Low efficiency of large volume protein sequence prediction

[Admire7494]

Can this model be used to generate features for a large number (more than 10,000) of protein sequences, and is there an improvement after trying the low efficiency of the model prediction?

[yangkky]

It should work for any number of sequences. The easiest way to make it faster is probably by multiprocessing? Gensim is already pretty fast, so I'm not sure I'd be able to make it much more efficient.

[Admire7494]

Thanks for your reply, it helps a lot! 发自我的iPhone

…

------------------ Original ------------------ From: Kevin Kaichuang Yang ***@***.***> Date: Fri,Jul 7,2023 4:30 AM To: fhalab/embeddings_reproduction ***@***.***> Cc: Admire7494 ***@***.***>, Author ***@***.***> Subject: Re: [fhalab/embeddings_reproduction] Low efficiency of large volumeprotein sequence prediction (Issue #13) It should work for any number of sequences. The easiest way to make it faster is probably by multiprocessing? Gensim is already pretty fast, so I'm not sure I'd be able to make it much more efficient. — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>