insitro/cp-posh

Model Repository for "A Pooled Cell Painting CRISPR Screening Platform Enables de novo Inference of Gene Function by Self-supervised Deep Learning"

Installation

To use these models, you need to install the CP-POSH package from the official repository: https://github.com/insitro/cp-posh

Available Models

• cp-dino-300: Cell-Painting DINO model trained on MoA - 300 dataset
• cp-dino-1640: Cell-Painting DINO model trained on Druggable Genome - 1640 dataset

Loading the Model

from cp_posh.ssl.inference import get_model_cp_dino

# Load the CP-DINO 300 model
cpdino_300 = get_model_cp_dino(model_name="cp-dino-300")

# Load the CP-DINO 1640 model
cpdino_1640 = get_model_cp_dino(model_name="cp-dino-1640")

Repository

For more information, code examples, and updates, visit the official repository: https://github.com/insitro/cp-posh

Citation

If you use these models in your research, please cite:

@article{sivanandan2023pooled,
  title={A pooled cell painting CRISPR screening platform enables de novo inference of gene function by self-supervised deep learning},
  author={Sivanandan, Srinivasan and Leitmann, Bobby and Lubeck, Eric and Sultan, Mohammad Muneeb and Stanitsas, Panagiotis and Ranu, Navpreet and Ewer, Alexis and Mancuso, Jordan E and Phillips, Zachary F and Kim, Albert and others},
  journal={bioRxiv},
  pages={2023--08},
  year={2023},
  publisher={Cold Spring Harbor Laboratory}
}

Copyright (C) 2025 Insitro, Inc. This software and any derivative works are licensed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License (CC-BY-NC-SA 4.0), accessible at https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode