Software and supporting data for the article "SpliSync: Genomic language model-driven splice site correction of long RNA sequencing reads"

This repository contains archived versions of the software, model weights, and supporting data for the article "SpliSync: Genomic language model-driven splice site correction of long RNA sequencing reads"

Content:

• Software (archived version): SpliSync-main.tar.gz (v.1.0)
• Model weights: ‘cdna’ image cdna_r9.ckpt.gz (default) [764 MB], ‘drna’ image drnahumanWTC11.ckpt.gz (not used) [2.1 GB], ‘r10_cdna’ image cdna_r10.ckpt.gz (not used) [2.2 GB]
• Simulated human ONT R9 cDNA data: simulation.tar.gz [2.6 GB]
• Analysis data – corrected alignments: correctors.tar.gz [7.0 GB]
• Analysis data – alternative splicing: alternative_splicing.tar.gz [273 MB]
• Analysis data – transcript assembly: assembly.tar.gz [1.7 GB]

Model weights files were too large to be included with the software and are provided separately. To run the software, copy the ckpt file into the ./model_weights subfolder in the SpliSync package.