Biolinguistic graph fusion model for circRNA-miRNA association prediction.

Emerging clinical evidence suggests that sophisticated associations with circular ribonucleic acids (RNAs) (circRNAs) and microRNAs (miRNAs) are a critical regulatory factor of various pathological processes and play a critical role in most intricate human diseases. Nonetheless, the above correlations via wet experiments are error-prone and labor-intensive, and the underlying novel circRNA-miRNA association (CMA) has been validated by numerous existing computational methods that rely only on single correlation data. Considering the inadequacy of existing machine learning models, we propose a new model named BGF-CMAP, which combines the gradient boosting decision tree with natural language processing and graph embedding methods to infer associations between circRNAs and miRNAs. Specifically, BGF-CMAP extracts sequence attribute features and interaction behavior features by Word2vec and two homogeneous graph embedding algorithms, large-scale information network embedding and graph factorization, respectively. Multitudinous comprehensive experimental analysis revealed that BGF-CMAP successfully predicted the complex relationship between circRNAs and miRNAs with an accuracy of 82.90% and an area under receiver operating characteristic of 0.9075. Furthermore, 23 of the top 30 miRNA-associated circRNAs of the studies on data were confirmed in relevant experiences, showing that the BGF-CMAP model is superior to others. BGF-CMAP can serve as a helpful model to provide a scientific theoretical basis for the study of CMA prediction.

Likelihood-based feature representation learning combined with neighborhood information for predicting circRNA-miRNA associations.

Connections between circular RNAs (circRNAs) and microRNAs (miRNAs) assume a pivotal position in the onset, evolution, diagnosis and treatment of diseases and tumors. Selecting the most potential circRNA-related miRNAs and taking advantage of them as the biological markers or drug targets could be conducive to dealing with complex human diseases through preventive strategies, diagnostic procedures and therapeutic approaches. Compared to traditional biological experiments, leveraging computational models to integrate diverse biological data in order to infer potential associations proves to be a more efficient and cost-effective approach. This paper developed a model of Convolutional Autoencoder for CircRNA-MiRNA Associations (CA-CMA) prediction. Initially, this model merged the natural language characteristics of the circRNA and miRNA sequence with the features of circRNA-miRNA interactions. Subsequently, it utilized all circRNA-miRNA pairs to construct a molecular association network, which was then fine-tuned by labeled samples to optimize the network parameters. Finally, the prediction outcome is obtained by utilizing the deep neural networks classifier. This model innovatively combines the likelihood objective that preserves the neighborhood through optimization, to learn the continuous feature representation of words and preserve the spatial information of two-dimensional signals. During the process of 5-fold cross-validation, CA-CMA exhibited exceptional performance compared to numerous prior computational approaches, as evidenced by its mean area under the receiver operating characteristic curve of 0.9138 and a minimal SD of 0.0024. Furthermore, recent literature has confirmed the accuracy of 25 out of the top 30 circRNA-miRNA pairs identified with the highest CA-CMA scores during case studies. The results of these experiments highlight the robustness and versatility of our model.

Memory effect of spider major ampullate silk in loading-unloading cycles and the structural connotations.

Spider silk is repeatedly stretched while performing biological functions. There is a close relationship between the shape change of the fibre materials and their mechanical properties. However, the effect of the deformation and interval time on the structure and tensile behaviour properties of spider silk after repeatedly stretching by given strain value has been rarely reported. Here we found that major ampullate silk (MAS) can revert its tensile behaviour independent of its previous loading history via intervals of approximately 8 s to 5 min with constant and increased elongation, respectively, after being subjected to yield and hardening regions. The true stress-true strain curve beyond a given value of true strain is independent from the previous loading history of the sample. Even after longer intervals (≥1 h), MAS can reproduce the last tensile behaviour via one stretched. Despite recognizing the development of irreversible deformations in the material when tested in air, the reversible change in tensile behaviour outside the spider silk's elastic region has rarely been observed before. MAS has at least one proper ground state that allows it to present good shape and mechanical behaviour memory in terms of longitudinal stretching, functioning as a new strategy to achieve certain tensile properties. The analysis of the true stress-true strain curves was performed from a series of loading‒unloading tests to evaluate the evolution of those mechanical parameters with the cycle number. The elastic modulus measured in the loading steps increases monotonously with increasing values of true strain reached in the cycles. In contrast, a marginal variation is found in the values of the yield stress measured in the different cycles. The memory and variation in the mechanical behaviour and performance of MAS can be accounted for through the irreversible and reversible deformation micromechanisms and its combination in which the viscoelasticity of the material plays a leading role. These findings may be helpful to guide the biomimetic design of novel fibre materials such as spider silk gut via artificially stretching spider silk glands.