HarveyYan
commented
5 years ago The only reason is not computational but rather a compromise given splicing efficiency of a gene is not known at the time of doing this project. Otherwise I would have taken alternative splicing into account, which would obviously improve the biological validity of this model.
On Aug 29, 2019, at 5:12 AM, Fiona notifications@github.com<mailto:notifications@github.com> wrote:
Hey I just stumbled upon your tool and paper. I read the README and saw you mentioned that: "It operates on the cDNA of the longest isoformic protein-coding transcript of a gene" Why is that? What is the computational reason for this necessity? Im asking because im interested in predicting possible altered sub-cellular localization of different transcript isoforms (only protein coding obviously) that belong to one gene.
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHubhttps://github.com/HarveyYan/RNATracker/issues/1?email_source=notifications&email_token=ABYS7WO6SXEYVRVG42KRHRDQG6HHLA5CNFSM4IR7ZUV2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4HIEQVGQ, or mute the threadhttps://github.com/notifications/unsubscribe-auth/ABYS7WO7IWK2AQNV2HYLMFDQG6HHLANCNFSM4IR7ZUVQ.
Hey I just stumbled upon your tool and paper. I read the README and saw you mentioned that: "It operates on the cDNA of the longest isoformic protein-coding transcript of a gene" Why is that? What is the computational reason for this necessity? Im asking because im interested in predicting possible altered sub-cellular localization of different transcript isoforms (only protein coding obviously) that belong to one gene.