Ion Channel Dose-Response Estimation From iPS Cardiac Waveforms

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for evaluating cardiotoxicity in drug candidates, particularly for QT prolongation, are inadequate as they fail to accurately determine the mechanism of action on ion channels beyond the hERG channel, leading to inefficiencies in predicting potential cardiotoxic effects.

Innovation Solution

A drug discovery support apparatus and method that utilizes a processor to derive prediction values from fluctuation waveforms of iPS myocardial cells, enabling estimation of ion channel inhibition or activation by candidate substances, and derive dose-response relationships to determine the mechanism of action.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If prediction values are acquired from fluctuation waveforms of iPS myocardial cells to estimate mechanism of action, then the accuracy of cardiotoxicity evaluation is improved, but the time and effort required for analysis increases

Engineering Contradiction:
Improveaccuracy of mechanism of action estimationVSAvoidtime and effort for analysis
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system pre-calculates and stores prediction values for multiple ion channels (hERG, Na, Ca) across various added amounts of candidate substances. These prediction values are derived in advance from fluctuation waveforms using machine learning models, so that when actual mechanism of action estimation is needed, the pre-computed values can be directly utilized without performing time-consuming waveform analysis from scratch.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates prediction value data that replicates the outcomes of complex waveform analysis. Instead of repeatedly analyzing raw fluctuation waveforms, the system uses copied prediction values that represent the essential information about ion channel inhibition/activation, thereby reducing analysis time while maintaining accuracy.

Inventive Principle:
Principle #26Copying

2Productivity

If index values indicating dose-response relationships are derived for each ion channel, then the efficiency of evaluating cardiotoxicity is improved, but the complexity of data processing increases

Engineering Contradiction:
Improveefficiency of cardiotoxicity evaluationVSAvoidcomplexity of data processing
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system divides the complex evaluation process into separate segments for different ion channels (hERG, Na, Ca channels). Each channel's prediction values are processed independently to derive specific index values, allowing parallel processing and reducing overall complexity. This segmentation enables the system to handle multiple channels without overwhelming data processing requirements.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system transforms complex waveform data into simplified index values that represent dose-response relationships. By changing the parameter representation from raw waveform signals to derived index values (such as prediction values at specific concentrations), the system reduces data complexity while preserving essential information about cardiotoxicity mechanisms.

Inventive Principle:
Principle #35Parameter changes

3Speed

If prediction models are used to estimate ion channel inhibition or activation, then the speed of mechanism of action analysis is improved, but the reliability of predictions may be reduced

Engineering Contradiction:
Improvespeed of mechanism of action analysisVSAvoidreliability of prediction
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The system employs machine learning models that are trained to handle multiple ion channel types (hERG, Na, Ca channels) with a single unified approach. These multi-functional models process prediction values for different channels using consistent algorithms, ensuring reliable and comparable results across channel types while maintaining fast processing speeds.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system uses prediction values derived from fluctuation waveforms as feedback to refine mechanism of action estimates. The prediction values serve as intermediate results that can be validated and adjusted based on their consistency with observed waveform patterns, thereby improving reliability while maintaining the speed benefits of model-based prediction.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4730345A1Drug discovery assistance device, method for operating drug discovery assistance device, and program for operating drug discovery assistance device
Publication Date: 2026.04.22 FUJIFILM CORP
  • EP4730345A1 patent drawingFigure 1
  • EP4730345A1 patent drawingFigure 2~3
  • EP4730345A1 patent drawingFigure 4

AI summary

A drug discovery support apparatus includes a processor, and the processor is configured to: acquire a first prediction value of a degree of inhibition indicating a degree to which a flow of ions in a plurality of ion channels present in an iPS myocardial cell, which is a myocardial cell derived from a human iPS cell, is inhibited by a candidate substance for a drug for each of the ion channels and for each added amount of the candidate substance, the first prediction value being output from a prediction model based on a first fluctuation waveform that is a fluctuation waveform of an extracellular potential of the iPS myocardial cell and is measured in a case where the candidate substance is added to the iPS myocardial cell while the added amount is changed; derive an index value indicating a dose-response relationship of the candidate substance for each of the ion channels, based on the first prediction value for each added amount; and present, to a user, estimated reference information that corresponds to the index value and is referred to in order to estimate a mechanism of action of the candidate substance.