
Citation: Yuri M. Moshkin. Chromatin—a global buffer for eukaryotic gene control[J]. AIMS Biophysics, 2015, 2(4): 531-554. doi: 10.3934/biophy.2015.4.531
[1] | Luis Almeida, Federica Bubba, Benoît Perthame, Camille Pouchol . Energy and implicit discretization of the Fokker-Planck and Keller-Segel type equations. Networks and Heterogeneous Media, 2019, 14(1): 23-41. doi: 10.3934/nhm.2019002 |
[2] | Karoline Disser, Matthias Liero . On gradient structures for Markov chains and the passage to Wasserstein gradient flows. Networks and Heterogeneous Media, 2015, 10(2): 233-253. doi: 10.3934/nhm.2015.10.233 |
[3] | José Antonio Carrillo, Yingping Peng, Aneta Wróblewska-Kamińska . Relative entropy method for the relaxation limit of hydrodynamic models. Networks and Heterogeneous Media, 2020, 15(3): 369-387. doi: 10.3934/nhm.2020023 |
[4] | Panpan Xu, Yongbin Ge, Lin Zhang . High-order finite difference approximation of the Keller-Segel model with additional self- and cross-diffusion terms and a logistic source. Networks and Heterogeneous Media, 2023, 18(4): 1471-1492. doi: 10.3934/nhm.2023065 |
[5] | Beatrice Crippa, Anna Scotti, Andrea Villa . A monotone finite volume scheme for linear drift-diffusion and pure drift equations on one-dimensional graphs. Networks and Heterogeneous Media, 2025, 20(2): 670-700. doi: 10.3934/nhm.2025029 |
[6] | Raul Borsche, Axel Klar, T. N. Ha Pham . Nonlinear flux-limited models for chemotaxis on networks. Networks and Heterogeneous Media, 2017, 12(3): 381-401. doi: 10.3934/nhm.2017017 |
[7] | Kenneth H. Karlsen, Süleyman Ulusoy . On a hyperbolic Keller-Segel system with degenerate nonlinear fractional diffusion. Networks and Heterogeneous Media, 2016, 11(1): 181-201. doi: 10.3934/nhm.2016.11.181 |
[8] | Jin Cui, Yayun Fu . A high-order linearly implicit energy-preserving Partitioned Runge-Kutta scheme for a class of nonlinear dispersive equations. Networks and Heterogeneous Media, 2023, 18(1): 399-411. doi: 10.3934/nhm.2023016 |
[9] | Michael T. Redle, Michael Herty . An asymptotic-preserving scheme for isentropic flow in pipe networks. Networks and Heterogeneous Media, 2025, 20(1): 254-285. doi: 10.3934/nhm.2025013 |
[10] | Tingting Ma, Yayun Fu, Yuehua He, Wenjie Yang . A linearly implicit energy-preserving exponential time differencing scheme for the fractional nonlinear Schrödinger equation. Networks and Heterogeneous Media, 2023, 18(3): 1105-1117. doi: 10.3934/nhm.2023048 |
With the development of automation, electromechanical systems play an important role in modern industry [1,2]. Steering gear and rolling bearing are the core components of the mechanical and electrical systems. Once there is a fault, it might cause economic costs and even serious accidents [3,4,5]. Hence, a practical fault diagnosis scheme is a key to improve the reliability and safety. During the past several decades, Mechanical Failure Prevention Group (MFPG) and Mechanical Health Monitor Center (MHMC) have been established for fault diagnosis and prediction. Simultaneously, the mechanism of fault diagnosis is also investigated [6,7]. However, the operation of electromechanical system is a dynamic process, and the existing fault detection methods are mostly static. It is difficult to use the vibrational data directly for the rolling bearing fault diagnosis.
To solve this problem, it is recommended that the features should be extracted from the vibrational data before the fault diagnosis. Ramachandran et al. [8] proposed a proximal support vector machine (PSVM) for fault diagnosis, which uses decision tree to select the best features. In [9], the SVM, naive Bayes and K-nearest neighbor were combined to extract the envelope spectrum of current as the feature. Nishchal et al. [10] employed unsupervised learning sparse auto-encoder (SAE) to extract fault features, and then the SVM is used to diagnose the shafts and valves. In addition, the effectiveness was verified in comparison with the Mahalanobis distance fast classifier. However, modern electromechanical equipment usually has multi-monitoring points, long monitoring time and high sensor sampling frequency, which can collect massive data [11,12]. These factors intensify the difficulty of fault diagnosis. Specifically, the previous feature extraction methods based on expert knowledge are no longer suitable. Regarding this new scenario, a practical method, which can extract features automatically from massive data, is urgently needed.
In the past decade, the deep learning (DL), which has strong feature extraction ability, is developing rapidly [13]. The DL can extract the features from the original signal, which will greatly enhance the accuracy of fault diagnosis and prediction [14]. Ahmed et al. [15] introduced the artificial neural network into expert system, and the fault diagnosis accuracy can be improved. In order to optimize the fault diagnosis performance of sparse automatic encoder, Jayaswal et al. [16] utilized sparse auto-encoder depth network and backpropagation algorithm in the fine-tuning stage (the second stage), which can achieve high classification accuracy even from highly compressed measurements. In [17], a health monitoring method based on convolution network is used for fault diagnosis of bearings, wherein the data is transformed from the time domain to the frequency domain and then the data are fed into a convolution network to carry out training. By doing so, the accuracy can be increased by 6%. Kumbhar et al. [18] combined the adaptive neural fuzzy inference system (ANFIS) and dimensional analysis to conduct the fault diagnosis under different working conditions. Ajagekar et al. [19] applied quantum computing based DL to fault diagnosis, which is suitable for big data problem. In [20], a three-channel data set was established by integrating time/frequency/time-frequency domain information and a new transfer learning (TL) model was provided. Zhao et al. [21] combined dynamic wavelet weighting coefficients (DWWC) with planetary gearbox diagnosis based on the deep residual network, which can dynamically tune the weights and greatly improve the diagnosis performance. Wu et al. [22] integrated empirical wavelet transform, fuzzy entropy and SVM to diagnose the motor bearing fault. Here, the vibrational signal is decomposed into amplitude and frequency modulation components to calculate the fuzzy entropy, then the faults can be identified by using the SVM. Yu et al. [23] utilized denoising autoencoder and elastic network to denoise the signal, and then the sparse exponential discriminant analysis was used to identify the fault neurons. By doing so, the relevant fault variables on each fault neuron can be separated. A deep enhanced fusion network (DEFN) was proposed for the fault diagnosis in [24], wherein three sparse auto-encoders are applied to extract deep features from three-axial vibrational signals, respectively. By using a feature enhancement mapping, the fused three-axis features are then fed into an echo state network for fault classification. Yang et al. [25] proposed a fault diagnosis method that combines hierarchical symbolic analysis with convolutional neural network (CNN). The initial feature extraction and automatic feature learning are implemented by using a simplified network structure. In summary, the above mentioned methods have good performance in fault diagnosis under "Big Data". In practice, the useful measurements are insufficient. In addition, the CNN has remarkable capability in image recognition, classification, target detection and other areas, however, it will encounter difficulties in dealing with 1-dimensional time series.
Motivated by these previous investigations, the bearing fault diagnosis by using the Gramian angular field (GAF) and the DenseNet is proposed in this paper. The GAF can transform the 1-dimensional time series into a 2-dimensional image, which can maintain the time-dependence. Then, the converted 2-dimensional images can train a DenseNet, which can extract the image features to be used in the fault detection. In order to deal with insufficient samples, the TL is combined with the DenseNet to enhance the accuracy and effectiveness of the training model.
The rest of this paper is organized as follows. Section 2 presents the visualization of time series by using the GAF. The DenseNet based fault diagnosis is provided in Section 3. The data sets are preprocessed in Section 4. Section 5 offers the simulation results. The concluding remarks are given in Section 6.
The GAF, which maintains the time dependency, can transform a 1-dimensional time series into a 2-dimensional image [26]. The polar coordinate is used to represent the time series, and then the sum/difference trigonometric function are calculated. The Gramian angular summation field (GASF) and Gramian angular difference field (GADF) represent the sum and difference of two corners, respectively.
Consider a time series $ X = \{{x}_{1}, {x}_{2}, \cdots, {x}_{n}\} $. The normalization can map each element onto [-1, 1] and [0, 1] as
$ {\stackrel{~}{x}}_{i} = \frac{{x}_{i}-{x}_{min}}{{xmin}_{max}} $ | (1) |
$ {\tilde x_i} = \frac{{({x_i} - {x_{\min }}) + ({x_i} - {x_{\max }})}}{{{x_{\max }} - {x_{\min }}}} $ | (2) |
where $ {x}_{min} $ and $ {x}_{max} $ are the minimum and maximum values of the data sequence, respectively. Time series can be expressed in the polar coordinates by using the angle $ {\phi }_{i} $ and the radius $ {r}_{i} $, $ \left(i = 1, 2, \cdots, n\right) $. $ {\phi }_{i} $ preserves the absoluteness of time relations, $ {r}_{i} $ is represented by a timestamp $ {t}_{i} $, which guarantees the time dependence. They have the forms of
$ \left\{ϕi=arccos( xi),−1≤ xi≤1ri=tin \right. $
|
(3) |
when the time series is mapped onto [-1, 1], $ {\phi }_{i} $ is mapped onto [0, $ \pi $]. $ n $ is the constant factor of the regularized polar coordinate system, [0, 1] can be divided into $ n $ equivalent subintervals. Except the initial point 0, we can obtain $ n $ segmentation points, which are associated with $ \stackrel{~}{X} = \{{\stackrel{~}{x}}_{1}, {\stackrel{~}{x}}_{2}, \cdots, {\stackrel{~}{x}}_{n}\} $.
Due to the monotonicity of the function, each sequence has a unique polar mapping. The GAF matrixes are constructed by using the sum and difference formulae of
$ GASF=[cos(φ1+φ1)⋯cos(φ1+φn)cos(φ2+φ1)⋯cos(φ2+φn)⋮⋮⋮cos(φn+φ1)⋯cos(φn+φn)]=˜XT⋅˜X−(√I−˜X2)T⋅√I−˜X2 $
|
(4) |
$ GADF=[cos(φ1−φ1)⋯cos(φ1−φn)cos(φ2−φ1)⋯cos(φ2−φn)⋮⋮⋮cos(φn−φ1)⋯cos(φn−φn)]=(√I−˜X2)T⋅˜X−˜XT⋅√I−˜X2 $
|
(5) |
where, $ \mathrm{I} = \left[1, 1, \cdots, 1\right] $. From the above equations, we can see that the matrix elements move from the upper left to the lower right over time, the time dimension is encoded into the geometry of the matrix, and the matrix diagonal elements are single angle values, therefore, the approximate reconstruction of time series can be achieved. However, the expansion of matrix size will increase the computational complexity. To solve this problem, the piecewise aggregation approximation is introduced, which can not only maintain the sequence tendency but also can greatly reduce the sequence size.
Take $ y = {sin}t $ as an example, which is a clean signal without noise, wherein $ t\in [0, 4\pi] $ and the number of sampling points $ n = 400 $ (in Figure 1). The time series are converted into 2-dimensional images by using the GAF (in Figure 2).
In order to realize the reconstruction of the original time series and avoid the loss of characteristic information, the GAF is used to preprocess the original signal. It can clearly show the difference of data features, which is helpful for the subsequent image recognition and classification. In fact, other approaches might also be suitable for the conversion from 1-dimensional signals into a 2-dimensional image, we concentrate on the GAF to perform the mission in this paper.
DenseNet is a dense CNN, wherein the layers are pairwise connected. The outputs of each layer are the inputs of subsequent layers to maximize the characteristic information between these two layers. In addition, the gradient disappearance in the training process can also be alleviated. The DenseNet can reuse the features and the CNN architecture is easy to train. Each layer is designed to be very narrow when specifying the network structure, and only a few new features are needed to learn at a time. The 5-layer network of Figure 3 is shown as a classical model that has won the world award [27]. According to Figure 3, each layer maps the features as the characteristic inputs and pass them to other layers. For the bearing vibrational data $ {\boldsymbol{x}}_{0} $, the output characteristic matrix $ {\boldsymbol{x}}_{l} $ of the $ l $ layer module can be expressed as
$ {\boldsymbol{x}}_{l} = {H}_{l}\left(\left[{\boldsymbol{x}}_{0}, {\boldsymbol{x}}_{1}, \cdots , {\boldsymbol{x}}_{l-1}\right]\right) $ | (6) |
where, $ {\boldsymbol{x}}_{1}, \cdots, {\boldsymbol{x}}_{l-1} $ are the outputs of each dense layer. $ {H}_{l} $ is a composite function, which includes batch normalization (BN), ReLU and $ 3\times 3 $ convolution function.
When the feature size is changed, Eq (6) is no longer applicable. The pooling layer, which is included in the transition layer, is needed to reduce the dimensional size of the feature. Assuming that $ {H}_{l} $ generates additional $ k $ features, and $ k $ is also the DenseNet growth rate, then the $ l $ layer has $ {k}_{0}+k(l-1) $ features, where $ {k}_{0} $ is the number of input features channels. Therefore, $ k = 4 $ in Figure 3.
The DenseNet has fewer parameters with small storage requirement and easier network training. Therefore, it is more suitable for feature extraction and fault diagnosis. However, CNN is a data-driven model, which requires a large number of labeled data to obtain satisfactory results, which leads to limitations in some applications.
In this section, the TL is introduced to address the sample dependency of the DenseNet in training models. In combination of CNN and TL, the network framework trained on specific data sets can be applied to new problems and new fields that need to be solved. The TL can generalize the source field knowledge to solve the target field task [28,29,30]. The definition is as follows.
Definition 1. Given the source definition domain $ {D}_{s} $, the learning task $ {T}_{s} $, the object definition domain $ {D}_{t} $ and the learning task $ {T}_{t} $. The knowledge of $ {D}_{s} $ and $ {T}_{s} $ are used to improve the results of object prediction function $ {f}_{t}\left(\cdot \right) $, which is on $ {D}_{t} $, wherein $ {D}_{s}\ne {D}_{t} $ and $ {T}_{s}\ne {T}_{t} $.
Remark 1. The domain $ D = \left\{X, P\left(X\right)\right\} $, the task $ T = \left\{Y, P\left(Y|X\right)\right\} $, $ f\left(\cdot \right) = P\left(Y|X\right) $, therefore $ {D}_{s}\ne {D}_{t} $ represents $ {X}_{s}\ne {X}_{t} $ or $ {P}_{s}\left(X\right)\ne {P}_{t}\left(X\right) $, the same as $ T $.
In this paper, the source dataset is the CIFAR (Canadian Institute for Advanced Research), and the target dataset is the CWRU (Case Western Reserve University). The combination of TL and CNN implementation process is as follows:
a) the CIFAR dataset is used to train the random initialization parameters;
b) the trained network framework is applied to the specific problem to be solved, and the data features are extracted automatically;
c) the extracted features are input into the CNN to diagnose and classify bearing faults.
The combination of TL and CNN can greatly improve the accuracy of network fault diagnosis, reduce the complexity of network training, avoid the dependence of artificial parameters on expert experience. It can also handle the insufficient samples problem, reducing training time and memory consumption. At the same time, the inherent pattern of the network model is changed, which enhances the network model applicability. Therefore, we can train a general model with insufficient samples in the absence of supervision.
The method is verified on the CWRU bearing data center, which has become the evaluation criterion for rolling bearing fault diagnosis [31,32].
The CWRU bearing experimental platform, which consists of a 2 horsepower (1.5 kw) motor, a torque sensor/decoder and a power tester, is shown in Figure 4 [31]. One motor end is connected to the fan end bearing, and the other end is connected to the drive end bearing. The acceleration sensor, which receives the bearing vibrational signal, is installed on each bearing. An electrical discharge machining (EDM) is used to cause inner/outer ring and rolling element faults and the faults diameters are 0.007, 0.014 and 0.021 inches, respectively. The single point fault of rolling bearing is reloaded to the test motor. The vibrational acceleration signal data, which have 0, 1, 2 and 3 horsepower loads, respectively, are collected by using a 16-channel data recorder. In addition, the sampling frequency is 12 kHz.
The samples include 8 normal samples, 23 inner ring fault samples, 53 outer ring fault samples and 11 rolling element fault samples. In this paper, we use 9 samples, which include three different fault diameters and locations, to train the CNN.
In this paper, the samples of fan end without load, which composes 240, 000 normal data and 120, 000 fault data of each type, are used. The non-overlapping sliding window is selected, and the image size is $ 300\times 300 $. Figure 5 shows the GASF and GADF images by using the same samples.
According to Figure 5, the GADF image is easy to distinguish. Therefore, GADF image can be selected for subsequent fault diagnosis. The fault-free GADF image is numbered 0 (in Figure 6), the GADF images corresponding to the different faults are numbered from 1 to 9 (in Figure 7), respectively.
The fault detection of the bearing is carried out by using the Tensorflow. The simulation platform is configured as follows: 64-bit Windows10 operating system, i7-10700k (CPU), NVIDIA Tesla P100 (GPU), the code is written in python3.7. The compilation software is Spyder and Jupyter Notebook. The Pytorch and Scikit-learn are used to train the CNN.
The analysis steps are as follows:
a) the 1-dimensional time series samples can be transformed into 2-dimensional images by using GAF;
b) the samples are divided, and then the CNN is trained. By changing different batch sizes, the results of different optimization methods can be obtained;
c) the sample datasets are extended by different coincidence rate, and CNN is trained with different batch sizes of samples;
d) the 2/3 coincidence rate of the samples are selected to train the DenseNet121 and ResNet18 networks in combination with the TL.
The GADF images of bearings (Figures 6 and 7), which are divided into 70% training set and 30% test set, are put into the CNN with the structure parameters as shown in Table 1. The initial learning rate is $ 1{0}^{-3} $, the epochs is 5, and the batch sizes are 20, 10 and 2, respectively. Two optimizers, the stochastic gradient descent (SGD) and the Adams, are selected. Table 2 shows the training accuracy results, and the training loss values are shown in Table 3.
Convolution layer | Input (N, C, W, H) | Convolution kernel (size, input, output) | Activation function | Output (N, C, W, H) |
1 | [128,4,300,300] | [5 × 5, 4, 16] | ReLU | [128,16,150,150] |
2 | [128,16,150,150] | [5 × 5, 16, 32] | ReLU | [128,32,75,75] |
3 | [128,32,75,75] | [5 × 5, 32, 64] | ReLU | [128,64,36,36] |
4 | [128,64,36,36] | [5 × 5, 64, 64] | ReLU | [128,64,4,4] |
Batch size | SGD | Adam |
20 | 83.03% | 73.26% |
10 | 83.33% | 72.58% |
2 | 86.44% | 71.46% |
Batch size | SGD | Adam |
20 | 0.5040 | 1.0498 |
10 | 0.5522 | 1.6858 |
2 | 0.5817 | 1.8479 |
According to Tables 2 and 3, the accuracy is not high enough and the training loss value cannot be reduced to a reasonable range. Although all the samples have been used for model training, the results are still not satisfactory. Therefore, the samples need to be expanded to obtain a useful training model.
The repetition rate of the sliding window is set to 2/3, then the normal samples (Figure 8) and different fault samples (Figure 9) can come to 2398 and 9 × 1198, respectively.
In addition, 4795 normal samples and 9 × 2395 different fault samples are obtained by setting 5/6 repetition rate. The CNN with the same structure is used for model training. The training accuracy and loss values for different batch sizes and repetition rates are shown in Tables 4 and 5, respectively.
Batch size | Repetition rate: 2/3 | Repetition rate: 5/6 |
20 | 92.10% | 96.28% |
10 | 91.69% | 94.70% |
2 | 92.65% | 90.34% |
Batch size | Repetition rate: 2/3 | Repetition rate: 5/6 |
20 | 0.3478 | 0.1201 |
10 | 0.4082 | 0.1886 |
2 | 0.3655 | 0.3635 |
According to Tables 4 and 5, the model accuracy can be greatly enhanced and the loss function can also reach within an acceptable range when the number of samples increases. The best accuracy can reach 96.28% through the basic CNN. Also each index has reached at a reasonable range. However, further improvement is needed.
To achieve better results, the ResNet and the DenseNet are trained by using the extended GADF images, wherein the TL is employed. The structure parameters of the two networks are shown in Tables 6 and 7, respectively.
Convolution layer | Parameters | Output |
Conv 1 | 7 × 7, 64, step length = 2 | 112 × 112 |
Conv 2 | $ \left[{3×3,643×3,64 } \right] \times 2 $ |
56 × 56 |
Conv 3 | $ \left[{3×3,1283×3,128 } \right] \times 2 $ |
28 × 28 |
Conv 4 | $ \left[{3×3,2563×3,256 } \right] \times 2 $ |
14 × 14 |
Conv 5 | $ \left[{3×3,5123×3,512 } \right] \times 2 $ |
7 × 7 |
Pooling layer | Average pooling | 1 × 1 |
Layer | Parameter | Output Size |
Convolution layer | 7 × 7, conv, stride = 2 | 112 × 112 |
Pooling | 3 × 3 max pooling, stride = 2 | 56 × 56 |
Block1 | $ \left[{1×13×3 } \right] \times 6 $ |
56 × 56 |
Transition layer 1 | 1 × 1 conv | 56 × 56 |
2 × 2 average pooling, stride = 2 | 28 × 28 | |
Block 2 | $ \left[{1×13×3 } \right] \times 12 $ |
28 × 28 |
Transition layer 2 | 1 × 1 conv | 28 × 28 |
2 × 2 average pooling, stride = 2 | 14 × 14 | |
Block 3 | $ \left[{1×13×3 } \right] \times 24 $ |
14 × 14 |
Transition layer 3 | 1 × 1 conv | 14 × 14 |
2 × 2 average pooling, stride = 2 | 7 × 7 | |
Block 4 | $ \left[{1×13×3 } \right] \times 16 $ |
7 × 7 |
Taxonomic hierarchies | 7 × 7 global average pooling | 1 × 1 |
A fully connected layer of 1000 dimensions, Softmax |
The results show that the training model accuracy can be as high as 99.69% (ResNet18) and 99.83% (DenseNet121), respectively; and the loss functions are also reduced to 0.013 (ResNet18) and 0.005 (DenseNet121). Compared with the existing basic CNN method, the augmented CNN approach based on expanded samples and the ResNet, the proposed scheme can achieve the best performance with regard to the accuracy and loss values.
In this paper, a bearing fault diagnosis method based on the GAF and the CNN, which could realize the classification diagnosis, was proposed. The GAF could convert time series information into a GADF image, which makes the fault diagnosis to be more intuitive. In addition, the GAF could also ensure the integrity of feature information and handle the time-dependent issue, which is suitable for the processing of non-stationary signals such as bearing vibration signals. The DenseNet was trained by using the GADF images, which could enhance the low classification accuracy caused by measurement noise in the original bearing signal. The TL, which could avoid the inaccurate training model caused by insufficient samples, was applied in the DenseNet. The simulation results demonstrate the effectiveness of the proposed method.
This work was supported by the National Natural Science Foundation of China (grant number 62073177, 61973175, 52175038).
The authors declare there is no conflict of interest.
[1] |
Lynch M (2006) Streamlining and simplification of microbial genome architecture. Annu Rev Microbiol 60: 327–349. doi: 10.1146/annurev.micro.60.080805.142300
![]() |
[2] |
Wade JT, Struhl K, Busby SJ, et al. (2007) Genomic analysis of protein-DNA interactions in bacteria: insights into transcription and chromosome organization. Mol Microbiol 65: 21–26. doi: 10.1111/j.1365-2958.2007.05781.x
![]() |
[3] |
Wade JT, Reppas NB, Church GM, et al. (2005) Genomic analysis of LexA binding reveals the permissive nature of the Escherichia coli genome and identifies unconventional target sites. Genes Dev 19: 2619–2630. doi: 10.1101/gad.1355605
![]() |
[4] |
Ptashne M (2011) Principles of a switch. Nat Chem Biol 7: 484–487. doi: 10.1038/nchembio.611
![]() |
[5] |
Jacob F, Monod J (1961) Genetic regulatory mechanisms in the synthesis of proteins. J Mol Biol 3: 318–356. doi: 10.1016/S0022-2836(61)80072-7
![]() |
[6] |
Wall ME, Hlavacek WS, Savageau MA (2004) Design of gene circuits: lessons from bacteria. Nat Rev Genet 5: 34–42. doi: 10.1038/nrg1244
![]() |
[7] |
Ronen M, Rosenberg R, Shraiman BI, et al. (2002) Assigning numbers to the arrows: parameterizing a gene regulation network by using accurate expression kinetics. Proc Natl Acad Sci U S A 99: 10555–10560. doi: 10.1073/pnas.152046799
![]() |
[8] |
Saiz L (2012) The physics of protein-DNA interaction networks in the control of gene expression. J Phys Condens Matter 24: 193102. doi: 10.1088/0953-8984/24/19/193102
![]() |
[9] |
Lewis M (2005) The lac repressor. C R Biol 328: 521–548. doi: 10.1016/j.crvi.2005.04.004
![]() |
[10] |
Yaniv M (2011) The 50th anniversary of the publication of the operon theory in the Journal of Molecular Biology: past, present and future. J Mol Biol 409: 1–6. doi: 10.1016/j.jmb.2011.03.041
![]() |
[11] |
Hill RJ, Billas IM, Bonneton F, et al. (2013) Ecdysone receptors: from the Ashburner model to structural biology. Annu Rev Entomol 58: 251–271. doi: 10.1146/annurev-ento-120811-153610
![]() |
[12] |
Ashburner M, Chihara C, Meltzer P, et al. (1974) Temporal control of puffing activity in polytene chromosomes. Cold Spring Harb Symp Quant Biol 38: 655–662. doi: 10.1101/SQB.1974.038.01.070
![]() |
[13] | Vologodskiĭ AV (2015) Biophysics of DNA. New York: Cambridge University Press. 272 p. |
[14] |
Vologodskaia M, Vologodskii A (2002) Contribution of the intrinsic curvature to measured DNA persistence length. J Mol Biol 317: 205–213. doi: 10.1006/jmbi.2001.5366
![]() |
[15] |
Hagerman PJ (1988) Flexibility of DNA. Annu Rev Biophys Biophys Chem 17: 265–286. doi: 10.1146/annurev.bb.17.060188.001405
![]() |
[16] |
Chereji RV, Morozov AV (2015) Functional roles of nucleosome stability and dynamics. Brief Funct Genomics 14: 50–60. doi: 10.1093/bfgp/elu038
![]() |
[17] | Mirny LA (2011) The fractal globule as a model of chromatin architecture in the cell. Chromosome Res 19: 37–51. |
[18] |
Oudet P, Gross-Bellard M, Chambon P (1975) Electron microscopic and biochemical evidence that chromatin structure is a repeating unit. Cell 4: 281–300. doi: 10.1016/0092-8674(75)90149-X
![]() |
[19] |
Luger K, Mader AW, Richmond RK, et al. (1997) Crystal structure of the nucleosome core particle at 2. 8 A resolution. Nature 389: 251-260. doi: 10.1038/38444
![]() |
[20] |
McGinty RK, Tan S (2015) Nucleosome structure and function. Chem Rev 115: 2255–2273. doi: 10.1021/cr500373h
![]() |
[21] | Cutter AR, Hayes JJ (2015) A brief review of nucleosome structure. FEBS Lett pii: S0014-5793(15)00392-0. |
[22] |
Kornberg RD (1974) Chromatin structure: a repeating unit of histones and DNA. Science 184: 868–871. doi: 10.1126/science.184.4139.868
![]() |
[23] |
Olins AL, Olins DE (1974) Spheroid chromatin units (v bodies). Science 183: 330–332. doi: 10.1126/science.183.4122.330
![]() |
[24] |
Woodcock CL, Safer JP, Stanchfield JE (1976) Structural repeating units in chromatin. I. Evidence for their general occurrence. Exp Cell Res 97: 101-110. doi: 10.1016/0014-4827(76)90659-5
![]() |
[25] | Van Holde KE (1989) Chromatin. New York: Springer-Verlag. xii, 497 p. |
[26] |
Song F, Chen P, Sun D, et al. (2014) Cryo-EM study of the chromatin fiber reveals a double helix twisted by tetranucleosomal units. Science 344: 376–380. doi: 10.1126/science.1251413
![]() |
[27] |
Balhorn R (2007) The protamine family of sperm nuclear proteins. Genome Biol 8: 227. doi: 10.1186/gb-2007-8-9-227
![]() |
[28] |
Ward WS (2010) Function of sperm chromatin structural elements in fertilization and development. Mol Hum Reprod 16: 30–36. doi: 10.1093/molehr/gap080
![]() |
[29] |
Hud NV, Allen MJ, Downing KH, et al. (1993) Identification of the elemental packing unit of DNA in mammalian sperm cells by atomic force microscopy. Biochem Biophys Res Commun 193: 1347–1354. doi: 10.1006/bbrc.1993.1773
![]() |
[30] |
Brewer LR (2011) Deciphering the structure of DNA toroids. Integr Biol (Camb) 3: 540–547. doi: 10.1039/c0ib00128g
![]() |
[31] | Hammoud SS, Nix DA, Zhang H, et al. (2009) Distinctive chromatin in human sperm packages genes for embryo development. Nature 460: 473–478. |
[32] |
Ward MA, Ward WS (2004) A model for the function of sperm DNA degradation. Reprod Fertil Dev 16: 547–554. doi: 10.1071/RD03072
![]() |
[33] | Furlong D, Swift H, Roizman B (1972) Arrangement of herpesvirus deoxyribonucleic acid in the core. J Virol 10: 1071–1074. |
[34] |
Cerritelli ME, Cheng N, Rosenberg AH, et al. (1997) Encapsidated conformation of bacteriophage T7 DNA. Cell 91: 271–280. doi: 10.1016/S0092-8674(00)80409-2
![]() |
[35] |
Agirrezabala X, Martin-Benito J, Caston JR, et al. (2005) Maturation of phage T7 involves structural modification of both shell and inner core components. EMBO J 24: 3820–3829. doi: 10.1038/sj.emboj.7600840
![]() |
[36] |
Hud NV, Downing KH (2001) Cryoelectron microscopy of lambda phage DNA condensates in vitreous ice: the fine structure of DNA toroids. Proc Natl Acad Sci U S A 98: 14925–14930. doi: 10.1073/pnas.261560398
![]() |
[37] |
Sun S, Wong JT, Liu M, et al. (2012) Counterion-mediated decompaction of liquid crystalline chromosomes. DNA Cell Biol 31: 1657–1664. doi: 10.1089/dna.2012.1708
![]() |
[38] |
Levi-Setti R, Gavrilov KL, Rizzo PJ (2008) Divalent cation distribution in dinoflagellate chromosomes imaged by high-resolution ion probe mass spectrometry. Eur J Cell Biol 87: 963–976. doi: 10.1016/j.ejcb.2008.06.002
![]() |
[39] |
Livolant F, Maestre MF (1988) Circular dichroism microscopy of compact forms of DNA and chromatin in vivo and in vitro: cholesteric liquid-crystalline phases of DNA and single dinoflagellate nuclei. Biochemistry 27: 3056–3068. doi: 10.1021/bi00408a058
![]() |
[40] |
Rill RL, Livolant F, Aldrich HC, et al. (1989) Electron microscopy of liquid crystalline DNA: direct evidence for cholesteric-like organization of DNA in dinoflagellate chromosomes. Chromosoma 98: 280–286. doi: 10.1007/BF00327314
![]() |
[41] |
Chow MH, Yan KT, Bennett MJ, et al. (2010) Birefringence and DNA condensation of liquid crystalline chromosomes. Eukaryot Cell 9: 1577–1587. doi: 10.1128/EC.00026-10
![]() |
[42] |
Wisecaver JH, Hackett JD (2011) Dinoflagellate genome evolution. Annu Rev Microbiol 65: 369–387. doi: 10.1146/annurev-micro-090110-102841
![]() |
[43] |
Kellenberger E, Arnold-Schulz-Gahmen B (1992) Chromatins of low-protein content: special features of their compaction and condensation. FEMS Microbiol Lett 100: 361–370. doi: 10.1111/j.1574-6968.1992.tb05727.x
![]() |
[44] |
Kellenberger E (1988) About the organisation of condensed and decondensed non-eukaryotic DNA and the concept of vegetative DNA (a critical review). Biophys Chem 29: 51–62. doi: 10.1016/0301-4622(88)87024-8
![]() |
[45] |
Strzelecka TE, Davidson MW, Rill RL (1988) Multiple liquid crystal phases of DNA at high concentrations. Nature 331: 457–460. doi: 10.1038/331457a0
![]() |
[46] |
Olesiak-Banska J, Mojzisova H, Chauvat D, et al. (2011) Liquid crystal phases of DNA: evaluation of DNA organization by two-photon fluorescence microscopy and polarization analysis. Biopolymers 95: 365–375. doi: 10.1002/bip.21583
![]() |
[47] |
Finch JT, Klug A (1976) Solenoidal model for superstructure in chromatin. Proc Natl Acad Sci U S A 73: 1897–1901. doi: 10.1073/pnas.73.6.1897
![]() |
[48] |
Woodcock CL, Frado LL, Rattner JB (1984) The higher-order structure of chromatin: evidence for a helical ribbon arrangement. J Cell Biol 99: 42–52. doi: 10.1083/jcb.99.1.42
![]() |
[49] |
Robinson PJ, Fairall L, Huynh VA, et al. (2006) EM measurements define the dimensions of the "30-nm" chromatin fiber: evidence for a compact, interdigitated structure. Proc Natl Acad Sci U S A 103: 6506–6511. doi: 10.1073/pnas.0601212103
![]() |
[50] |
Dorigo B, Schalch T, Kulangara A, et al. (2004) Nucleosome arrays reveal the two-start organization of the chromatin fiber. Science 306: 1571–1573. doi: 10.1126/science.1103124
![]() |
[51] |
Schalch T, Duda S, Sargent DF, et al. (2005) X-ray structure of a tetranucleosome and its implications for the chromatin fibre. Nature 436: 138–141. doi: 10.1038/nature03686
![]() |
[52] |
Maeshima K, Imai R, Tamura S, et al. (2014) Chromatin as dynamic 10-nm fibers. Chromosoma 123: 225–237. doi: 10.1007/s00412-014-0460-2
![]() |
[53] |
van Holde K, Zlatanova J (2007) Chromatin fiber structure: Where is the problem now? Semin Cell Dev Biol 18: 651–658. doi: 10.1016/j.semcdb.2007.08.005
![]() |
[54] |
Razin SV, Gavrilov AA (2014) Chromatin without the 30-nm fiber: constrained disorder instead of hierarchical folding. Epigenetics 9: 653–657. doi: 10.4161/epi.28297
![]() |
[55] |
Eltsov M, Maclellan KM, Maeshima K, et al. (2008) Analysis of cryo-electron microscopy images does not support the existence of 30-nm chromatin fibers in mitotic chromosomes in situ. Proc Natl Acad Sci U S A 105: 19732–19737. doi: 10.1073/pnas.0810057105
![]() |
[56] |
Eltsov M, Sosnovski S, Olins AL, et al. (2014) ELCS in ice: cryo-electron microscopy of nuclear envelope-limited chromatin sheets. Chromosoma 123: 303–312. doi: 10.1007/s00412-014-0454-0
![]() |
[57] |
Fussner E, Strauss M, Djuric U, et al. (2012) Open and closed domains in the mouse genome are configured as 10-nm chromatin fibres. EMBO Rep 13: 992–996. doi: 10.1038/embor.2012.139
![]() |
[58] | Li G, Zhu P (2015) Structure and organization of chromatin fiber in the nucleus. FEBS Lett. |
[59] |
Felsenfeld G, Groudine M (2003) Controlling the double helix. Nature 421: 448–453. doi: 10.1038/nature01411
![]() |
[60] |
Rosa A, Everaers R (2008) Structure and dynamics of interphase chromosomes. PLoS Comput Biol 4: e1000153. doi: 10.1371/journal.pcbi.1000153
![]() |
[61] |
Dekker J, Rippe K, Dekker M, et al. (2002) Capturing chromosome conformation. Science 295: 1306–1311. doi: 10.1126/science.1067799
![]() |
[62] |
Simonis M, Klous P, Splinter E, et al. (2006) Nuclear organization of active and inactive chromatin domains uncovered by chromosome conformation capture-on-chip (4C). Nat Genet 38: 1348–1354. doi: 10.1038/ng1896
![]() |
[63] |
Dostie J, Richmond TA, Arnaout RA, et al. (2006) Chromosome Conformation Capture Carbon Copy (5C): a massively parallel solution for mapping interactions between genomic elements. Genome Res 16: 1299–1309. doi: 10.1101/gr.5571506
![]() |
[64] |
Lieberman-Aiden E, van Berkum NL, Williams L, et al. (2009) Comprehensive mapping of long-range interactions reveals folding principles of the human genome. Science 326: 289–293. doi: 10.1126/science.1181369
![]() |
[65] |
Zhang Y, McCord RP, Ho YJ, et al. (2012) Spatial organization of the mouse genome and its role in recurrent chromosomal translocations. Cell 148: 908–921. doi: 10.1016/j.cell.2012.02.002
![]() |
[66] |
Mizuguchi T, Fudenberg G, Mehta S, et al. (2014) Cohesin-dependent globules and heterochromatin shape 3D genome architecture in S. pombe. Nature 516: 432–435. doi: 10.1038/nature13833
![]() |
[67] |
Tamm MV, Nazarov LI, Gavrilov AA, et al. (2015) Anomalous diffusion in fractal globules. Phys Rev Lett 114: 178102. doi: 10.1103/PhysRevLett.114.178102
![]() |
[68] |
Fudenberg G, Getz G, Meyerson M, et al. (2011) High order chromatin architecture shapes the landscape of chromosomal alterations in cancer. Nat Biotechnol 29: 1109–1113. doi: 10.1038/nbt.2049
![]() |
[69] |
Schram RD, Barkema GT, Schiessel H (2013) On the stability of fractal globules. J Chem Phys 138: 224901. doi: 10.1063/1.4807723
![]() |
[70] |
Bohn M, Heermann DW (2010) Diffusion-driven looping provides a consistent framework for chromatin organization. PLoS One 5: e12218. doi: 10.1371/journal.pone.0012218
![]() |
[71] |
Tark-Dame M, Jerabek H, Manders EM, et al. (2014) Depletion of the chromatin looping proteins CTCF and cohesin causes chromatin compaction: insight into chromatin folding by polymer modelling. PLoS Comput Biol 10: e1003877. doi: 10.1371/journal.pcbi.1003877
![]() |
[72] |
Barbieri M, Chotalia M, Fraser J, et al. (2012) Complexity of chromatin folding is captured by the strings and binders switch model. Proc Natl Acad Sci U S A 109: 16173–16178. doi: 10.1073/pnas.1204799109
![]() |
[73] |
Nicodemi M, Pombo A (2014) Models of chromosome structure. Curr Opin Cell Biol 28: 90–95. doi: 10.1016/j.ceb.2014.04.004
![]() |
[74] | Moscalets AP, Nazarov LI, Tamm MV (2015) Towards a robust algorithm to determine topological domains from colocalization data. AIMS Biophysics 2: 503–516. |
[75] | Caré BR, Emeriau PE, Cortini R, et al. (2015) Chromatin epigenomic domain folding: size matters. AIMS Biophysics 2: 517–530. |
[76] |
Turner BM, Birley AJ, Lavender J (1992) Histone H4 isoforms acetylated at specific lysine residues define individual chromosomes and chromatin domains in Drosophila polytene nuclei. Cell 69: 375–384. doi: 10.1016/0092-8674(92)90417-B
![]() |
[77] |
Strahl BD, Allis CD (2000) The language of covalent histone modifications. Nature 403: 41–45. doi: 10.1038/47412
![]() |
[78] |
Jenuwein T, Allis CD (2001) Translating the histone code. Science 293: 1074–1080. doi: 10.1126/science.1063127
![]() |
[79] |
Kouzarides T (2007) SnapShot: Histone-modifying enzymes. Cell 131: 822. doi: 10.1016/j.cell.2007.11.005
![]() |
[80] |
Kutateladze TG (2011) SnapShot: Histone readers. Cell 146: 842-842 e841. doi: 10.1016/j.cell.2011.08.022
![]() |
[81] |
Huang H, Sabari BR, Garcia BA, et al. (2014) SnapShot: histone modifications. Cell 159: 458–458 e451. doi: 10.1016/j.cell.2014.09.037
![]() |
[82] |
Ptashne M (2013) Epigenetics: core misconcept. Proc Natl Acad Sci U S A 110: 7101–7103. doi: 10.1073/pnas.1305399110
![]() |
[83] |
Iwafuchi-Doi M, Zaret KS (2014) Pioneer transcription factors in cell reprogramming. Genes Dev 28: 2679–2692. doi: 10.1101/gad.253443.114
![]() |
[84] |
Lidor Nili E, Field Y, Lubling Y, et al. (2010) p53 binds preferentially to genomic regions with high DNA-encoded nucleosome occupancy. Genome Res 20: 1361-1368. doi: 10.1101/gr.103945.109
![]() |
[85] |
Ballare C, Castellano G, Gaveglia L, et al. (2013) Nucleosome-driven transcription factor binding and gene regulation. Mol Cell 49: 67–79. doi: 10.1016/j.molcel.2012.10.019
![]() |
[86] |
Barozzi I, Simonatto M, Bonifacio S, et al. (2014) Coregulation of transcription factor binding and nucleosome occupancy through DNA features of mammalian enhancers. Mol Cell 54: 844–857. doi: 10.1016/j.molcel.2014.04.006
![]() |
[87] |
Cui F, Zhurkin VB (2014) Rotational positioning of nucleosomes facilitates selective binding of p53 to response elements associated with cell cycle arrest. Nucleic Acids Res 42: 836–847. doi: 10.1093/nar/gkt943
![]() |
[88] | Kal AJ, Mahmoudi T, Zak NB, et al. (2000) The Drosophila brahma complex is an essential coactivator for the trithorax group protein zeste. Genes Dev 14: 1058–1071. |
[89] |
Cirillo LA, Lin FR, Cuesta I, et al. (2002) Opening of compacted chromatin by early developmental transcription factors HNF3 (FoxA) and GATA-4. Mol Cell 9: 279–289. doi: 10.1016/S1097-2765(02)00459-8
![]() |
[90] |
Hsu HT, Chen HM, Yang Z, et al. (2015) TRANSCRIPTION. Recruitment of RNA polymerase II by the pioneer transcription factor PHA-4. Science 348: 1372-1376. doi: 10.1126/science.aab1223
![]() |
[91] |
Soufi A, Garcia MF, Jaroszewicz A, et al. (2015) Pioneer transcription factors target partial DNA motifs on nucleosomes to initiate reprogramming. Cell 161: 555–568. doi: 10.1016/j.cell.2015.03.017
![]() |
[92] |
Adam RC, Yang H, Rockowitz S, et al. (2015) Pioneer factors govern super-enhancer dynamics in stem cell plasticity and lineage choice. Nature 521: 366–370. doi: 10.1038/nature14289
![]() |
[93] |
Oldfield AJ, Yang P, Conway AE, et al. (2014) Histone-fold domain protein NF-Y promotes chromatin accessibility for cell type-specific master transcription factors. Mol Cell 55: 708–722. doi: 10.1016/j.molcel.2014.07.005
![]() |
[94] |
Takahashi K, Yamanaka S (2006) Induction of pluripotent stem cells from mouse embryonic and adult fibroblast cultures by defined factors. Cell 126: 663–676. doi: 10.1016/j.cell.2006.07.024
![]() |
[95] |
Okita K, Ichisaka T, Yamanaka S (2007) Generation of germline-competent induced pluripotent stem cells. Nature 448: 313–317. doi: 10.1038/nature05934
![]() |
[96] |
Takahashi K, Tanabe K, Ohnuki M, et al. (2007) Induction of pluripotent stem cells from adult human fibroblasts by defined factors. Cell 131: 861–872. doi: 10.1016/j.cell.2007.11.019
![]() |
[97] |
Gardner KE, Allis CD, Strahl BD (2011) Operating on chromatin, a colorful language where context matters. J Mol Biol 409: 36–46. doi: 10.1016/j.jmb.2011.01.040
![]() |
[98] |
Ruthenburg AJ, Allis CD, Wysocka J (2007) Methylation of lysine 4 on histone H3: intricacy of writing and reading a single epigenetic mark. Mol Cell 25: 15–30. doi: 10.1016/j.molcel.2006.12.014
![]() |
[99] |
Ruiz-Carrillo A, Wangh LJ, Allfrey VG (1975) Processing of newly synthesized histone molecules. Science 190: 117–128. doi: 10.1126/science.1166303
![]() |
[100] |
Brownell JE, Zhou J, Ranalli T, et al. (1996) Tetrahymena histone acetyltransferase A: a homolog to yeast Gcn5p linking histone acetylation to gene activation. Cell 84: 843–851. doi: 10.1016/S0092-8674(00)81063-6
![]() |
[101] |
Allfrey VG, Faulkner R, Mirsky AE (1964) Acetylation and Methylation of Histones and Their Possible Role in the Regulation of Rna Synthesis. Proc Natl Acad Sci U S A 51: 786–794. doi: 10.1073/pnas.51.5.786
![]() |
[102] |
Taunton J, Hassig CA, Schreiber SL (1996) A mammalian histone deacetylase related to the yeast transcriptional regulator Rpd3p. Science 272: 408–411. doi: 10.1126/science.272.5260.408
![]() |
[103] |
De Rubertis F, Kadosh D, Henchoz S, et al. (1996) The histone deacetylase RPD3 counteracts genomic silencing in Drosophila and yeast. Nature 384: 589–591. doi: 10.1038/384589a0
![]() |
[104] |
Turner BM (2014) Nucleosome signalling; an evolving concept. Biochim Biophys Acta 1839: 623–626. doi: 10.1016/j.bbagrm.2014.01.001
![]() |
[105] |
Vermeulen M, Eberl HC, Matarese F, et al. (2010) Quantitative interaction proteomics and genome-wide profiling of epigenetic histone marks and their readers. Cell 142: 967–980. doi: 10.1016/j.cell.2010.08.020
![]() |
[106] |
Koche RP, Smith ZD, Adli M, et al. (2011) Reprogramming factor expression initiates widespread targeted chromatin remodeling. Cell Stem Cell 8: 96–105. doi: 10.1016/j.stem.2010.12.001
![]() |
[107] |
Hatfield GW, Benham CJ (2002) DNA topology-mediated control of global gene expression in Escherichia coli. Annu Rev Genet 36: 175–203. doi: 10.1146/annurev.genet.36.032902.111815
![]() |
[108] | Hsieh LS, Rouviere-Yaniv J, Drlica K (1991) Bacterial DNA supercoiling and [ATP]/[ADP] ratio: changes associated with salt shock. J Bacteriol 173: 3914–3917. |
[109] |
Kusano S, Ding Q, Fujita N, et al. (1996) Promoter selectivity of Escherichia coli RNA polymerase E sigma 70 and E sigma 38 holoenzymes. Effect of DNA supercoiling. J Biol Chem 271: 1998-2004. doi: 10.1074/jbc.271.4.1998
![]() |
[110] |
Higgins CF, Dorman CJ, Stirling DA, et al. (1988) A physiological role for DNA supercoiling in the osmotic regulation of gene expression in S. typhimurium and E. coli. Cell 52: 569-584. doi: 10.1016/0092-8674(88)90470-9
![]() |
[111] | Sugino A, Cozzarelli NR (1980) The intrinsic ATPase of DNA gyrase. J Biol Chem 255: 6299–6306. |
[112] |
Sinden RR, Carlson JO, Pettijohn DE (1980) Torsional tension in the DNA double helix measured with trimethylpsoralen in living E. coli cells: analogous measurements in insect and human cells. Cell 21: 773-783. doi: 10.1016/0092-8674(80)90440-7
![]() |
[113] |
Travers A, Muskhelishvili G (2005) DNA supercoiling - a global transcriptional regulator for enterobacterial growth? Nat Rev Microbiol 3: 157–169. doi: 10.1038/nrmicro1088
![]() |
[114] |
Sobetzko P, Travers A, Muskhelishvili G (2012) Gene order and chromosome dynamics coordinate spatiotemporal gene expression during the bacterial growth cycle. Proc Natl Acad Sci U S A 109: E42–50. doi: 10.1073/pnas.1108229109
![]() |
[115] |
Marr C, Geertz M, Hutt MT, et al. (2008) Dissecting the logical types of network control in gene expression profiles. BMC Syst Biol 2: 18. doi: 10.1186/1752-0509-2-18
![]() |
[116] |
Blot N, Mavathur R, Geertz M, et al. (2006) Homeostatic regulation of supercoiling sensitivity coordinates transcription of the bacterial genome. EMBO Rep 7: 710–715. doi: 10.1038/sj.embor.7400729
![]() |
[117] |
Dorman CJ (2013) Genome architecture and global gene regulation in bacteria: making progress towards a unified model? Nat Rev Microbiol 11: 349–355. doi: 10.1038/nrmicro3007
![]() |
[118] |
Naughton C, Avlonitis N, Corless S, et al. (2013) Transcription forms and remodels supercoiling domains unfolding large-scale chromatin structures. Nat Struct Mol Biol 20: 387–395. doi: 10.1038/nsmb.2509
![]() |
[119] |
Kouzine F, Gupta A, Baranello L, et al. (2013) Transcription-dependent dynamic supercoiling is a short-range genomic force. Nat Struct Mol Biol 20: 396–403. doi: 10.1038/nsmb.2517
![]() |
[120] |
Noll M (1974) Subunit structure of chromatin. Nature 251: 249–251. doi: 10.1038/251249a0
![]() |
[121] |
Travers AA, Muskhelishvili G, Thompson JM (2012) DNA information: from digital code to analogue structure. Philos Trans A Math Phys Eng Sci 370: 2960–2986. doi: 10.1098/rsta.2011.0231
![]() |
[122] |
Cui F, Chen L, LoVerso PR, et al. (2014) Prediction of nucleosome rotational positioning in yeast and human genomes based on sequence-dependent DNA anisotropy. BMC Bioinformatics 15: 313. doi: 10.1186/1471-2105-15-313
![]() |
[123] |
Rosanio G, Widom J, Uhlenbeck OC (2015) In vitro selection of DNAs with an increased propensity to form small circles. Biopolymers 103: 303–320. doi: 10.1002/bip.22608
![]() |
[124] |
Zhurkin VB, Lysov YP, Ivanov VI (1979) Anisotropic flexibility of DNA and the nucleosomal structure. Nucleic Acids Res 6: 1081–1096. doi: 10.1093/nar/6.3.1081
![]() |
[125] |
Yakovchuk P, Protozanova E, Frank-Kamenetskii MD (2006) Base-stacking and base-pairing contributions into thermal stability of the DNA double helix. Nucleic Acids Res 34: 564–574. doi: 10.1093/nar/gkj454
![]() |
[126] |
Locke G, Haberman D, Johnson SM, et al. (2013) Global remodeling of nucleosome positions in C. elegans. BMC Genomics 14: 284-. doi: 10.1186/1471-2164-14-284
![]() |
[127] |
Locke G, Tolkunov D, Moqtaderi Z, et al. (2010) High-throughput sequencing reveals a simple model of nucleosome energetics. Proc Natl Acad Sci U S A 107: 20998–21003. doi: 10.1073/pnas.1003838107
![]() |
[128] |
Kaplan N, Moore IK, Fondufe-Mittendorf Y, et al. (2009) The DNA-encoded nucleosome organization of a eukaryotic genome. Nature 458: 362–366. doi: 10.1038/nature07667
![]() |
[129] |
Segal E, Fondufe-Mittendorf Y, Chen L, et al. (2006) A genomic code for nucleosome positioning. Nature 442: 772–778. doi: 10.1038/nature04979
![]() |
[130] |
Satchwell SC, Drew HR, Travers AA (1986) Sequence periodicities in chicken nucleosome core DNA. J Mol Biol 191: 659–675. doi: 10.1016/0022-2836(86)90452-3
![]() |
[131] |
Lowary PT, Widom J (1998) New DNA sequence rules for high affinity binding to histone octamer and sequence-directed nucleosome positioning. J Mol Biol 276: 19–42. doi: 10.1006/jmbi.1997.1494
![]() |
[132] |
Chua EY, Vasudevan D, Davey GE, et al. (2012) The mechanics behind DNA sequence-dependent properties of the nucleosome. Nucleic Acids Res 40: 6338–6352. doi: 10.1093/nar/gks261
![]() |
[133] |
Vasudevan D, Chua EY, Davey CA (2010) Crystal structures of nucleosome core particles containing the '601' strong positioning sequence. J Mol Biol 403: 1–10. doi: 10.1016/j.jmb.2010.08.039
![]() |
[134] |
Drew HR, Travers AA (1985) DNA bending and its relation to nucleosome positioning. J Mol Biol 186: 773–790. doi: 10.1016/0022-2836(85)90396-1
![]() |
[135] |
Teif VB, Beshnova DA, Vainshtein Y, et al. (2014) Nucleosome repositioning links DNA (de)methylation and differential CTCF binding during stem cell development. Genome Res 24: 1285–1295. doi: 10.1101/gr.164418.113
![]() |
[136] |
Xi Y, Yao J, Chen R, et al. (2011) Nucleosome fragility reveals novel functional states of chromatin and poises genes for activation. Genome Res 21: 718–724. doi: 10.1101/gr.117101.110
![]() |
[137] |
Knight B, Kubik S, Ghosh B, et al. (2014) Two distinct promoter architectures centered on dynamic nucleosomes control ribosomal protein gene transcription. Genes Dev 28: 1695–1709. doi: 10.1101/gad.244434.114
![]() |
[138] |
Wu C, Travers A (2005) Relative affinities of DNA sequences for the histone octamer depend strongly upon both the temperature and octamer concentration. Biochemistry 44: 14329–14334. doi: 10.1021/bi050915w
![]() |
[139] |
Kornberg R (1981) The location of nucleosomes in chromatin: specific or statistical. Nature 292: 579–580. doi: 10.1038/292579a0
![]() |
[140] |
Kornberg RD, Stryer L (1988) Statistical distributions of nucleosomes: nonrandom locations by a stochastic mechanism. Nucleic Acids Res 16: 6677–6690. doi: 10.1093/nar/16.14.6677
![]() |
[141] |
Chereji RV, Tolkunov D, Locke G, et al. (2011) Statistical mechanics of nucleosome ordering by chromatin-structure-induced two-body interactions. Phys Rev E Stat Nonlin Soft Matter Phys 83: 050903. doi: 10.1103/PhysRevE.83.050903
![]() |
[142] |
Chereji RV, Morozov AV (2011) Statistical Mechanics of Nucleosomes Constrained by Higher-Order Chromatin Structure. J Stat Phys 144: 379–404. doi: 10.1007/s10955-011-0214-y
![]() |
[143] | Mobius W, Gerland U (2010) Quantitative test of the barrier nucleosome model for statistical positioning of nucleosomes up- and downstream of transcription start sites. PLoS Comput Biol 6. |
[144] |
Eaton ML, Galani K, Kang S, et al. (2010) Conserved nucleosome positioning defines replication origins. Genes Dev 24: 748–753. doi: 10.1101/gad.1913210
![]() |
[145] |
Beshnova DA, Cherstvy AG, Vainshtein Y, et al. (2014) Regulation of the nucleosome repeat length in vivo by the DNA sequence, protein concentrations and long-range interactions. PLoS Comput Biol 10: e1003698. doi: 10.1371/journal.pcbi.1003698
![]() |
[146] | Cuddapah S, Jothi R, Schones DE, et al. (2009) Global analysis of the insulator binding protein CTCF in chromatin barrier regions reveals demarcation of active and repressive domains. Genome Res 19: 24–32. |
[147] |
Hu G, Schones DE, Cui K, et al. (2011) Regulation of nucleosome landscape and transcription factor targeting at tissue-specific enhancers by BRG1. Genome Res 21: 1650–1658. doi: 10.1101/gr.121145.111
![]() |
[148] |
Teif VB, Vainshtein Y, Caudron-Herger M, et al. (2012) Genome-wide nucleosome positioning during embryonic stem cell development. Nat Struct Mol Biol 19: 1185–1192. doi: 10.1038/nsmb.2419
![]() |
[149] |
Hu Z, Chen K, Xia Z, et al. (2014) Nucleosome loss leads to global transcriptional up-regulation and genomic instability during yeast aging. Genes Dev 28: 396–408. doi: 10.1101/gad.233221.113
![]() |
[150] |
Ricci MA, Manzo C, Garcia-Parajo MF, et al. (2015) Chromatin fibers are formed by heterogeneous groups of nucleosomes in vivo. Cell 160: 1145–1158. doi: 10.1016/j.cell.2015.01.054
![]() |
[151] |
Valouev A, Johnson SM, Boyd SD, et al. (2011) Determinants of nucleosome organization in primary human cells. Nature 474: 516–520. doi: 10.1038/nature10002
![]() |
[152] |
Cherstvy AG, Teif VB (2014) Electrostatic effect of H1-histone protein binding on nucleosome repeat length. Phys Biol 11: 044001. doi: 10.1088/1478-3975/11/4/044001
![]() |
[153] |
Bartholomew B (2014) Regulating the chromatin landscape: structural and mechanistic perspectives. Annu Rev Biochem 83: 671–696. doi: 10.1146/annurev-biochem-051810-093157
![]() |
[154] |
Mueller-Planitz F, Klinker H, Becker PB (2013) Nucleosome sliding mechanisms: new twists in a looped history. Nat Struct Mol Biol 20: 1026–1032. doi: 10.1038/nsmb.2648
![]() |
[155] |
Gerhold CB, Gasser SM (2014) INO80 and SWR complexes: relating structure to function in chromatin remodeling. Trends Cell Biol 24: 619–631. doi: 10.1016/j.tcb.2014.06.004
![]() |
[156] |
Narlikar GJ, Sundaramoorthy R, Owen-Hughes T (2013) Mechanisms and functions of ATP-dependent chromatin-remodeling enzymes. Cell 154: 490–503. doi: 10.1016/j.cell.2013.07.011
![]() |
[157] |
Zofall M, Persinger J, Kassabov SR, et al. (2006) Chromatin remodeling by ISW2 and SWI/SNF requires DNA translocation inside the nucleosome. Nat Struct Mol Biol 13: 339–346. doi: 10.1038/nsmb1071
![]() |
[158] |
Saha A, Wittmeyer J, Cairns BR (2005) Chromatin remodeling through directional DNA translocation from an internal nucleosomal site. Nat Struct Mol Biol 12: 747–755. doi: 10.1038/nsmb973
![]() |
[159] |
Schwanbeck R, Xiao H, Wu C (2004) Spatial contacts and nucleosome step movements induced by the NURF chromatin remodeling complex. J Biol Chem 279: 39933–39941. doi: 10.1074/jbc.M406060200
![]() |
[160] |
Moshkin YM, Chalkley GE, Kan TW, et al. (2012) Remodelers organize cellular chromatin by counteracting intrinsic histone-DNA sequence preferences in a class-specific manner. Mol Cell Biol 32: 675–688. doi: 10.1128/MCB.06365-11
![]() |
[161] |
Moshkin YM, Mohrmann L, van Ijcken WF, et al. (2007) Functional differentiation of SWI/SNF remodelers in transcription and cell cycle control. Mol Cell Biol 27: 651–661. doi: 10.1128/MCB.01257-06
![]() |
[162] |
Ho L, Crabtree GR (2010) Chromatin remodelling during development. Nature 463: 474–484. doi: 10.1038/nature08911
![]() |
[163] |
Ito T, Bulger M, Pazin MJ, et al. (1997) ACF, an ISWI-containing and ATP-utilizing chromatin assembly and remodeling factor. Cell 90: 145–155. doi: 10.1016/S0092-8674(00)80321-9
![]() |
[164] |
Varga-Weisz PD, Wilm M, Bonte E, et al. (1997) Chromatin-remodelling factor CHRAC contains the ATPases ISWI and topoisomerase II. Nature 388: 598–602. doi: 10.1038/41587
![]() |
[165] |
Poot RA, Dellaire G, Hulsmann BB, et al. (2000) HuCHRAC, a human ISWI chromatin remodelling complex contains hACF1 and two novel histone-fold proteins. EMBO J 19: 3377–3387. doi: 10.1093/emboj/19.13.3377
![]() |
[166] | LeRoy G, Orphanides G, Lane WS, et al. (1998) Requirement of RSF and FACT for transcription of chromatin templates in vitro. Science 282: 1900–1904. |
[167] |
LeRoy G, Loyola A, Lane WS, et al. (2000) Purification and characterization of a human factor that assembles and remodels chromatin. J Biol Chem 275: 14787–14790. doi: 10.1074/jbc.C000093200
![]() |
[168] |
Emelyanov AV, Vershilova E, Ignatyeva MA, et al. (2012) Identification and characterization of ToRC, a novel ISWI-containing ATP-dependent chromatin assembly complex. Genes Dev 26: 603–614. doi: 10.1101/gad.180604.111
![]() |
[169] |
Tsukiyama T, Wu C (1995) Purification and properties of an ATP-dependent nucleosome remodeling factor. Cell 83: 1011–1020. doi: 10.1016/0092-8674(95)90216-3
![]() |
[170] |
Hamiche A, Sandaltzopoulos R, Gdula DA, et al. (1999) ATP-dependent histone octamer sliding mediated by the chromatin remodeling complex NURF. Cell 97: 833–842. doi: 10.1016/S0092-8674(00)80796-5
![]() |
[171] |
Racki LR, Yang JG, Naber N, et al. (2009) The chromatin remodeller ACF acts as a dimeric motor to space nucleosomes. Nature 462: 1016–1021. doi: 10.1038/nature08621
![]() |
[172] |
Gangaraju VK, Prasad P, Srour A, et al. (2009) Conformational changes associated with template commitment in ATP-dependent chromatin remodeling by ISW2. Mol Cell 35: 58–69. doi: 10.1016/j.molcel.2009.05.013
![]() |
[173] |
Yamada K, Frouws TD, Angst B, et al. (2011) Structure and mechanism of the chromatin remodelling factor ISW1a. Nature 472: 448–453. doi: 10.1038/nature09947
![]() |
[174] |
Ferreira H, Flaus A, Owen-Hughes T (2007) Histone modifications influence the action of Snf2 family remodelling enzymes by different mechanisms. J Mol Biol 374: 563–579. doi: 10.1016/j.jmb.2007.09.059
![]() |
[175] |
Singh RP, Brysbaert G, Lensink MF, et al. (2015) Kinetic proofreading of chromatin remodeling: from gene activation to gene repression and back. AIMS Biophysics 2: 398–411. doi: 10.3934/biophy.2015.4.398
![]() |
[176] |
Blossey R, Schiessel H (2008) Kinetic proofreading of gene activation by chromatin remodeling. HFSP J 2: 167–170. doi: 10.2976/1.2909080
![]() |
[177] |
Blossey R, Schiessel H (2011) Kinetic proofreading in chromatin remodeling: the case of ISWI/ACF. Biophys J 101: L30–32. doi: 10.1016/j.bpj.2011.07.001
![]() |
[178] |
Florescu AM, Schiessel H, Blossey R (2012) Kinetic control of nucleosome displacement by ISWI/ACF chromatin remodelers. Phys Rev Lett 109: 118103. doi: 10.1103/PhysRevLett.109.118103
![]() |
[179] |
Narlikar GJ (2010) A proposal for kinetic proof reading by ISWI family chromatin remodeling motors. Curr Opin Chem Biol 14: 660–665. doi: 10.1016/j.cbpa.2010.08.001
![]() |
[180] |
Erdel F, Schubert T, Marth C, et al. (2010) Human ISWI chromatin-remodeling complexes sample nucleosomes via transient binding reactions and become immobilized at active sites. Proc Natl Acad Sci U S A 107: 19873–19878. doi: 10.1073/pnas.1003438107
![]() |
[181] |
Cochet-Meilhac M, Nuret P, Courvalin JC, et al. (1974) Animal DNA-dependent RNA polymerases. 12. Determination of the cellular number of RNA polymerase B molecules. Biochim Biophys Acta 353: 185-192. doi: 10.1016/0005-2787(74)90183-X
![]() |
[182] | Kimura H, Tao Y, Roeder RG, et al. (1999) Quantitation of RNA polymerase II and its transcription factors in an HeLa cell: little soluble holoenzyme but significant amounts of polymerases attached to the nuclear substructure. Mol Cell Biol 19: 5383–5392. |
[183] |
Jain D, Baldi S, Zabel A, et al. (2015) Active promoters give rise to false positive 'Phantom Peaks' in ChIP-seq experiments. Nucleic Acids Res 43: 6959–6968. doi: 10.1093/nar/gkv637
![]() |
[184] |
Gkikopoulos T, Schofield P, Singh V, et al. (2011) A role for Snf2-related nucleosome-spacing enzymes in genome-wide nucleosome organization. Science 333: 1758–1760. doi: 10.1126/science.1206097
![]() |
[185] |
Yen K, Vinayachandran V, Batta K, et al. (2012) Genome-wide nucleosome specificity and directionality of chromatin remodelers. Cell 149: 1461–1473. doi: 10.1016/j.cell.2012.04.036
![]() |
[186] |
Zentner GE, Tsukiyama T, Henikoff S (2013) ISWI and CHD chromatin remodelers bind promoters but act in gene bodies. PLoS Genet 9: e1003317. doi: 10.1371/journal.pgen.1003317
![]() |
[187] |
van Bakel H, Tsui K, Gebbia M, et al. (2013) A compendium of nucleosome and transcript profiles reveals determinants of chromatin architecture and transcription. PLoS Genet 9: e1003479. doi: 10.1371/journal.pgen.1003479
![]() |
[188] |
Zhang Z, Wippo CJ, Wal M, et al. (2011) A packing mechanism for nucleosome organization reconstituted across a eukaryotic genome. Science 332: 977–980. doi: 10.1126/science.1200508
![]() |
[189] |
Hartley PD, Madhani HD (2009) Mechanisms that specify promoter nucleosome location and identity. Cell 137: 445–458. doi: 10.1016/j.cell.2009.02.043
![]() |
[190] |
Ganguli D, Chereji RV, Iben JR, et al. (2014) RSC-dependent constructive and destructive interference between opposing arrays of phased nucleosomes in yeast. Genome Res 24: 1637–1649. doi: 10.1101/gr.177014.114
![]() |
[191] |
Whitehouse I, Rando OJ, Delrow J, et al. (2007) Chromatin remodelling at promoters suppresses antisense transcription. Nature 450: 1031–1035. doi: 10.1038/nature06391
![]() |
[192] |
Sala A, Toto M, Pinello L, et al. (2011) Genome-wide characterization of chromatin binding and nucleosome spacing activity of the nucleosome remodelling ATPase ISWI. EMBO J 30: 1766–1777. doi: 10.1038/emboj.2011.98
![]() |
[193] |
Bugga L, McDaniel IE, Engie L, et al. (2013) The Drosophila melanogaster CHD1 chromatin remodeling factor modulates global chromosome structure and counteracts HP1a and H3K9me2. PLoS One 8: e59496. doi: 10.1371/journal.pone.0059496
![]() |
[194] |
Corona DF, Siriaco G, Armstrong JA, et al. (2007) ISWI regulates higher-order chromatin structure and histone H1 assembly in vivo. PLoS Biol 5: e232. doi: 10.1371/journal.pbio.0050232
![]() |
[195] |
Fasulo B, Deuring R, Murawska M, et al. (2012) The Drosophila MI-2 chromatin-remodeling factor regulates higher-order chromatin structure and cohesin dynamics in vivo. PLoS Genet 8: e1002878. doi: 10.1371/journal.pgen.1002878
![]() |
[196] |
Clapier CR, Cairns BR (2009) The biology of chromatin remodeling complexes. Annu Rev Biochem 78: 273–304. doi: 10.1146/annurev.biochem.77.062706.153223
![]() |
[197] |
Brown E, Malakar S, Krebs JE (2007) How many remodelers does it take to make a brain. Diverse and cooperative roles of ATP-dependent chromatin-remodeling complexes in development. Biochem Cell Biol 85: 444-462. doi: 10.1139/O07-059
![]() |
[198] |
Bouazoune K, Brehm A (2006) ATP-dependent chromatin remodeling complexes in Drosophila. Chromosome Res 14: 433–449. doi: 10.1007/s10577-006-1067-0
![]() |
[199] |
Singhal N, Graumann J, Wu G, et al. (2010) Chromatin-Remodeling Components of the BAF Complex Facilitate Reprogramming. Cell 141: 943–955. doi: 10.1016/j.cell.2010.04.037
![]() |
[200] |
Hansis C, Barreto G, Maltry N, et al. (2004) Nuclear reprogramming of human somatic cells by xenopus egg extract requires BRG1. Curr Biol 14: 1475–1480. doi: 10.1016/j.cub.2004.08.031
![]() |
1. | Luis Almeida, Gissell Estrada-Rodriguez, Lisa Oliver, Diane Peurichard, Alexandre Poulain, Francois Vallette, Treatment-induced shrinking of tumour aggregates: a nonlinear volume-filling chemotactic approach, 2021, 83, 0303-6812, 10.1007/s00285-021-01642-x | |
2. | Giorgia Ciavolella, Effect of a Membrane on Diffusion-Driven Turing Instability, 2022, 178, 0167-8019, 10.1007/s10440-022-00475-0 | |
3. | André Schlichting, Christian Seis, The Scharfetter–Gummel scheme for aggregation–diffusion equations, 2022, 42, 0272-4979, 2361, 10.1093/imanum/drab039 | |
4. | Yangyang Qiao, Steinar Evje, A general cell–fluid Navier–Stokes model with inclusion of chemotaxis, 2020, 30, 0218-2025, 1167, 10.1142/S0218202520400096 | |
5. | Xueling Huang, Jie Shen, Bound/positivity preserving SAV schemes for the Patlak-Keller-Segel-Navier-Stokes system, 2023, 480, 00219991, 112034, 10.1016/j.jcp.2023.112034 | |
6. | Yong Zhang, Yu Zhao, Zhennan Zhou, A Unified Structure Preserving Scheme for a Multispecies Model with a Gradient Flow Structure and Nonlocal Interactions via Singular Kernels, 2021, 43, 1064-8275, B539, 10.1137/20M1348911 | |
7. | Federica Bubba, Camille Pouchol, Nathalie Ferrand, Guillaume Vidal, Luis Almeida, Benoît Perthame, Michèle Sabbah, A chemotaxis-based explanation of spheroid formation in 3D cultures of breast cancer cells, 2019, 479, 00225193, 73, 10.1016/j.jtbi.2019.07.002 | |
8. | Federica Bubba, Benoit Perthame, Daniele Cerroni, Pasquale Ciarletta, Paolo Zunino, A coupled 3D-1D multiscale Keller-Segel model of chemotaxis and its application to cancer invasion, 2022, 15, 1937-1632, 2053, 10.3934/dcdss.2022044 | |
9. | Jingwei Hu, Xiangxiong Zhang, Positivity-preserving and energy-dissipative finite difference schemes for the Fokker–Planck and Keller–Segel equations, 2022, 0272-4979, 10.1093/imanum/drac014 | |
10. | Clément Cancès, Thomas O. Gallouët, Gabriele Todeschi, A variational finite volume scheme for Wasserstein gradient flows, 2020, 146, 0029-599X, 437, 10.1007/s00211-020-01153-9 | |
11. | Federica Bubba, Alexandre Poulain, A nonnegativity preserving scheme for the relaxed Cahn–Hilliard equation with single-well potential and degenerate mobility, 2022, 56, 2822-7840, 1741, 10.1051/m2an/2022050 | |
12. | Jose A. Carrillo, Daniel Matthes, Marie-Therese Wolfram, 2021, 22, 9780444643056, 271, 10.1016/bs.hna.2020.10.002 | |
13. | Clément Cancès, Benoît Gaudeul, A Convergent Entropy Diminishing Finite Volume Scheme for a Cross-Diffusion System, 2020, 58, 0036-1429, 2684, 10.1137/20M1316093 | |
14. | Noemi David, Xinran Ruan, An asymptotic preserving scheme for a tumor growth model of porous medium type, 2022, 56, 2822-7840, 121, 10.1051/m2an/2021080 | |
15. | Clément Cancès, Virginie Ehrlacher, Laurent Monasse, Finite volumes for the Stefan–Maxwell cross-diffusion system, 2024, 44, 0272-4979, 1029, 10.1093/imanum/drad032 | |
16. | José A. Carrillo, Katy Craig, Yao Yao, 2019, Chapter 3, 978-3-030-20296-5, 65, 10.1007/978-3-030-20297-2_3 | |
17. | Rafael Bailo, José A. Carrillo, Jingwei Hu, Bound-Preserving Finite-Volume Schemes for Systems of Continuity Equations with Saturation, 2023, 83, 0036-1399, 1315, 10.1137/22M1488703 | |
18. | Ilka Budde, André Schlichting, David Ing, Sandra Schimmelpfennig, Anna Kuntze, Benedikt Fels, Joelle M.-J. Romac, Sandip M. Swain, Rodger A. Liddle, Angela Stevens, Albrecht Schwab, Zoltán Pethő, Piezo1-induced durotaxis of pancreatic stellate cells depends on TRPC1 and TRPV4 channels, 2025, 138, 0021-9533, 10.1242/jcs.263846 | |
19. | Gissell Estrada-Rodriguez, Diane Peurichard, Xinran Ruan, From a nonlinear kinetic equation to a volume-exclusion chemotaxis model via asymptotic preserving methods, 2025, 0, 1937-5093, 0, 10.3934/krm.2025012 |
Convolution layer | Input (N, C, W, H) | Convolution kernel (size, input, output) | Activation function | Output (N, C, W, H) |
1 | [128,4,300,300] | [5 × 5, 4, 16] | ReLU | [128,16,150,150] |
2 | [128,16,150,150] | [5 × 5, 16, 32] | ReLU | [128,32,75,75] |
3 | [128,32,75,75] | [5 × 5, 32, 64] | ReLU | [128,64,36,36] |
4 | [128,64,36,36] | [5 × 5, 64, 64] | ReLU | [128,64,4,4] |
Batch size | SGD | Adam |
20 | 83.03% | 73.26% |
10 | 83.33% | 72.58% |
2 | 86.44% | 71.46% |
Batch size | SGD | Adam |
20 | 0.5040 | 1.0498 |
10 | 0.5522 | 1.6858 |
2 | 0.5817 | 1.8479 |
Batch size | Repetition rate: 2/3 | Repetition rate: 5/6 |
20 | 92.10% | 96.28% |
10 | 91.69% | 94.70% |
2 | 92.65% | 90.34% |
Batch size | Repetition rate: 2/3 | Repetition rate: 5/6 |
20 | 0.3478 | 0.1201 |
10 | 0.4082 | 0.1886 |
2 | 0.3655 | 0.3635 |
Convolution layer | Parameters | Output |
Conv 1 | 7 × 7, 64, step length = 2 | 112 × 112 |
Conv 2 | $ \left[{3×3,643×3,64 } \right] \times 2 $ |
56 × 56 |
Conv 3 | $ \left[{3×3,1283×3,128 } \right] \times 2 $ |
28 × 28 |
Conv 4 | $ \left[{3×3,2563×3,256 } \right] \times 2 $ |
14 × 14 |
Conv 5 | $ \left[{3×3,5123×3,512 } \right] \times 2 $ |
7 × 7 |
Pooling layer | Average pooling | 1 × 1 |
Layer | Parameter | Output Size |
Convolution layer | 7 × 7, conv, stride = 2 | 112 × 112 |
Pooling | 3 × 3 max pooling, stride = 2 | 56 × 56 |
Block1 | $ \left[{1×13×3 } \right] \times 6 $ |
56 × 56 |
Transition layer 1 | 1 × 1 conv | 56 × 56 |
2 × 2 average pooling, stride = 2 | 28 × 28 | |
Block 2 | $ \left[{1×13×3 } \right] \times 12 $ |
28 × 28 |
Transition layer 2 | 1 × 1 conv | 28 × 28 |
2 × 2 average pooling, stride = 2 | 14 × 14 | |
Block 3 | $ \left[{1×13×3 } \right] \times 24 $ |
14 × 14 |
Transition layer 3 | 1 × 1 conv | 14 × 14 |
2 × 2 average pooling, stride = 2 | 7 × 7 | |
Block 4 | $ \left[{1×13×3 } \right] \times 16 $ |
7 × 7 |
Taxonomic hierarchies | 7 × 7 global average pooling | 1 × 1 |
A fully connected layer of 1000 dimensions, Softmax |
Convolution layer | Input (N, C, W, H) | Convolution kernel (size, input, output) | Activation function | Output (N, C, W, H) |
1 | [128,4,300,300] | [5 × 5, 4, 16] | ReLU | [128,16,150,150] |
2 | [128,16,150,150] | [5 × 5, 16, 32] | ReLU | [128,32,75,75] |
3 | [128,32,75,75] | [5 × 5, 32, 64] | ReLU | [128,64,36,36] |
4 | [128,64,36,36] | [5 × 5, 64, 64] | ReLU | [128,64,4,4] |
Batch size | SGD | Adam |
20 | 83.03% | 73.26% |
10 | 83.33% | 72.58% |
2 | 86.44% | 71.46% |
Batch size | SGD | Adam |
20 | 0.5040 | 1.0498 |
10 | 0.5522 | 1.6858 |
2 | 0.5817 | 1.8479 |
Batch size | Repetition rate: 2/3 | Repetition rate: 5/6 |
20 | 92.10% | 96.28% |
10 | 91.69% | 94.70% |
2 | 92.65% | 90.34% |
Batch size | Repetition rate: 2/3 | Repetition rate: 5/6 |
20 | 0.3478 | 0.1201 |
10 | 0.4082 | 0.1886 |
2 | 0.3655 | 0.3635 |
Convolution layer | Parameters | Output |
Conv 1 | 7 × 7, 64, step length = 2 | 112 × 112 |
Conv 2 | $ \left[{3×3,643×3,64 } \right] \times 2 $ |
56 × 56 |
Conv 3 | $ \left[{3×3,1283×3,128 } \right] \times 2 $ |
28 × 28 |
Conv 4 | $ \left[{3×3,2563×3,256 } \right] \times 2 $ |
14 × 14 |
Conv 5 | $ \left[{3×3,5123×3,512 } \right] \times 2 $ |
7 × 7 |
Pooling layer | Average pooling | 1 × 1 |
Layer | Parameter | Output Size |
Convolution layer | 7 × 7, conv, stride = 2 | 112 × 112 |
Pooling | 3 × 3 max pooling, stride = 2 | 56 × 56 |
Block1 | $ \left[{1×13×3 } \right] \times 6 $ |
56 × 56 |
Transition layer 1 | 1 × 1 conv | 56 × 56 |
2 × 2 average pooling, stride = 2 | 28 × 28 | |
Block 2 | $ \left[{1×13×3 } \right] \times 12 $ |
28 × 28 |
Transition layer 2 | 1 × 1 conv | 28 × 28 |
2 × 2 average pooling, stride = 2 | 14 × 14 | |
Block 3 | $ \left[{1×13×3 } \right] \times 24 $ |
14 × 14 |
Transition layer 3 | 1 × 1 conv | 14 × 14 |
2 × 2 average pooling, stride = 2 | 7 × 7 | |
Block 4 | $ \left[{1×13×3 } \right] \times 16 $ |
7 × 7 |
Taxonomic hierarchies | 7 × 7 global average pooling | 1 × 1 |
A fully connected layer of 1000 dimensions, Softmax |