search

kgori / sigfit

Flexible Bayesian inference of mutational signatures
GNU General Public License v3.0
33 stars 8 forks source link

Implement optional multi-chain extraction #23

Closed baezortega closed 5 years ago

baezortega commented 7 years ago

Complete the implementation of multi-chain extraction by:

Adding a variable 'chains' set by default to 1 and passed on to rstan::sampling Adding a parameter 'init' (list, default =NULL ) in extract_signatures(), such that, if provided, the number of chains will be equal to the length of 'init'.

baezortega commented 5 years ago

@kgori I think you implemented something along these lines in the paper branch?

kgori commented 5 years ago

Yes, I added the same thing. (From memory, so could be wrong) we don't need to add anything for 'init', it's already a keyword argument in rstan::sampling, so it will pass through "...".

On Wed, 19 Jun 2019, 18:35 Adrian Baez-Ortega, notifications@github.com wrote:

@kgori https://github.com/kgori I think you implemented something along these lines in the paper branch?

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/kgori/sigfit/issues/23?email_source=notifications&email_token=AAMQZ77UG677YGWBDC7NY2TP3JU63A5CNFSM4EAUGWVKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGODYCTMIQ#issuecomment-503658018, or mute the thread https://github.com/notifications/unsubscribe-auth/AAMQZ75KZ7RCESMYIIEO733P3JU63ANCNFSM4EAUGWVA .

baezortega commented 5 years ago

Then I guess I'll close this (we still need a vignette).