Asset Detail:

Combination Drug Response Predictor (Combo)

Combination Drug Response Predictor (Combo)

ASSET LINK:

https://modac.cancer.gov/assetDetails?dme_data_id=NCI-DME-MS01-7678072

PROGRAM NAME:

NCI-DOE Collaboration

STUDY NAME:

NCI-DOE Collaboration Cellular Level Pilot: Predictive Modeling for Pre-Clinical Screening

ASSET NAME:

Combination Drug Response Predictor (Combo)

ASSET PATH:

/NCI_DOE_Archive/JDACS4C/JDACS4C_Pilot_1/combination_drug_response_predictor

Asset Attributes

ATTRIBUTE: ASSET NAME	VALUE: Combination Drug Response Predictor (Combo)
ATTRIBUTE: ASSET DESCRIPTION	VALUE: This collection contains the model topology file and the trained model weights for the Pilot 1 combination drug response predictor (also called Combo). Combo is a deep neural network that predicts tumor cell line growth to drug pairs given combination drug screening results on NCI-60 cell lines available at the NCI-ALMANAC database. The model takes cell line molecular features, drug properties and dose information as input and predicts the response in percentage growth. The model consists of two-stage neural network that is jointly trained for feature encoding and response prediction. It uses a shared submodel for each drug in the pair. For more information, refer to the GitHub Repository link.
ATTRIBUTE: ASSET IDENTIFIER	VALUE: combination_drug_response_predictor
ATTRIBUTE: ASSET TYPE	VALUE: Model
ATTRIBUTE: MODEL DOMAIN	VALUE: Molecular and drug feature profiles
ATTRIBUTE: MODEL FRAMEWORK	VALUE: Keras
ATTRIBUTE: MODEL PLATFORM	VALUE: Candle
ATTRIBUTE: PLATFORM VERSION	VALUE: None
ATTRIBUTE: IS MODEL DEPLOYED	VALUE: No
ATTRIBUTE: COLLECTION SIZE	VALUE: 110.4 MB
ATTRIBUTE: CURATION STATUS	VALUE: Unverified
ATTRIBUTE: GITHUB REPOSITORY	VALUE:

Overview

ASSET LINK:	https://modac.cancer.gov/assetDetails?dme_data_id=NCI-DME-MS01-7678072
PROGRAM NAME:	NCI-DOE Collaboration
STUDY NAME:	NCI-DOE Collaboration Cellular Level Pilot: Predictive Modeling for Pre-Clinical Screening
ASSET NAME:	Combination Drug Response Predictor (Combo)
ASSET PATH:	/NCI_DOE_Archive/JDACS4C/JDACS4C_Pilot_1/combination_drug_response_predictor

Asset Attributes

ATTRIBUTE	VALUE
ASSET NAME	Combination Drug Response Predictor (Combo)
ASSET DESCRIPTION	This collection contains the model topology file and the trained model weights for the Pilot 1 combination drug response predictor (also called Combo). Combo is a deep neural network that predicts tumor cell line growth to drug pairs given combination drug screening results on NCI-60 cell lines available at the NCI-ALMANAC database. The model takes cell line molecular features, drug properties and dose information as input and predicts the response in percentage growth. The model consists of two-stage neural network that is jointly trained for feature encoding and response prediction. It uses a shared submodel for each drug in the pair. For more information, refer to the GitHub Repository link.
ASSET IDENTIFIER	combination_drug_response_predictor
ASSET TYPE	Model
MODEL DOMAIN	Molecular and drug feature profiles
MODEL FRAMEWORK	Keras
MODEL PLATFORM	Candle
PLATFORM VERSION	None
IS MODEL DEPLOYED	No
COLLECTION SIZE	110.4 MB
CURATION STATUS	Unverified
GITHUB REPOSITORY	https://github.com/CBIIT/NCI-DOE-Colab-Pilot1-Combo-combination-drug-response-predictor

Asset Files

To download files, please login.

Batch Select	FILE/COLLECTION	FILE SIZE	ACTIONS

Edit Metadata