Zhanglab forum

Hi, hello! I sincerely want to ask, in the ResPRE training process, how to deal with the problem of extremely imbalanced positive and negative samples? In all training sets, only a few residue pairs are in contact. Most of the residues are not touched. In this case, the training model will easily ...

Thank you very much! I figured out the problem.

Dear Zhang Yang Lab: Hello, I encountered some problems in the process of ResPRE building the contact matrix. :D :D 1. Download the protein structure file in the PDB. The PDBID of this protein is 1F88. Its sequence length is 348, as shown in Figure 1. But only 338 residues have structural ...

Sincerely thank you for your detailed answer. Thank you very much! :D :D :D In addition, I have another question. Q：Does the process of training ResPRE use supervised learning or unsupervised learning? If it is supervised learning, the sequence needs to be labeled before training. So what is this l ...

Dear zhangyang laboratory: Hello! I am a student who is new to bioinformatics, and I am studying the thesis of ResPRE recently. ResPRE uses the coupling precision matrix to achieve high-accuracy protein contact prediction. It has achieved excellent results. Is an outstanding work.I sincerely hope ...

I clearly figured out this problem. Thank you for your answers sincerely.

I would like to ask about the formula 1 in section 2.2.1.
How are the formulas for fi （a） andr fi j（a,b） derived? Or is this formula derived in another paper? Can provide some relevant papers?
Thanks！