Published October 23, 2025 | Version v2
Dataset Open

DrugReflector model checkpoints

Authors/Creators

Contributors

Contact person:

Description

DrugReflector is an ensemble of three multi-layer perceptron classifiers trained on Connectivity Map transcriptional signatures to predict compound classes from transcriptional signatures. The training set was partitioned into three non-overlapping splits, and each model was trained on two of the three splits using individual perturbation signatures as inputs (without replicate averaging).

This DOI contains the resulting three torch model checkpoints, one for each split-trained model. 

Files

Files (274.1 MB)

Name Size Download all
md5:0a27e253713c37f4874318b5ba0c27a9
91.4 MB Download
md5:0e785196fd046d946f84e4480c81ff53
91.4 MB Download
md5:d8e36f6a8f9fa7a22feda7acdd0bee86
91.4 MB Download

Additional details

Related works

Is supplement to
Software: 10.5281/zenodo.16921928 (DOI)

Software

Repository URL
https://github.com/Cellarity/drugreflector/
Programming language
Python
Development Status
Active

References

  • Benjamin DeMeo et al., Active learning framework leveraging transcriptomics identifies modulators of disease phenotypes.Science0,eadi8577DOI:10.1126/science.adi8577