RSG Schedule

• Mapping cell structure across scales by fusing protein images and interactions - Yue Qin
• A Network-based comparative framework to study conservation and divergence of proteomes in plant phylogenies - Junha Shin
• Mapping gene regulatory networks in the Drosophila brain using single-cell transcriptomics and epigenomics - Sara Aibar
• Identifying diverse modes of TF-DNA interactions in ChIP-exo data - Anushua Biswas

• Integrated multi-omics approach to identifying regulatory mechanisms in cancer metastatic processes - Saba Ghaffari
• Varmole: A biologically drop-connect deep neural network model for prioritizing disease risk variants and genes - Nam Nguyen
• Inferring cellular trajectories from scRNA-seq in pseudospace - Aly Khan
• Inferring the pan-cancer interactions and prognostic significance of driver mutations and the tumor immune microenvironment - Masroor Bayati

• SPICEMIX: Integrative single-cell spatial modeling for inferring cell identity - Benjamin Chidester
• Chromatin accessibility and transcription factor activity estimation on single cells - Ivan G. Costa
• Mapping vector field of single cells - Yan Zhang
• Developmental trajectory of pre-hematopoietic stem cell formation from endothelium - Qin Zhu

• Ledidi: Designing genome edits that induce functional activity - Jacob Schreiber
• Genome-wide identification and analysis of RNA structural disruptions induced by single nucleotide variants - Zhengqing Ouyang
• Neural Networks Can Extract Thermodynamic DNA Sequence Affinities from Genomic Occupancy Profiles of Transcription Factor Binding - Amr Alexandari
• Assessing the enrichment of somatic mutations in TF binding sites - Harshit Sahay

DREAM Schedule

• Crowdsourcing assessment of maternal blood multi-omics for predicting gestational age and preterm birth - Adi Tarca 
• Dealing with high dimensional data to predict preterm birth - Balint A. Pataki and Istvan Csabai (Team ELTEcomplex) 
• Omics-based prediction of preterm birth by Gaussian Process Regression models - Yuanfang Guan (Team gyuanfan)
• SVM-based approach to predict preterm birth using omics data - Rintu Kutum (Team rABiT)

• Metadata Automation DREAM Challenge - Denise Warzel
• Biomedical Analysis of Composite Ontological Networks - Lauren Cirillo (Team ENGR Dynamics)
• An Iterative Strategy Optimizing CDE Recommendations from Real-World Data - Attila L. Egyedi (Team CEDAR Team)
• Metadata Automation: A TF-IDF and Nearest Neighbors Approach - Emily Hartley (Team )

• CTD2 Pancancer Drug Activity DREAM Challenge - Robert Allaway & Eugene Douglass
• Predicting drug targets by integration of drug sensitivity data and drug gene signature data - the NETPHAR strategy - Wenyu Wang (Team netphar)
• A multitask neural network approach for predicting drug targets from chemogenomics data - Fangping Wang (Team Atom)

• Introduction to the RA2 DREAM Challenge: Automated Scoring of Radiographic Joint Damage - Lou Bridges
• Scoring and benchmarking for the RA2 DREAM Challenge - Jake Chen
• Prediction of Rheumatoid Arthritis Scores Ariel's Method (PRASAM) - Ariel Israel
• A multistage deep learning method for scoring radiographic hand and foot joint damage in rheumatoid arthritis - Isaac Dimitrovsky
• Li and Guan RA2 DREAM Challenge Solution - Hongyang Li
• Team Csabaibio RA2 DREAM Challenge Solution - Alex Olar

• CTD2 Beat AML DREAM Challenge: Strategies for Prediction of Drug Efficacy and Patient Outcomes - Jeff Tyner
• Prediction of drug sensitivity using a multi-response model - Rasmus Froberg Brøndum
• Beat AML SC2: Predicting clinical response using feature selection for survival analysis - Yasin Memari

• Parkinson's disease symptom assessment in free-living conditions; the BEAT-PD Challenge - Solveig Sieberts
• Personalized prediction of on-off medication state from wearable-derived time-series features - Yidi Huang
• Assessment of Parkinson's disease dyskinesia in a free-living environment - Alex Page
• Tremor severity in Parkinson’s disease can be monitored in a free-living environment - Yuanfang Guan

• The First EHR DREAM Challenge: overcoming data access barriers in biomedical competitions - Thomas Schaffter and Tim Bergquist
• A LightGBM Model to Predict 180 Days Mortality Using EHR Data - Jifan Gao  (Team UW-biostat)