chenkenbio / SpliceBERT

Primary RNA sequence model
BSD 3-Clause "New" or "Revised" License
23 stars 4 forks source link

In silico mutagenesis #2

Closed onionpork closed 2 months ago

onionpork commented 5 months ago

Hi there,

Thank you so much for this awesome paper! I am wondering how do you implement in silico mutagenesis analysis? Is there any materials that I can look into?

Thank you so much!

chenkenbio commented 5 months ago

Hello, thanks for reaching out. I am not sure which part you are referring to. Generally, we computed the difference in predictions for reference sequences (extracted from reference genome) and mutant sequences (with manually-introduced variants) to assess the impact of the variants. We also provided demo scripts of in silico mutagenesis analysis: insilico_mutagenesis_data.py (dataset) and insilico_mutagenesis_in_transcripts.py (main script). This method has been used in many studies and was first introduced in DeepSEA to the best of my knowledge.