Tumor Phylogeny Topology Inference via Deep Learning

Fast intratumor heterogeneity inference from single-cell sequencing data

We introduce HUNTRESS, a computational method for mutational intratumor heterogeneity inference from noisy genotype matrices derived from single-cell sequencing data, the running time of which is linear with the number of cells and quadratic with the number of mutations. We prove that, under reasonable conditions, HUNTRESS computes the true progression history of a tumor with high probability. On simulated and real tumor sequencing data, HUNTRESS is demonstrated to be faster than available alternatives with comparable or better accuracy. Additionally, the progression histories of tumors inferred by HUNTRESS on real single-cell sequencing datasets agree with the best known evolution scenarios for the associated tumors.

Current progress and open challenges for applying deep learning across the biosciences

Deep Learning (DL) has recently enabled unprecedented advances in one of the grand challenges in computational biology: the half-century-old problem of protein structure prediction. In this paper we discuss recent advances, limitations, and future perspectives of DL on five broad areas: protein structure prediction, protein function prediction, genome engineering, systems biology and data integration, and phylogenetic inference. We discuss each application area and cover the main bottlenecks of DL approaches, such as training data, problem scope, and the ability to leverage existing DL architectures in new contexts. To conclude, we provide a summary of the subject-specific and general challenges for DL across the biosciences.

CellPhy: accurate and fast probabilistic inference of single-cell phylogenies from scDNA-seq data

We introduce CellPhy, a maximum likelihood framework for inferring phylogenetic trees from somatic single-cell single-nucleotide variants. CellPhy leverages a finite-site Markov genotype model with 16 diploid states and considers amplification error and allelic dropout. We implement CellPhy into RAxML-NG, a widely used phylogenetic inference package that provides statistical confidence measurements and scales well on large datasets with hundreds or thousands of cells. Comprehensive simulations suggest that CellPhy is more robust to single-cell genomics errors and outperforms state-of-the-art methods under realistic scenarios, both in accuracy and speed. CellPhy is freely available at https://github.com/amkozlov/cellphy .

Distinguishing linear and branched evolution given single-cell DNA sequencing data of tumors

Background

Cancer arises from an evolutionary process where somatic mutations give rise to clonal expansions. Reconstructing this evolutionary process is useful for treatment decision-making as well as understanding evolutionary patterns across patients and cancer types. In particular, classifying a tumor’s evolutionary process as either linear or branched and understanding what cancer types and which patients have each of these trajectories could provide useful insights for both clinicians and researchers. While comprehensive cancer phylogeny inference from single-cell DNA sequencing data is challenging due to limitations with current sequencing technology and the complexity of the resulting problem, current data might provide sufficient signal to accurately classify a tumor’s evolutionary history as either linear or branched.

Results

We introduce the Linear Perfect Phylogeny Flipping (LPPF) problem as a means of testing two alternative hypotheses for the pattern of evolution, which we prove to be NP-hard. We develop Phyolin, which uses constraint programming to solve the LPPF problem. Through both in silico experiments and real data application, we demonstrate the performance of our method, outperforming a competing machine learning approach.

Conclusion

Phyolin is an accurate, easy to use and fast method for classifying an evolutionary trajectory as linear or branched given a tumor’s single-cell DNA sequencing data.

Machine Intelligence in Single-Cell Data Analysis: Advances and New Challenges

The rapid development of single-cell technologies allows for dissecting cellular heterogeneity at different omics layers with an unprecedented resolution. In-dep analysis of cellular heterogeneity will boost our understanding of complex biological systems or processes, including cancer, immune system and chronic diseases, thereby providing valuable insights for clinical and translational research. In this review, we will focus on the application of machine learning methods in single-cell multi-omics data analysis. We will start with the pre-processing of single-cell RNA sequencing (scRNA-seq) data, including data imputation, cross-platform batch effect removal, and cell cycle and cell-type identification. Next, we will introduce advanced data analysis tools and methods used for copy number variance estimate, single-cell pseudo-time trajectory analysis, phylogenetic tree inference, cell-cell interaction, regulatory network inference, and integrated analysis of scRNA-seq and spatial transcriptome data. Finally, we will present the latest analyzing challenges, such as multi-omics integration and integrated analysis of scRNA-seq data.

Incorporating Machine Learning into Established Bioinformatics Frameworks

The exponential growth of biomedical data in recent years has urged the application of numerous machine learning techniques to address emerging problems in biology and clinical research. By enabling the automatic feature extraction, selection, and generation of predictive models, these methods can be used to efficiently study complex biological systems. Machine learning techniques are frequently integrated with bioinformatic methods, as well as curated databases and biological networks, to enhance training and validation, identify the best interpretable features, and enable feature and model investigation. Here, we review recently developed methods that incorporate machine learning within the same framework with techniques from molecular evolution, protein structure analysis, systems biology, and disease genomics. We outline the challenges posed for machine learning, and, in particular, deep learning in biomedicine, and suggest unique opportunities for machine learning techniques integrated with established bioinformatics approaches to overcome some of these challenges.