Protein structural features and PSSM profile · Biostar

This is a test version of Biostars. For the public version, visit https://www.biostars.org.

Protein structural features and PSSM profile

Hi Everyone Hope you all doing great!

I have a question regarding protein sequence numerical descriptors.

I used tool Porter5 for structural prediction for protein sequences. However, the output is for each residue. Since I have thousands of sequences. I want to know how I use that data as an input for machine learning model.Similarly for PSSM profile i.e. I have one file for each sequence. Any help will be appreciated. Thanks in advance.

sequence classification machine learning encoding

• 1,275 views • link

written 6.1 years ago by Rana •

You'll have to clarify what you want to achieve, please edit the post or it will be closed. Thank you for your understanding

• 0 views • link

written 6.1 years ago by Asaf

I want to know how I use that data as an input for machine learning model.

Please make sure you understand the biology and biochemistry sufficiently before diving into machine learning models based on this data.

• 0 views • link

written 6.1 years ago by WouterDeCoster

0 answers

No answers yet.

Log in to answer this question.

More posts like this

How to create PSSM files?
written 3.4 years ago by Manzoor •

I'm quite new in the field of Bioinformatics. I have around 800 protein sequences and I need to have PSSM files for each sequence. How …
PSSMs for entire PDB
written 6.6 years ago by Simon •

Hello! For a machine learning algorithm I would like to have PSSM (position specific scoring matrix) profile for every entry in PDB. Regarding this I …
How to make different protein sequence length equal to the max length
written 7.3 years ago by Rana •

I want to generate protein descriptors but for some of them I need equal protein lengths. So is there any way to make all sequence …
Create PSI-BLAST PSSM from position-specific weight matrix (probabilities)
written 7.7 years ago by M •

I have a position-specific weight matrix for a class of protein. Each position has an associated probability for all 20 amino acids being found at …
RNA secondary structure - Feature extraction
written 8.2 years ago by Manu Madhavan •

Hi All, For coding-non coding RNA identification (using Machine learning classifier), I would like to add features extracted from RNA secondary structure. I used RNAfold …
Fold recognition application
written 8.3 years ago by apurvamehta2015 •

I have read few papers regarding protein fold recognition using Machine learning algorithms. I have a doubt, after able to build a good protein fold …
Best Representation of Protein Sequences
written 8.5 years ago by khaeuk

Hello, I am currently working on a project that utilizes neural networks on protein sequences. However, I am quite stuck on what the best way …
Get a CSI-BLAST PSSM
written 11.2 years ago by ddofer •

I'm trying to get the PSSMs (i.e per=site probability of each AA) for a batch of protein sequences. I haven't used PSI-BLAST or CS-BLAST in …
Protein Sequence Alignment
written 14.1 years ago by kylejudita •

<p>I want to know how to call Blast from java code, I have wildtype residue, mutant residue, position of mutation, and protein sequence</p> <p>I want …
How Can I Upload Pssm In Blast Tool?
written 15.1 years ago by Sreevinusha •

Hello, My research area is Data mining and my work on that is regarding "Protein Secondary Structure Prediction using support vector machine". I’m using CB513 …