An official website of the United States government
Showing 33 Results
Showing 11-20 of 33
Model & Software
To view details of each card, click 
icon
Project:
Cellular-Level Pilot
Description:
Builds a sparse autoencoder that can compress the expression profile of a sample of gene expression data into a low-dimensional vector.
DESCRIPTION:
Builds a sparse autoencoder that can compress the expression profile of a sample of gene expression data into a low-dimensional vector.
IMPACT: Offers an autoencoder to collapse high-dimensional expression profiles into low-dimensional vectors without significant loss of information.
INPUT DATA TYPE: Gene Expression
INPUT DATA FORMAT: Tabular
LEVEL OF DOCUMENTATION: Minimal
AVAILABLE ON GITHUB
Project:
IMPROVE
Description:
This is a community model for drug response prediction curated as part of the IMPROVE project.
DESCRIPTION:
This is a community model for drug response prediction curated as part of the IMPROVE project.
IMPACT: Enables prediction of drug response with drug and cancer features.
INPUT DATA TYPE: Mutation, Copy Number Variation, Drug SMILES
INPUT DATA FORMAT: Tabular
LEVEL OF DOCUMENTATION: Moderate
AVAILABLE ON GITHUB
Project:
IMPROVE
Description:
This is a community model for drug response prediction curated as part of the IMPROVE project.
DESCRIPTION:
This is a community model for drug response prediction curated as part of the IMPROVE project.
IMPACT: Enables prediction of drug response with drug and cancer features.
INPUT DATA TYPE: Gene Expression, Drug Fingerprints
INPUT DATA FORMAT: Tabular
LEVEL OF DOCUMENTATION: Moderate
AVAILABLE ON GITHUB
Project:
MOSSAIC
Description:
Offers a hierarchical self-attention network for information extraction from long (more than 400 words) cancer pathology reports.
DESCRIPTION:
Offers a hierarchical self-attention network for information extraction from long (more than 400 words) cancer pathology reports.
IMPACT: Allows automatic information extraction from free-form pathology report texts. More accurate than MT-CNN.
PRIMARY PUBLICATION: Limitations of Transformers on Clinical Text Classification
INPUT DATA FORMAT: Unspecified
LEVEL OF DOCUMENTATION: Minimal
AVAILABLE ON GITHUB
Project:
IMPROVE
Description:
This is a community model for drug response prediction curated as part of the IMPROVE project.
DESCRIPTION:
This is a community model for drug response prediction curated as part of the IMPROVE project.
IMPACT: Enables prediction of drug response with drug and cancer features.
INPUT DATA TYPE: Gene Expression, DNA Methylation, Mutation, Drug SMILES
INPUT DATA FORMAT: Tabular
LEVEL OF DOCUMENTATION: Moderate
AVAILABLE ON GITHUB
Project:
IMPROVE
Description:
This is a community model for drug response prediction curated as part of the IMPROVE project.
DESCRIPTION:
This is a community model for drug response prediction curated as part of the IMPROVE project.
IMPACT: Enables prediction of drug response with drug and cancer features.
INPUT DATA TYPE: Gene Expression, Drug Molecular Descriptors
INPUT DATA FORMAT: Tabular
LEVEL OF DOCUMENTATION: Moderate
AVAILABLE ON GITHUB
Project:
ATOM
Description:
IMPACT: A trained JTVAE model enables the user to encode chemical SMILES strings into a vector of numbers then decode the vector back to a SMILES string. This is often used in the field of molecular optimization where the user can apply some operators to modify and optimize the molecule within the autoencoder's latent space then decode the vector to a new molecule.
INPUT DATA FORMAT: Unspecified
LEVEL OF DOCUMENTATION: Minimal
AVAILABLE ON GITHUB
Project:
IMPROVE
Description:
This is a commonly used model curated for drug response prediction as part of the IMPROVE project.
DESCRIPTION:
This is a commonly used model curated for drug response prediction as part of the IMPROVE project.
IMPACT: Enables prediction of drug response with drug and cancer features.
INPUT DATA TYPE: Gene Expression, Drug Fingerprints
INPUT DATA FORMAT: Tabular
LEVEL OF DOCUMENTATION: Moderate
AVAILABLE ON GITHUB
Project:
MOSSAIC
Description:
Offers a convolutional neural network for natural language processing and information extraction from free-form texts.
DESCRIPTION:
Offers a convolutional neural network for natural language processing and information extraction from free-form texts.
IMPACT: Allows automatic information extraction from free-form pathology report texts. Faster than HiSAN.
PRIMARY PUBLICATION: Deep Active Learning for Classifying Cancer Pathology Reports
INPUT DATA TYPE: Tokenized Text
INPUT DATA FORMAT: Unspecified
LEVEL OF DOCUMENTATION: Minimal
AVAILABLE ON GITHUB
Project:
MOSSAIC
Description:
Builds a network to automatically extract information from biomedical text.
DESCRIPTION:
Builds a network to automatically extract information from biomedical text.
IMPACT: Allows automatic extraction of cancer-relevant information from free-text pathology reports.
PRIMARY PUBLICATION: Multi-task Deep Neural Networks for Automated Extraction of Primary Site and Laterality Information from Cancer Pathology Reports
INPUT DATA FORMAT: Tabular
LEVEL OF DOCUMENTATION: Minimal
AVAILABLE ON GITHUB