Asset Detail:

TULIP (TUmor cLassIfication Predictor)

TULIP (TUmor cLassIfication Predictor)

ASSET LINK:

https://modac.cancer.gov/assetDetails?dme_data_id=NCI-DME-MS01-17794660

PROGRAM NAME:

NCI-DOE Collaboration

STUDY NAME:

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

ASSET NAME:

TULIP (TUmor cLassIfication Predictor)

ASSET PATH:

/NCI_DOE_Archive/JDACS4C/JDACS4C_Pilot_1/Tumor_type_classifier_models

Asset Attributes

ATTRIBUTE: ASSET NAME	VALUE: TULIP (TUmor cLassIfication Predictor)
ATTRIBUTE: ASSET DESCRIPTION	VALUE: TULIP (the TUmor cLassIfication Predictor) is a 1D convolutional neural network for classifying RNA-Seq data with 60K genes or 19K protein coding genes. TULIP can classify either list into 17 or 32 tumor types. The resource transfer team trained and validated the models in TULIP on over 9,000 TCGA RNA-Seq files from the Genomic Data Commons (GDC) in February 2022. To use TULIP, the user must provide a file of RNA-Seq data expressed as FPKM-UQ (fragments per kilobase of transcript per million mapped reads upper quartile) for one or more samples. TULIP then converts FPKM-UQ values to TPM (transcripts per million), performs log10 normalization, and reformats the data into the correct dimensions before applying the selected model.
ATTRIBUTE: ASSET IDENTIFIER	VALUE: Tumor_type_classifier_models
ATTRIBUTE: ASSET TYPE	VALUE: Model
ATTRIBUTE: MODEL DOMAIN	VALUE: RNA-Seq gene expression profiles
ATTRIBUTE: MODEL FRAMEWORK	VALUE: Keras
ATTRIBUTE: MODEL PLATFORM	VALUE: Other
ATTRIBUTE: PLATFORM VERSION	VALUE: None
ATTRIBUTE: IS MODEL DEPLOYED	VALUE: No
ATTRIBUTE: COLLECTION SIZE	VALUE: 9.6 GB
ATTRIBUTE: GITHUB LINK	VALUE:

Overview

ASSET LINK:	https://modac.cancer.gov/assetDetails?dme_data_id=NCI-DME-MS01-17794660
PROGRAM NAME:	NCI-DOE Collaboration
STUDY NAME:	NCI-DOE Collaboration Cellular Level Pilot: Predictive Modeling for Pre-Clinical Screening
ASSET NAME:	TULIP (TUmor cLassIfication Predictor)
ASSET PATH:	/NCI_DOE_Archive/JDACS4C/JDACS4C_Pilot_1/Tumor_type_classifier_models

Asset Attributes

ATTRIBUTE	VALUE
ASSET NAME	TULIP (TUmor cLassIfication Predictor)
ASSET DESCRIPTION	TULIP (the TUmor cLassIfication Predictor) is a 1D convolutional neural network for classifying RNA-Seq data with 60K genes or 19K protein coding genes. TULIP can classify either list into 17 or 32 tumor types. The resource transfer team trained and validated the models in TULIP on over 9,000 TCGA RNA-Seq files from the Genomic Data Commons (GDC) in February 2022. To use TULIP, the user must provide a file of RNA-Seq data expressed as FPKM-UQ (fragments per kilobase of transcript per million mapped reads upper quartile) for one or more samples. TULIP then converts FPKM-UQ values to TPM (transcripts per million), performs log10 normalization, and reformats the data into the correct dimensions before applying the selected model.
ASSET IDENTIFIER	Tumor_type_classifier_models
ASSET TYPE	Model
MODEL DOMAIN	RNA-Seq gene expression profiles
MODEL FRAMEWORK	Keras
MODEL PLATFORM	Other
PLATFORM VERSION	None
IS MODEL DEPLOYED	No
COLLECTION SIZE	9.6 GB
GITHUB LINK	https://github.com/CBIIT/TULIP

Asset Files

To download files, please login.

Batch Select	FILE/COLLECTION	FILE SIZE	ACTIONS

Edit Metadata