charrick / sdn2go Goto Github PK

version python please + requirment

get_ProteinSeq.py

line 39 print len(fasta) --- > print(len(fasta))

Sir, we have successfully run the validation.py file which trains the model but we are unable to understand how can we get the predictions for our sequences and how should we give them as an input to the model.

您好，针对您发布的代码，我有一些疑问，需要您帮忙解答一下。

1，针对人相关蛋白的功能预测中，Validation.py 代码中line19的seqSet.csv和line90的selected_9606_protein_scores.csv不在data文件夹下面。

Validation.py中
line19: Seqfile_name = 'data/seqSet.csv'
line90: ppi_file = 'PPI_data/selected_9606_protein_scores.csv'

2，针对酵母相关蛋白的功能预测中，yeast_validation.py 代码中line90的selected_4932_protein_scores.csv不在data文件夹下面。

yeast_validation.py中
line90: ppi_file = 'PPI_data/selected_4932_protein_scores.csv'

3，针对人相关蛋白的功能预测中，Validation.py 中调用的line55的protVec_dict.npy和line56的prot_kmerWord_dict.npy，这两个文件生成的原始代码和上面两个问题中缺少的文件能我发我一份吗？我想学习一下。
   
 我的邮箱：[email protected]，谢谢您！