Tumor Phylogeny Topology Inference via Deep Learning

Azer, Erfan Sadeqi; Ebrahimabadi, Mohammad Haghir; Malikić, Salem; Khardon, Roni; Şahinalp, S. Cenk

doi:10.1016/j.isci.2020.101655

Cited by 12 publications

(15 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Shown is the patient identifier, the published evolutionary pattern of the tree, the number of mutations, the total cells sequenced [ 21 ], the median number of simulated false negatives over 10 replications, Phyolin estimated number of false negatives over 10 replications, the median over 10 replications, and the median probability of a linear perfect phylogeny as determined by the comparison deep learning method [ 14 ] …”

Section: Resultsmentioning

confidence: 99%

“…Azer et al [ 14 ] utilized a deep learning approach to decide if single-cell data indicates whether a tumor followed a linear or branched evolutionary process. Although their method is fast at prediction time and performs well on simulated data, it has not yet been proved whether the problem of identifying the minimum number of flips to obtain a linear perfect phylogeny is NP-hard.…”

Section: Introductionmentioning

confidence: 99%

“…Additionally, the neural networks are trained on inputs of a fixed size. While padding could be used in predicting an input smaller than the fixed size [ 14 ], a new network would have to be trained if the input size is larger than the trained network. This drawback significantly reduces the speed advantage of such an approach as training of neural networks is a time consuming process.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Weber

El-Kebir

2021

Algorithms Mol Biol

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Weber

El-Kebir

2021

Algorithms Mol Biol

View full text Add to dashboard Cite

show abstract

“…Sadeqi Azer et al (2020) inferred the most likely tumor phylogeny via deep learning and eliminate noises such as dropout events in alleles and low sequence coverage issues with a maximum likelihood/parsimony approach . The noise reduction processes target the possible set of false negative/false-positive variant calls to ensure constructing a reliable phylogenetic tree.…”

Section: Phylogenetic Tree Inferencementioning

confidence: 99%

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

Fan

Zhao

et al. 2021

Front. Genet.

View full text Add to dashboard Cite

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.

show abstract

“…In recent years, ML methods have been developed to address the challenges faced by molecular evolution research, in particular, by overcoming the difficulties of analyzing increasingly massive sets of sequence and other omics data. Examples of such applications include the use of autoencoders to impute incomplete data for phylogenetic tree construction [ 7 ], application of random forest for phylogenetic model selection [ 8 ], harnessing convolutional neural networks (CNNs) to infer tree topologies [ 9 ] and tumor phylogeny [ 10 ], and utilization of deep reinforcement learning for the construction of robust alignments of many sequences [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

Incorporating Machine Learning into Established Bioinformatics Frameworks

Auslander

Gussow

Koonin

2021

IJMS

View full text Add to dashboard Cite

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.

show abstract

Tumor Phylogeny Topology Inference via Deep Learning

Cited by 12 publications

References 55 publications

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

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

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

Incorporating Machine Learning into Established Bioinformatics Frameworks

Contact Info

Product

Resources

About