Directed Cell Culture Data Trees for Traceable AI-Ready Protocols

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current cell-related data is dispersed across various silos, lacking structured relationships and standards, making it difficult to share and trace the history of cell lines, which hinders reproducibility and trust in cell assets.

Innovation Solution

A directed tree structure is used to digitally represent cell populations and their relationships, allowing for semi-automated capture and storage of protocols and observations, enabling secure and efficient data sharing and provenance tracking.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If cell-related data is stored in separate silos using various formats (paper notebooks, Excel, PDFs, ELNs), then data can be captured at different stages, but the data becomes difficult to link, trace, and share across stages

Engineering Contradiction:

Improvedata traceabilityVSAvoiddata structure complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The patent merges previously separate data silos (protocols, observations, inventory) into a unified directed tree structure where all cell-related data is interconnected through node-edge relationships, enabling seamless tracing and sharing across all stages of cell culture workflows

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The directed tree structure serves multiple functions simultaneously: it stores protocols, captures observations, tracks inventory, enables AI/ML analysis, and facilitates data sharing across different laboratories and platforms through a universal standardized format

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Adaptability or versatility

If scientists manually capture and document cell culture protocols and observations using non-standardized formats, then flexibility in recording is maintained, but data cannot be easily shared or compared across different users and laboratories

Engineering Contradiction:

Improvedata sharing capabilityVSAvoiddata capture ease

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent transforms unstructured, free-text data capture into structured parameter-based recording within the directed tree framework, where observations and protocols are captured as standardized nodes with defined attributes, enabling both ease of entry and interoperability across laboratories

Inventive Principle:

Principle #35Parameter changes

3Loss of time

If detailed protocol steps and observations are recorded manually in paper notebooks or spreadsheets, then complete documentation is achieved, but finding and cross-referencing information from six months ago becomes highly complex and time-consuming

Engineering Contradiction:

Improveinformation retrieval timeVSAvoidcontextual relationship data

Core Design Contradiction:

Loss of timeVSLoss of information

Solution Approach 1:

The directed tree structure provides automatic feedback and contextual relationships through its hierarchical node-edge architecture, where any data point is automatically linked to its parent protocols, child observations, and related inventory items, enabling instant retrieval of contextual information without manual cross-referencing

Inventive Principle:

Principle #23Feedback

4Ease of operation

If cell culture data is stored in centralized locations like Google Drive or Dropbox, then data accessibility is improved, but the relationships between protocols, observations, and inventory data are lost

Engineering Contradiction:

Improvedata accessibilityVSAvoiddata relationship context

Core Design Contradiction:

Ease of operationVSLoss of information

Solution Approach 1:

The patent adds a dimensional layer of hierarchical relationships to flat file storage by implementing a directed tree structure where data points exist as interconnected nodes across multiple dimensions (protocols, observations, inventory), maintaining both accessibility and contextual relationships simultaneously

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS12400732B1Methods, apparatuses, and tools for semi-automated digital support and structured data capture for the multi-dimensional manual process of cell culture maintenance and manipulation enabling artificial intelligence (AI) driven prediction and controlled data sharing

Publication Date: 2025.08.26 THE JOAN & IRWIN JACOBS TECHNION CORNELL INST

AI summary

A method includes generating a first node of a directed tree. The first node digitally represents a first cell population of a cell line. The method further includes receiving an indication from a user of a protocol to be performed on the first cell population that will generate a second cell population of the cell line. The method further includes generating a second node of the directed tree after the user has performed the protocol on the first cell population to generate the second cell population. The second node is automatically assigned as (1) a child node of the first node and (2) digitally represents the second cell population. The first node is connected to the second node in the directed tree via an edge. The method further includes causing, data to be stored at the edge. The data is a transformation of the protocol used to generate the second cell population. This structured cell associated data can be used to train AI algorithms to predict how protocol steps affect cell behavior (cell morphology, viability, fitness, cell-cell interactions, protein/compound production, expression profiles among other things).