Motivation: Controlling the outcomes of CRISPR editing is crucial for the success of gene therapy. Since donor template-based editing is often inefficient, alternative strategies have emerged that leverage mutagenic end-joining repair instead. Existing machine learning models can accurately predict end-joining repair outcomes, however: generalisability beyond the specific cell line used for training remains a challenge, and interpretability is typically limited by suboptimal feature representation and model architecture. Results: We propose X-CRISP, a flexible and interpretable neural network for predicting repair outcome frequencies based on a minimal set of outcome and sequence features, including microhomologies (MH). Outperforming prior models on detailed and aggregate outcome predictions, X-CRISP prioritised MH location over MH sequence properties such as GC content for deletion outcomes. Through transfer learning, we adapted X-CRISP pre-trained on wild-type mESC data to target human cell lines K562, HAP1, U2OS, and mESC lines with altered DNA repair function. Adapted X-CRISP models improved over direct training on target data from as few as 50 samples, suggesting that this strategy could be leveraged to build models for new domains using a fraction of the data required to train models from scratch. Availability: An implementation of X-CRISP is available at https://github.com/joanagoncalveslab/xcrisp.@en

Motivation Understanding the factors involved in DNA double-strand break (DSB) repair is crucial for the development of targeted anti-cancer therapies, yet the roles of many genes remain unclear. Recent studies show that perturbations of certain genes can alter the distribution of sequence-specific mutations left behind after DSB repair. This suggests that genome-wide screening could reveal novel DSB repair factors by identifying genes whose perturbation causes the mutational distribution spectra observed at a given DSB site to deviate significantly from the wild-type. However, designing proper controls for a genome-wide perturbation screen could be challenging. We explore the idea that a genome-wide screen might allow us to forgo the use of traditional non-targeting controls by reframing the analysis as an outlier detection problem, assuming that most genes have minimal influence on DSB repair.

Results We propose MUSICiAn (Mutational Signature Catalogue Analysis), a compositional data analysis method that ranks gene perturbation-specific mutational spectra without controls by measuring deviations from the central tendency in the distributions of all spectra. We show that MUSICiAn can effectively estimate pseudo-controls for the existing Repair-seq dataset, screening 476 genes and 60 non-targeting controls. We further apply MUSICiAn to a genome-wide dataset profiling mutational outcomes induced by CRISPR-Cas9 at three target sites across cells with individual perturbations of 18,406 genes. MUSICiAn successfully recovers known genes, highlights the spliceosome as a lesser-appreciated player in DSB repair, and reveals candidates for further investigation.

Availability github.com/joanagoncalveslab/MUSICiAn.@en

Motivation

Anti-cancer therapies based on synthetic lethality (SL) exploit tumour vulnerabilities for treatment with reduced side effects, by targeting a gene that is jointly essential with another whose function is lost. Computational prediction is key to expedite SL screening, yet existing methods are vulnerable to prevalent selection bias in SL data and reliant on cancer or tissue type-specific omics, which can be scarce. Notably, sequence similarity remains underexplored as a proxy for related gene function and joint essentiality.
Results

We propose ELISL, Early–Late Integrated SL prediction with forest ensembles, using context-free protein sequence embeddings and context-specific omics from cell lines and tissue. Across eight cancer types, ELISL showed superior robustness to selection bias and recovery of known SL genes, as well as promising cross-cancer predictions. Co-occurring mutations in a BRCA gene and ELISL-predicted pairs from the HH, FGF, WNT, or NEIL gene families were associated with longer patient survival times, revealing therapeutic potential.@en

Motivation
Synthetic lethality (SL) between two genes occurs when simultaneous loss of function leads to cell death. This holds great promise for developing anti-cancer therapeutics that target synthetic lethal pairs of endogenously disrupted genes. Identifying novel SL relationships through exhaustive experimental screens is challenging, due to the vast number of candidate pairs. Computational SL prediction is therefore sought to identify promising SL gene pairs for further experimentation. However, current SL prediction methods lack consideration for generalizability in the presence of selection bias in SL data.
Results
We show that SL data exhibit considerable gene selection bias. Our experiments designed to assess the robustness of SL prediction reveal that models driven by the topology of known SL interactions (e.g. graph, matrix factorization) are especially sensitive to selection bias. We introduce selection bias-resilient synthetic lethality (SBSL) prediction using regularized logistic regression or random forests. Each gene pair is described by 27 molecular features derived from cancer cell line, cancer patient tissue and healthy donor tissue samples. SBSL models are built and tested using approximately 8000 experimentally derived SL pairs across breast, colon, lung and ovarian cancers. Compared to other SL prediction methods, SBSL showed higher predictive performance, better generalizability and robustness to selection bias. Gene dependency, quantifying the essentiality of a gene for cell survival, contributed most to SBSL predictions. Random forests were superior to linear models in the absence of dependency features, highlighting the relevance of mutual exclusivity of somatic mutations, co-expression in healthy tissue and differential expression in tumour samples.
Availability and implementation
https://github.com/joanagoncalveslab/sbsl
Supplementary information
Supplementary data are available at Bioinformatics online.@en