NeST-VNN is an interpretable neural network-based model that predicts cell response to a drug. the first explainable data-driven method for cancer therapeutic response prediction, in which cell structure is modeled using a hierarchical map of tumor cell systems.

2024年3月5日 · NeST-VNN is based on NeST, a whole-cell map of cancer protein complexes derived from systematic proteomics data (see the ‘Structural architecture of the NeST-VNN model’ section in Methods).

NeST-VNN is an interpretable neural network-based model that predicts cell response to a drug. This framework integrates information across multiple levels of cancer cell biology to understand drug response, and can serve to identify and explain biomarkers for clinical application.

NeST VNN 1. Park, S., Silva, E., Singhal, A. et al. A deep learning model of tumor cell architecture elucidates response and resistance to CDK4/6 inhibitors. Nat Cancer (2024). https://doi.org/10.1038/s43018-024-00740-1. Cell feature files

NeST-VNN is an interpretable neural network-based model that predicts cell response to a drug. The first explainable data-driven method for cancer therapeutic response prediction, in which cell structure is modeled using a hierarchical map of tumor cell systems, called NeST (https://idekerlab.ucsd.edu/nest/). This framework integrates ...

为了更清晰的将机器学习模型的结构与细胞的功能联系起来，文章开发了DrugCell方法，基于可视神经网络（visible neural network，VNN）将神经网络里的神经元与细胞的基因组学数据相关联并模拟生物通路的层级结构，从而准确的预测基因突变和药物对细胞活性的影响。

We constructed NeST-VNN drug response models for palbociclib and separately for each of the 50 benchmark drugs, using standard neural network learning procedures based on backpropagation...

The Cell Maps VNN Tool enables the creation, training, and usage of an interpretable neural network-based models that predict cell response to a drug. A hierarchy in HCX format (for instance, generated by cellmaps_generate_hierarchy tool) is used to define the structure of the visible neural network.

NeST-VNN repo. Contribute to idekerlab/nest_vnn development by creating an account on GitHub.

To elucidate the underlying mechanisms, we constructed an interpretable deep learning model of the response to palbociclib, a CDK4/6i, based on a reference map of multiprotein assemblies in cancer.