CellRank's reproducibility repository.

Last update: Oct 08, 2022

Overview

CellRank's reproducibility repository

We believe that reproducibility is key and have made it as simple as possible to reproduce our results. Please either open an issue or contact as at [email protected] should you experience difficulties reproducing any result.

Manuscript, code and data

CellRank is published in Nature Methods and the software package can be found at our main website, cellrank.org. Raw published data is available from the Gene Expression Omnibus (GEO) under accession codes:

Processed data, including spliced and unspliced count abundances, is available on figshare. To ease reproducibility, our data examples can also be accessed through CellRank's dataset interface.

Navigating this repository

We've organized this repository along the categories below. For each item, you can click the link under nbviewer to open the notebook in the browser using nbviewer. There is no 1-1 mapping from figures to notebooks - some notebooks produce panels for several figures, and some figures contain panels from several notebooks. The tables we provide here make the connection between figures and notebooks explicit. At the top of each notebook, we indicate the package versions we use.

Results

Main Figures

Figure	nbviewer	Notebook Path
Fig. 1	link	path
Fig. 2	link	path
Fig. 3	link	path
Fig. 4	link	path
Fig. 5 Palantir	link	path
Fig. 5 STEMNET	link	path
Fig. 5 Velocyto	link	path
Fig. 5 FateID	link	path
Fig. 6	link	path

Extended Data Figures

Figure	nbviewer	Notebook Path
Extended Data Fig. 1	NA (toy data)	NA (toy data)
Extended Data Fig. 2	link	path
Extended Data Fig. 3	link	path
Extended Data Fig. 4	link	path
Extended Data Fig. 5	link	path
Extended Data Fig. 6	link	path
Extended Data Fig. 7	link	path
Extended Data Fig. 8	link	path
Extended Data Fig. 9	link	path
Extended Data Fig. 10	link	path

Supplementary Figures

Figure	nbviewer	Notebook Path
Supplementary Fig. 1	link	path
Supplementary Fig. 2	link	path
Supplementary Fig. 3	link	path
Supplementary Fig. 4	link	path
Supplementary Fig. 5	link	path
Supplementary Fig. 6	link	path
Supplementary Fig. 7	link	path
Supplementary Fig. 8	link	path
Supplementary Fig. 9	link	path
Supplementary Fig. 10	link	path
Supplementary Fig. 11	link	path
Supplementary Fig. 12	link1 link2	path1 path2
Supplementary Fig. 13	link	path
Supplementary Fig. 14	link	path
Supplementary Fig. 15	link	path
Supplementary Fig. 16	link	path
Supplementary Fig. 17	NA (microscopy results)	NA (microscopy results)

Supplementary Tables

Table	nbviewer	Notebook Path
Supplementary Tab. 1	link	path
Supplementary Tab. 2	link	path
Supplementary Tab. 3	link	path

CellRank's reproducibility repository.

Related tags

Overview

CellRank's reproducibility repository

Manuscript, code and data

Navigating this repository

Results

Owner

Theis Lab

Compact Bilinear Pooling for PyTorch

PyTorch code for: Learning to Generate Grounded Visual Captions without Localization Supervision

An educational resource to help anyone learn deep reinforcement learning.

Boost learning for GNNs from the graph structure under challenging heterophily settings. (NeurIPS'20)

NVIDIA container runtime

Easily pull telemetry data and create beautiful visualizations for analysis.

Plaything for Autistic Children (demo for PaddlePaddle/Wechaty/Mixlab project)

AVD Quickstart Containerlab

DeepAL: Deep Active Learning in Python

Official codebase for "B-Pref: Benchmarking Preference-BasedReinforcement Learning" contains scripts to reproduce experiments.

Secure Distributed Training at Scale

Low Complexity Channel estimation with Neural Network Solutions

Python binding for Khiva library.

Improving Generalization Bounds for VC Classes Using the Hypergeometric Tail Inversion

Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"

FocusFace: Multi-task Contrastive Learning for Masked Face Recognition

Understanding Convolutional Neural Networks from Theoretical Perspective via Volterra Convolution

A custom DeepStack model that has been trained detecting ONLY the USPS logo

A robust camera and Lidar fusion based velocity estimator to undistort the pointcloud.

YOLOv4-v3 Training Automation API for Linux