Featured
-
-
Article
| Open AccessreplicAnt: a pipeline for generating annotated images of animals in complex environments using Unreal Engine
Deep learning-based computer vision tools are transforming animal behavioural research; however, many challenges remain. Here, Plum et al. present replicAnt, a novel tool for generating synthetic data to train computer vision models for animal behaviour studies, reducing the need for manual annotation.
- Fabian Plum
- , René Bulla
- & David Labonte
-
Article
| Open AccessSeasonal pigment fluctuation in diploid and polyploid Arabidopsis revealed by machine learning-based phenotyping method PlantServation
Long-term monitoring of plants in field fluctuating environments remains challenging. Here, the authors develop PlantServation, a machine learning-based phenotyping method, and estimate environmental and genotypic effects on the pigment anthocyanin content of diploid and polyploid Arabidopsis.
- Reiko Akiyama
- , Takao Goto
- & Kentaro K. Shimizu
-
Article
| Open AccessMining multi-center heterogeneous medical data with distributed synthetic learning
Here the authors present Distributed Synthetic Learning, a system that addresses data privacy, isolated data islands, and heterogeneity concerns in healthcare analytics by learning to generate state-of-the-art synthetic data for downstream tasks.
- Qi Chang
- , Zhennan Yan
- & Dimitris N. Metaxas
-
Article
| Open AccessFLASHIda enables intelligent data acquisition for top–down proteomics to boost proteoform identification counts
Data acquisition suitable for top-down proteomics (TDP) has the potential to significantly improve proteoform analysis. Here, the authors present FLASHIda, an intelligent online data acquisition algorithm for TDP that nearly doubles the number of proteoform-level identifications in complex samples.
- Kyowon Jeong
- , Maša Babović
- & Oliver Kohlbacher
-
Article
| Open AccessA reference single-cell regulomic and transcriptomic map of cynomolgus monkeys
Non-human primates are attractive laboratory animal models that can accurately reflect some developmental and pathological features of humans. Here the authors chart a reference cell map of cynomolgus monkeys using both scATAC-seq and scRNA-seq data across multiple organs, providing insights into the molecular dynamics and cellular heterogeneity of this organism.
- Jiao Qu
- , Fa Yang
- & Dijun Chen
-
Article
| Open AccessA mammalian methylation array for profiling methylation levels at conserved sequences
Methods to probe DNA methylation in the majority of non-human mammals are lacking. Here the authors developed a Mammalian Methylation Array that includes 36k well-conserved CpGs in mammals which will facilitate cross-species comparisons. They annotate the conserved CpGs in > 200 species. The array allows one to measure methylation in all mammalian species including unsequenced ones.
- Adriana Arneson
- , Amin Haghani
- & Steve Horvath
-
Article
| Open AccessA scalable, secure, and interoperable platform for deep data-driven health management
The increasing scale and scope of biomedical data is generating tremendous opportunities for improving health outcomes, but also raises new challenges ranging from data acquisition and storage to data analysis and utilization. To meet these challenges, the authors develop the Personal Health Dashboard, which provides an end-to-end solution for deep biomedical data analytics.
- Amir Bahmani
- , Arash Alavi
- & Michael P. Snyder
-
Article
| Open AccessEnhancing CRISPR-Cas9 gRNA efficiency prediction by data integration and deep learning
High-quality gRNA activity data is needed for accurate on-target efficiency predictions. Here the authors generate activity data for over 10,000 gRNA and build a deep learning model CRISPRon for improved performance predictions.
- Xi Xiang
- , Giulia I. Corsi
- & Yonglun Luo
-
Article
| Open AccessGo Get Data (GGD) is a framework that facilitates reproducible access to genomic data
Modern biological research is complicated by the difficulty of collecting, transforming, annotating, and integrating datasets. Here, the authors present Go Get Data, a fast, reproducible approach to installing standardized data recipes, with an application to genomics data.
- Michael J. Cormier
- , Jonathan R. Belyeu
- & Aaron R. Quinlan
-
Article
| Open AccessSurvey data and human computation for improved flu tracking
Digital trace data from search engines lacks information about the experiences of the individuals generating the data. Here the authors link search data and human computation to build a tracking model of influenza-like illness.
- Stefan Wojcik
- , Avleen S. Bijral
- & David Lazer
-
Article
| Open AccessAccelerated knowledge discovery from omics data by optimal experimental design
How to design experiments that accelerate knowledge discovery on complex biological landscapes remains a tantalizing question. Here, the authors present OPEX, an optimal experimental design method to identify informative omics experiments for both experimental space exploration and model training.
- Xiaokang Wang
- , Navneet Rai
- & Ilias Tagkopoulos
-
Article
| Open AccessGenetic variant effects on gene expression in human pancreatic islets and their implications for T2D
Mechanistic inference following GWAS is hampered by the lack of tissue-specific transcriptomic resources. Here the authors combine genetic variants predisposing to type 2 diabetes with human pancreatic islet RNA-seq data. They identify 7741 islet expression quantitative trait loci (eQTLs), providing a resource for functional interpretation of association signals mapping to non-coding sequence.
- Ana Viñuela
- , Arushi Varshney
- & Mark I. McCarthy
-
Article
| Open AccessSubnanometer-resolution structure determination in situ by hybrid subtomogram averaging - single particle cryo-EM
Combining cryo-electron tomography with subtomogram averaging (StA) allows the in situ structure determination of proteins and protein complexes. Here, the authors present the hybrid StA (hStA) workflow that combines the advantages of single particle cryo-EM and StA and consists of a tomographic data collection scheme and a data processing workflow and they demonstrate how hStA can improve the resolution using two examples: the ion channel RyR1 and tobacco mosaic virus.
- Ricardo M. Sanchez
- , Yingyi Zhang
- & Mikhail Kudryashev
-
Article
| Open AccessLandscape of transcriptomic interactions between breast cancer and its microenvironment
The transcriptomic profile of tumour-adjacent cells provides important information about tumour context but its clinical utility is unclear. Here, in breast cancer, Fox et al. show that the mRNA abundances of tumour and tumour-adjacent cells hold prognostic information.
- Natalie S. Fox
- , Syed Haider
- & Paul C. Boutros