Basic usage: This landing page is organized to consolidate and help community scientists and bioinformatics researchers to find the component JDACS4C repositories, clone or copy the related pilots code, validate interested models with provided sample testing dataset(s).  . 

The table below lists the individual NCI Git repositories with URL links:

Git Repository	Overview
JDACS4C Pilot 1: Pre-clinical Screening	The NCI-DOE JDACS4C Pilot 1 repositories of all software products, associated training/testing data and all relevant documentation.
Tumor Classifier (TC1)	TC1 shows how to train and use a neural network model to classify tumor types from molecular features (e.g., RNASeq expressions) provided in Genomics Data Commons (GDC).
Autoencoder Node Saliency (ANS)	ANS measures the distribution of the latent representations generated by an autoencoder, ranks and identifies specialty nodes that are able to seperate two given classes. ANS explains the unsupervised learning process in autoencoders.
Single Drug Response	Using the Random Forest machine learning algorithm to predict the concentration, cell line- and drug-dependent response function.
Synergy Drug Response	Predicting drug-pair synergy from the predicted synergy probabilities of individual drugs.
JDACS4C Pilot 2: RAS Structure and Dynamics in Cellular Membranes	The NCI-DOE JDACS4C Pilot 2 repositories of all software products, associated training/testing data and all relevant documentation.
MemSurfer	MemSurfer is a tool to compute and analyze membrane surfaces found in a wide variety of large-scale molecular simulations. MemSurfer works independent of the type of simulation, directly on the 3D point coordinates.
JDACS4C Pilot 3: Population Information Integration, Analysis and Modeling	The NCI-DOE JDACS4C Pilot 3 repositories of all software products, associated training/testing data and all relevant documentation.
Multi Task-Convolutional Neural Networks (MT-CNN)	MT-CNN is a CNN for Natural Language Processing and Information Extraction from free-form texts. BSEC group designed the model for information extraction from cancer pathology reports.
Pathology Reports HAN	Hierarchical attention networks for information extraction from cancer pathology reports.
Active Learning framework for NLP	Active Learning framework for Natural Language Processing of pathology reports.
Miscellaneous and related	CANDLE and related publications.
DOE CANDLE Exascale Computing Program Benchmarks	The CANDLE benchmark codes implement deep learning architectures that are relevant to problems in cancer. These architectures address problems at different biological scales, specifically problems at the molecular, cellular and population scales.
Referenced Publications	All JDACS4C pilots and CANDLE publications list with publication title, author(s), date and detailed source (journal title, issue, page ranges) exposed.