Hi,

I have an Excel table with gene symbols listed under the column "Symbol" (e.g., AKR1A1, adh) and their corresponding functions listed under the column "Function" (e.g., alcohol dehydrogenase (NADP+) [EC:1.1.1.2]). These symbols represent genes across various organisms. I would like to utilize the KEGG API to retrieve the cellular communities associated with these gene symbols and incorporate the results back into the Excel table. but I encounter this error

IndexError                                Traceback (most recent call last)

<ipython-input-17-1bf6ed03288a> in <cell line: 43>()
     41 
     42 # Add a new column for cellular community information
---> 43 df['Cellular Community'] = df['Symbol'].apply(get_cellular_community)
     44 
     45 # Save the updated DataFrame to a new Excel file

4 frames

<ipython-input-17-1bf6ed03288a> in get_cellular_community(symbol)
     24     if result:
     25         if len(result) > 0:  # Check if the result list is not empty
---> 26             kegg_id = result[0].split(':')[1]
     27             # Get the pathways associated with the gene from KEGG
     28             pathways = k.get_pathway_by_gene(kegg_id)

IndexError: list index out of range

and here is the script I used

import pandas as pd
from bioservices import KEGG

# Initialize the KEGG object
k = KEGG()

# Read the Excel file
try:
    df = pd.read_excel('/content/sample_data/function 1-5.xlsx')
except FileNotFoundError:
    print("Error: Excel file not found.")
    exit()

# Check if the 'Symbol' column exists in the DataFrame
if 'Symbol' not in df.columns:
    print("Error: 'Symbol' column not found in the Excel file.")
    exit()

# Function to get cellular community information for a gene symbol
def get_cellular_community(symbol):
    cellular_community = ""
    # Search for the gene symbol in KEGG
    result = k.find('genes', symbol)
    if result:
        if len(result) > 0:  # Check if the result list is not empty
            kegg_id = result[0].split(':')[1]
            # Get the pathways associated with the gene from KEGG
            pathways = k.get_pathway_by_gene(kegg_id)
            # Extract cellular community information from pathways
            for pathway_id, pathway_info in pathways.items():
                if 'Categories' in pathway_info:
                    categories = pathway_info['Categories']
                    if 'Cellular community - eukaryotes' in categories:
                        cellular_community = 'eukaryotes'
                        break
                    elif 'Cellular community - prokaryotes' in categories:
                        cellular_community = 'prokaryotes'
                        break
    return cellular_community


# Add a new column for cellular community information
df['Cellular Community'] = df['Symbol'].apply(get_cellular_community)

# Save the updated DataFrame to a new Excel file
output_file = 'output_with_cellular_community.xlsx'
df.to_excel(output_file, index=False)
print(f"Updated Excel file saved as: {output_file}")