A Hybrid Deep Neural Network for the Prediction of In-Vivo Protein-DNA Binding by Combining Multiple-Instance Learning

2021 ◽  
pp. 374-384
Author(s):  
Yue Zhang ◽  
Yuehui Chen ◽  
Wenzheng Bao ◽  
Yi Cao
Keyword(s):  
Neural Network ◽  
Dna Binding ◽  
Deep Neural Network ◽  
Multiple Instance Learning

Deep Neural Network Classification of In Vivo Burn injuries with Different Etiologies Using THz Time-Domain Spectral Imaging

2021 ◽  
Author(s):  
Omar B. Osman ◽  
Zachery B. Harris ◽  
Juin-Wan Zhou ◽  
Mahmoud E. Khani ◽  
Andrew Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Domain ◽  
Deep Neural Network ◽  
Spectral Imaging ◽  
Burn Injuries ◽  
Neural Network Classification

scholarly journals Multiple Instance Learning with Differential Evolutionary Pooling

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1403
Author(s):  
Kamanasish Bhattacharjee ◽  
Arti Tiwari ◽  
Millie Pant ◽  
Chang Wook Ahn ◽  
Sanghoun Oh
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Differential Evolution ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Multiple Instance Learning ◽  
Important Task ◽  
Class Label ◽  
Parameter Adaptation

While implementing Multiple Instance Learning (MIL) through Deep Neural Networks, the most important task is to design the bag-level pooling function that defines the instance-to-bag relationship and eventually determines the class label of a bag. In this article, Differential Evolutionary (DE) pooling—an MIL pooling function based on Differential Evolution (DE) and a bio-inspired metaheuristic—is proposed for the optimization of the instance weights in parallel with training the Deep Neural Network. This article also presents the effects of different parameter adaptation techniques with different variants of DE on MIL.

scholarly journals Neural network modeling of differential binding between wild-type and mutant CTCF reveals putative binding preferences for zinc fingers 1-2

2021 ◽  
Author(s):  
Irene Miriam Kaplow ◽  
Abhimanyu Banerjee ◽  
Chuan-Sheng Foo
Keyword(s):  
Neural Network ◽  
Dna Binding ◽  
Zinc Fingers ◽  
Neural Network Modeling ◽  
Binding Motif ◽  
Wild Type ◽  
Core Motif ◽  
Binding Motifs ◽  
Binding Domains

Background: Many transcription factors (TFs), such as multi zinc-finger (ZF) TFs, have multiple DNA binding domains (DBDs) with multiple components, and deciphering the DNA binding motifs of individual components is a major challenge. One example of such a TF is CCCTC-binding factor (CTCF), a TF with eleven ZFs that plays a variety of roles in transcriptional regulation, most notably anchoring DNA loops. Previous studies found that CTCF zinc fingers (ZFs) 3-7 bind CTCF's core motif and ZFs 9-11 bind a specific upstream motif, but the motifs of ZFs 1-2 have yet to be identified. Results: We developed a new approach to identifying the binding motifs of individual DBDs of a TF through analyzing chromatin immunoprecipitation sequencing (ChIP-seq) experiments in which a single DBD is mutated: we train a deep convolutional neural network to predict whether wild-type TF binding sites are preserved in the mutant TF dataset and interpret the model. We applied this approach to mouse CTCF ChIP-seq data and, in addition to identifying the known binding preferences of CTCF ZFs 3-11, we identified a GAG binding motif for ZF1 and a weak ATT binding motif for ZF2. We analyzed other CTCF datasets to provide additional evidence that ZFs 1-2 interact with the motifs we identified, and we found that the presence of the motif for ZF1 is associated with Ctcf peak strength. Conclusions: Our approach can be applied to any TF for which in vivo binding data from both the wild-type and mutated versions of the TF are available, and our findings provide an unprecedently comprehensive understanding of the binding preferences of CTCF's DBDs.

scholarly journals Computer-Aided Cobb Measurement Based on Automatic Detection of Vertebral Slopes Using Deep Neural Network

2017 ◽  
Vol 2017 ◽  
pp. 1-6 ◽  
Author(s):  
Junhua Zhang ◽  
Hongjian Li ◽  
Liang Lv ◽  
Yufeng Zhang
Keyword(s):  
Neural Network ◽  
Cobb Angle ◽  
Deep Neural Network ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Angle Measurement ◽  
Training Data ◽  
Manual Measurement ◽  
Computer Aided

Objective. To develop a computer-aided method that reduces the variability of Cobb angle measurement for scoliosis assessment. Methods. A deep neural network (DNN) was trained with vertebral patches extracted from spinal model radiographs. The Cobb angle of the spinal curve was calculated automatically from the vertebral slopes predicted by the DNN. Sixty-five in vivo radiographs and 40 model radiographs were analyzed. An experienced surgeon performed manual measurements on the aforementioned radiographs. Two examiners used both the proposed and the manual measurement methods to analyze the aforementioned radiographs. Results. For model radiographs, the intraclass correlation coefficients were greater than 0.98, and the mean absolute differences were less than 3°. This indicates that the proposed system showed high repeatability for measurements of model radiographs. For the in vivo radiographs, the reliabilities were lower than those from the model radiographs, and the differences between the computer-aided measurement and the manual measurement by the surgeon were higher than 5°. Conclusion. The variability of Cobb angle measurements can be reduced if the DNN system is trained with enough vertebral patches. Training data of in vivo radiographs must be included to improve the performance of DNN. Significance. Vertebral slopes can be predicted by DNN. The computer-aided system can be used to perform automatic measurements of Cobb angle, which is used to make reliable and objective assessments of scoliosis.

scholarly journals Predicting dynamic cellular protein-RNA interactions using deep learning and in vivo RNA structure

2020 ◽  
Author(s):  
Lei Sun ◽  
Kui Xu ◽  
Wenze Huang ◽  
Yucheng T. Yang ◽  
Lei Tang ◽  
...  
Keyword(s):  
Neural Network ◽  
Binding Sites ◽  
Rna Structure ◽  
Rna Secondary Structure ◽  
Deep Neural Network ◽  
Cell Types ◽  
Cellular Protein ◽  
Rna Regulation ◽  
Multiple Cell

AbstractInteractions with RNA-binding proteins (RBPs) are crucial for RNA regulation and function. While both RNA sequence and structure are critical determinants, RNA structure is dependent on cellular environment and especially important in regulating dynamic RBP bindings across various conditions. However, how distinct it contributes to RBP binding in vivo remains poorly understood. To address this issue, we obtained transcriptome-wide RNA secondary structure profiles in multiple cell-types, and established a deep neural network, PrismNet, that uses in vivo RNA structures to accurately predict cellular protein-RNA interactions. With a deep learning “attention” strategy, PrismNet discovers the exact binding nucleotides and their mutational effect. The predicted binding sites are highly conserved and enriched for rare, deleterious genetic variants. Remarkably, dynamic RBP binding sites are enriched for structure-changing variants (riboSNitches), which are often associated with disease, reflecting dysregulated RBP bindings. Our resource enables the analysis of cell-type-specific RNA regulation, with applications in human disease.Highlights1, A big data resource of transcriptome-wide RNA secondary structure profiles in multiple cell types2, PrismNet, a deep neural network, accurately models the sequence and structural combined patterns of protein-RNA interactions in vivo3, RNA structural information in vivo is critical for the accurate prediction of dynamic RBP binding in various cellular conditions4, PrismNet can dissect and predict how mutations affect RBP binding via RNA sequence or structure changes5, RNA structure-changing RiboSNitches are enriched in dynamic RBP binding sites and often associated with disease, likely disrupting RBP-based regulation

Deep Neural Network-Based Method for Detecting Obstructive Meibomian Gland Dysfunction With in Vivo Laser Confocal Microscopy

Cornea ◽  
2020 ◽  
Vol 39 (6) ◽  
pp. 720-725 ◽  
Author(s):  
Sachiko Maruoka ◽  
Hitoshi Tabuchi ◽  
Daisuke Nagasato ◽  
Hiroki Masumoto ◽  
Taiichiro Chikama ◽  
...  
Keyword(s):  
Neural Network ◽  
Confocal Microscopy ◽  
Deep Neural Network ◽  
Meibomian Gland ◽  
Meibomian Gland Dysfunction ◽  
Laser Confocal Microscopy

scholarly journals Deep neural network analysis employing diffusion basis spectrum imaging metrics as classifiers improves prostate cancer detection and grading

2021 ◽  
Author(s):  
Zezhong Ye ◽  
Qingsong Yang ◽  
Joshua Lin ◽  
Peng Sun ◽  
Chengwei Shao ◽  
...  
Keyword(s):  
Neural Network ◽  
Prostate Cancer ◽  
Sensitivity And Specificity ◽  
Cancer Detection ◽  
Deep Neural Network ◽  
Tumor Grade ◽  
Noninvasive Detection ◽  
Spectrum Imaging ◽  
Cellular Components

AbstractStructural and cellular complexity of prostatic histopathology limits the accuracy of noninvasive detection and grading of prostate cancer (PCa). We addressed this limitation by employing a novel diffusion basis spectrum imaging (DBSI) to derive structurally-specific diffusion fingerprints reflecting various underlying prostatic structural and cellular components. We further developed diffusion histology imaging (DHI) by combining DBSI-derived structural fingerprints with a deep neural network (DNN) algorithm to more accurately classify different histopathological features and predict tumor grade in PCa. We examined 243 patients suspected with PCa using in vivo DBSI. The in vivo DBSI-derived diffusion metrics detected coexisting prostatic pathologies distinguishing inflammation, PCa, and benign prostatic hyperplasia. DHI distinguished PCa from benign peripheral and transition zone tissues with over 95% sensitivity and specificity. DHI also demonstrated over 90% sensitivity and specificity for Gleason score noninvasively. We present DHI as a novel diagnostic tool capable of noninvasive detection and grading of PCa.One sentence summaryDiffusion histology imaging noninvasively and accurately detects and grades prostate cancer.

Sign in / Sign up

Export Citation Format

Share Document