search

bm2-lab / PanPep

GNU General Public License v3.0
44 stars 9 forks source link

There maybe a bug #4

Closed JiaweiZhang1997 closed 1 year ago

JiaweiZhang1997 commented 1 year ago

In zero-shot setting, If my input csv's "Peptide" column not sorted and have same peptide in nonadjacent rows，the result will be wrong. I think it may cause by below code: '''for i,j in enumerate(peptides): if j not in Z_data: Z_data[j] = [] Z_data[j].append(TCRs[i])''' '''output = pd.DataFrame({'Peptide':peptides,'CDR3':TCRs,'Score':starts})'''

The order of output document of "Peptide" and "CDR3" is different with the order of model input of "Peptide" and "CDR3".

If I am wrong, please point it out and I am very sorry about it.

GaoYiChengTJ commented 1 year ago

Hi: Thanks for your interest in our work. We appreciated that you raised this bug in our code. You are right! We have highlighted the importance of sorting peptides in the input *csv in README.

JiaweiZhang1997 commented 1 year ago

^-^