cs.LGFeb 18, 2026

Guide-Guard: Off-Target Predicting in CRISPR Applications

Authors: Joseph Bingham, Netanel Arussy, Saman Zonouz

Organizations: Rutgers University, New Bruswick, NJ 08901, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

With the introduction of cyber-physical genome sequencing and editing technologies, such as CRISPR, researchers can more easily access tools to investigate and create remedies for a variety of topics in genetics and health science (e.g. agriculture and medicine). As the field advances and grows, new concerns present themselves in the ability to predict the off-target behavior. In this work, we explore the underlying biological and chemical model from a data driven perspective. Additionally, we present a machine learning based solution named Guide-Guard to predict the behavior of the system given a gRNA in the CRISPR gene-editing process with 84% accuracy. This solution is able to be trained on multiple different genes at the same time while retaining accuracy.

Figures & tables

Figure 1: A general model for genetic modification. The process on the user end may start with the collection of the DNA or RNA (1), or pulling down the information from a database (2) if the sequence has already been cataloged. This solution protects the boundaries between (1) and (2) as well as (2) and (3).
Figure 2: A pictorial representation of CRISPR Cas9 in action. Note, CRISPR Cas13 functions nearly identically, but on RNA instead.
Figure 3: A histogram of the binding potential where three mismatches occurs next to each other. The index given if the first mismatch.
Figure 4
Figure 6: A heat map detailing the binding potential as related to where two mismatches occur within a guide sequence, but may not be next to each other.
Figure 6
Figure 7
Figure 11: The ROC representing our results in correctly identifying malicious guide sequences.
 Perfect MatchesMismatch
Accuracy85.51%77.50%
True Positive Rate98.87%98.44%
True Negative Rate79.48%66.92%
Table 1: This table takes a more fine grained look of guide-guard. These are the accuracies and performance measures of the solution on guide sequences that are perfect matches as well as off targets.
More in this topic

Genomics

Genomics uses computational and experimental methods to study genomes, genetic variation, gene regulation, and their links to traits and disease.

See all 125 papers

Explore similar work

CardsList

  1. Can We Trust In-Distribution Success? Locked Evaluation Reveals Transfer Failure and Sampling-Depth Entanglement in CRISPRi Perturbation Prediction

    Jul 31, 2026Mehrdad Shoeibi, Niloofar YousefiOOD GeneralizationSingle-Cell Perturbation Modeling

    University of Central Florida

  2. STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations

    Feb 10, 2026Boyang Fu, Sameer Gabbita, George Dasoulas +5Single-Cell Perturbation ModelingSingle-Cell Transcriptomics

    Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA · Merck & Co., Inc., Cambridge, MA, USA · Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA +3

  3. Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens

    Sep 10, 2026Carl Edwards, Edward De Brouwer, Xiner Li +5Benchmark DesignActive Experimental Design

    Genentech, South San Francisco, CA, USA