Season combinatorial intervention predictions with Salt & Peper (2404.16907v1)
Abstract: Interventions play a pivotal role in the study of complex biological systems. In drug discovery, genetic interventions (such as CRISPR base editing) have become central to both identifying potential therapeutic targets and understanding a drug's mechanism of action. With the advancement of CRISPR and the proliferation of genome-scale analyses such as transcriptomics, a new challenge is to navigate the vast combinatorial space of concurrent genetic interventions. Addressing this, our work concentrates on estimating the effects of pairwise genetic combinations on the cellular transcriptome. We introduce two novel contributions: Salt, a biologically-inspired baseline that posits the mostly additive nature of combination effects, and Peper, a deep learning model that extends Salt's additive assumption to achieve unprecedented accuracy. Our comprehensive comparison against existing state-of-the-art methods, grounded in diverse metrics, and our out-of-distribution analysis highlight the limitations of current models in realistic settings. This analysis underscores the necessity for improved modelling techniques and data acquisition strategies, paving the way for more effective exploration of genetic intervention effects.
- Recover identifies synergistic drug combinations in vitro through sequential model optimization. Cell Reports Methods, 3(10), 2023.
- Inferring dynamic regulatory interaction graphs from time series data with perturbations. arXiv preprint arXiv:2306.07803, 2023.
- Advances in crispr therapeutics. Nature Reviews Nephrology, 19(1):9–22, 2023.
- Perturb-seq: dissecting molecular circuits with scalable single-cell rna profiling of pooled genetic screens. Cell, 167(7):1853–1866, 2016.
- Interventions and causal inference. Philosophy of Science, 74(5):981–995, 2007.
- In silico studies on the sensitivity of myocardial pcr/atp to changes in mitochondrial enzyme activity and oxygen concentration. Mol. BioSyst., 7:3335–3342, 2011.
- Transcriptomic forecasting with neural ordinary differential equations. Patterns, 4(8), 2023.
- Vincent Fortuin. Priors in bayesian deep learning: A review. International Statistical Review, 90(3):563–591, 2022.
- Multimodal pooled perturb-cite-seq screens in patient models define mechanisms of cancer immune evasion. Nature Genetics, 53(3):332–341, 2021.
- Data and theory point to mainly additive genetic variance for complex traits. PLoS Genetics, 4(2):e1000008, 2008.
- Andrew L Hopkins. Network pharmacology: the next paradigm in drug discovery. Nature Chemical Biology, 4(11):682–690, 2008.
- Renge infers gene regulatory networks using time-series single-cell rna-seq data with crispr perturbations. Communications Biology, 6(1):1290, 2023.
- Optimal distance metrics for single-cell rna-seq populations. bioRxiv, pp. 2023–12, 2023.
- Crispr approaches to small molecule target identification. ACS Chemical Biology, 13(2):366–375, 2018.
- Crispr-cas system is an effective tool for identifying drug combinations that provide synergistic therapeutic potential in cancers. Cells, 12(22):2593, 2023.
- Crispr/cas9 mutagenesis invalidates a putative cancer dependency targeted in on-going clinical trials. Elife, 6:e24179, 2017.
- Crispr screen in mechanism and target discovery for cancer immunotherapy. Biochimica et Biophysica Acta (BBA)-Reviews on Cancer, 1874(1):188378, 2020.
- Deep generative modeling for single-cell transcriptomics. Nature Methods, 15(12):1053–1058, 2018.
- scgen predicts single-cell perturbation responses. Nature Methods, 16(8):715–721, 2019.
- Predicting cellular responses to complex perturbations in high-throughput screens. Molecular Systems Biology, pp. e11517, 2023.
- Using deep learning to model the hierarchical structure and function of a cell. Nature Methods, 15(4):290–298, 2018.
- Olwenn V Martin. Synergistic effects of chemical mixtures: how frequent is rare? Current Opinion in Toxicology, pp. 100424, 2023.
- Exploring genetic interaction manifolds constructed from rich single-cell phenotypes. Science, 365(6455):786–793, 2019.
- scperturb: harmonized single-cell perturbation data. Nature Methods, pp. 1–10, 2024.
- Mapping information-rich genotype-phenotype landscapes with genome-scale perturb-seq. Cell, 185(14):2559–2575, 2022.
- bayesynergy: flexible bayesian modelling of synergistic interaction effects in in vitro drug combination experiments. Briefings in Bioinformatics, 22(6):bbab251, 2021.
- Predicting transcriptional outcomes of novel multigene perturbations with gears. Nature Biotechnology, pp. 1–9, 2023.
- Donald B Rubin. Causal inference using potential outcomes: Design, modeling, decisions. Journal of the American Statistical Association, 100(469):322–331, 2005.
- Pyrelational: A library for active learning research and development. arXiv preprint arXiv:2205.11117, 2022.
- Burr Settles. Uncertainty sampling. In Active Learning, Synthesis Lectures on Artificial Intelligence and Machine Learning, pp. 11–21. Morgan & Claypool Publishers, 2012.
- Combinatorial crispr–cas9 screens for de novo mapping of genetic interactions. Nature Methods, 14(6):573–576, 2017.
- Gordon K Smyth. Limma: linear models for microarray data. In Bioinformatics and Computational Biology Solutions using R and Bioconductor, pp. 397–420. Springer, 2005.
- What is synergy? the saariselkä agreement revisited. Frontiers in Pharmacology, 6:181, 2015.
- From louvain to leiden: guaranteeing well-connected communities. Scientific Reports, 9(1):5233, 2019.
- Efficient combinatorial targeting of rna transcripts in single cells with cas13 rna perturb-seq. Nature Methods, 20(1):86–94, 2023.
- Variational causal inference. In NeurIPS 2022 Workshop on Causality for Real-world Impact, 2022.
- Central moment discrepancy (cmd) for domain-invariant representation learning. In International Conference on Learning Representations, 2016.
- Identifiability guarantees for causal disentanglement from soft interventions. arXiv preprint arXiv:2307.06250, 2023.