GLDM: hit molecule generation with constrained graph latent diffusion model.

Discovering hit molecules with desired biological activity in a directed manner is a promising but profound task in computer-aided drug discovery. Inspired by recent generative AI approaches, particularly Diffusion Models (DM), we propose Graph Latent Diffusion Model (GLDM)-a latent DM that preserves both the effectiveness of autoencoders of compressing complex chemical data and the DM's capabilities of generating novel molecules. Specifically, we first develop an autoencoder to encode the molecular data into low-dimensional latent representations and then train the DM on the latent space to generate molecules inducing targeted biological activity defined by gene expression profiles. Manipulating DM in the latent space rather than the input space avoids complicated operations to map molecule decomposition and reconstruction to diffusion processes, and thus improves training efficiency. Experiments show that GLDM not only achieves outstanding performances on molecular generation benchmarks, but also generates samples with optimal chemical properties and potentials to induce desired biological activity.

MEMS-based two-photon microscopy with Lissajous scanning and image reconstruction under a feed-forward control strategy.

Two-photon microscopy (TPM) based on two-dimensional micro-electro-mechanical (MEMS) system mirrors shows promising applications in biomedicine and the life sciences. To improve the imaging quality and real-time performance of TPM, this paper proposes Lissajous scanning control and image reconstruction under a feed-forward control strategy, a dual-parameter alternating drive control algorithm and segmented phase synchronization mechanism, and pipe-lined fusion-mean filtering and median filtering to suppress image noise. A 10 fps frame rate (512 × 512 pixels), a 140 µm × 140 µm field of view, and a 0.62 µm lateral resolution were achieved. The imaging capability of MEMS-based Lissajous scanning TPM was verified by ex vivo and in vivo biological tissue imaging.

Miniature Two-Photon Microscopic Imaging Using Dielectric Metalens.

Miniature two-photon microscopy has emerged as a powerful technique for investigating brain activity in freely moving animals. Ongoing research objectives include reducing probe weight and minimizing animal behavior constraints caused by probe attachment. Employing dielectric metalenses, which enable the use of sizable optical components in flat device structures while maintaining imaging resolution, is a promising solution for addressing these challenges. In this study, we designed and fabricated a titanium dioxide metalens with a wavelength of 920 nm and a high aspect ratio. Furthermore, a meta-optic two-photon microscope weighing 1.36 g was developed. This meta-optic probe has a lateral resolution of 0.92 µm and an axial resolution of 18.08 µm. Experimentally, two-photon imaging of mouse brain structures in vivo was also demonstrated. The flat dielectric metalens technique holds promising opportunities for high-performance integrated miniature nonlinear microscopy and endomicroscopy platforms in the biomedical field.

Graph Neural Networks With Multiple Prior Knowledge for Multi-Omics Data Analysis.

With the development of biotechnology, a large amount of multi-omics data have been collected for precision medicine. There exists multiple graph-based prior biological knowledge about omics data, such as gene-gene interaction networks. Recently, there has been an increasing interest in introducing graph neural networks (GNNs) into multi-omics learning. However, existing methods have not fully exploited these graphical priors since none have been able to integrate knowledge from multiple sources simultaneously. To solve this problem, we propose a multi-omics data analysis framework by incorporating multiple prior knowledge into graph neural network (MPK-GNN). To the best of our knowledge, this is the first attempt to introduce multiple prior graphs into multi-omics data analysis. Specifically, the proposed method contains four parts: (1) a feature-level learning module to aggregate information from prior graphs; (2) a projection module to maximize the agreement among prior networks by optimizing a contrastive loss; (3) a sample-level module to learn a global representation from input multi-omics features; (4) a task-specific module to flexibly extend MPK-GNN for various downstream multi-omics analysis tasks. Finally, we verify the effectiveness of the proposed multi-omics learning algorithm on the cancer molecular subtype classification task. Experimental results show that MPK-GNN outperforms other state-of-the-art algorithms, including multi-view learning methods and multi-omics integrative approaches.

Genomic analysis, trajectory tracking, and field surveys reveal sources and long-distance dispersal routes of wheat stripe rust pathogen in China.

Identifying sources of phytopathogen inoculum and determining their contributions to disease outbreaks are essential for predicting disease development and establishing control strategies. Puccinia striiformis f. sp. tritici (Pst), the causal agent of wheat stripe rust, is an airborne fungal pathogen with rapid virulence variation that threatens wheat production through its long-distance migration. Because of wide variation in geographic features, climatic conditions, and wheat production systems, Pst sources and related dispersal routes in China are largely unclear. In the present study, we performed genomic analyses of 154 Pst isolates from all major wheat-growing regions in China to determine Pst population structure and diversity. Through trajectory tracking, historical migration studies, genetic introgression analyses, and field surveys, we investigated Pst sources and their contributions to wheat stripe rust epidemics. We identified Longnan, the Himalayan region, and the Guizhou Plateau, which contain the highest population genetic diversities, as the Pst sources in China. Pst from Longnan disseminates mainly to eastern Liupan Mountain, the Sichuan Basin, and eastern Qinghai; that from the Himalayan region spreads mainly to the Sichuan Basin and eastern Qinghai; and that from the Guizhou Plateau migrates mainly to the Sichuan Basin and the Central Plain. These findings improve our current understanding of wheat stripe rust epidemics in China and emphasize the need for managing stripe rust on a national scale.

Deep learning and multi-omics approach to predict drug responses in cancer.

BACKGROUND: Cancers are genetically heterogeneous, so anticancer drugs show varying degrees of effectiveness on patients due to their differing genetic profiles. Knowing patient's responses to numerous cancer drugs are needed for personalized treatment for cancer. By using molecular profiles of cancer cell lines available from Cancer Cell Line Encyclopedia (CCLE) and anticancer drug responses available in the Genomics of Drug Sensitivity in Cancer (GDSC), we will build computational models to predict anticancer drug responses from molecular features. RESULTS: We propose a novel deep neural network model that integrates multi-omics data available as gene expressions, copy number variations, gene mutations, reverse phase protein array expressions, and metabolomics expressions, in order to predict cellular responses to known anti-cancer drugs. We employ a novel graph embedding layer that incorporates interactome data as prior information for prediction. Moreover, we propose a novel attention layer that effectively combines different omics features, taking their interactions into account. The network outperformed feedforward neural networks and reported 0.90 for [Formula: see text] values for prediction of drug responses from cancer cell lines data available in CCLE and GDSC. CONCLUSION: The outstanding results of our experiments demonstrate that the proposed method is capable of capturing the interactions of genes and proteins, and integrating multi-omics features effectively. Furthermore, both the results of ablation studies and the investigations of the attention layer imply that gene mutation has a greater influence on the prediction of drug responses than other omics data types. Therefore, we conclude that our approach can not only predict the anti-cancer drug response precisely but also provides insights into reaction mechanisms of cancer cell lines and drugs as well.

Two-photon endomicroscopy with microsphere-spliced double-cladding antiresonant fiber for resolution enhancement.

We demonstrate a miniature fiber-optic two two-photon endomicroscopy with microsphere-spliced double-cladding antiresonant fiber for resolution enhancement. An easy-to-operate process for fixing microsphere permanently in an antiresonant fiber core, by arc discharge, is proposed. The flexible fiber-optic probe is integrated with a parameter of 5.8 mm × 49.1 mm (outer diameter × rigid length); the field of view is 210 µm, the resolution is 1.3 µm, and the frame rate is 0.7 fps. The imaging ability is verified using ex-vivo mouse kidney, heart, stomach, tail tendon, and in-vivo brain neural imaging.

Network-based integration of multi-omics data for clinical outcome prediction in neuroblastoma.

Multi-omics data are increasingly being gathered for investigations of complex diseases such as cancer. However, high dimensionality, small sample size, and heterogeneity of different omics types pose huge challenges to integrated analysis. In this paper, we evaluate two network-based approaches for integration of multi-omics data in an application of clinical outcome prediction of neuroblastoma. We derive Patient Similarity Networks (PSN) as the first step for individual omics data by computing distances among patients from omics features. The fusion of different omics can be investigated in two ways: the network-level fusion is achieved using Similarity Network Fusion algorithm for fusing the PSNs derived for individual omics types; and the feature-level fusion is achieved by fusing the network features obtained from individual PSNs. We demonstrate our methods on two high-risk neuroblastoma datasets from SEQC project and TARGET project. We propose Deep Neural Network and Machine Learning methods with Recursive Feature Elimination as the predictor of survival status of neuroblastoma patients. Our results indicate that network-level fusion outperformed feature-level fusion for integration of different omics data whereas feature-level fusion is more suitable incorporating different feature types derived from same omics type. We conclude that the network-based methods are capable of handling heterogeneity and high dimensionality well in the integration of multi-omics.

Combining Neuroimaging and Omics Datasets for Disease Classification Using Graph Neural Networks.

Both neuroimaging and genomics datasets are often gathered for the detection of neurodegenerative diseases. Huge dimensionalities of neuroimaging data as well as omics data pose tremendous challenge for methods integrating multiple modalities. There are few existing solutions that can combine both multi-modal imaging and multi-omics datasets to derive neurological insights. We propose a deep neural network architecture that combines both structural and functional connectome data with multi-omics data for disease classification. A graph convolution layer is used to model functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI) data simultaneously to learn compact representations of the connectome. A separate set of graph convolution layers are then used to model multi-omics datasets, expressed in the form of population graphs, and combine them with latent representations of the connectome. An attention mechanism is used to fuse these outputs and provide insights on which omics data contributed most to the model's classification decision. We demonstrate our methods for Parkinson's disease (PD) classification by using datasets from the Parkinson's Progression Markers Initiative (PPMI). PD has been shown to be associated with changes in the human connectome and it is also known to be influenced by genetic factors. We combine DTI and fMRI data with multi-omics data from RNA Expression, Single Nucleotide Polymorphism (SNP), DNA Methylation and non-coding RNA experiments. A Matthew Correlation Coefficient of greater than 0.8 over many combinations of multi-modal imaging data and multi-omics data was achieved with our proposed architecture. To address the paucity of paired multi-modal imaging data and the problem of imbalanced data in the PPMI dataset, we compared the use of oversampling against using CycleGAN on structural and functional connectomes to generate missing imaging modalities. Furthermore, we performed ablation studies that offer insights into the importance of each imaging and omics modality for the prediction of PD. Analysis of the generated attention matrices revealed that DNA Methylation and SNP data were the most important omics modalities out of all the omics datasets considered. Our work motivates further research into imaging genetics and the creation of more multi-modal imaging and multi-omics datasets to study PD and other complex neurodegenerative diseases.

Genetic Analysis Reveals Relationships Among Populations of Puccinia striiformis f. sp. tritici from the Longnan, Longdong, and Central Shaanxi Regions of China.

Wheat stripe rust, caused by Puccinia striiformis f. sp. tritici, is one of the most important diseases of wheat worldwide. In China, Longnan (LN) and Longdong (LD) in the south and east of Gansu province, respectively, are important P. striiformis f. sp. tritici oversummering areas and are a source of P. striiformis f. sp. tritici inoculum for the major wheat-growing regions in eastern China. Central Shaanxi (CS) is a wheat-growing region that acts as an important bridge zone for stripe rust epidemic development between LN and LD in the west and the Huanghuai wheat-growing region in the east, and thus, it plays an essential role in P. striiformis f. sp. tritici epidemics in China. To study the relationships among P. striiformis f. sp. tritici populations in the three regions (LN, LD, and CS), we sampled 284 isolates from different geographic locations. Based on 10 simple sequence repeat markers, the results demonstrated high genetic diversity in all three regions, although diversity did vary among regions, with LN > LD > CS. Genetic differentiation was lower, with more extensive gene flow between LD and CS. P. striiformis f. sp. tritici populations in the CS region were genetically closer to those from LD than those from LN, which may be a result of geographical proximity and topography. A positive and significant correlation existed between linearized fixation index (FST) and the log of geographical distances among all subpopulations. Linkage disequilibrium analysis showed that subpopulations of P. striiformis f. sp. tritici from Qinzhou, Qincheng, Beidao, and Maiji from LN and Qianyang and Longxian from CS were in equilibrium (P > 0.05), suggesting that somatic hybridization and/or sexual reproduction may exist in these subpopulations.

Population Genetic Analysis of Puccinia striiformis f. sp. tritici Suggests Two Distinct Populations in Tibet and the Other Regions of China.

Wheat stripe rust, caused by Puccinia striiformis f. sp. tritici (Pst), is an important disease on wheat, seriously threatening wheat production worldwide. China is one of the largest stripe rust epidemic regions in the world. The pathogen sexual reproduction and migration routes between Tibet and the other regions in China are still unknown. In this study, we obtained 961 Pst isolates from 1,391 wheat leaf samples from Gansu (277), Shaanxi (253), Sichuan (172), and Tibet (259), comprising 13 natural populations, and genotyped them with simple sequence repeat (SSR) markers. The isolates can be divided into two distinct clusters based on DAPC and STRUCTURE analyses. The genetic diversity of Longnan (in Gansu) and Yibin (in Sichuan) populations was the highest and lowest among the 13 populations, respectively. The hypothesis of multilocus linkage disequilibrium was rejected for the populations from Linzhi in the Himalayan, Longnan, Hanzhong, Guangyuan, Mianyang, Liangshan, and Chendu in the south Qinling Mountains at the level of P = 0.01, which indicated significant linkage among markers in these populations. Populations in the other regions had extensive gene exchange (Nm > 4); little gene exchange was found between Tibet and the other regions (Nm < 1). The results suggest that the Tibet epidemic region of Pst is highly differentiated from the other epidemic regions in China.

Vayg1 is required for microsclerotium formation and melanin production in Verticillium dahliae.

The fungus Verticillium dahliae causes vascular wilt disease on many plant species, including economically important crop and ornamental plants worldwide. It produces darkly pigmented resting structures known as microsclerotia, which are able to survive for up to 14years in soil, and represent one of the defining characteristics of this species. The pigment produced in V. dahliae is dihydroxynaphthalene (DHN)-melanin, a form of melanin common among fungi and named so for the intermediary of this melanin biosynthetic pathway. In this study, we characterized the function of the V. dahliae Vayg1 gene, whose homologs were involved in melanin biosynthesis in Exophiala dermatitidis (Wayg1) and Aspergillus fumigatus (Aayg1), by deletion and complementation of the gene and co-incubating deletion mutant with wild-type strain. Results showed that melanin production and microsclerotial formation in deletion mutants are inhibited. The Vayg1 deletion mutant also exhibited reduced pathogenicity. These results showed that Vayg1 is necessary for melanin and microsclerotium production, and we may thus hypothesize that the Vayg1 product may catalyze two different precursors, one of which is essential for DHN melanin production and the other one is involved in a signal network for microsclerotial formation in V. dahliae.