https://github.com/katherinemossdeveloper/midnight-train

A browser app presenting data from the Georgia Project.
https://github.com/katherinemossdeveloper/midnight-train

antibiotic cephalexin classification-activation-mapping crystallization entropy force-directed-graphs histogram image-gallery kmeans-clustering mettler-toledo nextjs opencrystaldata pca phenylglycine reactjs tailwind-css vector-database vercel weaviatedb

Last synced: about 1 month ago
JSON representation

A browser app presenting data from the Georgia Project.

• Host: GitHub
• URL: https://github.com/katherinemossdeveloper/midnight-train
• Owner: KatherineMossDeveloper
• License: mit
• Created: 2026-03-24T14:17:11.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2026-04-17T14:38:44.000Z (about 2 months ago)
• Last Synced: 2026-04-17T16:37:11.677Z (about 2 months ago)
• Topics: antibiotic, cephalexin, classification-activation-mapping, crystallization, entropy, force-directed-graphs, histogram, image-gallery, kmeans-clustering, mettler-toledo, nextjs, opencrystaldata, pca, phenylglycine, reactjs, tailwind-css, vector-database, vercel, weaviatedb
• Language: TypeScript
• Homepage: https://midnight-train-explorer.vercel.app/
• Size: 8.15 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          


  



[![Vercel](https://img.shields.io/badge/Live%20Demo-Vercel-000000?logo=vercel&logoColor=white)](https://midnight-train-explorer.vercel.app/)

[![React](https://img.shields.io/badge/Built%20with-React-61DAFB?logo=react&logoColor=white)](https://react.dev/)

[![Next.js](https://img.shields.io/badge/Built%20with-Next.js-000000?logo=nextdotjs&logoColor=white)](https://nextjs.org/)

[![Tailwind CSS](https://img.shields.io/badge/Styled%20with-Tailwind%20CSS-38B2AC?logo=tailwindcss&logoColor=white)](https://tailwindcss.com/)

[![D3](https://img.shields.io/badge/Built%20with-D3-F9A03C?logo=d3&logoColor=white)](https://d3js.org/)

[![Weaviate](https://img.shields.io/badge/Powered%20by-Weaviate-orange?logo=github)](https://github.com/weaviate/weaviate)

![Crystallization](https://img.shields.io/badge/domain-Crystallization-white)

[![](https://img.shields.io/badge/Kaggle-Dataset-green?logo=kaggle&logoColor=white)](https://www.kaggle.com/datasets/opencrystaldata/cephalexin-reactive-crystallization)

![Binary Classification](https://img.shields.io/badge/task-Binary_Classification-yellowgreen)

![ResNet](https://img.shields.io/badge/model-ResNet-yellow)

![PyCharm](https://img.shields.io/badge/PyCharm-2023.2.4-lightorange)

![MIT License](https://img.shields.io/badge/License-MIT-green)

## Really quick start. 

See the live demo now by clicking [here.](https://midnight-train-explorer.vercel.app/)  

## Quick start. 

Clone the repository by downloading the code or using this at a prompt: 

```

 git clone https://github.com/KatherineMossDeveloper/Midnight-Train.git

```

Open the project in Pycharm, or your preferred editor, and start the local development server:

```

 npm run dev

```

Open the app in your browser at...

```

 http://localhost:3000 

```

## Slow start.  

This project was inspired by a research paper:  Salami, H., McDonald, M. A., Bommarius, A. S., Rousseau, R. W., & Grover, M. A. (2021). [In Situ Imaging Combined with Deep Learning for Crystallization Process Monitoring: Application to Cephalexin Production](https://doi.org/10.1021/acs.oprd.1c00136). *Organic Process Research & Development*, 25, 1670–1679. 

The scientists who wrote the paper trained ResNet models with ImageNet weights on the OpenCrystalData dataset. The models were trained to do binary classification of images of crystals, designating them as either CEX (a.k.a., “cephalexin antibiotic,” a good thing) or PG (a.k.a. “phenylglycine,” a bad thing).  

The Georgia Project, in this same GitHub site, recreates their work, then it stores details in a database.  

Midnight train, in turn, pulls these details from the database and creates graphs in order to study the dataset.  Here is Midnight Train's detailed documentation.  

[Go to the main doc file](docs/maindoc.md)    

## Contributions.  

If you found an issue or would like to make a suggestion for an improvement to the code or documentation, please click on the issue tab on the project page and leave me a note.  If you like this project, leave a star.  

## Known issues.  

None.  

## Contact info.                                                                     

For more details about this project, feel free to reach out to me at katherinemossdeveloper@gmail.com or my account on [LinkedIn](https://www.linkedin.com/pub/katherine-moss/3/b49/228).  My time zone is EST in the U.S.

[back to top](#content)