The New York Stem Cell Foundation Research Institute (NYSCF) has built a deep learning framework for automatically detecting clonalized cell colonies and assessing clonality from daily imaging data. Our approach, Monoqlo, features multiple CNN “modules” for both detection and classification, which are integrated and automatically deployed using Python scripts. 

Full details on the design and rationale of the Monoqlo framework are provided in the article linked here. 

NYSCF GitHub Repository  

The NYSCF GitHub repository contains all of the code necessary for executing the Monoqlo framework using an example dataset. 

Monoqlo℠ Imaging Dataset 

Below we provide a demonstrative example of an imaging dataset, which includes an illustration of the Monoqlo framework’s execution logic and performance.

DMR0001 represents the image set for an entire, real-world monoclonalization run which has been fully deidentified, consisting of daily scans for each well of 8 96-well plates.

Note: this dataset is >160 GB in size

Monoqlo Dataset (DMR0001) by NYSCF is licensed under CC BY-NC-SA 4.0


The code and example datasets provided are intended as a demonstration of the Monoqlo framework’s capabilities and general uses only, without any representations or warrantiesDepending on imaging modality and requirements for use, it may be necessary to train new models and/or adapt the source code for execution on your own data.