🐛 Bug: Convert model input file from csv to a smiles list

[paulinebanye]

Describe the bug.

Hi @GemmaTuron

I encountered an error on colab, whilst converting the model prediction output - eos6o0z.csv to a smiles list.

Describe the steps to reproduce the behavior

To replicate this error

• [x] Install Ersilia on Google Colab.
• [x] Connect Colab to the google drive and specify the path to the input file eos6o0z.csv
• [ ] Convert eos6o0z.csv from csv to a smiles list to pass to Ersilia Models

Expected behavior.

Eos6o0z.csv file converted successfully

Screenshots.

Initial steps successful

Error encountered during conversion

Operating environment

Windows 10. Brave browser version 1.44.105

Additional context

No response

[Malikbadmus]

Hello @pauline-banye, the data you're attempting to convert to smiles to read into python contains a wrong column name.

smiles = df["CAN_SMILES"].tolists() change the CAN_SMILES to the column that contain your SMILES string in this case can_smiles.

so what you should have is smiles = df["can_smiles"].tolist()

[GemmaTuron]

Thanks @Malikbadmus Indeed this notebook is coded for a specific input file, in this case the problem is that python recognizes lowercase and uppercase, so we are asking it to find the column "CAN_SMILES" (which is the short version of canonical smiles") when we actually have a column named "can_smiles" it seems? You can run: import pandas as pd #package for working with tables df = pd.read_csv(path) df.columns This will output the column names.

To select a single column (in this case we only have one): df["columnname"]

[Cee-tech21]

hola @GemmaTuron, @pauline-banye, @Malikbadmus I am not sure which file/data we need to use for the conversion to smiles list. Is it the eml_canonical.csv file whose path we should pass to pd.read_csv(path)? Or is there another file we should be using for this??

[paulinebanye]

@Cee-tech21 it's the eml_canonical.csv we need to specify as the path