Opening up the blackbox: an interpretable deep neural network-based classifier for cell-type specific enhancer predictions

AbstractWe propose SeqEnhDL, a deep learning framework for classifying cell type-specific enhancers based on sequence features. DNA sequences of “strong enhancer” chromatin states in nine cell types from the ENCODE project were retrieved to build and test enhancer classifiers. For any DNA sequence, sequential k-mer (k=5, 7, 9 and 11) fold changes relative to randomly selected non-coding sequences were used as features for deep learning models. Three deep learning models were implemented, including multi-layer perceptron (MLP), Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). All models in SeqEnhDL outperform state-of-the-art enhancer classifiers including gkm-SVM and DanQ, with regard to distinguishing cell type-specific enhancers from randomly selected non-coding sequences. Moreover, SeqEnhDL is able to directly discriminate enhancers from different cell types, which has not been achieved by other enhancer classifiers. Our analysis suggests that both enhancers and their tissue-specificity can be accurately identified according to their sequence features. SeqEnhDL is publicly available at https://github.com/wyp1125/SeqEnhDL.

Download Full-text

SeqEnhDL: sequence-based classification of cell type-specific enhancers using deep learning models

10.21203/rs.3.rs-94396/v1 ◽

2020 ◽

Author(s):

Yupeng Wang ◽

Rosario Jaime-Lara ◽

Abhrarup Roy ◽

Ying Sun ◽

Xinyue Liu ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Cell Types ◽

Regulatory Elements ◽

Learning Models ◽

Cell Type ◽

Coding Sequences ◽

Sequence Features ◽

A Genome ◽

Cell Type Specific

Abstract ObjectiveComputational identification of cell type-specific regulatory elements on a genome-wide scale is very challenging.ResultsWe propose SeqEnhDL, a deep learning framework for classifying cell type-specific enhancers based on sequence features. DNA sequences of “strong enhancer” chromatin states in nine cell types from the ENCODE project were retrieved to build and test enhancer classifiers. For any DNA sequence, sequential k-mer (k=5, 7, 9 and 11) fold changes relative to randomly selected non-coding sequences were used as features for deep learning models. Three deep learning models were implemented, including multi-layer perceptron (MLP), Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). All models in SeqEnhDL outperform state-of-the-art enhancer classifiers including gkm-SVM and DanQ, with regard to distinguishing cell type-specific enhancers from randomly selected non-coding sequences. Moreover, SeqEnhDL is able to directly discriminate enhancers from different cell types, which has not been achieved by other enhancer classifiers. Our analysis suggests that both enhancers and their tissue-specificity can be accurately identified according to their sequence features. SeqEnhDL is publicly available at https://github.com/wyp1125/SeqEnhDL.

Download Full-text

DeepDRIM: a deep neural network to reconstruct cell-type-specific gene regulatory network using single-cell RNA-Seq Data

10.1101/2021.02.03.429484 ◽

2021 ◽

Author(s):

Jiaxing Chen ◽

Chinwang Cheong ◽

Liang Lan ◽

Xin Zhou ◽

Jiming Liu ◽

...

Keyword(s):

Neural Network ◽

Single Cell ◽

Regulatory Networks ◽

Deep Neural Network ◽

Neighborhood Context ◽

Cellular Heterogeneity ◽

Specific Gene ◽

Rna Seq ◽

Cell Type Specific ◽

Gene Regulatory

AbstractSingle-cell RNA sequencing is used to capture cell-specific gene expression, thus allowing reconstruction of gene regulatory networks. The existing algorithms struggle to deal with dropouts and cellular heterogeneity, and commonly require pseudotime-ordered cells. Here, we describe DeepDRIM a supervised deep neural network that represents gene pair joint expression as images and considers the neighborhood context to eliminate the transitive interactions. Deep-DRIM yields significantly better performance than the other nine algorithms used on the eight cell lines tested, and can be used to successfully discriminate key functional modules between patients with mild and severe symptoms of coronavirus disease 2019 (COVID-19).

Download Full-text

Cell-type–specific neuromodulation guides synaptic credit assignment in a spiking neural network

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.2111821118 ◽

2021 ◽

Vol 118 (51) ◽

pp. e2111821118

Author(s):

Yuhan Helena Liu ◽

Stephen Smith ◽

Stefan Mihalas ◽

Eric Shea-Brown ◽

Uygar Sümbül

Keyword(s):

Neural Network ◽

Normative Theory ◽

Synaptic Connections ◽

Neuron Type ◽

Cell Type ◽

Credit Assignment ◽

Neural Network Learning ◽

Network Learning ◽

Cell Type Specific ◽

Synaptic Learning

Brains learn tasks via experience-driven differential adjustment of their myriad individual synaptic connections, but the mechanisms that target appropriate adjustment to particular connections remain deeply enigmatic. While Hebbian synaptic plasticity, synaptic eligibility traces, and top-down feedback signals surely contribute to solving this synaptic credit-assignment problem, alone, they appear to be insufficient. Inspired by new genetic perspectives on neuronal signaling architectures, here, we present a normative theory for synaptic learning, where we predict that neurons communicate their contribution to the learning outcome to nearby neurons via cell-type–specific local neuromodulation. Computational tests suggest that neuron-type diversity and neuron-type–specific local neuromodulation may be critical pieces of the biological credit-assignment puzzle. They also suggest algorithms for improved artificial neural network learning efficiency.

Download Full-text

An interpretable bimodal neural network characterizes the sequence and preexisting chromatin predictors of induced TF binding

10.1101/672790 ◽

2019 ◽

Cited By ~ 3

Author(s):

Divyanshi Srivastava ◽

Begüm Aydin ◽

Esteban O. Mazzoni ◽

Shaun Mahony

Keyword(s):

Neural Network ◽

Dna Binding ◽

Dna Sequences ◽

Binding Specificity ◽

Chromatin Accessibility ◽

Cell Type ◽

Genome Wide ◽

Binding Preference ◽

Cell Type Specific ◽

Insight Into

AbstractTranscription factor (TF) binding specificity is determined via a complex interplay between the TF’s DNA binding preference and cell type-specific chromatin environments. The chromatin features that correlate with TF binding in a given cell type have been well characterized. For instance, the binding sites for a majority of TFs display concurrent chromatin accessibility. However, concurrent chromatin features reflect the binding activities of the TF itself, and thus provide limited insight into how genome-wide TF-DNA binding patterns became established in the first place. To understand the determinants of TF binding specificity, we therefore need to examine how newly activated TFs interact with sequence and preexisting chromatin landscapes.Here, we investigate the sequence and preexisting chromatin predictors of TF-DNA binding by examining the genome-wide occupancy of TFs that have been induced in well-characterized chromatin environments. We develop Bichrom, a bimodal neural network that jointly models sequence and preexisting chromatin data to interpret the genome-wide binding patterns of induced TFs. We find that the preexisting chromatin landscape is a differential global predictor of TF-DNA binding; incorporating preexisting chromatin features improves our ability to explain the binding specificity of some TFs substantially, but not others. Furthermore, by analyzing site-level predictors, we show that TF binding in previously inaccessible chromatin tends to correspond to the presence of more favorable cognate DNA sequences. Bichrom thus provides a framework for modeling, interpreting, and visualizing the joint sequence and chromatin landscapes that determine TF-DNA binding dynamics.

Download Full-text

SeqEnhDL: sequence-based classification of cell type-specific enhancers using deep learning models

BMC Research Notes ◽

10.1186/s13104-021-05518-7 ◽

2021 ◽

Vol 14 (1) ◽

Author(s):

Yupeng Wang ◽

Rosario B. Jaime-Lara ◽

Abhrarup Roy ◽

Ying Sun ◽

Xinyue Liu ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Cell Types ◽

Regulatory Elements ◽

Learning Models ◽

Cell Type ◽

Coding Sequences ◽

Sequence Features ◽

A Genome ◽

Cell Type Specific

Abstract Objective To address the challenge of computational identification of cell type-specific regulatory elements on a genome-wide scale. Results We propose SeqEnhDL, a deep learning framework for classifying cell type-specific enhancers based on sequence features. DNA sequences of “strong enhancer” chromatin states in nine cell types from the ENCODE project were retrieved to build and test enhancer classifiers. For any DNA sequence, positional k-mer (k = 5, 7, 9 and 11) fold changes relative to randomly selected non-coding sequences across each nucleotide position were used as features for deep learning models. Three deep learning models were implemented, including multi-layer perceptron (MLP), Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). All models in SeqEnhDL outperform state-of-the-art enhancer classifiers (including gkm-SVM and DanQ) in distinguishing cell type-specific enhancers from randomly selected non-coding sequences. Moreover, SeqEnhDL can directly discriminate enhancers from different cell types, which has not been achieved by other enhancer classifiers. Our analysis suggests that both enhancers and their tissue-specificity can be accurately identified based on their sequence features. SeqEnhDL is publicly available at https://github.com/wyp1125/SeqEnhDL.

Download Full-text

The enigmatic helicase DHX9 and its association with the hallmarks of cancer

Future Science OA ◽

10.2144/fsoa-2020-0140 ◽

2021 ◽

Vol 7 (2) ◽

pp. FSO650

Author(s):

Chloe Gulliver ◽

Ralf Hoffmann ◽

George S Baillie

Keyword(s):

Tumor Suppressor ◽

Precision Medicine ◽

Signaling Pathways ◽

Therapeutic Target ◽

Cell Type ◽

Hallmarks Of Cancer ◽

Binding Partners ◽

Cell Type Specific ◽

The Impact ◽

Opening Up

Much interest has been expended lately in characterizing the association between DExH-Box helicase 9 (DHX9) dysregulation and malignant development, however, the enigmatic nature of DHX9 has caused conflict as to whether it regularly functions as an oncogene or tumor suppressor. The impact of DHX9 on malignancy appears to be cell-type specific, dependent upon the availability of binding partners and activation of inter-connected signaling pathways. Realization of DHX9’s pivotal role in the development of several hallmarks of cancer has boosted the enzyme's potential as a cancer biomarker and therapeutic target, opening up novel avenues for exploring DHX9 in precision medicine applications. Our review discusses the ascribed functions of DHX9 in cancer, explores its enigmatic nature and potential as an antineoplastic target.

Download Full-text

Neuromodulators enable overlapping synaptic memory regimes and nonlinear transition dynamics in recurrent neural networks

10.1101/2021.05.31.446462 ◽

2021 ◽

Author(s):

Ben Tsuda ◽

Stefan C Pate ◽

Kay M Tye ◽

Hava T Siegelmann ◽

Terrence J Sejnowski

Keyword(s):

Neural Network ◽

Network Activity ◽

Cell Type ◽

Transition Dynamics ◽

Linear Dose ◽

Multiplicative Factor ◽

Computational Capability ◽

Electrical Modulation ◽

Cell Type Specific ◽

Experimental Findings

Mood, arousal, and other internal neural states can drastically alter behavior, even in identical external circumstances - the proverbial glass half full or empty. Neuromodulators are critical in controlling these internal neural states, and aberrations in neuromodulatory processes are linked to various neuropsychiatric disorders. To study how neuromodulators influence neural behavior, we modeled neuromodulation as a multiplicative factor acting on synaptic transmission between neurons in a recurrent neural network. We found this simple mechanism could vastly increase the computational capability and flexibility of a neural network by enabling overlapping storage of synaptic memories able to drive diverse, even diametrically opposed, behaviors. We analyzed how local or cell-type specific neuromodulation changes network activity to support such behaviors and reproduced experimental findings of Drosophila starvation behavior. We revealed that circuits have idiosyncratic, non-linear dose-response properties that can be different for chemical versus electrical modulation. Our findings help explain how neuromodulation "unlocks" specific behaviors with important implications for neuropsychiatric therapeutics.

Download Full-text

Specular Reflections Detection and Removal Based on Deep Neural Network for Endoscope Images

10.36227/techrxiv.16918234.v1 ◽

2021 ◽

Author(s):

Tianyu Liu ◽

chongyu wang ◽

Junyu Chang ◽

Liangjing Yang

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Specular Reflection ◽

New Approach ◽

Learning Framework ◽

Specular Reflections ◽

Clinical Purpose ◽

Novel Model ◽

Opening Up ◽

Surgical Videos

Specular reflections have always been undesirable when processing endoscope vision for clinical purpose. Scene afflicted with strong specular reflection could result in visual confusion for the operation of surgical robot. In this paper, we propose a novel model based on deep learning framework, known as Surgical Fix Deep Neural Network (SFDNN). This model can effectively detect and fix the reflection points in different surgical videos hence opening up a whole new approach in handling undesirable specular reflections.

Download Full-text

Specular Reflections Detection and Removal Based on Deep Neural Network for Endoscope Images

10.36227/techrxiv.16918234 ◽

2021 ◽

Author(s):

Tianyu Liu ◽

chongyu wang ◽

Junyu Chang ◽

Liangjing Yang

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Specular Reflection ◽

New Approach ◽

Learning Framework ◽

Specular Reflections ◽

Clinical Purpose ◽

Novel Model ◽

Opening Up ◽

Surgical Videos

Specular reflections have always been undesirable when processing endoscope vision for clinical purpose. Scene afflicted with strong specular reflection could result in visual confusion for the operation of surgical robot. In this paper, we propose a novel model based on deep learning framework, known as Surgical Fix Deep Neural Network (SFDNN). This model can effectively detect and fix the reflection points in different surgical videos hence opening up a whole new approach in handling undesirable specular reflections.

Download Full-text