Multimodal MRIs play a crucial role in clinical diagnosis and treatment. Feature disentanglement (FD)-based methods, aiming at learning superior feature representations for multimodal data analysis, have achieved significant success in multimodal learning (MML). Typically, existing FD-based methods separate multimodal data into modality-shared and modality-specific features, and employ concatenation or attention mechanisms to integrate these features. However, our preliminary experiments indicate that these methods could lead to a loss of shared information among subsets of modalities when the inputs contain more than two modalities, and such information is critical for prediction accuracy. Furthermore, these methods do not adequately interpret the relationships between the decoupled features at the fusion stage. To address these limitations, we propose a novel Complete Feature Disentanglement (CFD) strategy that recovers the lost information during feature decoupling. Specifically, the CFD strategy not only identifies modality-shared and modality-specific features, but also decouples shared features among subsets of multimodal inputs, termed as modality-partial-shared features. We further introduce a new Dynamic Mixture-of-Experts Fusion (DMF) module that dynamically integrates these decoupled features, by explicitly learning the local-global relationships among the features. The effectiveness of our approach is validated through classification tasks on three multimodal MRI datasets. Extensive experimental results demonstrate that our approach outperforms other state-of-the-art MML methods with obvious margins, showcasing its superior performance.

Single-cell CRISPR screens have been widely used to investigate gene regulatory circuits in diverse biological systems. The recent development of single-cell CRISPR screens has enabled multimodal profiling of perturbed cells with both gene expression, chromatin accessibility and protein levels. However, current methods cannot meet the analysis requirements of different types of data and have limited functions. Here, we introduce Single-cell CRISPR screens data analysEs and perturbation modEling (SCREE) as a comprehensive and flexible pipeline to facilitate the analyses of various types of single-cell CRISPR screens data. SCREE performs read alignment, sgRNA assignment, quality control, clustering and visualization, perturbation enrichment evaluation, perturbation efficiency modeling, gene regulatory score calculation and functional analyses of perturbations for single-cell CRISPR screens with both RNA, ATAC and multimodal readout. SCREE is available at https://github.com/wanglabtongji/SCREE.

Existing segmentation methods for brain MRI data usually leverage 3D CNNs on 3D volumes or employ 2D CNNs on 2D image slices. We discovered that while volume-based approaches well respect spatial relationships across slices, slice-based methods typically excel at capturing fine local features. Furthermore, there is a wealth of complementary information between their segmentation predictions. Inspired by this observation, we develop an Uncertainty-aware Multi-dimensional Mutual learning framework to learn different dimensional networks simultaneously, each of which provides useful soft labels as supervision to the others, thus effectively improving the generalization ability. Specifically, our framework builds upon a 2D-CNN, a 2.5D-CNN, and a 3D-CNN, while an uncertainty gating mechanism is leveraged to facilitate the selection of qualified soft labels, so as to ensure the reliability of shared information. The proposed method is a general framework and can be applied to varying backbones. The experimental results on three datasets demonstrate that our method can significantly enhance the performance of the backbone network by notable margins, achieving a Dice metric improvement of 2.8% on MeniSeg, 1.4% on IBSR, and 1.3% on BraTS2020.

The parameter estimation of a photovoltaic (PV) model that measures the change of the current-voltage dataset is a key issue for PV system applications. It is regarded as a complex multimodal optimization problem, and there have been several attempts to solve the problem in this field of research. To further address this problem in a faster and more accurate manner, we demonstrate an improved covariance matrix adaptive evolutionary strategy (CMA-ES) with novel modifications in an eigen coordinates framework named EC-CMA-ES. The original CMA-ES suffers from premature convergence and has poor exploration performance. Thus, we propose an eigenvalue adjustment strategy on a covariance matrix in order to drive evolution towards the dominant domain by adjusting its eigenvalues. Moreover, we perform a local search strategy in a later stage by utilizing the neglected inferior solutions to enrich the population diversity. We apply EC-CMA-ES to address the parameter identification of three commonly used PV models. The statistical results and comparisons with other state-of-the-art algorithms demonstrate the competitive performance of our modified CMA-ES in terms of efficiency and accuracy.

This paper addresses the issue of control parameter uncertainties in total transfer capability (TTC) calculation for meshed transmission grids with VSC-HVDC. A new concept of TTC embodying control parameter uncertainties (TTCU) is first proposed. And then the calculation model of TTCU for meshed transmission grids with VSC-HVDC and its solving approach are further presented. Simulations are carried on the modified IEEE 39-bus system, illustrating that control parameter uncertainties can decrease TTC and impact the optimal operation of VSC-HVDC with respect to TTC, and the proposed TTCU providing robust operation mode for VSC-HVDC is superior to TTC.