Computational model for predicting CRISPR editing effects

This technology is a machine learning model that can predict post-CRISPR gene expression in human cell types.

Unmet Need: Tool to predict gene expression changes as a function of gene editing in human cells

CRISPR is a technology that enables researchers to edit parts of the genome by removing, adding, or mutating sections of DNA. Although a powerful tool, CRISPR experiments are labor-intensive and often confounded by environmental factors, making probing gene expression effects a difficult process that may not yield scalable results. There is a need for tools and methods that can improve the efficiency and scalability of genetic research using CRISPR.

The Technology: Computational pipeline to predict expression after gene editing

This technology describes a computational pipeline that predicts gene expression data in human cell types. The model is trained from published human single-cell multi-omics data and accurately predicts gene expression in that cell type from chromatin accessibility data. The ability to perform in silico CRISPR enables a more effective strategy for choosing how to edit the genome in both research and therapeutic applications.

Applications:

CRISPR-based therapy response prediction
In silico perturbation of regulatory elements
Non-coding mutation effect evaluation
Enhancer-promoter target prediction
Transcription factor interaction analysis
Generation of databases of gene editing sites

Advantages:

Trained with reliable, rich multi-omics data sets
Enables in silico CRISPR
Data-driven prediction model
Cost-effective CRISPR target selection

Lead Inventor:

Raul Rabadan, Ph.D.

Patent Information:

Patent Pending(WO2024178321)

Related Publications:

Fu X, Mo S, Buendia A, Laurent A, Shao A, Alvarez-Torres MD, Yu T, Tan J, Su J, Sagatelian R, Ferrando AA. “GET: a foundation model of transcription across human cell types.” bioRxiv. 2023 Sep 24:2023-09.

Tech Ventures Reference:

IR CU23168
Licensing Contact: Joan Martinez