CRADLE-VAE: Enhancing Single-Cell Gene Perturbation Modeling with Counterfactual Reasoning-based Artifact Disentanglement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910597286723584 |
|---|---|
| author | Baek, Seungheun Park, Soyon Chok, Yan Ting Lee, Junhyun Park, Jueon Gim, Mogan Kang, Jaewoo |
| author_facet | Baek, Seungheun Park, Soyon Chok, Yan Ting Lee, Junhyun Park, Jueon Gim, Mogan Kang, Jaewoo |
| contents | Predicting cellular responses to various perturbations is a critical focus in drug discovery and personalized therapeutics, with deep learning models playing a significant role in this endeavor. Single-cell datasets contain technical artifacts that may hinder the predictability of such models, which poses quality control issues highly regarded in this area. To address this, we propose CRADLE-VAE, a causal generative framework tailored for single-cell gene perturbation modeling, enhanced with counterfactual reasoning-based artifact disentanglement. Throughout training, CRADLE-VAE models the underlying latent distribution of technical artifacts and perturbation effects present in single-cell datasets. It employs counterfactual reasoning to effectively disentangle such artifacts by modulating the latent basal spaces and learns robust features for generating cellular response data with improved quality. Experimental results demonstrate that this approach improves not only treatment effect estimation performance but also generative quality as well. The CRADLE-VAE codebase is publicly available at https://github.com/dmis-lab/CRADLE-VAE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05484 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CRADLE-VAE: Enhancing Single-Cell Gene Perturbation Modeling with Counterfactual Reasoning-based Artifact Disentanglement Baek, Seungheun Park, Soyon Chok, Yan Ting Lee, Junhyun Park, Jueon Gim, Mogan Kang, Jaewoo Machine Learning Artificial Intelligence Genomics Quantitative Methods Predicting cellular responses to various perturbations is a critical focus in drug discovery and personalized therapeutics, with deep learning models playing a significant role in this endeavor. Single-cell datasets contain technical artifacts that may hinder the predictability of such models, which poses quality control issues highly regarded in this area. To address this, we propose CRADLE-VAE, a causal generative framework tailored for single-cell gene perturbation modeling, enhanced with counterfactual reasoning-based artifact disentanglement. Throughout training, CRADLE-VAE models the underlying latent distribution of technical artifacts and perturbation effects present in single-cell datasets. It employs counterfactual reasoning to effectively disentangle such artifacts by modulating the latent basal spaces and learns robust features for generating cellular response data with improved quality. Experimental results demonstrate that this approach improves not only treatment effect estimation performance but also generative quality as well. The CRADLE-VAE codebase is publicly available at https://github.com/dmis-lab/CRADLE-VAE. |
| title | CRADLE-VAE: Enhancing Single-Cell Gene Perturbation Modeling with Counterfactual Reasoning-based Artifact Disentanglement |
| topic | Machine Learning Artificial Intelligence Genomics Quantitative Methods |
| url | https://arxiv.org/abs/2409.05484 |