Skip to content

kozodoi/BMS_Molecular_Translation

main
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Code

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 
 
 

BMS Molecular Translation

Top-5% solution to the BMS Molecular Translation Kaggle competition on chemical image-to-text translation.

sample

Summary

Organic chemists frequently draw molecular work using structural graph notations. As a result, decades of scanned publications and medical documents contain drawings not annotated with chemical formulas. Time-consuming manual work of experts is required to reliably convert such images into machine-readable formulas. Automated recognition of optical chemical structures with deep learning helps to speed up research and development in the field.

The goal of this project is to develop a deep learning framework for chemical image captioning. In other words, the project aims at translating unlabeled chemical images into the text formulas. To do that, I work with a large dataset of more than 4 million chemical images provided by Bristol-Myers Squibb.

My solution is an ensemble of seven CNN-LSTM Encoder-Decoder models implemented in PyTorch. The table below summarizes the architectures and main training parameters. The solution reaches the test score of 1.31 Levenstein Distance and places in the top-5% of the competition leaderboard. The detailed summary is provided in this writeup.

models

Repo structure

The project has the following structure:

  • codes/: .py main codes with data, model, training and inference modules
  • notebooks/: .ipynb Colab-friendly notebooks for data augmentation and model training
  • input/: input data (not included due to size constraints, can be downloaded here)
  • output/: model weights, configurations and figures exported from the notebooks

Working with the repo

Environment

To work with the repo, I recommend to create a virtual Conda environment from the environment.yml file:

conda env create --name bms --file environment.yml
conda activate bms

Reproducing solution

The solution can then be reproduced in the following steps:

  1. Download competition data and place it in the input/ folder.
  2. Run 01_preprocessing_v1.ipynb to preprocess the data and define a chemical tokenizer.
  3. Run 02_gen_extra_data.ipynb and 03_preprocessing_v2.ipynb to construct additional synthetic images.
  4. Run training notebooks 04_model_v6.ipynb - 10_model_v33.ipynb to obtain weights of base models.
  5. Perform normalization of model predictions using 11_normalization.ipynb.
  6. Run the ensembling notebook 12_ensembling.ipynb to obtain the final predictions.

All training notebooks have the same structure and differ in model/data parameters. Different versions are included to ensure reproducibility. To understand the training process, it is sufficient to go through the codes/ and inspect one of the modeling notebooks. The ensembling code is also provided in this Kaggle notebook.

More details are provided in the documentation within the codes & notebooks.

About

Image-to-text translation of chemical molecule structures with deep learning (top-5% Kaggle solution)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published