Scop3P¶

A comprehensive database of human phosphosites within their full context. Scop3P integrates sequences (UniProtKB/Swiss-Prot), structures (PDB), and uniformly reprocessed phosphoproteomics data (PRIDE) to annotate all known human phosphosites.

Scop3P, available at https://iomics.ugent.be/scop3p, presents a unique resource for visualization and analysis of phosphosites and for understanding of phosphosite structure–function relationships.

Install Dependencies¶

In [1]:

%%capture
!jupyter labextension install jupyterlab_3dmol
!jupyter labextension install @jupyter-widgets/jupyterlab-manager
!pip install pandas matplotlib py3Dmol b2btools==3.0.7b2

Import required packages¶

In [1]:

%%capture
import requests, tempfile,json,sys
sys.path.append("./scripts") ## get python scripts from this directory
import pandas as pd 
from b2bTools import SingleSeq, constants
import py3Dmol
import ipywidgets as widgets

Upload your peptide (tab delimited .txt) file in the next cell¶

In [7]:

wid=widgets.FileUpload(
    accept='',  # Accepted file extension e.g. '.txt', '.pdf', 'image/*', 'image/*,.pdf'
    multiple=False  # True to accept multiple files upload else False
)

display(wid)

In [50]:

# wid.values
# print (infile)
# content=infile['content']
# content=io.String(content.decode('utf-8'))
# df=pd.read_csv(content)

In [2]:

pepfile=pd.read_csv('peptidefile.txt',sep='\t',usecols=[1,2,4,5,6,7])
proteincol=input("Enter Protein ID column number: ")
proteincolname=pepfile.columns[int(proteincol)-1]
print ("Protein column name in provided file is: ", proteincolname)

Enter Protein ID column number: 5
Protein column name in provided file is:  ACC_ID

In [3]:

pepgroup=pepfile.groupby(proteincolname)
proteinlist=list(set(pepfile[proteincolname].tolist()))
print ("Total number of proteins in your file: ", len(proteinlist))

Total number of proteins in your file:  4

In [4]:

def fetch_prot_sequence(accession):
    BASE_URL = f"http://uniprot.org/uniprotkb/{accession}.fasta"
    url = f'{BASE_URL}?accession={accession}'
    response = requests.get(url)
    if response.status_code == 200:
        raw_fasta_sequence = response.content.decode("utf-8")
    else:
        raw_fasta_sequence = ""
    
    lines = raw_fasta_sequence.split('\n')
    protein_id = str(lines[0])
    amino_acids = "".join([str(l) for l in lines[1:]])
    
    return protein_id, amino_acids

In [5]:

# def UPseqfetch(protseq,accsn,pep):
import re

def add_element(tmpdict, key, value):
    if key not in tmpdict:
        tmpdict[key] = []
    tmpdict[key].append(value)

def pepMapper(protDF):
    dataDF={}
    for idx, grp in pepgroup:
        protid=grp[proteincolname].tolist()[0]
        peplis=list(set(grp['Pep_seq'].tolist()))
        id_,protseq=fetch_prot_sequence(protid)
        for pep in peplis:
            for match in re.finditer(pep, protseq):
                newpos=[match.start()+1, match.end()+1]
                add_element(dataDF,protid,[pep,newpos[0],newpos[1]])
    return dataDF

In [6]:

mapped_peptides=pepMapper(pepgroup)
print ("Protein\t#Peptides")
print("\n".join("{}\t{}".format(key,len(value)) for key,value in mapped_peptides.items()))

Protein	#Peptides
P55884	1
Q9BXS5	2
Q9H0H5	1
Q9HC35	1

In [7]:

structureID=input("Please enter the protein Id for 3D visualization: ")
peptides=mapped_peptides[structureID]

Please enter the protein Id for 3D visualization: Q9BXS5

In [8]:

## Get alphaFold model for the protein
import urllib.request
AFurl="https://alphafold.ebi.ac.uk/files/AF-"
modelurl = f'{AFurl}{structureID}{"-F1-model_v4.pdb"}'
AFmodel = urllib.request.urlretrieve(modelurl,f'{structureID}{".pdb"}')

In [ ]:

In [11]:

import itertools
def display_3D(peptides):
    view = py3Dmol.view()
    view.addModel(open((structureID+'.pdb'), 'r').read(),'pdb')
    allpos=[]
    colordict,commoncol={},{}
    view.setStyle({'cartoon': { 'color': 'silver' }})
    view.addSurface(py3Dmol.VDW, {'opacity': 0.60, 'color': 'white' })
    for pep in peptides:
        for aapos in range(pep[1],pep[2]+1):
            allpos.append(list(range(pep[1],pep[2]+1)))
            
    mergedPos = list(itertools.chain.from_iterable(allpos))
    commonPos=list(set.intersection(*map(set, allpos))) 
    for aapos in mergedPos:
        colordict[aapos]='blue'
#         view.addSurface(py3Dmol.VDW, {'opacity': 0.6,'color':'red'},{'resi': [aapos]})
    for aapos1 in commonPos:
        commoncol[aapos1]='purple'
#         view.addSurface(py3Dmol.VDW, {'opacity': 0.6,'color':'purple'},{'resi': [aapos1]})              
    print ("Common positions colored in Purple")    

    view.setStyle({'cartoon': {'colorscheme':{'prop':'resi','map':colordict}}})     
    view.setStyle({'cartoon': {'colorscheme':{'prop':'resi','map':commoncol}}})
    
    view.zoomTo()
    return view

In [12]:

display_3D(peptides)

Common positions colored in Purple

You appear to be running in JupyterLab (or JavaScript failed to load for some other reason). You need to install the 3dmol extension:
jupyter labextension install jupyterlab_3dmol

Out[12]:

<py3Dmol.view at 0x7f29d3f8aa70>