Kebabci, N. | bioRxiv Science

bioRxiv2026

A predicted cancer dependency map for paralog pairs

BackgroundGenome-wide CRISPR screening has enabled the development of dependency maps in hundreds of cancer cell lines, facilitating the identification of genetic vulnerabilities associated with specific biomarkers. Paralogs, despite being common drug targets, are often missed in these screens as their individual disruption rarely causes a significant fitness defect. Combinatorial screens have revealed that paralog pairs are often synthetic lethal but that these effects are highly context specific. To develop paralogs as therapeutic targets we must identify which paralog pairs are synthetic lethal in which cancer contexts. ResultsWe develop a machine learning classifier to predict cell-line specific synthetic lethality between paralog pairs. We demonstrate the utility of features derived from the cell-line specific expression and essentiality of the pair and their protein-protein interaction partners for this purpose. We evaluate our predictions across multiple scenarios: predicting for the same pairs in unseen cell lines, for new gene pairs in seen cell lines, and for entirely uncharacterized pairs in unseen cell lines. We show that we can make predictions across all scenarios. We validate our predictions using independent combinatorial CRISPR screens and show that the agreement between our predictions and published experiments approaches the agreement across experiments. ConclusionsOur classifier predicts cell-line-specific synthetic lethality between paralog pairs and provides insights into the underlying features driving these interactions. We make our predictions for 1,005 cell lines available as a resource to facilitate the discovery of context-specific paralog synthetic lethalities and to guide the design of more targeted combinatorial screens.

cancer biology↗

bioRxiv2021

Towards Compilation of Balanced Protein Stability Datasets: Flattening the ΔΔG Curve through Systematic Under-sampling

Protein stability datasets contain neutral mutations that are highly concentrated in a much narrower {Delta}{Delta}G range than destabilizing and stabilizing mutations. Notwith-standing their high density, often studies analyzing stability datasets and/or predictors ignore the neutral mutations and use a binary classification scheme labeling only destabilizing and stabilizing mutations. Recognizing that highly concentrated neutral mutations would affect the quality of stability datasets, we have explored three protein stability datasets; S2648, PON-tstab and the symmetric Ssym that differ in size and quality. A characteristic leptokurtic shape in the {Delta}{Delta}G distributions of all three datasets including the curated and symmetric ones were reported due to concentrated neutral mutations. To further investigate the impact of neutral mutations on {Delta}{Delta}G predictions, we have comprehensively assessed the performance of eleven predictors on the PON-tstab dataset. Correlation and error analyses showed that all of the predictors performed the best on the neutral mutations while their performance became gradually worse as the {Delta}{Delta}G of the mutations departed further from the neutral zone regardless of the direction, implying a bias towards dense mutations. To this end, after unraveling the role of concentrated neutral mutations in biases of stability datasets, we described a systematic under-sampling approach to balance the {Delta}{Delta}G distributions. Before under-sampling, mutations were clustered based on their biochemical and/or structural features and then three mutations were systematically selected from every 2 kcal/mol of each cluster. Upon implementation of this approach by distinct clustering schemes, we generated five subsets varying in size and {Delta}{Delta}G distributions. All subsets notably showed amelioration of not only the shape of {Delta}{Delta}G distributions but also other pre-existing imbalances in the frequency distributions. We also reported differences in the performance of the predictors between the parent and under-sampled subsets due to the enrichment of previously under-represented mutations in the subsets. Altogether, this study not only elaborated the pivotal role of concentrated mutations in the dataset biases but also contemplated and realized a rational strategy to tackle this and other forms of biases. Under-sampling code is available on GitHub (https://github.com/narodkebabci/gRoR).

bioinformatics↗