GithubHelp home page GithubHelp logo

zlatkojoncev / reactiondataextractor2 Goto Github PK

View Code? Open in Web Editor NEW

This project forked from dmw51/reactiondataextractor2

0.0 0.0 0.0 92.35 MB

This repo contains ReactionDataExtractor v.2 - software toolkit for extraction of information from chemical reaction schemes

Home Page: http://www.reactiondataextractor.org

License: MIT License

Python 100.00%

reactiondataextractor2's Introduction

ReactionDataExtractor is a toolkit for the automatic extraction of data from chemical reaction schemes.

Features

  • Automatic extraction of chemical reaction schemes
  • Segmentation of reaction arrows, conditions, diagrams and labels
  • Optical recognition of chemical structures and text, parsing of reaction condiitions
  • Whole-reaction-scheme recovery and conversion into a machine-readable format
  • High-throughput capabilities
  • Direct extraction from image files
  • PNG, GIF, JPEG, TIFF image format support

Installation

This section outlines the steps required to install ReactionDataExtractor. The simplest way is to do this through conda.

Installation via Conda

Anaconda Python is a self-contained Python environment that is useful for scientific applications.

First, install Miniconda, which contains a complete Python distribution alongside the conda package manager.

Next, go to the command line terminal and clone the git repository by typing

git clone https://github.com/dmw51/reactiondataextractor2 

Update apt and apt-get, then install the following required packages:

sudo apt-get install gcc g++ libpotrace-dev pkg-config libagg-dev ffmpeg libsm6 libxext6
sudo apt install libtesseract-dev

Inside the cloned directory, create the conda environment by typing

conda env create -f environment.yaml

Once this is created, enter this environment with the command

conda activate rde2

Then, install ReactionDataExtractor by typing

pip install -e .

This installs the full version of ReactionDataExtractor framework. Finally, download the model weights from Google Drive and extract the archive into reactiondataextractor/models.

If you run into problems with underlying Tesseract engine, clone the following repository:

git clone https://github.com/tesseract-ocr/tessdata

and replace the TESSDATA_PATH value inside reactiondataextractor/configs/config.py to point to this tessdata directory.

Getting Started

This page gives a introduction on how to quickly get started with ReactionDataExtractor This assumes you already have ReactionDataExtractor and all dependencies installed.

Extract from Images

You can run ReactionDataExtractor using our command line interface by typing:

>>> python reactiondataextractor/extract.py --path <path> --output_dir <dir>

where path is a pth to a single image or a directory of images and dir is a directory where output files will be stored. If a path to a single image file is given, then the output directory is not necessary. In this case, the information will be returned instead.

The output files contain the reaction graph with all detected and recognised objects in the form. Each file has a list of nodes specifying information about each reaction entity, as well as an adjacency dictionary with node connectivity information.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.