The clustered regularly interspaced short palindromic repeat (CRISPR)/CRISPR-associated protein 9 (Cas9) system has become a successful and promising technology for gene-editing. To facilitate its effective application, various computational tools have been developed. These tools can assist researchers in the guide RNA (gRNA) design process by predicting cleavage efficiency and specificity and excluding undesirable targets. However, while many tools are available, assessment of their application scenarios and performance benchmarks are limited. Moreover, new deep learning tools have been explored lately for gRNA efficiency prediction, but have not been systematically evaluated. Here, we discuss the approaches that pertain to the on-target activity problem, focusing mainly on the features and computational methods they utilize. Furthermore, we evaluate these tools on independent datasets and give some suggestions for their usage. We conclude with some challenges and perspectives about future directions for CRISPR–Cas9 guide design.
The development of the CRISPR-Cas9 technology has provided a simple yet powerful system for genome editing. Current gRNA design tools serve as an important platform for the efficient application of the CRISPR systems. However, most of the existing tools are black-box models that suffer from limitations, such as variable performance and unclear mechanism of decision making. Here, we introduce CRISPRedict, an interpretable gRNA efficiency prediction model for CRISPR-Cas9 gene editing. Its strength lies in the fact that it can accurately predict efficient guide RNAs—with equivalent performance to state-of-the-art tools—while being a simple linear model. Implemented as a user-friendly web server, CRISPRedict offers (i) quick and accurate predictions across various experimental conditions (e.g. U6/T7 transcription); (ii) regression and classification models for scoring gRNAs and (iii) multiple visualizations to explain the obtained results. Given its performance, interpretability, and versatility, we expect that it will assist researchers in the gRNA design process and facilitate genome editing research. CRISPRedict is available for use at http://www.crispredict.org/.
Transcriptional enhancers are the genomic elements that contain critical information for the regulation of gene expression. This information is encoded through precisely arranged transcription factor-binding sites. Genomic sequence-to-function models, computational models that take DNA sequences as input and predict gene regulatory features, have become essential for unravelling the complex combinatorial rules that govern cell-type-specific activities of enhancers. These models function as biological ‘oracles’, capable of accurately predicting the activity of novel DNA sequences. By leveraging these oracles, DNA sequences can be optimized towards designed synthetic enhancers with tailored cell-type-specific or cell-state-specific activities. In parallel, generative artificial intelligence is rapidly advancing in genomics and enhancer design. Synthetic enhancers hold great promise for a wide range of biomedical applications, from facilitating fundamental research to enabling gene therapies.
Sequence-based deep learning models have become the state of the art for analyzing the genomic regulatory code. Particularly for enhancers, these models excel at deciphering sequence grammar that underlies their activity. To enable end-to-end enhancer modeling and design, we developed a software package called CREsted ( cis -regulatory element sequence training, explanation and design). It combines preprocessing and analysis of single-cell assay for transposase-accessible chromatin using sequencing data, modeling chromatin accessibility from sequence, sequence design and downstream analysis to decipher enhancer grammar. We demonstrate CREsted’s functionality on a mouse cortex and a human peripheral blood mononuclear cell dataset. Additionally, we use CREsted to compare mesenchymal-like cancer cell states between tumor types, and we investigate different fine-tuning strategies of genomic foundation models within CREsted. Finally, we train a model on a zebrafish development atlas and use this to design and in vivo validate cell-type-specific enhancers. For varying datasets, we demonstrate that CREsted facilitates efficient training and analyses, enabling scrutinization of the enhancer logic and design of synthetic enhancers across tissues and species.
Liquid chromatography-high resolution mass spectrometry (LC-HRMS) and gas chromatography-high resolution mass spectrometry (GC-HRMS) have revolutionized analytical chemistry among many other disciplines. These advanced instrumentations allow to theoretically capture the whole chemical universe that is contained in samples, giving unimaginable opportunities to the scientific community. Laboratories equipped with these instruments produce a lot of data daily that can be digitally archived. Digital storage of data opens up the opportunity for retrospective suspect screening investigations for the occurrence of chemicals in the stored chromatograms. The first step of this approach involves the prediction of which data is more appropriate to be searched. In this study, we built an optimized multi-label classifier for predicting the most appropriate instrumental method (LC-HRMS or GC-HRMS or both) for the analysis of chemicals in digital specimens. The approach involved the generation of a baseline model based on the knowledge that an expert would use and the generation of an optimized machine learning model. A multi-step feature selection approach, a model selection strategy, and optimization of the classifier’s hyperparameters led to a model with accuracy that outperformed the baseline implementation. The models were used to predict the most appropriate instrumental technique for new substances. The scripts are available at GitHub and the dataset at Zenodo.
Identifying cell-type-specific enhancers is critical for developing genetic tools to study the mammalian brain. We organized the "Brain Initiative Cell Census Network (BICCN) Challenge: Predicting Functional Cell Type-Specific Enhancers from Cross-Species Multi-Omics" to evaluate machine learning and feature-based methods for nominating enhancer sequences targeting mouse cortical cell types. Methods were assessed using in vivo data from hundreds of adeno-associated virus (AAV)-packaged, retro-orbitally delivered enhancers. Open chromatin was the strongest predictor of functional enhancers, while sequence models improved prediction of non-functional enhancers and identified cell-type-specific transcription factor codes to inform in silico enhancer design. This challenge establishes a benchmark for enhancer prioritization and highlights computational and molecular features critical for identifying functional cortical enhancers, advancing efforts to map and manipulate gene regulation in the mammalian cortex.