Joel T. Dudley

We announce the release of the fourth version of MEGA software, which expands on the existing facilities for editing DNA sequence data from autosequencers, mining Web-databases, performing automatic and manual sequence alignment, analyzing sequence alignments to estimate evolutionary distances, inferring phylogenetic trees, and testing evolutionary hypotheses. Version 4 includes a unique facility to generate captions, written in figure legend format, in order to provide natural language descriptions of the models and methods used in the analyses. This facility aims to promote a better understanding of the underlying assumptions used in analyses, and of the results generated. Another new feature is the Maximum Composite Likelihood (MCL) method for estimating evolutionary distances between all pairs of sequences simultaneously, with and without incorporating rate variation among sites and substitution pattern heterogeneities among lineages. This MCL method also can be used to estimate transition/transversion bias and nucleotide substitution pattern without knowledge of the phylogenetic tree. This new version is a native 32-bit Windows application with multi-threading and multi-user supports, and it is also available to run in a Linux desktop environment (via the Wine compatibility layer) and on Intel-based Macintosh computers under the Parallels program. The current version of MEGA is available free of charge at (http://www.megasoftware.net).

The Molecular Evolutionary Genetics Analysis (MEGA) software is a desktop application designed for comparative analysis of homologous gene sequences either from multigene families or from different species with a special emphasis on inferring evolutionary relationships and patterns of DNA and protein evolution. In addition to the tools for statistical analysis of data, MEGA provides many convenient facilities for the assembly of sequence data sets from files or web-based repositories, and it includes tools for visual presentation of the results obtained in the form of interactive phylogenetic trees and evolutionary distance matrices. Here we discuss the motivation, design principles and priorities that have shaped the development of MEGA. We also discuss how MEGA might evolve in the future to assist researchers in their growing need to analyze large data set using new computational methods.

Gaining knowledge and actionable insights from complex, high-dimensional and heterogeneous biomedical data remains a key challenge in transforming health care. Various types of data have been emerging in modern biomedical research, including electronic health records, imaging, -omics, sensor data and text, which are complex, heterogeneous, poorly annotated and generally unstructured. Traditional data mining and statistical learning approaches typically need to first perform feature engineering to obtain effective and more robust features from those data, and then build prediction or clustering models on top of them. There are lots of challenges on both steps in a scenario of complicated data and lacking of sufficient domain knowledge. The latest advances in deep learning technologies provide new effective paradigms to obtain end-to-end learning models from complex data. In this article, we review the recent literature on applying deep learning technologies to advance the health care domain. Based on the analyzed work, we suggest that deep learning approaches could be the vehicle for translating big biomedical data into improved human health. However, we also note limitations and needs for improved methods development and applications, especially in terms of ease-of-understanding for domain experts and citizen scientists. We discuss such challenges and suggest developing holistic and meaningful interpretable architectures to bridge deep learning models and human interpretability.

Secondary use of electronic health records (EHRs) promises to advance clinical research and better inform clinical decision making. Challenges in summarizing and representing patient data prevent widespread practice of predictive modeling using EHRs. Here we present a novel unsupervised deep feature learning method to derive a general-purpose patient representation from EHR data that facilitates clinical predictive modeling. In particular, a three-layer stack of denoising autoencoders was used to capture hierarchical regularities and dependencies in the aggregated EHRs of about 700,000 patients from the Mount Sinai data warehouse. The result is a representation we name "deep patient". We evaluated this representation as broadly predictive of health states by assessing the probability of patients to develop various diseases. We performed evaluation using 76,214 test patients comprising 78 diseases from diverse clinical domains and temporal windows. Our results significantly outperformed those achieved using representations based on raw EHR data and alternative feature learning strategies. Prediction performance for severe diabetes, schizophrenia, and various cancers were among the top performing. These findings indicate that deep learning applied to EHRs can derive patient representations that offer improved clinical predictions, and could provide a machine learning framework for augmenting clinical decision systems.

UNLABELLED: Biologists and other scientists routinely need to know times of divergence between species and to construct phylogenies calibrated to time (timetrees). Published studies reporting time estimates from molecular data have been increasing rapidly, but the data have been largely inaccessible to the greater community of scientists because of their complexity. TimeTree brings these data together in a consistent format and uses a hierarchical structure, corresponding to the tree of life, to maximize their utility. Results are presented and summarized, allowing users to quickly determine the range and robustness of time estimates and the degree of consensus from the published literature. AVAILABILITY: TimeTree is available at http://www.timetree.net