You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -4,9 +4,9 @@ A multi-mapped read rescue strategy for gene regulatory analyses.
4
4
5
5
**Genome Research paper now online:**[https://genome.cshlp.org/content/early/2024/07/10/gr.278638.123.abstract](https://genome.cshlp.org/content/early/2024/07/10/gr.278638.123.abstract)
6
6
7
-
[Or check out our pre-print to learn more!](https://www.biorxiv.org/content/10.1101/2023.09.12.556916v1)
8
7
9
8
### Releases
9
+
As of **v1.2.0**, the CNNs were retrained using Tensorflow 2.17 to allow for compatibility with pip installations.
10
10
11
11
As of **v1.1.0**, Allo has neural networks trained for DNase-seq and ATAC-seq under the MACS2 parameters "--nomodel --shift -100 --extsize 200" for ATAC-seq and MACS2 default parameters for DNase-seq. Additionally, Allo now has the option to remove introns as identified by splice junction information in the CIGAR string of an aligned read. This affects the window used to sum uniquely mapped reads. Information below regarding the use of Allo for RNA-seq data processing.
0 commit comments