Documentation

[JohnTigue]

This is a staging place for stuff to add to the Reconstrue Handbook, for how to use these tools.

• Evaluation of UMAP as an alternative to t-SNE for single-cell data (2018) Becht et alia
• Ten quick tips for effective dimensionality reduction PLOS Comp Biol 2019-06
• A Survey of Dimensionality Reduction Techniques Based on Random Projection

Single-cell articles

• Single-cell RNA sequencing technologies and bioinformatics pipelines Nature review article (2018-08)

Single-cell "books"

• https://broadinstitute.github.io/2019_scWorkshop/
  • Loves that R
• Galaxy: Pre-processing of Single-Cell RNA Data

[JohnTigue]

UMAP

• 2018 PyData Ann Arbor: Leland McInnes | PCA, t-SNE, and UMAP: Modern Approaches to Dimension Reduction
• UMAP speeds graphed

[JohnTigue]

tSNE

• Realtime tSNE Visualizations with TensorFlow.js Pezzotti 2018-06
• The art of using t-SNE for single-cell transcriptomics

[JohnTigue]

Colab as free-tier platform instance

10 Minutes to cuDF and Dask cuDF:

With Dask, anything you can do on a single GPU with cuDF you can scale out and in parallel across multiple GPUs. Fundamentally, an instance of a cudf.DataFrame object is a single partition of a distributed GPU DataFrame, managed by Dask. Distributing DataFrames and computation with Dask lets you analyze datasets far larger than a single GPU’s memory without running into out of memory errors. The RAPIDS team is working with Dask maintainers and developers to fully support the GPU DataFrame in Dask...

With cuDF and Dask, whether you’re using a single NVIDIA T4 GPU or using all eight NVIDIA V100 GPUs in a DGX-1, your RAPIDS workflow will run smoothly — intelligently distributing the workload across the resources available. Interested in giving it a try? You can quickly get started with RAPIDS on Google Colab

In other words, Colab is the free tier () level for code that can scale.

[JohnTigue]

End to end on the GPU (purple block diagram): https://github.com/rapidsai/cudf

[JohnTigue]

Non-commercially licensed:

• BBrowser: "To support academic research, importing Seurat and Scanpy objects to BBrowser is now free for academic users."

[JohnTigue]

Manifold learning mindset

• Manifold Learning and Dimensionality Reduction for Data Visualization... - Stefan Kühn