Timezone: »

 
A sandbox for prediction and integration of DNA, RNA, and proteins in single cells
Malte Luecken · Daniel Burkhardt · Robrecht Cannoodt · Christopher Lance · Aditi Agrawal · Hananeh Aliee · Ann Chen · Louise Deconinck · Angela Detweiler · Alejandro Granados · Shelly Huynh · Laura Isacco · Yang Kim · Dominik Klein · BONY DE KUMAR · Sunil Kuppasani · Heiko Lickert · Aaron McGeever · Honey Mekonen · Joaquin Melgarejo · Maurizio Morri · Michaela Müller · Norma Neff · Sheryl Paul · Bastian Rieck · Kaylie Schneider · Scott Steelman · Michael Sterr · Daniel Treacy · Alexander Tong · Alexandra-Chloe Villani · Guilin Wang · Jia Yan · Ce Zhang · Angela Pisco · Smita Krishnaswamy · Fabian Theis · Jonathan M Bloom

The last decade has witnessed a technological arms race to encode the molecular states of cells into DNA libraries, turning DNA sequencers into scalable single-cell microscopes. Single-cell measurement of chromatin accessibility (DNA), gene expression (RNA), and proteins has revealed rich cellular diversity across tissues, organisms, and disease states. However, single-cell data poses a unique set of challenges. A dataset may comprise millions of cells with tens of thousands of sparse features. Identifying biologically relevant signals from the background sources of technical noise requires innovation in predictive and representational learning. Furthermore, unlike in machine vision or natural language processing, biological ground truth is limited. Here we leverage recent advances in multi-modal single-cell technologies which, by simultaneously measuring two layers of cellular processing in each cell, provide ground truth analogous to language translation. We define three key tasks to predict one modality from another and learn integrated representations of cellular state. We also generate a novel dataset of the human bone marrow specifically designed for benchmarking studies. The dataset and tasks are accessible through an open-source framework that facilitates centralized evaluation of community-submitted methods.

Author Information

Malte Luecken (Helmholtz Center Munich)

* Computational biologist * Multimodal single-cell data integration challenge organizer * Single-cell data integration * Benchmarking

Daniel Burkhardt (Cellarity)
Robrecht Cannoodt (Data Intuitive)
Christopher Lance (Helmholtz Center Munich)
Aditi Agrawal (Chan Zuckerberg Biohub)
Hananeh Aliee (Computational Biology)

I am a postdoctoral researcher in computational biology working in the ngroup of Prof. Fabian Theis. I did my phd in Computer Science.

Ann Chen (Chan Zuckerberg Biohub)
Louise Deconinck (Ghent University)
Angela Detweiler
Alejandro Granados
Shelly Huynh (University of California, Santa Cruz)
Laura Isacco (Cellarity)
Yang Kim
Dominik Klein (Helmholtz Munich)
BONY DE KUMAR (Yale University)
Sunil Kuppasani (Rutgers University)
Heiko Lickert
Aaron McGeever
Honey Mekonen
Joaquin Melgarejo
Maurizio Morri
Michaela Müller
Norma Neff
Sheryl Paul
Bastian Rieck (Institute of AI for Health, Helmholtz Centre Munich)
Kaylie Schneider (Friedman School of Nutrition Science and Policy, Tufts University)
Scott Steelman
Michael Sterr (None)
Daniel Treacy (Cellarity)
Alexander Tong (Yale University; MILA; UdeM)
Alexandra-Chloe Villani
Guilin Wang (Yale University)
Jia Yan
Ce Zhang (Yale University)
Angela Pisco
Smita Krishnaswamy (Yale University)
Fabian Theis (Helmholtz Munich)
Jonathan M Bloom (Cellarity)

More from the Same Authors