Published September 8, 2023 | Version v1
Dataset Open

Models and Data associated with: Single-cell gene expression prediction from DNA sequence at large contexts

Authors/Creators

  • 1. GSK, plc

Description

This archive holds trained models and associated data for the manuscript:
"Single-cell gene expression prediction from DNA sequence at large contexts"

Structure:

  • configs - example configs for the workflows to produce publication data 
  • data_* - pre-processed single cell data used for publication
  • models_* - model checkpoints, hyperparameters and training progress in tensorboard logs
  • preprocessing - additional data required to reproduce the pre-processing workflow

 

"Copyright 2023 GlaxoSmithKline Research & Development Limited. All rights reserved."

Files

Files (34.5 GB)

Name Size Download all
md5:fb865c7abec37533c95a673e839dfa35
3.2 kB Download
md5:694a6dcf3dfc8caabeca659708f56a14
6.8 GB Download
md5:68cd7a834165fb593b4d445f1a9cfadb
228.4 MB Download
md5:fdf34852abf91a6524c36c30261d4d79
2.4 GB Download
md5:5e3d507dd4c85bfb09904b4a14d85c02
10.2 GB Download
md5:62ac723590aa98b6d1994bb1d2940cc8
7.3 GB Download
md5:37182f6fe01d1228624e8b878ff01524
5.7 GB Download
md5:24044dfe63015a6eb0fe6326401e066f
1.5 GB Download
md5:e509cf4d2ad33306b0e3f91ef91b504e
402.4 MB Download

Additional details

Related works

Is supplement to
Preprint: 10.1101/2023.07.26.550634 (DOI)