Artificial Intelligence (AI) is revolutionizing computational biology by introducing innovative methods across various fields. This review explores the role of AI in key areas such as drug discovery, genomics, and proteomics. In genomics, AI accelerates tasks like DeoxyriboNucleic Acid (DNA) sequencing and gene function analysis, enhancing our understanding of gene interactions. In proteomics, AI models aid in predicting protein functions, while in drug discovery, AI facilitates virtual testing of drug candidates, target identification, side-effect prediction, drug function analysis, and classification of anatomical therapeutic chemical classes, and drug property optimization, significantly expediting drug development. However, challenges remain, including diverse and noisy datasets, data imbalance, model transparency issues, and the limited generalizability of AI models to new species, cell types, or conditions. The effective application of AI also requires seamless collaboration among computational scientists, biologists, and clinicians, which can be difficult to achieve. This review identifies critical research challenges and proposes solutions, such as improved data integration techniques, more interpretable AI models, and hybrid approaches that combine AI with biological knowledge. Future directions emphasize the need for enhanced data-sharing frameworks, interdisciplinary collaboration, and advanced tools capable of managing complex biological information. By addressing these challenges, AI has the potential to drive significant advancements in computational biology, enriching our understanding of biology and advancing precision medicine.
The rapid growth of CPU-intensive and latency-sensitive applications has intensified the need for efficient resource management within edge computing environments. While existing simulators such as iFogSim, EdgeCloudSim, and PureEdgeSim have contributed significantly to edge computing research, they lack comprehensive support for modeling modern hardware heterogeneity, energy-aware mechanisms, service providers’ economic models, dependent task modeling, and reliability-driven task management. This paper presents MECSim (multi-access edge computing simulator), an enhanced simulation framework that extends PureEdgeSim to enable realistic modeling of heterogeneous, cooperative, and fault-tolerant edge computing ecosystems. MECSim supports multi-data-center clusters along with dynamic voltage and frequency scaling (DVFS) capable user devices for energy-efficient operation. The framework further integrates dependent-task modeling, cost and profit evaluation for service providers, and reliability mechanisms via transient-failure simulation, caching, and task replication. We have implemented five state-of-the-art approaches, demonstrating the effectiveness of our simulation platform and building confidence in its practical utility to handle diverse system architectures. With its extensible architecture and comprehensive modeling capabilities, MECSim provides a promising platform for future research on energy-efficient, profit-driven, and fault-tolerant task offloading and scheduling in heterogeneous MEC environments. The results also demonstrate that MECSim achieves a 44.13% (on average) reduction in simulation time compared to EdgeCloudSim. In addition, we have conducted experiments using dispersion-aware metrics to quantify variability and stability across 50 independent runs, thereby enabling a more robust and reliable performance evaluation.
This paper proposes a projected quantum gradient descent (P-QGD) framework for joint beamforming and simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) configuration in full-duplex non-orthogonal multiple access (NOMA)-assisted integrated sensing and communication (ISAC) systems. A parameterized quantum circuit (PQC) encodes downlink beamforming vectors, STAR-RIS phase shifts, and amplitude reflection/transmission coefficients into quantum states using Pauli-X rotation gates. At each iteration, measurement-based stochastic gradients are projected onto a constrained feasible set to ensure physical realizability, including unit-modulus phase constraints, amplitude normalization, and transmit power limits. A convergence guarantee is established under standard smoothness and bounded variance assumptions. The proposed P-QGD method exhibits logarithmic scaling in parameter dimensionality and achieves faster convergence compared to classical projected stochastic gradient descent (P-SGD). Extensive simulations validate that P-QGD yields higher downlink sum rate, improved sensing signal-to-interference-plus-noise ratio, and superior beamforming sharpness across varying reconfigurable intelligent surfaces (RIS) sizes, channel state information errors, and sensing-communication trade-offs. The framework also enables physical interpretability by linking quantum-optimized parameters to far-field beam pattern behavior. This work demonstrates the feasibility and advantages of quantum-native optimization in RIS-aided ISAC systems with constrained, multi-objective requirements.
Recurrent flooding in the Brahmaputra Valley of Assam — where nearly forty percent of land is vulnerable to inundation — poses severe threats to agricultural livelihoods, infrastructure, and household well-being. Despite the scale of this hazard, systematic household-level evidence on the spatial distribution of flood vulnerability across the region remains limited. This study assesses flood vulnerability across five strategically selected districts — Dhemaji, Lakhimpur, Morigaon, Nalbari, and Barpeta — using the Flood Vulnerability Index (FVI), integrating primary data from 627 households from January to May 2024, with qualitative focus group discussions and secondary government sources. Findings reveal that Morigaon is the most vulnerable district, driven by the highest exposure and susceptibility scores, a predominantly agrarian household economy, the lowest income levels, and the largest family sizes among the study districts. Dhemaji and Lakhimpur record moderate-to-high vulnerability, with institutional inaccessibility and dependence on informal coping mechanisms as key aggravating factors. Barpeta and Nalbari are comparatively less vulnerable, though Barpeta's char-dwelling population faces structural marginalisation that composite scores understate. Across all districts, institutional failure — including inequitable relief distribution and inadequate disaster shelters — consistently amplifies vulnerability regardless of physical exposure levels. The study underscores the need for spatially differentiated flood management strategies that combine livelihood diversification, strengthened institutional delivery, and community-based resilience building in Assam's most flood-exposed communities.
The flexibility of finite mixture models makes them suitable candidates for analyzing survival data with complex, multimodal distributions. Such data is often available if the event of interest occurs due to multiple failure modes. Here, we explore the modeling of competing risks time-to-event data with covariates in the presence of long-term survivors in the population using finite mixture models. The mixture cure rate model is used to describe the uncertainty in the population, where the susceptible part of the population is modeled using a finite mixture of Weibull distributions with different shape and scale parameters. Moreover, if information on covariates is available, the cure rate may be modeled using a binary regression model on the covariates. Here, we use the logistic function to relate covariates to the cure rate. The distribution corresponding to the susceptible part may also depend on covariates. To explore such dependency, we model the scale parameter of the Weibull distribution using covariates. Then, we discuss the classical parametric inference for the constructed model based on random and non-informative right-censored competing risks time-to-event data. An efficient method based on the expectation-maximization algorithm is proposed to estimate model parameters, thereby avoiding the complexity of directly maximizing the likelihood function. Additionally, a method for constructing confidence intervals for all model parameters is addressed. A simulation study is performed in the presence of two competing causes to investigate the finite sample properties of the proposed estimation methodologies. Finally, the methods are illustrated by analyzing a real data set on malignant melanoma cancer. Predicting the conditional survival function of an alive patient is of natural interest to an experimenter or medical researcher. A method for estimating such a conditional survival probability is also discussed.
