Extraction of local structure differences in silica based on unsupervised learning.

Silica exhibits a rich phase diagram with numerous stable structures existing at different temperature and pressure conditions, including its glassy form. In large-scale atomistic simulations, due to the small energy difference, several phases may coexist. While, in terms of long-range order, there are clear differences between these phases, their short- or medium-range structural properties are similar for many phases, thus making it difficult to detect the structural differences. In this study, a methodology based on unsupervised learning is proposed to detect the differences in local structures between eight phases of silica, using atomic models prepared by molecular dynamics (MD) simulations. A combination of two-step locality preserving projections (TS-LPP) and locally averaged atomic fingerprints (LAAF) descriptor was employed to find a low-dimensional space in which the differences among all the phases can be detected. From the distance between each structure in the found low-dimensional space, the similarity between the structures can be discussed and subtle local changes in the structures can be detected. Using the obtained low-dimensional space, the ß-α transition in quartz at a low temperature was analyzed, as well as the structural evolution during the melt-quench process starting from α-quartz. The proper differentiation and ease of visualization make the present methodology promising for improving the analysis of the structure and properties of glasses, where subtle differences in structure appear due to differences in the temperature and pressure conditions at which they were synthesized.

Determination of hyper-parameters in the atomic descriptors for efficient and robust molecular dynamics simulations with machine learning forces.

The atomic descriptors used in machine learning to predict forces are often high dimensional. In general, by retrieving a significant amount of structural information from these descriptors, accurate force predictions can be achieved. On the other hand, to acquire higher robustness for transferability without overfitting, sufficient reduction of descriptors should be necessary. In this study, we propose a method to automatically determine hyperparameters in the atomic descriptors, aiming to obtain accurate machine learning forces while using a small number of descriptors. Our method focuses on identifying an appropriate threshold cut-off for the variance value of the descriptor components. To demonstrate the effectiveness of our method, we apply it to crystalline, liquid, and amorphous structures in SiO2, SiGe, and Si systems. By using both conventional two-body descriptors and our introduced split-type three-body descriptors, we demonstrate that our method can provide machine learning forces that enable efficient and robust molecular dynamics simulations.

iLoc-miRNA: extracellular/intracellular miRNA prediction using deep BiLSTM with attention mechanism.

The location of microRNAs (miRNAs) in cells determines their function in regulation activity. Studies have shown that miRNAs are stable in the extracellular environment that mediates cell-to-cell communication and are located in the intracellular region that responds to cellular stress and environmental stimuli. Though in situ detection techniques of miRNAs have made great contributions to the study of the localization and distribution of miRNAs, miRNA subcellular localization and their role are still in progress. Recently, some machine learning-based algorithms have been designed for miRNA subcellular location prediction, but their performance is still far from satisfactory. Here, we present a new data partitioning strategy that categorizes functionally similar locations for the precise and instructive prediction of miRNA subcellular location in Homo sapiens. To characterize the localization signals, we adopted one-hot encoding with post padding to represent the whole miRNA sequences, and proposed a deep bidirectional long short-term memory with the multi-head self-attention algorithm to model. The algorithm showed high selectivity in distinguishing extracellular miRNAs from intracellular miRNAs. Moreover, a series of motif analyses were performed to explore the mechanism of miRNA subcellular localization. To improve the convenience of the model, a user-friendly web server named iLoc-miRNA was established (http://iLoc-miRNA.lin-group.cn/).

Extracellular vesicles derived from Wharton's Jelly mesenchymal stem cells inhibit the tumor environment via the miR-125b/HIF1α signaling pathway.

Triple negative breast cancer (TNBC) is associated with worse outcomes and results in high mortality; therefore, great efforts are required to find effective treatment. In the present study, we suggested a novel strategy to treat TNBC using mesenchymal stem cell (MSC)-derived extracellular vesicles (EV) to transform the behaviors and cellular communication of TNBC cells (BCC) with other non-cancer cells related to tumorigenesis and metastasis. Our data showed that, BCC after being internalized with EV derived from Wharton's Jelly MSC (WJ-EV) showed the impaired proliferation, stemness properties, tumorigenesis and metastasis under hypoxic conditions. Moreover, these inhibitory effects may be involved in the transfer of miRNA-125b from WJ-EV to BCC, which downregulated the expression of HIF1α and target genes related to proliferation, epithelial-mesenchymal transition, and angiogenesis. Of note, WJ-EV-internalized BCC (wBCC) showed transformed behaviors that attenuated the in vivo development and metastatic ability of TNBC, the angiogenic abilities of endothelial cells and endothelial progenitor cells and the generation of cancer-associated fibroblasts from MSC. Furthermore, wBCC generated a new EV with modified functions that contributed to the inhibitory effects on tumorigenesis and metastasis of TNBC. Taken together, our findings suggested that WJ-EV treatment is a promising therapy that results in the generation of wBCC to interrupt the cellular crosstalk in the tumor environment and inhibit the tumor progression in TNBC.

Multiview network embedding for drug-target Interactions prediction by consistent and complementary information preserving.

Accurate prediction of drug-target interactions (DTIs) can reduce the cost and time of drug repositioning and drug discovery. Many current methods integrate information from multiple data sources of drug and target to improve DTIs prediction accuracy. However, these methods do not consider the complex relationship between different data sources. In this study, we propose a novel computational framework, called MccDTI, to predict the potential DTIs by multiview network embedding, which can integrate the heterogenous information of drug and target. MccDTI learns high-quality low-dimensional representations of drug and target by preserving the consistent and complementary information between multiview networks. Then MccDTI adopts matrix completion scheme for DTIs prediction based on drug and target representations. Experimental results on two datasets show that the prediction accuracy of MccDTI outperforms four state-of-the-art methods for DTIs prediction. Moreover, literature verification for DTIs prediction shows that MccDTI can predict the reliable potential DTIs. These results indicate that MccDTI can provide a powerful tool to predict new DTIs and accelerate drug discovery. The code and data are available at: https://github.com/ShangCS/MccDTI.

Detecting Interactive Gene Groups for Single-Cell RNA-Seq Data Based on Co-Expression Network Analysis and Subgraph Learning.

High-throughput sequencing technologies have enabled the generation of single-cell RNA-seq (scRNA-seq) data, which explore both genetic heterogeneity and phenotypic variation between cells. Some methods have been proposed to detect the related genes causing cell-to-cell variability for understanding tumor heterogeneity. However, most existing methods detect the related genes separately, without considering gene interactions. In this paper, we proposed a novel learning framework to detect the interactive gene groups for scRNA-seq data based on co-expression network analysis and subgraph learning. We first utilized spectral clustering to identify the subpopulations of cells. For each cell subpopulation, the differentially expressed genes were then selected to construct a gene co-expression network. Finally, the interactive gene groups were detected by learning the dense subgraphs embedded in the gene co-expression networks. We applied the proposed learning framework on a real cancer scRNA-seq dataset to detect interactive gene groups of different cancer subtypes. Systematic gene ontology enrichment analysis was performed to examine the detected genes groups by summarizing the key biological processes and pathways. Our analysis shows that different subtypes exhibit distinct gene co-expression networks and interactive gene groups with different functional enrichment. The interactive genes are expected to yield important references for understanding tumor heterogeneity.

Efficient Calculation of Electronic Structure Using O(N) Density Functional Theory.

We propose an efficient way to calculate the electronic structure of large systems by combining a large-scale first-principles density functional theory code, Conquest, and an efficient interior eigenproblem solver, the Sakurai-Sugiura method. The electronic Hamiltonian and charge density of large systems are obtained by Conquest, and the eigenstates of the Hamiltonians are then obtained by the Sakurai-Sugiura method. Applications to a hydrated DNA system and adsorbed P2 molecules and Ge hut clusters on large Si substrates demonstrate the applicability of this combination on systems with 10,000+ atoms with high accuracy and efficiency.