DeepVelo: deep learning extends RNA velocity to multi-lineage systems with cell-specific kinetics.

Existing RNA velocity estimation methods strongly rely on predefined dynamics and cell-agnostic constant transcriptional kinetic rates, assumptions often violated in complex and heterogeneous single-cell RNA sequencing (scRNA-seq) data. Using a graph convolution network, DeepVelo overcomes these limitations by generalizing RNA velocity to cell populations containing time-dependent kinetics and multiple lineages. DeepVelo infers time-varying cellular rates of transcription, splicing, and degradation, recovers each cell's stage in the differentiation process, and detects functionally relevant driver genes regulating these processes. Application to various developmental and pathogenic processes demonstrates DeepVelo's capacity to study complex differentiation and lineage decision events in heterogeneous scRNA-seq data.

Effect of Material Anisotropy on the Mechanical Response of Automotive Steel under High Strain Rates.

A constitutive model for automobile steel with high elongation needs to be established to predict the dynamic deformation behavior under hydroforming applications. In order to clarify the confusing discrepancy in the essential parameters of the classical Cowper-Symonds (C-S) model, a series of automobile structural steels have been employed to investigate the strain rate response by conducting tensile dynamic deformation. Metallographic microscopy and orientation distribution functions were used to characterize the microstructure and texture components of the steels. The microstructure observation discloses that the matrix of all steels is mainly of ferrite and the texture constituent provides a framework for steel to withstand external deformation. The C-S model can be applied to simulate the dynamic deformation with satisfied expectations. It is concluded that the essential parameters D and p in the model show a specific relationship with the steel grade, and the parameter D is proportional to the steel grade and related to material anisotropy, while the parameter p is inversely proportional to the steel grade and has close links with the grain boundary characteristics.