IP Library Granted Patent US 12,462,325
Granted Patent B2
US 12,462,325 · App. 18/148,854 · Granted Nov 4, 2025

Method and system for converting a protein data bank file into a grayscale image array

Inventors: Sudhanshu Kumar (Bokaro, IN); Joel Joseph (Palayi, IN); Ansh Gupta (Menhdawal, IN)
Assignee: Innoplexus AG
G06T1/20G06T9/00G06T11/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,462,325
App. No.
18/148,854
Granted
Nov 4, 2025
Kind
B2
Abstract

A system and a method for converting protein data bank (PDB) files into a grayscale image array is provided. The method includes extracting PDB files from a PDB, using a data extraction module. The method also includes converting, using a file conversion module, the PDB files into a data frame based on BioPandas. The method further includes selecting, using a column selection module, one or more columns from the data frame based on a pre-determined criteria. The method furthermore includes converting, using a column conversion module, the selected one or more columns into a NumPy array for rendering the data frame to resemble an image. The method furthermore includes resizing the NumPy array using an OpenCV for making size of the NumPy array uniform and for generating a grayscale image array.

Claims (33)

1 . A processor-implemented method of converting protein data bank (PDB) files into a grayscale image array, the method comprising:

extracting PDB files from a PDB, using a data extraction module;

converting, using a file conversion module, the PDB files into a data frame based on BioPandas;

selecting, using a column selection module, one or more columns from the data frame based on a pre-determined criteria;

converting, using a column conversion module, the selected one or more columns into a NumPy array for rendering the data frame to resemble an image; and

resizing, using an image array generation module, the NumPy array for making size of the NumPy array uniform and for generating a grayscale image array.

2 . The processor-implemented method of claim 1 , wherein selecting the one or more columns comprises:

shortlisting one or more columns based on the pre-determined criteria; and

performing a one hot encoding of the non-numeric columns.

3 . The processor-implemented method of claim 1 , wherein converting the one or more columns into the NumPy array comprises:

scaling each column between 0 to 255; and

normalizing one or more columns of the data frame using min-max normalization for obtaining.

4 . The processor-implemented method of claim 1 , wherein the NumPy array is resized to a height of 100.

5 . A system for converting protein data bank (PDB) files into a grayscale image array, the system comprising:

a non-transitory memory configured to store PDB files and one or more executable modules; and

a processor configured to execute the one or more executable modules for converting protein data bank (PDB) files into a grayscale image array, wherein the one or more executable modules comprises:

a data extraction module configured to extracting PDB files from a PDB;

a file conversion module configured to convert the PDB files into a data frame based on BioPandas; and

a column selection module configured to select one or more columns from the data frame based on a pre-determined criteria;

an image array generation module for resizing the NumPy array for making size of the NumPy array uniform and for generating a grayscale image array.

6 . The system of claim 5 , wherein the column selection module is further configured to:

shortlist one or more columns based on the pre-determined criteria; and

perform a one hot encoding of the non-numeric columns.

7 . The system of claim 5 , wherein the file conversion module is further configured to:

scale each column between 0 to 255; and

normalize one or more columns of the data frame using min-max normalization.

8 . The system of claim 5 , wherein the NumPy array is resized to a height of 100.

9 . One or more non-transitory computer readable storage mediums storing one or more sequences of instructions, which when executed by one or more processors, causes a method for converting protein data bank (PDB) files into a grayscale image array, the method comprising:

extracting PDB files from a PDB, using a data extraction module;

converting, using a file conversion module, the PDB files into a data frame based on BioPandas;

selecting, using a column selection module, one or more columns from the data frame based on a pre-determined criteria;

converting, using a column conversion module, the selected one or more columns into a NumPy array for rendering the data frame to resemble an image;

resizing, using an image array generation module, the NumPy array for making size of the NumPy array uniform and for generating a grayscale image array.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 3, 2023
From: INNOPLEXUS CONSULTING SERVICES PVT. LTD.
To: INNOPLEXUS AG
Reel/Frame 063203/0232 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 30, 2022
From: KUMAR, SUDHANSHU; JOSEPH, JOEL; GUPTA, ANSH
To: INNOPLEXUS CONSULTING SERVICES PVT. LTD.
Reel/Frame 062247/0001 →
Continuity (1)
Related Publication 20240221109A1 · Jul 4, 2024
References Cited (4)
US 20200174789A1 · Miller · 2020 [cited by examiner]
Raschka, Sebastian, published “Working with PDB Structures in DataFrames”. Downloaded on Dec. 29, 2022 from url: http://rasbt.github.io/biopandas/tutorials/Working_with_PDB_Structures_in_DataFrames/#working-with-pdb-dat… [cited by applicant]
Barthelme, Simon, published “as.cimg.data.frame: Create an image from a data.frame”. Downloaded on Dec. 29, 2022 from url: https://rdrr.io/cran/imager/man/as.cimg.data.frame.html. [cited by applicant]
Sentdex, published “Handling Non-Numerical Data for Machine Learning”. Downloaded on Dec. 29, 2022 from url: https://pythonprogramming.net/working-with-non-numerical-data-machine-learning-tutorial/. [cited by applicant]