RESUMO
Functional genomics networks are widely used to identify unexpected pathway relationships in large genomic datasets. However, it is challenging to compare the signal-to-noise ratios of different networks and to identify the optimal network with which to interpret a particular genetic dataset. We present GeNets, a platform in which users can train a machine-learning model (Quack) to carry out these comparisons and execute, store, and share analyses of genetic and RNA-sequencing datasets.
Assuntos
Genômica/métodos , Internet , Aprendizado de Máquina , DNA/genética , Bases de Dados de Ácidos Nucleicos , Técnicas de Amplificação de Ácido Nucleico , RNA/genética , SoftwareRESUMO
Single-cell omics research has the power to leave a deep impact on modern healthcare. Sharing data widely and freely advances this progress in both the academic and clinical spheres. We developed the Single Cell Portal (SCP) to maximize the impact of this work. SCP enables data sharing, supports dynamic results visualization, and facilitates scientific exploration across a large repository of single-cell datasets. SCP's data contributors maintain full control over how their data are shared and presented, without requiring web development expertise. Finally, SCP supports the entire lifecycle of a research project, from sparking an idea, to fine-tuning the data with collaborators, to sharing results in an accessible and interactive way. This paper highlights the most valuable ways in which SCP helps to advance single-cell research.