Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Toolkits and Libraries for Deep Learning.

ABSTRACT: Deep learning is an important new area of machine learning which encompasses a wide range of neural network architectures designed to complete various tasks. In the medical imaging domain, example tasks include organ segmentation, lesion detection, and tumor classification. The most popular network architecture for deep learning for images is the convolutional neural network (CNN). Whereas traditional machine learning requires determination and calculation of features from which the algorithm learns, deep learning approaches learn the important features as well as the proper weighting of those features to make predictions for new data. In this paper, we will describe some of the libraries and tools that are available to aid in the construction and efficient execution of deep learning as applied to medical images.

SUBMITTER: Erickson BJ

PROVIDER: S-EPMC5537091 | biostudies-other | 2017 Aug

REPOSITORIES: biostudies-other

ACCESS DATA

Json Xml

Similar Datasets

In silico spectral libraries by deep learning facilitate data-independent acquisition proteomics.

Project description:Data-independent acquisition (DIA) is an emerging technology for quantitative proteomic analysis of large cohorts of samples. However, sample-specific spectral libraries built by data-dependent acquisition (DDA) experiments are required prior to DIA analysis, which is time-consuming and limits the identification/quantification by DIA to the peptides identified by DDA. Herein, we propose DeepDIA, a deep learning-based approach to generate in silico spectral libraries for DIA analysis. We demonstrate that the quality of in silico libraries predicted by instrument-specific models using DeepDIA is comparable to that of experimental libraries, and outperforms libraries generated by global models. With peptide detectability prediction, in silico libraries can be built directly from protein sequence databases. We further illustrate that DeepDIA can break through the limitation of DDA on peptide/protein detection, and enhance DIA analysis on human serum samples compared to the state-of-the-art protocol using a DDA library. We expect this work expanding the toolbox for DIA proteomics.

| S-EPMC6952453 | biostudies-literature

YAMDA: thousandfold speedup of EM-based motif discovery using deep learning libraries and GPU.

Project description:Motivation:Motif discovery in large biopolymer sequence datasets can be computationally demanding, presenting significant challenges for discovery in omics research. MEME, arguably one of the most popular motif discovery software, takes quadratic time with respect to dataset size, leading to excessively long runtimes for large datasets. Therefore, there is a demand for fast programs that can generate results of the same quality as MEME. Results:Here we describe YAMDA, a highly scalable motif discovery software package. It is built on Pytorch, a tensor computation deep learning library with strong GPU acceleration that is highly optimized for tensor operations that are also useful for motifs. YAMDA takes linear time to find motifs as accurately as MEME, completing in seconds or minutes, which translates to speedups over a thousandfold. Availability and implementation:YAMDA is freely available on Github (https://github.com/daquang/YAMDA). Supplementary information:Supplementary data are available at Bioinformatics online.

| S-EPMC6184538 | biostudies-literature

Genome-scale validation of deep-sequencing libraries.

Project description:Chromatin immunoprecipitation followed by high-throughput (HTP) sequencing (ChIP-seq) is a powerful tool to establish protein-DNA interactions genome-wide. The primary limitation of its broad application at present is the often-limited access to sequencers. Here we report a protocol, Mab-seq, that generates genome-scale quality evaluations for nucleic acid libraries intended for deep-sequencing. We show how commercially available genomic microarrays can be used to maximize the efficiency of library creation and quickly generate reliable preliminary data on a chromosomal scale in advance of deep sequencing. We also exploit this technique to compare enriched regions identified using microarrays with those identified by sequencing, demonstrating that they agree on a core set of clearly identified enriched regions, while characterizing the additional enriched regions identifiable using HTP sequencing.

| S-EPMC2577887 | biostudies-literature

Merging full-spectrum and fragment ion intensity predictions from deep learning for high quality spectral libraries

Project description:In this work, we present a deep learning based full-spectrum prediction method and demonstrate the merits of using full-spectrum predicted approaches for library searching. Our proposed model provides flexibility to accommodate post-translational modifications and fills the current gap for long peptide predictions.

2023-06-28 | PXD040721 | Pride

Direct data-independent acquisition proteomics with in silico spectral libraries by deep learning

Project description:Data-independent acquisition (DIA) proteomics allows systematic and unbiased measurement of protein samples and enables fast quantitative analysis of large cohorts of samples. However, sample-specific spectral libraries are usually required prior to perform DIA experiments. The libraries are built by data-dependent acquisition (DDA) proteomic analysis on the same samples normally with pre-fractionation, which is time-consuming and limits the identification/quantification by DIA to the peptides identified by DDA. Herein, we propose DeepDIA, a deep learning based approach to generate in silico spectral libraries for DIA analysis. We benchmarked DeepDIA with HeLa and mixed proteome data sets, showing that the quality of in silico spectral libraries is comparable to that of experimental spectral libraries. We further demonstrated that DeepDIA can be performed on human cell lines and human serum without pre-knowledge of peptides lists by DDA experiments. Compared to the state-of-the-art protocol using DDA-based spectral library with high abundance protein depletion and pre-fractionation, the number of identified and quantified proteins from human serum was increased by >100% using DeepDIA. Accuracy of the identification results was validated using a standard mixture containing >800 stable isotope labelled reference peptides from >500 proteins in human plasma. We expect this work contributing to the studies of quantitative proteomics and especially blood proteomics, whereas expanding the toolbox for DIA proteomics.

2019-12-02 | PXD014108 |

Deep learning in deep time.

Project description: Not available

| S-EPMC7703579 | biostudies-literature

Deep, deep learning with BART.

Project description:PurposeTo develop a deep-learning-based image reconstruction framework for reproducible research in MRI.MethodsThe BART toolbox offers a rich set of implementations of calibration and reconstruction algorithms for parallel imaging and compressed sensing. In this work, BART was extended by a nonlinear operator framework that provides automatic differentiation to allow computation of gradients. Existing MRI-specific operators of BART, such as the nonuniform fast Fourier transform, are directly integrated into this framework and are complemented by common building blocks used in neural networks. To evaluate the use of the framework for advanced deep-learning-based reconstruction, two state-of-the-art unrolled reconstruction networks, namely the Variational Network and MoDL, were implemented.ResultsState-of-the-art deep image-reconstruction networks can be constructed and trained using BART's gradient-based optimization algorithms. The BART implementation achieves a similar performance in terms of training time and reconstruction quality compared to the original implementations based on TensorFlow.ConclusionBy integrating nonlinear operators and neural networks into BART, we provide a general framework for deep-learning-based reconstruction in MRI.

| S-EPMC10898647 | biostudies-literature

Deep sequencing of small RNA libraries from chicken embryo

Project description:MicroRNA (miRNA) and other types of small regulatory RNAs play a crucial role in the regulation of gene expression in eukaryotes. Several distinct classes of small regulatory RNAs have been discovered in recent years. To extend the repertoire of small regulatory RNAs characterized in chickens we used a deep sequencing approach developed by Solexa (now Illumina Inc.). We sequenced three small RNA libraries prepared from different developmental stages of the chicken embryo (days 5, 7, and 9) to produce over 9.5 million short sequence reads. We developed a bioinformatics pipeline to distinguish authentic mature miRNA sequences from other classes of small RNAs and short RNA fragments represented in the sequencing data. Using this approach we detected almost all of the previously known chicken miRNAs and their respective miRNA* sequences. In addition we discovered 449 putative new chicken miRNAs. Of these, 430 miRNAs appear to be specific to the avian lineage. Another 6 new miRNAs had evidence of evolutionary conservation in at least one vertebrate species outside of the bird lineage. The remaining 13 putative miRNAs appear to represent chicken orthologs of known vertebrate miRNAs. We discovered 39 additional putative miRNA candidates originating from miRNA generating intronic sequences known as mirtrons. Keywords: miRNA discovery, mirtrons, chicken embryo

2008-05-12 | GSE10686 | GEO

Targeted insertional mutagenesis libraries for deep domain insertion profiling.

Project description:Domain recombination is a key principle in protein evolution and protein engineering, but inserting a donor domain into every position of a target protein is not easily experimentally accessible. Most contemporary domain insertion profiling approaches rely on DNA transposons, which are constrained by sequence bias. Here, we establish Saturated Programmable Insertion Engineering (SPINE), an unbiased, comprehensive, and targeted domain insertion library generation technique using oligo library synthesis and multi-step Golden Gate cloning. Through benchmarking to MuA transposon-mediated library generation on four ion channel genes, we demonstrate that SPINE-generated libraries are enriched for in-frame insertions, have drastically reduced sequence bias as well as near-complete and highly-redundant coverage. Unlike transposon-mediated domain insertion that was severely biased and sparse for some genes, SPINE generated high-quality libraries for all genes tested. Using the Inward Rectifier K+ channel Kir2.1, we validate the practical utility of SPINE by constructing and comparing domain insertion permissibility maps. SPINE is the first technology to enable saturated domain insertion profiling. SPINE could help explore the relationship between domain insertions and protein function, and how this relationship is shaped by evolutionary forces and can be engineered for biomedical applications.

| S-EPMC6954442 | biostudies-literature

Metatranscriptomic analysis of small RNAs present in soybean deep sequencing libraries.

Project description:A large number of small RNAs unrelated to the soybean genome were identified after deep sequencing of soybean small RNA libraries. A metatranscriptomic analysis was carried out to identify the origin of these sequences. Comparative analyses of small interference RNAs (siRNAs) present in samples collected in open areas corresponding to soybean field plantations and samples from soybean cultivated in greenhouses under a controlled environment were made. Different pathogenic, symbiotic and free-living organisms were identified from samples of both growth systems. They included viruses, bacteria and different groups of fungi. This approach can be useful not only to identify potentially unknown pathogens and pests, but also to understand the relations that soybean plants establish with microorganisms that may affect, directly or indirectly, plant health and crop production.

| S-EPMC3392881 | biostudies-other

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data