Predicting gene knockout effects from expression data

Abstract

Background The study of gene essentiality, which measures the importance of a gene for cell division and survival, is used for the identification of cancer drug targets and understanding of tissue-specific manifestation of genetic conditions. In this work, we analyze essentiality and gene expression data from over 900 cancer lines from the DepMap project to create predictive models of gene essentiality. Methods We developed machine learning algorithms to identify those genes whose essentiality levels are explained by the expression of a small set of “modifier genes”. To identify these gene sets, we developed an ensemble of statistical tests capturing linear and non-linear dependencies. We trained several regression models predicting the essentiality of each target gene, and used an automated model selection procedure to identify the optimal model and hyperparameters. Overall, we examined linear models, gradient boosted trees, Gaussian process regression models, and deep learning networks. Results We identified nearly 3000 genes for which we accurately predict essentiality using gene expression data of a small set of modifier genes. We show that both in the number of genes we successfully make predictions for, as well as in the prediction accuracy, our model outperforms current state-of-the-art works. Conclusions Our modeling framework avoids overfitting by identifying the small set of modifier genes, which are of clinical and genetic importance, and ignores the expression of noisy and irrelevant genes. Doing so improves the accuracy of essentiality prediction in various conditions and provides interpretable models. Overall, we present an accurate computational approach, as well as interpretable modeling of essentiality in a wide range of cellular conditions, thus contributing to a better understanding of the molecular mechanisms that govern tissue-specific effects of genetic disease and cancer.

Robust Evaluation of Deep Learning-based Representation Methods for Survival and Gene Essentiality Prediction on Bulk RNA-seq Data

“…To evaluate model performances, we used the Spearman rank correlation. While in the original DeepDEP paper Pearson correlation coefficients were computed, both methods are suited to evaluate this task (Rosenski, Shifman, et Kaplan 2023; Ma et al 2021). The Spearman correlation was preferred as it is more robust to outliers on non-normally distributed data (Hou et al 2022) and fits better the framework of ranking genes for target selection.…”

Refining computational inference of gene regulatory networks: integrating knockout data within a multi-task framework

“…Gene knockout prediction adds a critical perspective to our methodology, enabling researchers to predict how specific gene knockouts will influence the broader GRN. This task is instrumental in understanding the cascading effects of gene manipulation, as it reveals how knockouts in one gene can lead to changes in the expression of other genes[ 33 ]. By jointly optimizing these tasks, we gain a more comprehensive and holistic view of transcriptional regulation and gene knockouts within biological systems.…”

Flexynesis: A deep learning framework for bulk multi-omics data integration for precision oncology and beyond

“…The DepMap database contains measurements of cellular proliferation after perturbation of all protein coding genes. It has been previously shown that for a given cell line, the gene expression profiles of the cell lines can be used to predict the gene essentiality scores [26,27]. Here, we carried out a similar approach, where gene expression profiles of genes across cell lines were used as input with a goal to reconstruct the cancer cell line dependency scores of the same genes.…”