Group heuristic

.github/workflows/lint.yml

@@ -1,49 +1,29 @@
-# This is a basic workflow to help you get started with Actions
-
 name: Check code style
 
-# Controls when the workflow will run
 on:
-  # Triggers the workflow on push or pull request events
   [ push, pull_request ]
 
-# A workflow run is made up of one or more jobs that can run sequentially or in parallel
 jobs:
 
-  # This workflow contains a single job called "Check_code_style"
   Check_code_style:
-
-    # The type of runner that the job will run on
-    runs-on: ubuntu-latest
-
-    # A strategy creates a build matrix for your jobs
+    runs-on: ubuntu-18.04
     strategy:
-
-      # You can define a matrix of different job configurations
       matrix:
-
-        # Each option you define in the matrix has a key and value
         python-version: [ 3.8 ]
-
-    # Steps represent a sequence of tasks that will be executed as part of the job
     steps:
-      # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
       - name: Set up Git repository
         uses: actions/checkout@v2
 
-      # Setup Python with version from matrix
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python-version }}
 
-      # Install pre-commit
       - name: Install pre-commit
         run: |
           python -m pip install pre-commit==2.15.0
           pre-commit install
 
-      # Run pre-commit on all the files in the repo
       - name: Run pre-commit
         run: |
           pre-commit run --all-files --color always --verbose --show-diff-on-failure

.github/workflows/test.yml

@@ -0,0 +1,28 @@
+name: Test
+
+on: [ push, pull_request ]
+
+jobs:
+  tests:
+    runs-on: ubuntu-18.04
+    strategy:
+      matrix:
+        python-version: [ "3.8" ]
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install packages
+        run: |
+          python -m pip install --upgrade pip wheel setuptools
+          python -m pip install .
+          python -m pip install -r requirements/test.txt
+          python -m pip list
+
+      - name: Test Genegram
+        run: |
+          pytest -vv -s tests

.pre-commit-config.yaml

@@ -6,6 +6,6 @@ repos:
       - id: end-of-file-fixer
       - id: trailing-whitespace
   - repo: https://github.com/psf/black
-    rev: 20.8b1
+    rev: 22.3.0
     hooks:
       - id: black

README.md

@@ -1,58 +1,131 @@
-[![Check code style](https://github.com/JetBrains-Research/Genegram/actions/workflows/check_code_style.yml/badge.svg)](https://github.com/JetBrains-Research/Genegram/actions/workflows/check_code_style.yml)
+[![Check code style](https://github.com/JetBrains-Research/Genegram/actions/workflows/lint.yml/badge.svg)](https://github.com/JetBrains-Research/Genegram/actions/workflows/lint.yml)
+[![Check code style](https://github.com/JetBrains-Research/Genegram/actions/workflows/test.yml/badge.svg)](https://github.com/JetBrains-Research/Genegram/actions/workflows/test.yml)
 ---
-# Genegram
+
+# Genegram: RNA Secondary Structure Prediction by Combination of Formal Grammars and Neural Networks
 
 ## Description
 
-[comment]: <> (TODO)
+Command Line Tool for Predicting RNA Secondary Structure Connectivity Table
 
-## Install
+## FASTA format
 
-We use [`Pipenv`](https://pipenv.pypa.io/en/latest/) to manage dependencies.
+**⚠️ We use a slightly more strict FASTA format than the [standard](https://en.wikipedia.org/wiki/FASTA_format) ⚠️**
 
-### [Install Pipenv](https://pipenv.pypa.io/en/latest/#install-pipenv-today)
+### Our format
 
-```shell
-pip install --user pipenv
+```text
+>RNA description
+RNA sequence
+...
+>RNA description
+RNA sequence
 ```
 
-### Install Genegram (from sources)
+### Example
+
+```text
+>34551
+GGCCUCCAAGCUGUGCCUUGGGUGGCC
+>34552
+CCUCCCUUACAAGGAGG
+>34553
+GGAGUGGCCGAAAGGCAUCUCC
+>34735
+GGCUCUCAGUGAGCC
+```
 
-```shell
-git clone https://github.com/JetBrains-Research/Genegram
-cd Genegram
-pipenv install --ignore-pipfile
+## Requirements
+
+### Hardware
+
+* Genegram requires only a standard computer with around 16 GB RAM to support the in-memory operations for RNAs sequence length less than 500
+
+### OS
+
+* [`Ubuntu 18.04`](https://releases.ubuntu.com/18.04/)
+
+### Software
+
+* [`Python 3.8`](https://www.python.org/downloads/release/python-380/)
+* [`Virtualenv`](https://virtualenv.pypa.io/en/latest/installation/)
+* [`CUDA 11.2`](https://developer.nvidia.com/cuda-11.2.0-download-archive) *(Optional If using GPU)*
+* [`cuDNN 8.1`](https://developer.nvidia.com/cudnn) *(Optional If using GPU)*
+
+### Python packages
+
+```text
+tensorflow==2.7.0
+pygraphblas==4.2.2
+pyformlang==0.1.26
 ```
 
+## Installation
+
+### From PyPI
+
+To install **Gengram** from PyPI following commands can be used in terminal:
+
+1. `virtualenv -p python3.8 venv`
+2. `source ./venv/bin/activate`
+3. `pip install genegram`
+
+### From sources
+
+To install **Gengram** from sources following commands can be used in terminal:
+
+1. `git clone https://github.com/JetBrains-Research/Genegram.git`
+2. `cd Genegram`
+
+Either follow `virtualenv` column steps or `conda` column steps to create virtual environment
+and to install **Genegram** dependencies given in table below:
+
+|  | virtualenv                                                                                                                                             | conda                                                                                                                                                                                                  |
+| --- |--------------------------------------------------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| 3. | `virtualenv -p python3.8 venv`                                                                                                                         | `conda create -n venv python=3.8`                                                                                                                                                                      |
+| 4. | `source ./venv/bin/activate`                                                                                                                           | `conda activate venv`                                                                                                                                                                                  |
+| 5. | To run Genegram on **CPU:** <br> `pip install tensorflow-cpu==2.7.0` <br> or <br> To run Genegram on **GPU:** <br> `pip install tensorflow-gpu==2.7.0` | To run Genegram on **CPU:** <br> `conda install tensorflow-cpu==2.7.0 --channel conda-forge` <br> or <br> To run Genegram on **GPU:** <br> `conda install tensorflow-gpu==2.7.0 --channel conda-forge` |
+| 6. | `pip install .` | `pip install .` |
+
 ## Usage
 
-Run the following command with arguments.
+After successfully installing the package, you have three options to use it:
 
-```bash
-python -m genegram
-```
+1. `python -m genegram <arguments>`
+2. `genegram <arguments>`
+3. ```Python
+   from genegram import process_fasta_group
+   process_fasta_group(<arguments>)
+   ```
 
-### **Arguments**
+### Arguments
 
 Argument | Required | Description
 :--- | :---: | :---
 -i, --inp | True | Path to the [`FASTA`](http://genetics.bwh.harvard.edu/pph/FASTA.html) file
 -o, --out | True | Path to the folder where the [`Connectivity Tables`](http://rna.urmc.rochester.edu/Text/File_Formats.html#CT) will be saved
 -m, --model | False | Type of the model to be used: </br> `main` -- The default model, the best on average </br> `mps` -- Multiplet prediction model </br> `pks` -- Pseudoknots prediction model
--l, --log | False | Type of the logging level to be used: </br> `INFO` -- Confirmation that things are working as expected </br> `WARNING` -- An indication that something unexpected happened, the software is still working as expected </br> `ERROR` -- Due to a more serious problem, the software has not been able to perform some function </br> `CRITICAL` -- A serious error, indicating that the program itself may be unable to continue running </br> `DEBUG` -- Detailed information, typically of interest only when diagnosing problems
 
-## Code style
+## Examples
+
+If you have installed Genegram from sources, you can run the following example (in the Genegram folder)
+
+`genegram -i tests/data/seq.fasta -o EXAMPLE_FOLDER -m main`
+
+## Information for Developers
+
+### Code Style
 
 We recommend you use a [pre-commit](https://pre-commit.com/#install) hook, which runs [black](https://github.com/psf/black) when you type git commit.
 
-### Install pre-commit
+#### Install pre-commit
 
 ```shell
 pipenv install --dev
 pre-commit install
 ```
 
-### Use pre-commit
+#### Use pre-commit
 
 ```shell
 pre-commit run --all-files --color always --verbose

genegram/__init__.py

@@ -1,6 +1,11 @@
+__version__ = "1.0.0"
+
 import genegram.shared
 from genegram.shared import *
 
+import genegram.utils
+from genegram.utils import *
+
 import genegram.cfpq_pyalgo
 from genegram.cfpq_pyalgo import *
 
@@ -9,3 +14,6 @@
 
 import genegram.predict
 from genegram.predict import *
+
+import genegram.main
+from genegram.main import *

genegram/__main__.py

@@ -1,12 +1,11 @@
-import logging
+"""Genegram CLI"""
 from argparse import ArgumentParser, RawTextHelpFormatter
 from pathlib import Path
 
-from genegram.parsing import read_fasta
-from genegram.predict import rna_predict, setup_model, clear_session
-from genegram.shared import ROOT
+from genegram.main import process_fasta_group
 
-if __name__ == "__main__":
+
+def main():
     parser = ArgumentParser(
         description="Genegram", formatter_class=RawTextHelpFormatter
     )
@@ -34,49 +33,15 @@
             "\npks -- Pseudoknots prediction model"
         ),
     )
-    parser.add_argument(
-        "-l",
-        "--log",
-        required=False,
-        type=str,
-        choices=["INFO", "WARNING", "ERROR", "CRITICAL", "DEBUG"],
-        default="INFO",
-        help=(
-            "Type of the logging level to be used:"
-            "\nINFO -- Confirmation that things are working as expected"
-            "\nWARNING -- An indication that something unexpected happened, the software is still working as expected"
-            "\nERROR -- Due to a more serious problem, the software has not been able to perform some function"
-            "\nCRITICAL -- A serious error, indicating that the program itself may be unable to continue running"
-            "\nDEBUG -- Detailed information, typically of interest only when diagnosing problems"
-        ),
-    )
 
     args = parser.parse_args()
 
-    logging.basicConfig(
-        level=args.log,
-        format="[%(asctime)s]>%(levelname)s>%(message)s",
-        datefmt="%Y-%m-%d %H:%M:%S",
+    process_fasta_group(
+        fasta=Path(args.inp).resolve(),
+        out=Path(args.out).resolve(),
+        weights=args.model,
     )
 
-    logging.info(f"Parse {args=}")
-
-    out = Path(args.out).resolve()
-    if not out.exists():
-        out.mkdir(parents=True, exist_ok=True)
-        logging.info(f"Create {out} dir")
-
-    model = setup_model(ROOT / "weights" / f"{args.model}.h5")
-
-    for rna in read_fasta(Path(args.inp).resolve()):
-        pred = rna_predict(rna, model)
 
-        target_path = out / f"{rna.description}.ct"
-
-        with open(target_path, "w") as fout:
-            fout.write(pred.ct)
-            logging.info(
-                f"Save {rna=} secondary structure connectivity table to {target_path=}"
-            )
-
-    clear_session()
+if __name__ == "__main__":
+    main()