changelog/compare/0.1.9...0.1.10
 [0.1.9]: https://github.com/olivierlacan/keep-a-changelog/compare/0.1.8...0.1.9
 [0.1.8]: https://github.com/olivierlacan/keep-a-changelog/compare/0.1.7...0.1.8
 [0.1.7]: https://github.com/olivierlacan/keep-a-changelog/compare/0.1.6...0.1.7

diff --git a/README.md b/README.md
@@ -1,75 +1,84 @@
-# plinkliftover
+# PLINKLiftOver
 
-<div align="center">
+<div align="justified">
 
 [![Build status](https://github.com/milescsmith/plinkliftover/workflows/build/badge.svg?branch=master&event=push)](https://github.com/milescsmith/plinkliftover/actions?query=workflow%3Abuild)
 [![Python Version](https://img.shields.io/pypi/pyversions/plinkliftover.svg)](https://pypi.org/project/plinkliftover/)
 [![Dependencies Status](https://img.shields.io/badge/dependencies-up%20to%20date-brightgreen.svg)](https://github.com/milescsmith/plinkliftover/pulls?utf8=%E2%9C%93&q=is%3Apr%20author%3Aapp%2Fdependabot)
 
 [![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 [![Security: bandit](https://img.shields.io/badge/security-bandit-green.svg)](https://github.com/PyCQA/bandit)
-[![Pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/milescsmith/plinkliftover/blob/master/.pre-commit-config.yaml)
 [![Semantic Versions](https://img.shields.io/badge/%F0%9F%9A%80-semantic%20versions-informational.svg)](https://github.com/milescsmith/plinkliftover/releases)
 [![License](https://img.shields.io/github/license/milescsmith/plinkliftover)](https://github.com/milescsmith/plinkliftover/blob/master/LICENSE)
+![Alt](https://repobeats.axiom.co/api/embed/8d9c682229fb45f45eef3f300367eb33a44bd347.svg "Repobeats analytics image")
 
-Awesome `plinkliftover` is a Python cli/package created with https://github.com/TezRomacH/python-package-template
+**PLINKLiftOver** is a utility enabling [liftOver](http://genome.ucsc.edu/cgi-bin/hgLiftOver)
+to work on genomics files from [PLINK](https://www.cog-genomics.org/plink/),
+allowing one to update the coordinates from one genome reference version to
+another.
 
 </div>
-
 ## Installation
 
+PLINKLiftOver requires
+* Python 3.8 
+* The command line version of [liftOver](http://genome.ucsc.edu/cgi-bin/hgLiftOver),
+installed and on the system path
+* An appropriate [chain file](http://hgdownload.soe.ucsc.edu/downloads.html#liftover)
+* The [MAP file](https://zzz.bwh.harvard.edu/plink/data.shtml) from a PLINK
+dataset
+
 ```bash
 pip install -U plinkliftover
 ```
 
-or install with `Poetry`
+or install with the development version with
 
 ```bash
-poetry add plinkliftover
+pip install -U git+https://github.com/milescsmith/plinkliftover.git
 ```
 
-Then you can run
+## Usage
 
 ```bash
-plinkliftover --help
+Usage: plinkliftover [OPTIONS] MAPFILE CHAINFILE
+
+  Converts genotype data stored in plink's PED+MAP format from one genome
+  build to another, using liftOver.
+
+Arguments:
+  MAPFILE    The plink MAP file to `liftOver`.  [required]
+  CHAINFILE  The location of the chain files to provide to `liftOver`.
+             [required]
+
+Options:
+  --pedfile TEXT             Optionally remove "unlifted SNPs" from the plink
+                             PED file after running `liftOver`.
+  --datfile TEXT             Optionally remove 'unlifted SNPs' from a data
+                             file containing a list of SNPs (e.g. for
+                             --exclude or --include in `plink`)
+  --prefix TEXT              The prefix to give to the output files.
+  --liftoverexecutable TEXT  The location of the `liftOver` executable.
+  -v, --version              Prints the version of the plinkliftover package.
+  --help                     Show this message and exit.
 ```
 
+For example
+
 ```bash
-plinkliftover --name Roman
+plinkliftover updating.map hg19ToHg38.over.chain.gz
 ```
 
-or if installed with `Poetry`:
+### Note!
 
-```bash
-poetry run plinkliftover --help
-```
+By default, [PLINK 2.0](https://www.cog-genomics.org/plink/2.0/) does not 
+use/create the required MAP file.  It can be generated using PLINK 1.9 by
 
 ```bash
-poetry run plinkliftover --name Roman
+plink --bfile original --recode --out to_update
 ```
 
-## 📈 Releases
-
-You can see the list of available releases on the [GitHub Releases](https://github.com/milescsmith/plinkliftover/releases) page.
-
-We follow [Semantic Versions](https://semver.org/) specification.
-
-We use [`Release Drafter`](https://github.com/marketplace/actions/release-drafter). As pull requests are merged, a draft release is kept up-to-date listing the changes, ready to publish when you’re ready. With the categories option, you can categorize pull requests in release notes using labels.
-
-For Pull Request this labels are configured, by default:
-
-|               **Label**               |  **Title in Releases**  |
-| :-----------------------------------: | :---------------------: |
-|       `enhancement`, `feature`        |       🚀 Features       |
-| `bug`, `refactoring`, `bugfix`, `fix` | 🔧 Fixes & Refactoring  |
-|       `build`, `ci`, `testing`        | 📦 Build System & CI/CD |
-|              `breaking`               |   💥 Breaking Changes   |
-|            `documentation`            |    📝 Documentation     |
-|            `dependencies`             | ⬆️ Dependencies updates |
-
-You can update it in [`release-drafter.yml`](https://github.com/milescsmith/plinkliftover/blob/master/.github/release-drafter.yml).
-
-GitHub creates the `bug`, `enhancement`, and `documentation` labels for you. Dependabot creates the `dependencies` label. Create the remaining labels on the Issues tab of your GitHub repository, when you need them.
+where `original` is the prefix for the bed/bim/fam files and `to_update` is the prefix to give the new files.
 
 ## 🛡 License
 

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -6,7 +6,7 @@ build-backend = "poetry.masonry.api"
 
 [tool.poetry]
 name = "plinkliftover"
-version = "0.1.11"
+version = "0.2.0"
 description = "Converts genotype data stored in plink's PED+MAP format from one genome build to another, using liftOver"
 readme = "README.md"
 authors = [
@@ -32,8 +32,7 @@ classifiers = [  # Update me
 "plinkliftover" = "plinkliftover.__main__:app"
 
 [tool.poetry.dependencies]
-python = "^3.8"
-importlib_metadata = {version = "^3.4.0", python = "<3.8"}
+python = ">=3.8.3,<4.0"
 typer = "^0.4.0"
 rich = "^10.2.1"
 psutil = "^5.8.0"

diff --git a/src/plinkliftover/__init__.py b/src/plinkliftover/__init__.py
@@ -1,10 +1,6 @@
 # type: ignore[attr-defined]
 """`plinkliftover` Converts genotype data stored in plink's PED+MAP format from one genome build to another, using liftOver"""
-try:
-    from importlib.metadata import PackageNotFoundError, version
-except ImportError:  # pragma: no cover
-    from importlib_metadata import PackageNotFoundError, version
-
+from importlib.metadata import PackageNotFoundError, version
 
 try:
     __version__ = version(__name__)

diff --git a/src/plinkliftover/__main__.py b/src/plinkliftover/__main__.py
@@ -5,9 +5,9 @@
 from pathlib import Path
 
 import typer
-from plinkliftover import __version__
-from plinkliftover.liftover import bed2map, liftBed, liftDat, liftPed, map2bed
-from plinkliftover.logger import plo_logger as logger
+from . import __version__
+from .liftover import bed2map, liftBed, liftDat, liftPed, map2bed
+from .logger import plo_logger as logger
 from rich.console import Console
 
 app = typer.Typer(
@@ -66,9 +66,6 @@ def main(
     # Show usage message if user hasn't provided any arguments, rather
     # than giving a non-descript error message with the usage()
 
-    lifted_set = set()
-    unlifted_set = set()
-
     mapfile = Path(mapfile)
     oldbed = mapfile.with_suffix(".bed")
     map2bed(mapfile, oldbed)
@@ -94,14 +91,11 @@ def main(
             )
 
     newbed = Path(f"{mapfile}.bed")
-    # unlifted = Path(f"{prefix}.unlifted")
     lifted_set, unlifted_set, lb_status = liftBed(
         fin=oldbed,
         fout=newbed,
         chainfile=chainfile,
         liftOverPath=liftOverPath,
-        unlifted_set=unlifted_set,
-        lifted_set=lifted_set,
     )
 
     if lb_status:

diff --git a/src/plinkliftover/liftover.py b/src/plinkliftover/liftover.py
@@ -23,7 +23,7 @@
 from pathlib import Path
 from subprocess import check_output
 
-from plinkliftover.logger import plo_logger as logger
+from .logger import plo_logger as logger
 from rich.console import Console
 from typer import progressbar
 
@@ -36,10 +36,10 @@ def map2bed(fin: Path, fout: Path) -> bool:
         f"Converting [green]MAP[/] file [yellow]{fin.name}[/] file to [green]UCSC BED[/] file [blue]{fout.name}[/]..."
     )
     lines = fin.read_text().split("\n")
-    output = []
+    output = list()
     with progressbar(lines) as map_lines:
-        for ln in map_lines:
-            if len(x := ln.split()) == 4:
+        for line in map_lines:
+            if len(x := line.split()) == 4:
                 chrom, rs, _, pos = x
                 output.append(f"chr{chrom}\t{int(pos)-1}\t{int(pos)}\t{rs}")
             else:
@@ -53,8 +53,6 @@ def liftBed(
     fout: Path,
     chainfile: Path,
     liftOverPath: Path,
-    unlifted_set: Set[str],
-    lifted_set: Set[str],
 ) -> Tuple[Set[str]]:
     console.print(f"Lifting [green]BED[/] file [blue]{fin.name}[/]...")
     params = {
@@ -70,18 +68,14 @@ def liftBed(
     unlifted_lines = Path(params["UNLIFTED"]).read_text().split("\n")
     console.print(f"Processing [red]unlifted[/] {fout.name}.unlifted")
     with progressbar(unlifted_lines) as unlifted:
-        for ln in unlifted:
-            if len(ln) == 0 or ln[0] == "#":
-                continue
-            unlifted_set.add(ln.strip().split()[-1])
+        print("Using new set comprehension for 'unlifted_set'")
+        unlifted_set = {ln.strip().split()[-1] for ln in unlifted if len(ln) > 0 and ln[0] != "#"}
 
     console.print(f"Processing [red]new[/] {fout.name}")
     new_bed_lines = Path(params["NEW"]).read_text().split("\n")
     with progressbar(new_bed_lines) as new_bed:
-        for ln in new_bed:
-            if len(ln) == 0 or ln[0] == "#":
-                continue
-            lifted_set.add(ln.strip().split()[-1])
+        print("Using new set comprehension for 'lifted_set'")
+        lifted_set = {ln.strip().split()[-1] for ln in new_bed if len(ln) != 0 and ln[0] != "#"}
 
     return lifted_set, unlifted_set, True
 
@@ -91,7 +85,7 @@ def bed2map(fin: Path, fout: Path) -> bool:
         f"Converting lifted [green]BED[/] [blue]{fin.name}[/] file back to [green]MAP[/] [yellow]{fout.name}[/]..."
     )
     bed_lines = fin.read_text().split("\n")
-    output = []
+    output = list()
     with progressbar(bed_lines) as lines:
         for ln in lines:
             if len(x := ln.split()) == 4:
@@ -105,7 +99,7 @@ def bed2map(fin: Path, fout: Path) -> bool:
 def liftDat(fin: Path, fout: Path, lifted_set: Set[str]) -> bool:
     console.print(f"Updating [green]DAT[/] file [pink]{fin.name}[/]...")
     lines = fin.read_text().split("\n")
-    output = []
+    output = list()
     with progressbar(lines) as dat_lines:
         for ln in dat_lines:
             if len(ln) == 0 or ln[0] != "M":
@@ -133,12 +127,11 @@ def liftPed(
 
     console.print(f"Updating [green]PED[/] file [orange]{fin.resolve()}[/]...")
     lines = fin.read_text().split("\n")
-    output = []
+    output = list()
     with progressbar(lines) as liftped_lines:
         for ln in liftped_lines:
             if ln.strip() != "":
                 f = ln.strip().split()
-                # l = len(f)
                 f = f[:6] + [
                     f[i * 2] + " " + f[i * 2 + 1] for i in range(3, len(f) // 2)
                 ]
@@ -151,7 +144,6 @@ def liftPed(
                 a = "\t".join(f[:6])
                 b = "\t".join(newmarker)
                 output.append(f"{a}\t{b}\n")
-            # print marker[:10]
     console.print(
         f"Writing new [green]PED[/] data to [light_slate_blue]{fout.resolve()}[/]"
     )