jinyuan sun
jinyuan sun
@Timtaran You may use HTML style like this: ```python put_image(img).style('display: block;margin-left: auto;margin-right: auto;width: 40%;') ```
@juliaLopanskaia Wow, great job! Thanks a lot!
1. You need a dataset, where known TFs and targets are paired. 2. Finetune this model.
A fine-tuning example in pull request #17
@philippbayer Nice job! I also found there are no special token in this tokenizer, but the paper says they used EOS tokens to split individual DNA sequences.
@philippbayer I tried to use bf16, seems to work. Another way might be freezing some layers. I am using Human cds sequences to finetune the last layer. Not sure will...
 Oh, I found this. Still curious about which model was used. I checked some cases, those structures seem not precisely the same as in the Alphafold DB, especially some...
Also, a following up discussion, if the sequences were removed greedily, should we be concerned about enriching too many 'orphan' sequences? I see you kept sequences with more than 50...
The same error.
@brianhie Is there any thing we can do to help get this API back online?