DeepCRISPR: optimized CRISPR guide RNA design by deep learning

Machine Learning Empowering Microbial Cell Factory: A Comprehensive Review

The wide application of machine learning has provided more possibilities for biological manufacturing, and the combination of machine learning and synthetic biology technology has ignited even more brilliant sparks, which has created an unpredictable value for the upgrading of microbial cell factories. The review delves into the synergies between machine learning and synthetic biology to create research worth investigating in biotechnology. We explore relevant databases, toolboxes, and machine learning-derived models. Furthermore, we examine specific applications of this combined approach in chemical production, human health, and environmental remediation. By elucidating these successful integrations, this review aims to provide valuable guidance for future research at the intersection of biomanufacturing and artificial intelligence.

T2D-LVDD: neural network-based predictive models for left ventricular diastolic dysfunction in type 2 diabetes

Cardiovascular disease complications are the leading cause of morbidity and mortality in patients with Type 2 diabetes (T2DM). Left ventricular diastolic dysfunction (LVDD) is one of the earliest myocardial characteristics of diabetic cardiac dysfunction. Therefore, we aimed to develop an LVDD-risk predictive model to diagnose cardiac dysfunction before severe cardiovascular complications arise. We trained an artificial neural network model to predict LVDD risk with patients' clinical information. The model showed better performance than classical machine learning methods such as logistic regression, random forest and support vector machine. We further explored LVDD-risk/protective features with interpretability methods in neural network. Finally, we provided a freely accessible web server called LVDD-risk, where users can submit their clinical information to obtain their LVDD-risk probability and the most noteworthy risk indicators.

Accurate Prediction of CRISPR/Cas13a Guide Activity Using Feature Selection and Deep Learning

CRISPR/Cas13a serves as a key tool for nucleic acid tests; therefore, accurate prediction of its activity is essential for creating robust and sensitive diagnosis. In this study, we create a dual-branch neural network model that achieves high prediction accuracy and classification performance across two independent CRISPR/Cas13a data sets, outperforming previously published models relying solely on sequence features. The model integrates direct sequence encoding with descriptive features and yields 99 key descriptive features out of 1553, extracted through statistical analysis, which critically influence guide-target interactions and Cas13a guide activity. By employing Shapley Additive Explanations and Integrated Gradients for feature importance analysis, we show that sequence composition, mismatch type and frequency, and the protospacer flanking site region are primary features. These findings underscore the importance of using descriptive features as complementary inputs to deep learning-based encoding and provide valuable insights into the mechanisms underlying guide-target interaction. All in all, this study not only introduces a reliable and efficient model for Cas13a guide activity prediction but also offers a foundation for future rational design efforts.

Unraveling the future of genomics: CRISPR, single-cell omics, and the applications in cancer and immunology

The CRISPR system has transformed many research areas, including cancer and immunology, by providing a simple yet effective genome editing system. Its simplicity has facilitated large-scale experiments to assess gene functionality across diverse biological contexts, generating extensive datasets that boosted the development of computational methods and machine learning/artificial intelligence applications. Integrating CRISPR with single-cell technologies has further advanced our understanding of genome function and its role in many biological processes, providing unprecedented insights into human biology and disease mechanisms. This powerful combination has accelerated AI-driven analyses, enhancing disease diagnostics, risk prediction, and therapeutic innovations. This review provides a comprehensive overview of CRISPR-based genome editing systems, highlighting their advancements, current progress, challenges, and future opportunities, especially in cancer and immunology.

A CRISPRi library screen in group B Streptococcus identifies surface immunogenic protein (Sip) as a mediator of multiple host interactions

Group B Streptococcus (GBS; Streptococcus agalactiae) is an important pathobiont capable of colonizing various host environments, contributing to severe perinatal infections. Surface proteins play critical roles in GBS-host interactions; however, comprehensive studies of these proteins' functions have been limited by genetic manipulation challenges. This study leveraged a CRISPR interference (CRISPRi) library to target genes encoding surface-trafficked proteins in GBS, identifying their roles in modulating macrophage cytokine responses. Bioinformatic analysis of 654 GBS genomes revealed 66 conserved surface protein genes. Using a GBS strain expressing chromosomally integrated dCas9, we generated and validated CRISPRi strains targeting these genes. THP-1 macrophage-like cells were exposed to ethanol-killed GBS variants, and pro-inflammatory cytokines TNF-⍺ and IL-1β were measured. Notably, knockdown of the sip gene, encoding the Surface Immunogenic Protein (Sip), significantly increased IL-1β secretion, implicating Sip in caspase-1-dependent regulation. Furthermore, Δsip mutants demonstrated impaired biofilm formation, reduced adherence to human fetal membranes, and diminished uterine persistence in a mouse colonization model. These findings suggest that Sip modulates GBS-host interactions critical for pathogenesis, underscoring its potential as a therapeutic target or vaccine component.

Mapping the therapeutic landscape of CRISPR-Cas9 for combating age-related diseases

CRISPR-Cas9 (clustered regularly interspaced short palindromic repeats-associated protein 9) has emerged as a transformative genome-editing tool with significant therapeutic potential for age-related diseases, including Alzheimer's disease, Parkinson's disease, cardiovascular disorders, and osteoporosis. This study presents a bibliometric analysis of CRISPR-Cas9 research in age-related diseases, identifying key contributors, major research hotspots, and critical technological advancements. While promising applications have been demonstrated in gene repair, functional regulation, and molecular interventions, significant barriers persist, including off-target effects, low delivery efficiency, and limited editing in non-dividing cells. Ethical concerns over germline editing and gaps in long-term safety data further complicate clinical translation. Future directions emphasize the development of high-precision Cas9 variants, homology-directed repair-independent tools, and efficient delivery systems, alongside the establishment of international regulatory frameworks and multicenter clinical trials. These efforts are essential to fully realize the potential of CRISPR-Cas9 in addressing the global health challenges of aging.

An Overview and Comparative Analysis of CRISPR-SpCas9 gRNA Activity Prediction Tools

Design of guide RNA (gRNA) with high efficiency and specificity is vital for successful application of the CRISPR gene editing technology. Although many machine learning (ML) and deep learning (DL)-based tools have been developed to predict gRNA activities, a systematic and unbiased evaluation of their predictive performance is still needed. Here, we provide a brief overview of in silico tools for CRISPR design and assess the CRISPR datasets and statistical metrics used for evaluating model performance. We benchmark seven ML and DL-based CRISPR-Cas9 editing efficiency prediction tools across nine CRISPR datasets covering six cell types and three species. The DL models CRISPRon and DeepHF outperform the other models exhibiting greater accuracy and higher Spearman correlation coefficient across multiple datasets. We compile all CRISPR datasets and in silico prediction tools into a GuideNet resource web portal, aiming to facilitate and streamline the sharing of CRISPR datasets. Furthermore, we summarize features affecting CRISPR gene editing activity, providing important insights into model performance and the further development of more accurate CRISPR prediction models.

CRISPR-MFH: A Lightweight Hybrid Deep Learning Framework with Multi-Feature Encoding for Improved CRISPR-Cas9 Off-Target Prediction

BACKGROUND

The CRISPR-Cas9 system has emerged as one of the most promising gene-editing technologies in biology. However, off-target effects remain a significant challenge. While recent advances in deep learning have led to the development of models for off-target prediction, these models often fail to fully leverage sequence pair information. Furthermore, as the models' parameter sizes increase, so do their complexities, limiting their practical applicability.

METHODS

In this study, we introduce a novel multi-feature independent encoding method, which encodes the gRNA-DNA sequence pair into three distinct feature matrices to minimize information loss. Additionally, we propose a lightweight hybrid deep learning framework, CRISPR-MFH, that integrates multi-scale separable convolutions and hybrid attention mechanisms for efficient and accurate off-target prediction.

RESULTS

Extensive experiments across multiple benchmark datasets demonstrate that the proposed encoding method effectively captures critical features and that CRISPR-MFH outperforms or matches state-of-the-art models with significantly fewer parameters across multiple evaluation metrics.

CONCLUSIONS

This study offers a novel perspective for advancing deep learning technology in the realm of CRISPR-Cas9 off-target detection.

MultiCRISPR-EGA: Optimizing Guide RNA Array Design for Multiplexed CRISPR Using the Elitist Genetic Algorithm

Multiplexed CRISPR design, which allows for the concurrent and efficient editing of multiple genomic sites, is a powerful tool for complex genetic modifications. However, designing effective multiplexed guide RNA (gRNA) arrays remains challenging due to the exponential increase in potential gRNA array candidates and the significant impact of different target site selections on efficiency and specificity. Recognizing that more stable gRNAs, characterized by lower minimum free energy (MFE), have prolonged activity and thus higher efficacy, we developed MultiCRISPR-EGA, a graphical user interface (GUI)-based tool that employs the Elitist Genetic Algorithm (EGA) to design optimized single-promoter-driven multiplexed gRNA arrays. Computational experiments on Escherichia coli gene targets demonstrate that the EGA can rapidly optimize multiplexed gRNA arrays, outperforming other intelligent optimization algorithms in CRISPR interference (CRISPRi) applications, while the GUI provides real-time design progress control and compatibility with various CRISPR-Cas systems. This tool aims to advance the multiplexed gRNA array design process, enabling more efficient and cost-effective genome editing for synthetic biology.

Engineering a New Generation of Gene Editors: Integrating Synthetic Biology and AI Innovations

CRISPR-Cas technology has revolutionized biology by enabling precise DNA and RNA edits with ease. However, significant challenges remain for translating this technology into clinical applications. Traditional protein engineering methods, such as rational design, mutagenesis screens, and directed evolution, have been used to address issues like low efficacy, specificity, and high immunogenicity. These methods are labor-intensive, time-consuming, and resource-intensive and often require detailed structural knowledge. Recently, computational strategies have emerged as powerful solutions to these limitations. Using artificial intelligence (AI) and machine learning (ML), the discovery and design of novel gene-editing enzymes can be streamlined. AI/ML models predict activity, specificity, and immunogenicity while also enhancing mutagenesis screens and directed evolution. These approaches not only accelerate rational design but also create new opportunities for developing safer and more efficient genome-editing tools, which could eventually be translated into the clinic.

Recent advances in therapeutic gene-editing technologies

The advent of gene-editing technologies, particularly CRISPR-based systems, has revolutionized the landscape of biomedical research and gene therapy. Ongoing research in gene editing has led to the rapid iteration of CRISPR technologies, such as base and prime editors, enabling precise nucleotide changes without the need for generating harmful double-strand breaks (DSBs). Furthermore, innovations such as CRISPR fusion systems with DNA recombinases, DNA polymerases, and DNA ligases have expanded the size limitations for edited sequences, opening new avenues for therapeutic development. Beyond the CRISPR system, mobile genetic elements (MGEs) and epigenetic editors are emerging as efficient alternatives for precise large insertions or stable gene manipulation in mammalian cells. These advances collectively set the stage for next-generation gene therapy development. This review highlights recent developments of genetic and epigenetic editing tools and explores preclinical innovations poised to advance the field.

Application of CRISPR-Cas System in Human Papillomavirus Detection Using Biosensor Devices and Point-of-Care Technologies

Human papillomavirus (HPV) is the most common virus for genital tract infections. Cervical cancer ranks as the fourth most prevalent cancer globally, with over 99% of cases in women attributed to HPV infection. This infection continues to pose an ongoing threat to public health. Therefore, the development of rapid, high-throughput, and sensitive HPV detection platforms is important, especially in regions with limited access to advanced medical resources. CRISPR-based biosensors, a promising new method for nucleic acid detection, are now rapidly and widely used in basic and applied research and have received much attention in recent years for HPV diagnosis and treatment. In this review, we discuss the mechanisms and functions of the CRISPR-Cas system, focusing on its applications in HPV diagnostics. The review covers CRISPR technologies such as CRISPR-Cas9, CRISPR-Cas12, and CRISPR-Cas13, along with nucleic acid amplification methods, CRISPR-based signal output systems, and point-of-care testing (POCT) strategies. This comprehensive overview highlights the versatility and potential of CRISPR technologies in HPV detection. We also discuss the numerous CRISPR biosensors developed since the introduction of CRISPR to detect HPV. Finally, we discuss some of the challenges faced in HPV detection by the CRISPR-Cas system.

Current state and future prospects of Horizontal Gene Transfer detection

Artificial intelligence (AI) has been shown to be beneficial in a wide range of bioinformatics applications. Horizontal Gene Transfer (HGT) is a driving force of evolutionary changes in prokaryotes. It is widely recognized that it contributes to the emergence of antimicrobial resistance (AMR), which poses a particularly serious threat to public health. Many computational approaches have been developed to study and detect HGT. However, the application of AI in this field has not been investigated. In this work, we conducted a review to provide information on the current trend of existing computational approaches for detecting HGT and to decipher the use of AI in this field. Here, we show a growing interest in HGT detection, characterized by a surge in the number of computational approaches, including AI-based approaches, in recent years. We organize existing computational approaches into a hierarchical structure of computational groups based on their computational methods and show how each computational group evolved. We make recommendations and discuss the challenges of HGT detection in general and the adoption of AI in particular. Moreover, we provide future directions for the field of HGT detection.

Beyond precision: evaluation of off-target clustered regularly interspaced short palindromic repeats/Cas9-mediated genome editing

The gene editing field has advanced rapidly since the development of the clustered regularly interspaced short palindromic repeats (CRISPR)/Cas9 system because of its applicability in precisely modifying the genome. Among its multiple applications, the correction of genetic diseases has emerged as a potential curative treatment for many disorders that have eluded a cure to date. Despite its efficiency in achieving therapeutic levels of correction, the unexpected adverse effects of editing due to CRISPR/Cas9 nuclease activity are a major concern when translating these new strategies to the clinic. Multiple in silico tools and empirical methods have been developed to evaluate these off-target edits as well as other adverse alterations of the genome, including rearrangements, not only in ex vivo experiments but also in in vivo experiments. In this review, we summarize the available methods for the assessment of off-target effects of CRISPR/Cas9 systems, highlighting their advantages and limitations. Special attention will be paid to their application in pre-clinical studies and clinical trials, both in the manufacturing product and in the long-term follow-up of patients.

Transitioning from wet lab to artificial intelligence: a systematic review of AI predictors in CRISPR

The revolutionary CRISPR-Cas9 system leverages a programmable guide RNA (gRNA) and Cas9 proteins to precisely cleave problematic regions within DNA sequences. This groundbreaking technology holds immense potential for the development of targeted therapies for a wide range of diseases, including cancers, genetic disorders, and hereditary diseases. CRISPR-Cas9 based genome editing is a multi-step process such as designing a precise gRNA, selecting the appropriate Cas protein, and thoroughly evaluating both on-target and off-target activity of the Cas9-gRNA complex. To ensure the accuracy and effectiveness of CRISPR-Cas9 system, after the targeted DNA cleavage, the process requires careful analysis of the resultant outcomes such as indels and deletions. Following the success of artificial intelligence (AI) in various fields, researchers are now leveraging AI algorithms to catalyze and optimize the multi-step process of CRISPR-Cas9 system. To achieve this goal AI-driven applications are being integrated into each step, but existing AI predictors have limited performance and many steps still rely on expensive and time-consuming wet-lab experiments. The primary reason behind low performance of AI predictors is the gap between CRISPR and AI fields. Effective integration of AI into multi-step CRISPR-Cas9 system demands comprehensive knowledge of both domains. This paper bridges the knowledge gap between AI and CRISPR-Cas9 research. It offers a unique platform for AI researchers to grasp deep understanding of the biological foundations behind each step in the CRISPR-Cas9 multi-step process. Furthermore, it provides details of 80 available CRISPR-Cas9 system-related datasets that can be utilized to develop AI-driven applications. Within the landscape of AI predictors in CRISPR-Cas9 multi-step process, it provides insights of representation learning methods, machine and deep learning methods trends, and performance values of existing 50 predictive pipelines. In the context of representation learning methods and classifiers/regressors, a thorough analysis of existing predictive pipelines is utilized for recommendations to develop more robust and precise predictive pipelines.

Appraisal of CRISPR Technology as an Innovative Screening to Therapeutic Toolkit for Genetic Disorders

The high frequency of genetic diseases compels the development of refined diagnostic and therapeutic systems. CRISPR is a precise genome editing tool that offers detection of genetic mutation with high sensitivity, specificity and flexibility for point-of-care testing in low resource environment. Advancements in CRISPR ushered new hope for the detection of genetic diseases. This review aims to explore the recent advances in CRISPR for the detection and treatment of genetic disorders. It delves into the advances like next-generation CRISPR diagnostics like nano-biosensors, digitalized CRISPR, and omics-integrated CRISPR technologies to enhance the detection limits and to facilitate the "lab-on-chip" technologies. Additionally, therapeutic potential of CRISPR technologies is reviewed to evaluate the implementation potential of CRISPR technologies for the treatment of hematological diseases, (sickle cell anemia and β-thalassemia), HIV, cancer, cardiovascular diseases, and neurological disorders, etc. Emerging CRISPR therapeutic approaches such as base/epigenetic editing and stem cells for the development of foreseen CRIPSR drugs are explored for the development of point-of-care testing. A combination of predictive models of artificial intelligence and machine learning with growing knowledge of genetic disorders has also been discussed to understand their role in acceleration of genetic detection. Ethical consideration are briefly discussed towards to end of review. This review provides the comprehensive insights into advances in the CRISPR diagnostics/therapeutics which are believed to pave the way for reliable, effective, and low-cost genetic testing.

Gene therapy for genetic diseases: challenges and future directions

Genetic diseases constitute the majority of rare human diseases, resulting from abnormalities in an individual's genetic composition. Traditional treatments offer limited relief for these challenging conditions. In contrast, the rapid advancement of gene therapy presents significant advantages by directly addressing the underlying causes of genetic diseases, thereby providing the potential for precision treatment and the possibility of curing these disorders. This review aims to delineate the mechanisms and outcomes of current gene therapy approaches in clinical applications across various genetic diseases affecting different body systems. Additionally, genetic muscular disorders will be examined as a case study to investigate innovative strategies of novel therapeutic approaches, including gene replacement, gene suppression, gene supplementation, and gene editing, along with their associated advantages and limitations at both clinical and preclinical levels. Finally, this review emphasizes the existing challenges of gene therapy, such as vector packaging limitations, immunotoxicity, therapy specificity, and the subcellular localization and immunogenicity of therapeutic cargos, while discussing potential optimization directions for future research. Achieving delivery specificity, as well as long-term effectiveness and safety, will be crucial for the future development of gene therapies targeting genetic diseases.

PathoGD: an integrative genomics approach to primer and guide RNA design for CRISPR-based diagnostics

Critical to the success of CRISPR-based diagnostic assays is the selection of a diagnostic target highly specific to the organism of interest, a process often requiring iterative cycles of manual selection, optimisation, and redesign. Here we present PathoGD, a bioinformatic pipeline for rapid and high-throughput design of RPA primers and gRNAs for CRISPR-Cas12a-based pathogen detection. PathoGD is fully automated, leverages publicly available sequences and is scalable to large datasets, allowing rapid continuous monitoring and validation of primer/gRNA sets to ensure ongoing assay relevance. We designed primers and gRNAs for five clinically relevant bacterial pathogens, and experimentally validated a subset of the designs for detecting Streptococcus pyogenes and/or Neisseria gonorrhoeae in assays with and without pre-amplification. We demonstrated high specificity of primers and gRNAs designed, with minimal off-target signal observed for all combinations. We anticipate PathoGD will be an important resource for assay design for current and emerging pathogens. PathoGD is available on GitHub at https://github.com/sjlow23/pathogd .

Deep learning in microbiome analysis: a comprehensive review of neural network models

Microbiome research, the study of microbial communities in diverse environments, has seen significant advances due to the integration of deep learning (DL) methods. These computational techniques have become essential for addressing the inherent complexity and high-dimensionality of microbiome data, which consist of different types of omics datasets. Deep learning algorithms have shown remarkable capabilities in pattern recognition, feature extraction, and predictive modeling, enabling researchers to uncover hidden relationships within microbial ecosystems. By automating the detection of functional genes, microbial interactions, and host-microbiome dynamics, DL methods offer unprecedented precision in understanding microbiome composition and its impact on health, disease, and the environment. However, despite their potential, deep learning approaches face significant challenges in microbiome research. Additionally, the biological variability in microbiome datasets requires tailored approaches to ensure robust and generalizable outcomes. As microbiome research continues to generate vast and complex datasets, addressing these challenges will be crucial for advancing microbiological insights and translating them into practical applications with DL. This review provides an overview of different deep learning models in microbiome research, discussing their strengths, practical uses, and implications for future studies. We examine how these models are being applied to solve key problems and highlight potential pathways to overcome current limitations, emphasizing the transformative impact DL could have on the field moving forward.

DeepMEns: an ensemble model for predicting sgRNA on-target activity based on multiple features

The CRISPR/Cas9 system developed from Streptococcus pyogenes (SpCas9) has high potential in gene editing. However, its successful application is hindered by the considerable variability in target efficiencies across different single guide RNAs (sgRNAs). Although several deep learning models have been created to predict sgRNA on-target activity, the intrinsic mechanisms of these models are difficult to explain, and there is still scope for improvement in prediction performance. To overcome these issues, we propose an ensemble interpretable model termed DeepMEns based on deep learning to predict sgRNA on-target activity. By using five different training and validation datasets, we constructed five sub-regressors, each comprising three parts. The first part uses one-hot encoding, wherein 0-1 representation of the secondary structure is used as the input to the convolutional neural network (CNN) with Transformer encoder. The second part uses the DNA shape feature matrix as the input to the CNN with Transformer encoder. The third part uses positional encoding feature matrices as the proposed input into a long short-term memory network with an attention mechanism. These three parts are concatenated through the flattened layer, and the final prediction result is the average of the five sub-regressors. Extensive benchmarking experiments indicated that DeepMEns achieved the highest Spearman correlation coefficient for 6 of 10 independent test datasets as compared to previous predictors, this finding confirmed that DeepMEns can accomplish state-of-the-art performance. Moreover, the ablation analysis also indicated that the ensemble strategy may improve the performance of the prediction model.

CRISPRoffT: comprehensive database of CRISPR/Cas off-targets

The CRISPR (clustered regularly interspaced short palindromic repeats)/Cas (CRISPR-associated protein) programmable nuclease system continues to evolve, with in vivo therapeutic gene editing increasingly applied in clinical settings. However, off-target effects remain a significant challenge, hindering its broader clinical application. To enhance the development of gene-editing therapies and the accuracy of prediction algorithms, we developed CRISPRoffT (https://ccsm.uth.edu/CRISPRoffT/). Users can access a comprehensive repository of off-target regions predicted and validated by a diverse range of technologies across various cell lines, Cas enzyme variants, engineered sgRNAs (single guide RNAs) and CRISPR editing systems. CRISPRoffT integrates results of off-target analysis from 74 studies, encompassing 29 experimental prediction techniques, 368 guide sequences, 226 164 potential guide and off-target pairs and 8840 validated off-targets. CRISPRoffT features off-target data from different CRISPR approaches (knockout, base editing and prime editing) applied under diverse experimental conditions, including 85 different Cas/guide RNA (gRNA) combinations used across 34 different human and mouse cell lines. CRISPRoffT provides results of comparative analyses for individual guide sequences, genes, cell types, techniques and Cas/gRNA combinations under different conditions. CRISPRoffT is a unique resource providing valuable insights that facilitate the safety-driven design of CRISPR-based therapeutics, inform experimental design, advance the development of computational off-target prediction algorithms and guide RNA design algorithms.

CRISPRepi: a multi-omic atlas for CRISPR-based epigenome editing

CRISPR-based epigenome editing integrates the precision of CRISPR with the capability of epigenetic mark rewriting, offering a tunable and reversible gene regulation strategy without altering the DNA sequences. Various epigenome editing systems have been developed and applied in different organisms and cell types; however, the detailed information is discrete, making it challenging to evaluate the precision of different editing systems and design the optimal sgRNAs for further functional studies. Herein, we developed CRISPRepi (http://crisprepi.maolab.org/ or http://crisprepi.lilab-pkuhsc.org/), a pioneering platform that consolidates extensive sequencing data from 671 meticulously curated RNA-seq, ChIP-seq, Bisulfite-seq and ATAC-seq datasets in 87 cell types manipulated by 74 epigenome editing systems. In total, we have curated 5962 sgRNAs associated with 283 target genes from 2277 samples across six species. CRISPRepi incorporates tools for analyzing editing outcomes and assessing off-target effects by analyzing gene expression changes pre- and post-editing, along with the details of multi-omic epigenetic landscapes. Moreover, CRISPRepi supports the investigation of editing potentials for newly designed sgRNA sequences in a cell/tissue-specific context. By providing a user-friendly interface for searching and selecting optimal editing designs across multiple organisms, CRISPRepi serves as an integrated resource for researchers to evaluate editing efficiency and off-target effects among diverse CRISPR-based epigenome editing systems.

Predicting CRISPR-Cas9 off-target effects in human primary cells using bidirectional LSTM with BERT embedding

Motivation

Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)-Cas9 system is a ground-breaking genome editing tool, which has revolutionized cell and gene therapies. One of the essential components involved in this system that ensures its success is the design of an optimal single-guide RNA (sgRNA) with high on-target cleavage efficiency and low off-target effects. This is challenging as many conditions need to be considered, and empirically testing every design is time-consuming and costly. In silico prediction using machine learning models provides high-performance alternatives.

Results

We present CrisprBERT, a deep learning model incorporating a Bidirectional Encoder Representations from Transformers (BERT) architecture to provide a high-dimensional embedding for paired sgRNA and DNA sequences and Bidirectional Long Short-term Memory networks for learning, to predict the off-target effects of sgRNAs utilizing only the sgRNAs and their paired DNA sequences. We proposed doublet stack encoding to capture the local energy configuration of the Cas9 binding and applied the BERT model to learn the contextual embedding of the doublet pairs. Our results showed that the new model achieved better performance than state-of-the-art deep learning models regarding single split and leave-one-sgRNA-out cross-validations as well as independent testing.

Availability and implementation

The CrisprBERT is available at GitHub: https://github.com/OSsari/CrisprBERT.

A tool for CRISPR-Cas9 sgRNA evaluation based on computational models of gene expression

BACKGROUND

CRISPR is widely used to silence genes by inducing mutations expected to nullify their expression. While numerous computational tools have been developed to design single-guide RNAs (sgRNAs) with high cutting efficiency and minimal off-target effects, only a few tools focus specifically on predicting gene knockouts following CRISPR. These tools consider factors like conservation, amino acid composition, and frameshift likelihood. However, they neglect the impact of CRISPR on gene expression, which can dramatically affect the success of CRISPR-induced gene silencing attempts. Furthermore, information regarding gene expression can be useful even when the objective is not to silence a gene. Therefore, a tool that considers gene expression when predicting CRISPR outcomes is lacking.

RESULTS

We developed EXPosition, the first computational tool that combines models predicting gene knockouts after CRISPR with models that forecast gene expression, offering more accurate predictions of gene knockout outcomes. EXPosition leverages deep-learning models to predict key steps in gene expression: transcription, splicing, and translation initiation. We showed our tool performs better at predicting gene knockout than existing tools across 6 datasets, 4 cell types and ~207k sgRNAs. We also validated our gene expression models using the ClinVar dataset by showing enrichment of pathogenic mutations in high-scoring mutations according to our models.

CONCLUSIONS

We believe EXPosition will enhance both the efficiency and accuracy of genome editing projects, by directly predicting CRISPR's effect on various aspects of gene expression. EXPosition is available at http://www.cs.tau.ac.il/~tamirtul/EXPosition . The source code is available at https://github.com/shaicoh3n/EXPosition .

Structure-optimized sgRNA selection with PlatinumCRISPr for efficient Cas9 generation of knockouts

A single guide RNA (sgRNA) directs Cas9 nuclease for gene-specific scission of double-stranded DNA. High Cas9 activity is essential for efficient gene editing to generate gene deletions and gene replacements by homologous recombination. However, cleavage efficiency is below 50% for more than half of randomly selected sgRNA sequences in human cell culture screens or model organisms. We used in vitro assays to determine intrinsic molecular parameters for maximal sgRNA activity including correct folding of sgRNAs and Cas9 structural information. From the comparison of over 10 data sets, we find major constraints in sgRNA design originating from defective secondary structure of the sgRNA, sequence context of the seed region, GC context, and detrimental motifs, but we also find considerable variation among different prediction tools when applied to different data sets. To aid selection of efficient sgRNAs, we developed web-based PlatinumCRISPr, an sgRNA design tool to evaluate base-pairing and sequence composition parameters for optimal design of highly efficient sgRNAs for Cas9 genome editing. We applied this tool to select sgRNAs to efficiently generate gene deletions in Drosophila Ythdc1 and Ythdf, that bind to N 6 methylated adenosines (m6A) in mRNA. However, we discovered that generating small deletions with sgRNAs and Cas9 leads to ectopic reinsertion of the deleted DNA fragment elsewhere in the genome. These insertions can be removed by standard genetic recombination and chromosome exchange. These new insights into sgRNA design and the mechanisms of CRISPR-Cas9 genome editing advance the efficient use of this technique for safer applications in humans.

State of the art CRISPR-based strategies for cancer diagnostics and treatment

Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR) technology is a groundbreaking and dynamic molecular tool for DNA and RNA "surgery". CRISPR/Cas9 is the most widely applied system in oncology research. It is a major advancement in genome manipulation due to its precision, efficiency, scalability and versatility compared to previous gene editing methods. It has shown great potential not only in the targeting of oncogenes or genes coding for immune checkpoint molecules, and in engineering T cells, but also in targeting epigenomic disturbances, which contribute to cancer development and progression. It has proven useful for detecting genetic mutations, enabling the large-scale screening of genes involved in tumor onset, progression and drug resistance, and in speeding up the development of highly targeted therapies tailored to the genetic and immunological profiles of the patient's tumor. Furthermore, the recently discovered Cas12 and Cas13 systems have expanded Cas9-based editing applications, providing new opportunities in the diagnosis and treatment of cancer. In addition to traditional cis-cleavage, they exhibit trans-cleavage activity, which enables their use as sensitive and specific diagnostic tools. Diagnostic platforms like DETECTR, which employs the Cas12 enzyme, that cuts single-stranded DNA reporters, and SHERLOCK, which uses Cas12, or Cas13, that specifically target and cleave single-stranded RNA, can be exploited to speed up and advance oncological diagnostics. Overall, CRISPR platform has the great potential to improve molecular diagnostics and the functionality and safety of engineered cellular medicines. Here, we will emphasize the potentially transformative impact of CRISPR technology in the field of oncology compared to traditional treatments, diagnostic and prognostic approaches, and highlight the opportunities and challenges raised by using the newly introduced CRISPR-based systems for cancer diagnosis and therapy.

AI-empowered visualization of nucleic acid testing

AIMS

The visualization of nucleic acid testing (NAT) results plays a critical role in diagnosing and monitoring infectious and genetic diseases. The review aims to review the current status of AI-based NAT result visualization. It systematically introduces commonly used AI-based methods and techniques for NAT, emphasizing the importance of result visualization for accessible, clear, and rapid interpretation. This highlights the importance of developing a NAT visualization platform that is user-friendly and efficient, setting a clear direction for future advancements in making nucleic acid testing more accessible and effective for everyday applications.

METHOD

This review explores both the commonly used NAT methods and AI-based techniques for NAT result visualization. The focus then shifts to AI-based methodologies, such as color detection and result interpretation through AI algorithms. The article presents the advantages and disadvantages of these techniques, while also comparing the performance of various NAT platforms in different experimental contexts. Furthermore, it explores the role of AI in enhancing the accuracy, speed, and user accessibility of NAT results, highlighting visualization technologies adapted from other fields of experimentation.

SIGNIFICANCE

This review offers valuable insights for researchers and everyday users, aiming to develop effective visualization platforms for NAT, ultimately enhancing disease diagnosis and monitoring.

Multiomics Research: Principles and Challenges in Integrated Analysis

Multiomics research is a transformative approach in the biological sciences that integrates data from genomics, transcriptomics, proteomics, metabolomics, and other omics technologies to provide a comprehensive understanding of biological systems. This review elucidates the fundamental principles of multiomics, emphasizing the necessity of data integration to uncover the complex interactions and regulatory mechanisms underlying various biological processes. We explore the latest advances in computational methodologies, including deep learning, graph neural networks (GNNs), and generative adversarial networks (GANs), which facilitate the effective synthesis and interpretation of multiomics data. Additionally, this review addresses the critical challenges in this field, such as data heterogeneity, scalability, and the need for robust, interpretable models. We highlight the potential of large language models to enhance multiomics analysis through automated feature extraction, natural language generation, and knowledge integration. Despite the important promise of multiomics, the review acknowledges the substantial computational resources required and the complexity of model tuning, underscoring the need for ongoing innovation and collaboration in the field. This comprehensive analysis aims to guide researchers in navigating the principles and challenges of multiomics research to foster advances in integrative biological analysis.

CRISPR-powered RNA sensing in vivo

RNA sensing in vivo evaluates past or ongoing endogenous RNA disturbances, which is crucial for identifying cell types and states and diagnosing diseases. Recently, the CRISPR-driven genetic circuits have offered promising solutions to burgeoning challenges in RNA sensing. This review delves into the cutting-edge developments of CRISPR-powered RNA sensors in vivo, reclassifying these RNA sensors into four categories based on their working mechanisms, including programmable reassembly of split single-guide RNA (sgRNA), RNA-triggered RNA processing and protein cleavage, miRNA-triggered RNA interference (RNAi), and strand displacement reactions. Then, we discuss the advantages and challenges of existing methodologies in diverse application scenarios and anticipate and analyze obstacles and opportunities in forthcoming practical implementations.

The interplay of DNA repair context with target sequence predictably biases Cas9-generated mutations

Repair of double-stranded breaks generated by CRISPR/Cas9 is highly dependent on the flanking DNA sequence. To learn about interactions between DNA repair and target sequence, we measure frequencies of over 236,000 distinct Cas9-generated mutational outcomes at over 2800 synthetic target sequences in 18 DNA repair deficient mouse embryonic stem cells lines. We classify the outcomes in an unbiased way, finding a specialised role for Prkdc (DNA-PKcs protein) and Polm in creating 1 bp insertions matching the nucleotide on the protospacer-adjacent motif side of the break, a variable involvement of Nbn and Polq in the creation of different deletion outcomes, and uni-directional deletions dependent on both end-protection and end-resection. Using our dataset, we build predictive models of the mutagenic outcomes of Cas9 scission that outperform the current standards. This work improves our understanding of DNA repair gene function, and provides avenues for more precise modulation of Cas9-generated mutations.

Optimizing CRISPR/Cas9 precision: Mitigating off-target effects for safe integration with photodynamic and stem cell therapies in cancer treatment

CRISPR/Cas9 precision genome editing has revolutionized cancer treatment by introducing specific alterations to the cancer genome. But the therapeutic potential of CRISPR/Cas9 is limited by off-target effects, which can cause undesired changes to genomic regions and create major safety concerns. The primary emphasis lies in their implications within the realm of cancer photodynamic therapy (PDT), where precision is paramount. PDT is a promising cancer treatment method; nevertheless, its effectiveness is severely limited and readily leads to recurrence due to the therapeutic resistance of cancer stem cells (CSCs). With a focus on targeted genome editing into cancer cells during PDT and stem cell treatment (SCT), the review aims to further the ongoing search for safer and more accurate CRISPR/Cas9-mediated methods. At the core of this exploration are recent advancements and novel techniques that offer promise in mitigating the risks associated with off-target effects. With a focus on cancer PDT and SCT, this review critically assesses the landscape of off-target effects in CRISPR/Cas9 applications, offering a comprehensive knowledge of their nature and prevalence. A key component of the review is the assessment of cutting-edge delivery methods, such as technologies based on nanoparticles (NPs), to optimize the distribution of CRISPR components. Additionally, the study delves into the intricacies of guide RNA design, focusing on advancements that bolster specificity and minimize off-target effects, crucial elements in ensuring the precision required for effective cancer PDT and SCT. By synthesizing insights from various methodologies, including the exploration of innovative genome editing tools and leveraging robust validation methods and bioinformatics tools, the review aspires to chart a course towards more reliable and precise CRISPR-Cas9 applications in cancer PDT and SCT. For safe PDT and SCT integration in cancer therapy, CRISPR/Cas9 precision optimization is essential. Utilizing sophisticated molecular and computational techniques to address off-target effects is crucial to realizing the therapeutic promise of these technologies, which will ultimately lead to the development of individualized and successful cancer treatment strategies. Our long-term goals are to improve precision genome editing for more potent cancer therapy approaches by refining the way CRISPR/Cas9 is integrated with photodynamic and stem cell therapies.

The transformative potential of AI-driven CRISPR-Cas9 genome editing to enhance CAR T-cell therapy

This narrative review examines the promising potential of integrating artificial intelligence (AI) with CRISPR-Cas9 genome editing to advance CAR T-cell therapy. AI algorithms offer unparalleled precision in identifying genetic targets, essential for enhancing the therapeutic efficacy of CAR T-cell treatments. This precision is critical for eliminating negative regulatory elements that undermine therapy effectiveness. Additionally, AI streamlines the manufacturing process, significantly reducing costs and increasing accessibility, thereby encouraging further research and development investment. A key benefit of AI integration is improved safety; by predicting and minimizing off-target effects, AI enhances the specificity of CRISPR-Cas9 edits, contributing to safer CAR T-cell therapy. This advancement is crucial for patient safety and broader clinical adoption. The convergence of AI and CRISPR-Cas9 has transformative potential, poised to revolutionize personalized immunotherapy. These innovations could expand the application of CAR T-cell therapy beyond hematologic malignancies to various solid tumors and other non-hematologic conditions, heralding a new era in cancer treatment that substantially improves patient outcomes.

Integrating Genomic Data with the Development of CRISPR-Based Point-of-Care-Testing for Bacterial Infections

Purpose of Review

Bacterial infections and antibiotic resistance contribute to global mortality. Despite many infections being preventable and treatable, the lack of reliable and accessible diagnostic tools exacerbates these issues. CRISPR (Clustered Regularly Interspaced Short Palindromic Repeats)-based diagnostics has emerged as a promising solution. However, the development of CRISPR diagnostics has often occurred in isolation, with limited integration of genomic data to guide target selection. In this review, we explore the synergy between bacterial genomics and CRISPR-based point-of-care tests (POCT), highlighting how genomic insights can inform target selection and enhance diagnostic accuracy.

Recent Findings

We review recent advances in CRISPR-based technologies, focusing on the critical role of target sequence selection in improving the sensitivity of CRISPR-based diagnostics. Additionally, we examine the implementation of these technologies in resource-limited settings across Asia and Africa, presenting successful case studies that demonstrate their potential.

Summary

The integration of bacterial genomics with CRISPR technology offers significant promise for the development of effective point-of-care diagnostics.

Learning to quantify uncertainty in off-target activity for CRISPR guide RNAs

CRISPR-based genome editing technologies have revolutionised the field of molecular biology, offering unprecedented opportunities for precise genetic manipulation. However, off-target effects remain a significant challenge, potentially leading to unintended consequences and limiting the applicability of CRISPR-based genome editing technologies in clinical settings. Current literature predominantly focuses on point predictions for off-target activity, which may not fully capture the range of possible outcomes and associated risks. Here, we present crispAI, a neural network architecture-based approach for predicting uncertainty estimates for off-target cleavage activity, providing a more comprehensive risk assessment and facilitating improved decision-making in single guide RNA (sgRNA) design. Our approach makes use of the count noise model Zero Inflated Negative Binomial (ZINB) to model the uncertainty in the off-target cleavage activity data. In addition, we present the first-of-its-kind genome-wide sgRNA efficiency score, crispAI-aggregate, enabling prioritization among sgRNAs with similar point aggregate predictions by providing richer information compared to existing aggregate scores. We show that uncertainty estimates of our approach are calibrated and its predictive performance is superior to the state-of-the-art in silico off-target cleavage activity prediction methods. The tool and the trained models are available at https://github.com/furkanozdenn/crispr-offtarget-uncertainty.

Crispr-SGRU: Prediction of CRISPR/Cas9 Off-Target Activities with Mismatches and Indels Using Stacked BiGRU

CRISPR/Cas9 is a popular genome editing technology, yet its clinical application is hindered by off-target effects. Many deep learning-based methods are available for off-target prediction. However, few can predict off-target activities with insertions or deletions (indels) between single guide RNA and DNA sequence pairs. Additionally, the analysis of off-target data is challenged due to a data imbalance issue. Moreover, the prediction accuracy and interpretability remain to be improved. Here, we introduce a deep learning-based framework, named Crispr-SGRU, to predict off-target activities with mismatches and indels. This model is based on Inception and stacked BiGRU. It adopts a dice loss function to solve the inherent imbalance issue. Experimental results show our model outperforms existing methods for off-target prediction in terms of accuracy and robustness. Finally, we study the interpretability of this model through Deep SHAP and teacher-student-based knowledge distillation, and find it can provide meaningful explanations for sequence patterns regarding off-target activity.

Compartmentalized CRISPR Reactions (CCR) for High-Throughput Screening of Guide RNA Potency and Specificity

CRISPR ribonucleoproteins (RNPs) use a variable segment in their guide RNA (gRNA) called a spacer to determine the DNA sequence at which the effector protein will exhibit nuclease activity and generate target-specific genetic mutations. However, nuclease activity with different gRNAs can vary considerably in a spacer sequence-dependent manner that can be difficult to predict. While computational tools are helpful in predicting a CRISPR effector's activity and/or potential for off-target mutagenesis with different gRNAs, individual gRNAs must still be validated in vitro prior to their use. Here, the study presents compartmentalized CRISPR reactions (CCR) for screening large numbers of spacer/target/off-target combinations simultaneously in vitro for both CRISPR effector activity and specificity by confining the complete CRISPR reaction of gRNA transcription, RNP formation, and CRISPR target cleavage within individual water-in-oil microemulsions. With CCR, large numbers of the candidate gRNAs (output by computational design tools) can be immediately validated in parallel, and the study shows that CCR can be used to screen hundreds of thousands of extended gRNA (x-gRNAs) variants that can completely block cleavage at off-target sequences while maintaining high levels of on-target activity. It is expected that CCR can help to streamline the gRNA generation and validation processes for applications in biological and biomedical research.

Artificial intelligence and machine learning applications for cultured meat

Cultured meat has the potential to provide a complementary meat industry with reduced environmental, ethical, and health impacts. However, major technological challenges remain which require time-and resource-intensive research and development efforts. Machine learning has the potential to accelerate cultured meat technology by streamlining experiments, predicting optimal results, and reducing experimentation time and resources. However, the use of machine learning in cultured meat is in its infancy. This review covers the work available to date on the use of machine learning in cultured meat and explores future possibilities. We address four major areas of cultured meat research and development: establishing cell lines, cell culture media design, microscopy and image analysis, and bioprocessing and food processing optimization. In addition, we have included a survey of datasets relevant to CM research. This review aims to provide the foundation necessary for both cultured meat and machine learning scientists to identify research opportunities at the intersection between cultured meat and machine learning.

The interplay of DNA repair context with target sequence predictably biases Cas9-generated mutations

Mutagenic outcomes of CRISPR/Cas9-generated double-stranded breaks depend on both the sequence flanking the cut and cellular DNA damage repair. The interaction of these features has been largely unexplored, limiting our ability to understand and manipulate the outcomes. Here, we measured how the absence of 18 repair genes changed frequencies of 83,680 unique mutational outcomes generated by Cas9 double-stranded breaks at 2,838 synthetic target sequences in mouse embryonic stem cells. This large scale survey allowed us to classify the outcomes in an unbiased way, generating hypotheses about new modes of double-stranded break repair. Our data indicate a specialised role for Prkdc (DNA-PKcs protein) and Polm (Polμ) in creating 1bp insertions that match the nucleotide on the proximal side of the Cas9 cut with respect to the protospacer-adjacent motif (PAM), a variable involvement of Nbn (NBN) and Polq (Polθ) in the creation of different deletion outcomes, and a unique class of uni-directional deletion outcomes that are dependent on both end-protection gene Xrcc5 (Ku80) and the resection gene Nbn (NBN). We used the knowledge of the reproducible variation across repair milieus to build predictive models of the mutagenic outcomes of Cas9 scission that outperform the current standards. This work improves our understanding of DNA repair gene function, and provides avenues for more precise modulation of CRISPR/Cas9-generated mutations.

Codon usage and expression-based features significantly improve prediction of CRISPR efficiency

CRISPR is a precise and effective genome editing technology; but despite several advancements during the last decade, our ability to computationally design gRNAs remains limited. Most predictive models have relatively low predictive power and utilize only the sequence of the target site as input. Here we suggest a new category of features, which incorporate the target site genomic position and the presence of genes close to it. We calculate four features based on gene expression and codon usage bias indices. We show, on CRISPR datasets taken from 3 different cell types, that such features perform comparably with 425 state-of-the-art predictive features, ranking in the top 2-12% of features. We trained new predictive models, showing that adding expression features to them significantly improves their r2 by up to 0.04 (relative increase of 39%), achieving average correlations of up to 0.38 on their validation sets; and that these features are deemed important by different feature importance metrics. We believe that incorporating the target site's position, in addition to its sequence, in features such as we have generated here will improve our ability to predict, design and understand CRISPR experiments going forward.

PI3K/AKT confers intrinsic and acquired resistance to pirtobrutinib in chronic lymphocytic leukemia

PURPOSE

Pirtobrutinib, a non-covalent Bruton's tyrosine kinase (BTK) inhibitor, has been approved as the first agent to overcome resistance to covalent BTK inhibitors (such as ibrutinib, acalabrutinib, and zanubrutinib). However, the mechanisms of pirtobrutinib resistance in chronic lymphocytic leukemia (CLL) remain poorly understood.

METHODS

To investigate pirtobrutinib resistance, we established resistant cell models using BTK knock-out via CRISPR-Cas9 or chronic exposure to pirtobrutinib in MEC-1 cells. These models mimicked intrinsic or acquired resistance, respectively. We then analyzed differential protein expression between wild-type (WT) and resistant MEC-1 cells using Revers Phase Protein microArray (RPPA) and confirmed the findings through Western Blot. Additionally, we evaluated potential drugs to overcome pirtobrutinib resistance by conducting cell proliferation assays, apoptosis studies, and animal experiments using both sensitive and resistant cells.

RESULTS

MEC-1 cells developed resistance to pirtobrutinib either through BTK knock-out or prolonged drug exposure over three months. RPPA analysis revealed significant activation of proteins related to the PI3K/AKT pathway, including AKT and S6, in the resistant cells. Western Blot confirmed increased phosphorylation of AKT and S6 in pirtobrutinib-resistant MEC-1 cells. Notably, both the PI3K inhibitor (CAL101) and the AKT inhibitor (MK2206) effectively reduced cell proliferation and induced apoptosis in the resistant cells. The anti-tumor efficacy of these drugs was mediated by inhibiting the PI3K/AKT pathway. In vivo animal studies further supported the potential of targeting PI3K/AKT to overcome both intrinsic and acquired resistance to pirtobrutinib.

CONCLUSION

The PI3K/AKT pathway plays a crucial role in both intrinsic and acquired resistance to pirtobrutinib in CLL. Therapeutically targeting this pathway may offer a promising strategy to overcome pirtobrutinib resistance.

Gene Therapies in Clinical Development to Treat Retinal Disorders

Gene therapies have emerged as promising treatments in clinical development for various retinal disorders, offering hope to patients with inherited degenerative eye conditions. Several gene therapies have already shown remarkable success in clinical trials, with significant improvements observed in visual acuity and the preservation of retinal function. A multitude of gene therapies have now been delivered safely in human clinical trials for a wide range of inherited retinal disorders but there are some gaps in the reported trial data. Some of the most exciting treatment options are not under peer review and information is only available in press release form. Whilst many trials appear to have delivered good outcomes of safety, others have failed to meet primary endpoints and therefore not proceeded to phase III. Despite this, such trials have enabled researchers to learn how best to assess and monitor patient outcomes, which will guide future trials to greater success. In this review, we consider recent and ongoing clinical trials for a variety of potential retinal gene therapy treatments and discuss the positive and negative issues related to these trials. We discuss the treatment potential following clinical trials as well as the potential risks of some treatments under investigation. As these therapies continue to advance through rigorous testing and regulatory approval processes, they hold the potential to revolutionise the landscape of retinal disorder treatments, providing renewed vision and enhancing the quality of life for countless individuals worldwide.

Overcoming CRISPR-Cas9 off-target prediction hurdles: A novel approach with ESB rebalancing strategy and CRISPR-MCA model

The off-target activities within the CRISPR-Cas9 system remains a formidable barrier to its broader application and development. Recent advancements have highlighted the potential of deep learning models in predicting these off-target effects, yet they encounter significant hurdles including imbalances within datasets and the intricacies associated with encoding schemes and model architectures. To surmount these challenges, our study innovatively introduces an Efficiency and Specificity-Based (ESB) class rebalancing strategy, specifically devised for datasets featuring mismatches-only off-target instances, marking a pioneering approach in this realm. Furthermore, through a meticulous evaluation of various One-hot encoding schemes alongside numerous hybrid neural network models, we discern that encoding and models of moderate complexity ideally balance performance and efficiency. On this foundation, we advance a novel hybrid model, the CRISPR-MCA, which capitalizes on multi-feature extraction to enhance predictive accuracy. The empirical results affirm that the ESB class rebalancing strategy surpasses five conventional methods in addressing extreme dataset imbalances, demonstrating superior efficacy and broader applicability across diverse models. Notably, the CRISPR-MCA model excels in off-target effect prediction across four distinct mismatches-only datasets and significantly outperforms contemporary state-of-the-art models in datasets comprising both mismatches and indels. In summation, the CRISPR-MCA model, coupled with the ESB rebalancing strategy, offers profound insights and a robust framework for future explorations in this field.

The impact and future of artificial intelligence in medical genetics and molecular medicine: an ongoing revolution

Artificial intelligence (AI) platforms have emerged as pivotal tools in genetics and molecular medicine, as in many other fields. The growth in patient data, identification of new diseases and phenotypes, discovery of new intracellular pathways, availability of greater sets of omics data, and the need to continuously analyse them have led to the development of new AI platforms. AI continues to weave its way into the fabric of genetics with the potential to unlock new discoveries and enhance patient care. This technology is setting the stage for breakthroughs across various domains, including dysmorphology, rare hereditary diseases, cancers, clinical microbiomics, the investigation of zoonotic diseases, omics studies in all medical disciplines. AI's role in facilitating a deeper understanding of these areas heralds a new era of personalised medicine, where treatments and diagnoses are tailored to the individual's molecular features, offering a more precise approach to combating genetic or acquired disorders. The significance of these AI platforms is growing as they assist healthcare professionals in the diagnostic and treatment processes, marking a pivotal shift towards more informed, efficient, and effective medical practice. In this review, we will explore the range of AI tools available and show how they have become vital in various sectors of genomic research supporting clinical decisions.

DeepCRISTL: deep transfer learning to predict CRISPR/Cas9 on-target editing efficiency in specific cellular contexts

MOTIVATION

CRISPR/Cas9 technology has been revolutionizing the field of gene editing. Guide RNAs (gRNAs) enable Cas9 proteins to target specific genomic loci for editing. However, editing efficiency varies between gRNAs and so computational methods were developed to predict editing efficiency for any gRNA of interest. High-throughput datasets of Cas9 editing efficiencies were produced to train machine-learning models to predict editing efficiency. However, these high-throughput datasets have a low correlation with functional and endogenous datasets, which are too small to train accurate machine-learning models on.

RESULTS

We developed DeepCRISTL, a deep-learning model to predict the editing efficiency in a specific cellular context. DeepCRISTL takes advantage of high-throughput datasets to learn general patterns of gRNA editing efficiency and then fine-tunes the model on functional or endogenous data to fit a specific cellular context. We tested two state-of-the-art models trained on high-throughput datasets for editing efficiency prediction, our newly improved DeepHF and CRISPRon, combined with various transfer-learning approaches. The combination of CRISPRon and fine-tuning all model weights was the overall best performer. DeepCRISTL outperformed state-of-the-art methods in predicting editing efficiency in a specific cellular context on functional and endogenous datasets. Using saliency maps, we identified and compared the important features learned by DeepCRISTL across cellular contexts. We believe DeepCRISTL will improve prediction performance in many other CRISPR/Cas9 editing contexts by leveraging transfer learning to utilize both high-throughput datasets and smaller and more biologically relevant datasets.

AVAILABILITY AND IMPLEMENTATION

DeepCRISTL is available via https://github.com/OrensteinLab/DeepCRISTL.

A systematic method for solving data imbalance in CRISPR off-target prediction tasks

Accurately identifying potential off-target sites in the CRISPR/Cas9 system is crucial for improving the efficiency and safety of editing. However, the imbalance of available off-target datasets has posed a major obstacle in enhancing prediction performance. Despite several prediction models have been developed to address this issue, there remains a lack of systematic research on handling data imbalance in off-target prediction. This article systematically investigates the data imbalance issue in off-target datasets and explores numerous methods to process data imbalance from a novel perspective. First, we highlight the impact of the imbalance problem on off-target prediction tasks by determining the imbalance ratios present in these datasets. Then, we provide a comprehensive review of various sampling techniques and cost-sensitive methods to mitigate class imbalance in off-target datasets. Finally, systematic experiments are conducted on several state-of-the-art prediction models to illustrate the impact of applying data imbalance solutions. The results show that class imbalance processing methods significantly improve the off-target prediction capabilities of the models across multiple testing datasets. The code and datasets used in this study are available at https://github.com/gzrgzx/CRISPR_Data_Imbalance.

Generating, modeling and evaluating a large-scale set of CRISPR/Cas9 off-target sites with bulges

The CRISPR/Cas9 system is a highly accurate gene-editing technique, but it can also lead to unintended off-target sites (OTS). Consequently, many high-throughput assays have been developed to measure OTS in a genome-wide manner, and their data was used to train machine-learning models to predict OTS. However, these models are inaccurate when considering OTS with bulges due to limited data compared to OTS without bulges. Recently, CHANGE-seq, a new in vitro technique to detect OTS, was used to produce a dataset of unprecedented scale and quality. In addition, the same study produced in cellula GUIDE-seq experiments, but none of these GUIDE-seq experiments included bulges. Here, we generated the most comprehensive GUIDE-seq dataset with bulges, and trained and evaluated state-of-the-art machine-learning models that consider OTS with bulges. We first reprocessed the publicly available experimental raw data of the CHANGE-seq study to generate 20 new GUIDE-seq experiments, and hundreds of OTS with bulges among the original and new GUIDE-seq experiments. We then trained multiple machine-learning models, and demonstrated their state-of-the-art performance both in vitro and in cellula over all OTS and when focusing on OTS with bulges. Last, we visualized the key features learned by our models on OTS with bulges in a unique representation.

A mechanistic study on the tolerance of PAM distal end mismatch by SpCas9

The therapeutic application of CRISPR-Cas9 is limited due to its off-target activity. To have a better understanding of this off-target effect, we focused on its mismatch-prone PAM distal end. The off-target activity of SpCas9 depends directly on the nature of mismatches, which in turn results in deviation of the active site of SpCas9 due to structural instability in the RNA-DNA duplex strand. In order to test the hypothesis, we designed an array of mismatched target sites at the PAM distal end and performed in vitro and cell line-based experiments, which showed a strong correlation for Cas9 activity. We found that target sites having multiple mismatches in the 18th to 15th position upstream of the PAM showed no to little activity. For further mechanistic validation, Molecular Dynamics simulations were performed, which revealed that certain mismatches showed elevated root mean square deviation values that can be attributed to conformational instability within the RNA-DNA duplex. Therefore, for successful prediction of the off-target effect of SpCas9, along with complementation-derived energy, the RNA-DNA duplex stability should be taken into account.

Foundation models in molecular biology

Determining correlations between molecules at various levels is an important topic in molecular biology. Large language models have demonstrated a remarkable ability to capture correlations from large amounts of data in the field of natural language processing as well as image generation, and correlations captured from data using large language models can also be applicable to solving a wide range of specific tasks, hence large language models are also referred to as foundation models. The massive amount of data that exists in the field of molecular biology provides an excellent basis for the development of foundation models, and the recent emergence of foundation models in the field of molecular biology has really pushed the entire field forward. We summarize the foundation models developed based on RNA sequence data, DNA sequence data, protein sequence data, single-cell transcriptome data, and spatial transcriptome data respectively, and further discuss the research directions for the development of foundation models in molecular biology.

Big data and deep learning for RNA biology

The exponential growth of big data in RNA biology (RB) has led to the development of deep learning (DL) models that have driven crucial discoveries. As constantly evidenced by DL studies in other fields, the successful implementation of DL in RB depends heavily on the effective utilization of large-scale datasets from public databases. In achieving this goal, data encoding methods, learning algorithms, and techniques that align well with biological domain knowledge have played pivotal roles. In this review, we provide guiding principles for applying these DL concepts to various problems in RB by demonstrating successful examples and associated methodologies. We also discuss the remaining challenges in developing DL models for RB and suggest strategies to overcome these challenges. Overall, this review aims to illuminate the compelling potential of DL for RB and ways to apply this powerful technology to investigate the intriguing biology of RNA more effectively.