https://github.com/gyjames/CIRI-deep/tree/main

Predict differentially spliced circRNAs.

CIRI-deep is a deep-learning model used to predict differentially spliced circRNAs between two biological samples using totalRNA sequencing data. An adapted version of CIRI-deep, CIRI-deepA, was trained for poly(A) selected RNA-seq data.
CIRIdeep provides probability of given circRNAs being differentially spliced between any of two samples. When predict with CIRIdeep, expression value of 1499 RBPs and splicing amount (derived from SAM alignment files) in both samples are needed.
-Predict list: CircRNAs are given as coodination on hg19 genome, like chr10:102683732|102685776. CircRNAs not in training data of CIRI-deep will not be included in output.
-RBP A: RBP expression values of sample A. There are two columns in RBP expression value file, the first column identifies gene symbols and the second column gives expression value of the RBP in TPM. The order of genes should keep exactly the same with the example file.
-RBP B: RBP expression value (TPM) of sample B.
-Splicing amount A: Splicing amount of sample A. Splicing amount value can be generated by script_splicingamount.py in https://github.com/gyjames/CIRI-deep.
-Splicing amount B: Splicing amount of sample A.