PhyloMissForest: a random forest framework to construct phylogenetic trees with missing data

Abstract

Background In the pursuit of a better understanding of biodiversity, evolutionary biologists rely on the study of phylogenetic relationships to illustrate the course of evolution. The relationships among natural organisms, depicted in the shape of phylogenetic trees, not only help to understand evolutionary history but also have a wide range of additional applications in science. One of the most challenging problems that arise when building phylogenetic trees is the presence of missing biological data. More specifically, the possibility of inferring wrong phylogenetic trees increases proportionally to the amount of missing values in the input data. Although there are methods proposed to deal with this issue, their applicability and accuracy is often restricted by different constraints. Results We propose a framework, called PhyloMissForest, to impute missing entries in phylogenetic distance matrices and infer accurate evolutionary relationships. PhyloMissForest is built upon a random forest structure that infers the missing entries of the input data, based on the known parts of it. PhyloMissForest contributes with a robust and configurable framework that incorporates multiple search strategies and machine learning, complemented by phylogenetic techniques, to provide a more accurate inference of lost phylogenetic distances. We evaluate our framework by examining three real-world datasets, two DNA-based sequence alignments and one containing amino acid data, and two additional instances with simulated DNA data. Moreover, we follow a design of experiments methodology to define the hyperparameter values of our algorithm, which is a concise method, preferable in comparison to the well-known exhaustive parameters search. By varying the percentages of missing data from 5% to 60%, we generally outperform the state-of-the-art alternative imputation techniques in the tests conducted on real DNA data. In addition, significant improvements in execution time are observed for the amino acid instance. The results observed on simulated data also denote the attainment of improved imputations when dealing with large percentages of missing data. Conclusions By merging multiple search strategies, machine learning, and phylogenetic techniques, PhyloMissForest provides a highly customizable and robust framework for phylogenetic missing data imputation, with significant topological accuracy and effective speedups over the state of the art.

Interpretable machine learning framework to predict gout associated with dietary fiber and triglyceride-glucose index

“…Simple direct deletion of data will result in the loss of valuable information and waste of resources, so the filling of missing data is a reasonable and realistic operation. Conventional data-filling methods such as multiple interpolation and median interpolation are unable to deal with data interactions and nonlinearities of variables in the face of high dimensional and large sample data, so algorithm-based data-filling can more accurately maintain the overall characteristics of the data [ 28 ]. We used the missForest R package (hyperparameters: maxiter = 10, ntree = 1000, verbose = TRUE) to interpolate variables with a few missing data.…”

Machine learning can be as good as maximum likelihood when reconstructing phylogenetic trees and determining the best evolutionary model on four taxon alignments

“…Several machine learning algorithms proposed so far are inferior to the ML method and only as good as distance-based methods (Zhu & Cai, 2021;Pinheiro et al, 2022). Suvorov Here we propose supervised machine learning using NNs as an alternative to existing model selection and topology reconstruction methods.…”

“…Image classification of alignments using deep CNNs has also been suggested for determining the best evolutionary model of sequence evolution (Burgstaller-Muehlbacher et al, preprint 2021). Furthermore, Pinheiro et al (2022) used a RF algorithm for predicting missing sequence regions and using this information to reconstruct phylogenetic trees. However, the accuracy of the RF method could hardly come close to that of the Neighbour Joining method.…”

“…Several machine learning algorithms proposed so far are inferior to the ML method and only as good as distance-based methods (Zhu & Cai, 2021; Pinheiro et al, 2022). Suvorov et al (2020) and Zou et al (2020) showed that an image-based alignment classification with CNNs can yield good results.…”

SNPtotree—Resolving the Phylogeny of SNPs on Non-Recombining DNA

“…The latter also removes data that might not be missing in some sequences, which can reduce phylogeny accuracies [22,25]. Machine learning-based imputation of missing data has been explored specifically for distance-based approaches [27,28]. Data imputation for character-based approaches requires a reference dataset of a comprehensive set of variants that are comparable to those in the study data to extrapolate correlations between the variants.…”