It has been a challenge in systems biology to unravel relationships between structural properties and dynamic behaviors of biological networks. A Cytoscape plugin named NetDS was recently proposed to analyze the robustness-related dynamics and feed-forward/feedback loop structures of biological networks. Despite such a useful function, limitations on the network size that can be analyzed exist due to high computational costs. In addition, the plugin cannot verify an intrinsic property which can be induced by an observed result because it has no function to simulate the observation on a large number of random networks. To overcome these limitations, we have developed a novel software tool, PANET. First, the time-consuming parts of NetDS were redesigned to be processed in parallel using the OpenCL library. This approach utilizes the full computing power of multi-core central processing units and graphics processing units. Eventually, this made it possible to investigate a large-scale network such as a human signaling network with 1,609 nodes and 5,063 links. We also developed a new function to perform a batch-mode simulation where it generates a lot of random networks and conducts robustness calculations and feed-forward/feedback loop examinations of them. This helps us to determine if the findings in real biological networks are valid in arbitrary random networks or not. We tested our plugin in two case studies based on two large-scale signaling networks and found interesting results regarding relationships between coherently coupled feed-forward/feedback loops and robustness. In addition, we verified whether or not those findings are consistently conserved in random networks through batch-mode simulations. Taken together, our plugin is expected to effectively investigate various relationships between dynamics and structural properties in large-scale networks. Our software tool, user manual and example datasets are freely available at http://panet-csc.sourceforge.net/.

Machinery diagnostics and prognostics usually involve the prediction process of fault-types and remaining useful life (RUL) of a machine, respectively. The process of developing a data-driven diagnostics and prognostics method involves some fundamental subtasks such as data rebalancing, feature extraction, dimension reduction, and machine learning. In general, the best performing algorithm and the optimal hyper-parameters suitable for each subtask are varied across the characteristics of datasets. Therefore, it is challenging to develop a general diagnostic/prognostic framework that can automatically identify the best subtask algorithms and the optimal involved parameters for a given dataset. To resolve this problem, we propose a new framework based on an ensemble of genetic algorithms (GAs) that can be used for both the fault-type classification and RUL prediction. Our GA is combined with a specific machine-learning method and then tries to select the best algorithm and optimize the involved parameter values in each subtask. In addition, our method constructs an ensemble of various prediction models found by the GAs. Our method was compared to a traditional grid-search over three benchmark datasets of the fault-type classification and the RUL prediction problems and showed a significantly better performance than the latter. Taken together, our framework can be an effective approach for the fault-type and RUL prediction of various machinery systems.

Motivation: Biological networks are composed of molecular components and their interactions represented by nodes and edges, respectively, in a graph model. Based on this model, there were many studies with respect to effects of node-based mutations on the network dynamics, whereas little attention was paid to edgetic mutations so far. Results: In this paper, we defined an edgetic sensitivity measure that quantifies how likely a converging attractor is changed by edge-removal mutations in a Boolean network model. Through extensive simulations based on that measure, we found interesting properties of highly sensitive edges in both random and real signaling networks. First, the sensitive edges in random networks tend to link two end nodes both of which are susceptible to node-knockout mutations. Interestingly, it was analogous to an observation that the sensitive edges in human signaling networks are likely to connect drug-target genes. We further observed that the edgetic sensitivity predicted drug-targets better than the node-based sensitivity. In addition, the sensitive edges showed distinguished structural characteristics such as a lower connectivity, more involving feedback loops and a higher betweenness. Moreover, their gene-ontology enrichments were clearly different from the other edges. We also observed that genes incident to the highly sensitive interactions are more central by forming a considerably large connected component in human signaling networks. Finally, we validated our approach by showing that most sensitive interactions are promising edgetic drug-targets in p53 cancer and T-cell apoptosis networks. Taken together, the edgetic sensitivity is valuable to understand the complex dynamics of signaling networks. Contact:kwonyk@ulsan.ac.kr Supplementary information:Supplementary data are available at Bioinformatics online.

There have been many in silico studies based on a Boolean network model to investigate network sensitivity against gene or interaction mutations. However, there are no proper tools to examine the network sensitivity against many different types of mutations, including user-defined ones. To address this issue, we developed RMut, which is an R package to analyze the Boolean network-based sensitivity by efficiently employing not only many well-known node-based and edgetic mutations but also novel user-defined mutations. In addition, RMut can specify the mutation area and the duration time for more precise analysis. RMut can be used to analyze large-scale networks because it is implemented in a parallel algorithm using the OpenCL library. In the first case study, we observed that the real biological networks were most sensitive to overexpression/state-flip and edge-addition/-reverse mutations among node-based and edgetic mutations, respectively. In the second case study, we showed that edgetic mutations can predict drug-targets better than node-based mutations. Finally, we examined the network sensitivity to double edge-removal mutations and found an interesting synergistic effect. Taken together, these findings indicate that RMut is a flexible R package to efficiently analyze network sensitivity to various types of mutations. RMut is available at https://github.com/csclab/RMut.

Accurate prediction of the Remaining Useful Life (RUL) of lithium-ion batteries is critical for safe, reliable Battery Health Management in diverse operating conditions. Existing RUL models often fail to generalize when test data diverge from the training distribution. To address this, we introduce HybridoNet-Adapt, a domain-adaptive RUL prediction framework that explicitly bridges the gap between labeled source and unlabeled target domains. During training, we minimize the Maximum Mean Discrepancy (MMD) between feature distributions to learn domain-invariant representations. Simultaneously, we employ two parallel predictors—one tailored to the source domain and one to the target domain—and balance their outputs via two learnable trade-off parameters, enabling the model to dynamically weight domain-specific insights. Our architecture couples this adaptation strategy with LSTM, multi-head attention, and Neural ODE blocks for deep temporal feature extraction, but its core novelty lies in the MMD-based alignment and hybrid prediction mechanism. On two large, publicly available battery datasets, HybridoNet-Adapt consistently outperforms non-adaptive baselines (Structural Pruning, Multi-Time Scale Feature Extraction Hybrid model, XGBoost, Elastic Net), archiving an RMSE reduction of up to 152 cycles under domain shifts. These results demonstrate that incorporating domain adaptation into RUL modeling substantially enhances robustness and real-world applicability.

Accurate prediction of the Remaining Useful Life (RUL) is essential for enabling timely maintenance of lithium-ion batteries, impacting the operational efficiency of electric applications that rely on them. This paper proposes a RUL prediction approach that leverages data from recent charge-discharge cycles to estimate the number of remaining usable cycles. The approach introduces both a novel signal preprocessing pipeline and a deep learning prediction model. In the signal preprocessing pipeline, a derived capacity feature is computed using interpolated current and capacity signals. Alongside original capacity, voltage and current, these features are denoised and enhanced using statistical metrics and a delta-based method to capture differences between the current and previous cycles. In the prediction model, the processed features are then fed into a hybrid deep learning architecture composed of 1D Convolutional Neural Networks (CNN), Attentional Long Short-Term Memory (A-LSTM), and Ordinary Differential Equation-based LSTM (ODE-LSTM) blocks. The ODE-LSTM architecture employs ordinary differential equations to integrate continuous dynamics into sequence-to-sequence modeling, thereby combining continuous and discrete temporal representations, while the A-LSTM incorporates an attention mechanism to capture local temporal dependencies. The model is further evaluated using transfer learning across different learning strategies and target data partitioning scenarios. Results indicate that the model maintains robust performance, even when fine-tuned on limited target data. Experimental results on two publicly available LFP/graphite lithium-ion battery datasets demonstrate that the proposed method outperforms a baseline deep learning approach and machine learning techniques, achieving an RMSE of 101.59, highlighting its potential for real-world RUL prediction applications.