A Novel Computational Framework for Precision Diagnosis and Subtype Discovery of Plant With Lesion

Plants are often attacked by various pathogens during their growth, which may cause environmental pollution, food shortages, or economic losses in a certain area. Integration of high throughput phenomics data and computer vision (CV) provides a great opportunity to realize plant disease diagnosis in the early stage and uncover the subtype or stage patterns in the disease progression. In this study, we proposed a novel computational framework for plant disease identification and subtype discovery through a deep-embedding image-clustering strategy, Weighted Distance Metric and the t-stochastic neighbor embedding algorithm (WDM-tSNE). To verify the effectiveness, we applied our method on four public datasets of images. The results demonstrated that the newly developed tool is capable of identifying the plant disease and further uncover the underlying subtypes associated with pathogenic resistance. In summary, the current framework provides great clustering performance for the root or leave images of diseased plants with pronounced disease spots or symptoms.

A Parameter-free Deep Embedded Clustering Method for Single-cell RNA-seq Data

Clustering analysis is widely utilized in single-cell RNA-sequencing (scRNA-seq) data to discover cell heterogeneity and cell states. While many clustering methods have been developed for scRNA-seq analysis, most of these methods require to provide the number of clusters. However, it is not easy to know the exact number of cell types in advance, and experienced determination is not always reliable. Here, we have developed ADClust, an automatic deep embedding clustering method for scRNA-seq data, which can accurately cluster cells without requiring a predefined number of clusters. Specifically, ADClust first obtains low-dimensional representation through pre-trained autoencoder, and uses the representations to cluster cells into initial micro-clusters. The clusters are then compared in between by a statistical test, and similar micro-clusters are merged into larger clusters. According to the clustering, cell representations are updated so that each cell will be pulled toward centres of its assigned cluster and similar clusters, while cells are separated to keep distances between clusters. This is accomplished through jointly optimizing the carefully designed clustering and autoencoder loss functions. This merging process continues until convergence. ADClust was tested on eleven real scRNA-seq datasets, and shown to outperform existing methods in terms of both clustering performance and the accuracy on the number of the determined clusters. More importantly, our model provides high speed and scalability for large datasets.

Deep embedding and alignment of protein sequences

Protein sequence alignment is a key component of most bioinformatics pipelines to study the structures and functions of proteins. Aligning highly divergent sequences remains, however, a difficult task that current algorithms often fail to perform accurately, leaving many proteins or open reading frames poorly annotated. Here, we leverage recent advances in deep learning for language modelling and differentiable programming to propose DEDAL, a flexible model to align protein sequences and detect homologs. DEDAL is a machine learning-based model that learns to align sequences by observing large datasets of raw protein sequences and of correct alignments. Once trained, we show that DEDAL improves by up to two- or three-fold the alignment correctness over existing methods on remote homologs, and better discriminates remote homologs from evolutionarily unrelated sequences, paving the way to improvements on many downstream tasks relying on sequence alignment in structural and functional genomics.

Pathologic Complete Response Prediction after Neoadjuvant Chemoradiation Therapy for Rectal Cancer Using Radiomics and Deep Embedding Network of MRI

Assessment of magnetic resonance imaging (MRI) after neoadjuvant chemoradiation therapy (nCRT) is essential in rectal cancer staging and treatment planning. However, when predicting the pathologic complete response (pCR) after nCRT for rectal cancer, existing works either rely on simple quantitative evaluation based on radiomics features or partially analyze multi-parametric MRI. We propose an effective pCR prediction method based on novel multi-parametric MRI embedding. We first seek to extract volumetric features of tumors that can be found only by analyzing multiple MRI sequences jointly. Specifically, we encapsulate multiple MRI sequences into multi-sequence fusion images (MSFI) and generate MSFI embedding. We merge radiomics features, which capture important characteristics of tumors, with MSFI embedding to generate multi-parametric MRI embedding and then use it to predict pCR using a random forest classifier. Our extensive experiments demonstrate that using all given MRI sequences is the most effective regardless of the dimension reduction method. The proposed method outperformed any variants with different combinations of feature vectors and dimension reduction methods or different classification models. Comparative experiments demonstrate that it outperformed four competing baselines in terms of the AUC and F1-score. We use MRI sequences from 912 patients with rectal cancer, a much larger sample than in any existing work.

Hyperspectral Image Classification Based on Cross-Scene Adaptive Learning

Aiming at few-shot classification in the field of hyperspectral remote sensing images, this paper proposes a classification method based on cross-scene adaptive learning. First, based on the unsupervised domain adaptive technology, cross-scene knowledge transfer learning is carried out to reduce the differences between source scene and target scene. At the same time, depthwise over-parameterized convolution is used in the deep embedding model to improve the convergence speed and feature extraction ability. Second, two symmetrical subnetworks are designed in the model to further reduce the differences between source scene and target scene. Then, Manhattan distance is learned in the Manhattan metric space in order to reduce the computational cost of the model. Finally, the weighted K-nearest neighbor is introduced for classification, in which the weighted Manhattan metric distance is assigned to the clustered samples to improve the processing ability to the imbalanced hyperspectral image data. The effectiveness of the proposed algorithm is verified on the Pavia and Indiana hyperspectral dataset. The overall classification accuracy is 90.90% and 65.01%. Compared with six other kinds of hyperspectral image classification methods, the proposed cross-scene method has better classification accuracy.

Design Concept Generation With Variational Deep Embedding Over Comprehensive Optimization

This paper proposes a framework for generating design concepts through the loop of comprehensive exploitation and consequent exploration. The former is by any sophisticated optimization such as topology optimization with diversely different. The latter realization is due to the variational deep embedding (VaDE), a deep learning technique with classification capability. In the process of design concept generation first, exploitation through computational optimization generates various possibilities of design entities. Second, VaDE learns them. This learning encodes the clusters of similar entities over the latent space with smaller dimensions. The clustering result reveals some design concepts and identifies voids where as-yet-unrecognized design concepts are prospective. Third, the decoder of the learned VaDE generates some possibilities for new design entities. Forth such new entities are examined, and relevant new conditions will trigger further exploitation by the optimization. In this paper, this framework is implemented for and applied to the conceptual design problem of bridge structures. This application demonstrates that the framework can identify voids over the latent space and explore the possibility of new concepts. This paper brings up some discussion on the promises and possibilities of the proposed framework.

Probing T Cell 3D Mechanosensing With Magnetically-Actuated Structures

The ability of cells to recognize and respond to the mechanical properties of their environment is of increasing importance in T cell physiology. However, initial studies in this direction focused on planar hydrogel and elastomer surfaces, presenting several challenges in interpretation including difficulties in separating mechanical stiffness from changes in chemistry needed to modulate this property. We introduce here the use of magnetic fields to change the structural rigidity of microscale elastomer pillars loaded with superparamagnetic nanoparticles, independent of substrate chemistry. This magnetic modulation of rigidity, embodied as the pillar spring constant, changed the interaction of mouse naïve CD4+ T cells from a contractile morphology to one involving deep embedding into the array. Furthermore, increasing spring constant was associated with higher IL-2 secretion, showing a functional impact on mechanosensing. The system introduced here thus separates local substrate stiffness and long-range structural rigidity, revealing new facets of T cell interaction with their environment.