Automatic generation of RTL code for digital hardware designs remains challenging due to long-horizon reasoning, multi-step dependencies, and strict correctness constraints in Verilog and VHDL. We present StepPRM-RTL, a novel framework that combines stepwise trajectory modeling, process-reward modeling (PRM), and retrieval-augmented fine-tuning (RAFT) to enhance both the functional correctness and reasoning fidelity of LLM-based RTL code generation. StepPRM-RTL constructs stepwise reasoning trajectories from canonical solutions, where each step contains a rationale and incremental code modification. A Process Reward Model (PRM) evaluates intermediate steps, providing dense feedback that guides reinforcement-style updates during RAFT fine-tuning. Monte Carlo Tree Search (MCTS) explores alternative reasoning paths, enriching the training dataset with high-quality trajectories. This integration of stepwise and outcome-aware rewards allows the model to learn both how and why to construct correct RTL, improving long-horizon reasoning beyond standard supervised or outcome-based training. Experimental evaluation on benchmark Verilog and VHDL datasets demonstrates that StepPRM-RTL outperforms the best prior methods by over 10% in functional correctness and reasoning fidelity metrics. Ablation studies confirm that the combination of PRM-guided rewards and stepwise trajectory exploration is key to its performance. StepPRM-RTL generalizes across RTL languages and provides a scalable framework for high-fidelity, interpretable code generation, establishing a new standard for LLM-assisted hardware design automation.

Register-Transfer Level (RTL) synthesis and summarization are central to hardware design automation but remain challenging for Large Language Models (LLMs) due to rigid HDL syntax, limited supervision, and weak alignment with natural language. Existing prompting and retrieval-augmented generation (RAG) methods have not incorporated symbolic planning, limiting their structural precision. We introduce SYMDIREC, a neuro-symbolic framework that decomposes RTL tasks into symbolic subgoals, retrieves relevant code via a fine-tuned retriever, and assembles verified outputs through LLM reasoning. Supporting both Verilog and VHDL without LLM fine-tuning, SYMDIREC achieves 20

Optimizing Register Transfer Level (RTL) code is a critical step in Electronic Design Automation (EDA) for improving power, performance, and area (PPA). We present CODMAS (Collaborative Optimization via a Dialectic Multi-Agent System), a framework that combines structured dialectic reasoning with domain-aware code generation and deterministic evaluation to automate RTL optimization. At the core of CODMAS are two dialectic agents: the Articulator, inspired by rubber-duck debugging, which articulates stepwise transformation plans and exposes latent assumptions; and the Hypothesis Partner, which predicts outcomes and reconciles deviations between expected and actual behavior to guide targeted refinements. These agents direct a Domain-Specific Coding Agent (DCA) to generate architecture-aware Verilog edits and a Code Evaluation Agent (CEA) to verify syntax, functionality, and PPA metrics. We introduce RTLOPT, a benchmark of 120 Verilog triples (unoptimized, optimized, testbench) for pipelining and clock-gating transformations. Across proprietary and open LLMs, CODMAS achieves 25

Large language models (LLMs) have shown promise in code summarization, yet their effectiveness for Hardware Description Languages (HDLs) like VHDL and Verilog remains underexplored. We propose RoSum-Mcts, an LLM-guided approach inspired by Monte Carlo Tree Search (MCTS) that refines summaries through structured exploration and reinforcement-driven optimization. Our method integrates both local and global context via a hierarchical candidate expansion mechanism and optimizes summaries using a composite reward function balancing functional correctness (FC), local content adequacy (LCA), and fluency. We evaluate RoSum-Mcts on the VHDL-eval and Verilog-eval datasets, demonstrating its consistent outperformance over baseline methods by leveraging structured bottom-up refinement and reinforcement-based optimization. Ablation studies confirm the necessity of both local and global expansion strategies, as well as the importance of balancing FC and LCA for optimal performance. Furthermore, RoSum-Mcts proves robust against superficial modifications, such as variable renaming, maintaining summary quality where baselines degrade. These results establish RoSum-Mcts as an effective and robust HDL summarization framework, paving the way for further research into reinforcement-enhanced code summarization.

Bacterial pathogenicity has traditionally focused on gene-level content with experimentally confirmed functional properties. Hence, significant inferences are made based on similarity to known pathotypes and DNA-based genomic subtyping for risk. Herein, we achieved de novo prediction of human virulence in Klebsiella pneumoniae by expanding known virulence genes with spatially proximal gene discoveries linked by functional domain architectures across all prokaryotes. This approach identified gene ontology functions not typically associated with virulence sensu stricto. By leveraging machine learning models with these expanded discoveries, public genomes were assessed for virulence prediction using categorizations derived from isolation sources captured in available metadata. Performance for de novo strain-level virulence prediction achieved 0.81 F1-Score. Virulence predictions using expanded "discovered" functional genetic content were superior to that restricted to extant virulence database content. Additionally, this approach highlighted the incongruence in relying on traditional phylogenetic subtyping for categorical inferences. Our approach represents an improved deconstruction of genome-scale datasets for functional predictions and risk assessment intended to advance public health surveillance of emerging pathogens.

Analog circuit topology synthesis is integral to Electronic Design Automation (EDA), enabling the automated creation of circuit structures tailored to specific design requirements. However, the vast design search space and strict constraint adherence make efficient synthesis challenging. Leveraging the versatility of Large Language Models (LLMs), we propose AUTOCIRCUIT-RL,a novel reinforcement learning (RL)-based framework for automated analog circuit synthesis. The framework operates in two phases: instruction tuning, where an LLM learns to generate circuit topologies from structured prompts encoding design constraints, and RL refinement, which further improves the instruction-tuned model using reward models that evaluate validity, efficiency, and output voltage. The refined model is then used directly to generate topologies that satisfy the design constraints. Empirical results show that AUTOCIRCUIT-RL generates ~12% more valid circuits and improves efficiency by ~14% compared to the best baselines, while reducing duplicate generation rates by ~38%. It achieves over 60% success in synthesizing valid circuits with limited training data, demonstrating strong generalization. These findings highlight the framework's effectiveness in scaling to complex circuits while maintaining efficiency and constraint adherence, marking a significant advancement in AI-driven circuit design.

Bacterial pathogenicity has traditionally focused on gene-level content with experimentally-confirmed functional properties. Hence, significant inferences are made based on similarity to known pathotypes and DNA-based genomic subtyping for risk. Herein, we achieved de novo prediction of human virulence in Klebsiella pneumoniae by expanding known virulence genes with spatially proximal gene discoveries linked by functional domain architectures across all prokaryotes. This approach identified gene ontology functions not typically associated with virulence sensu stricto . By leveraging machine learning models with these expanded discoveries, public genomes were assessed for virulence prediction using categorizations derived from isolation sources captured in available metadata. Performance for de novo strain-level virulence prediction achieved 0.81 F1-Score. Virulence predictions using expanded “discovered” functional genetic content were superior to that restricted to extant virulence database content. Additionally, this approach highlighted the incongruence in relying on traditional phylogenetic subtyping for categorical inferences. Our approach represents an improved deconstruction of genome-scale datasets for functional predictions and risk assessment intended to advance public health surveillance of emerging pathogens.### Competing Interest StatementThe authors have declared no competing interest.

The COVID-19 pandemic has caused major disruptions to workplace safety and productivity. A browser-based interactive disease transmission simulation was developed to enable managers and individuals (agents) to optimize safe office work activities during pandemic conditions. The application provides a user interface to evaluate the impact of non-pharmaceutical interventions (NPIs) policies on airborne disease exposure based on agents’ meeting patterns and room properties. Exposure is empirically calibrated using CO2 as a proxy for viral aerosol dispersion. For the building studied, the major findings are that the cubicles during low occupancy produce unexpectedly high exposure, upgrading meetings to larger rooms reduces total average exposure by 44%, and when all meetings are conducted in large rooms, a 79% exposure reduction is realized.

Agent-based social simulation can be useful for creating digital twins of societies of interacting autonomous agents. Such simulations are useful for testing hypotheses about behaviour and belief change in the presence of interventions. In this paper, we introduce Clockwork, an efficient multi-agent simulation framework. The key contribution of this framework is integrating a behaviour-level simulation of autonomous agent schedules with a Discrete Event Simulator (DES) and a rich model of social interaction among agents modelled with Agent-Based Social Simulation (ABSS) methodology. Clockwork's ability to simulate deterministic and stochastic events and changes in individual agent models due to the influence of other agents through event-based emergent interactions is novel. We describe the design, architecture, and development of the Clockwork framework. Combining DES and ABSS in this way enables the modelling of detailed individual agent histories while maintaining population-level statistical distributions. We evaluated Clockwork with a real-life scenario modelling the digital twin of employees at a real-world worksite to test the efficacy of various policies put in place to mitigate the risk of contracting COVID-19 through a hybrid or in-person work model.

The rapid growth in biological sequence data is revolutionizing our understanding of genotypic diversity and challenging conventional approaches to informatics. With the increasing availability of genomic data, traditional bioinformatic tools require substantial computational time and the creation of ever-larger indices each time a researcher seeks to gain insight from the data. To address these challenges, we pre-computed important relationships between biological entities spanning the Central Dogma of Molecular Biology and captured this information in a relational database. The database can be queried across hundreds of millions of entities and returns results in a fraction of the time required by traditional methods. In this paper, we describe Functional Genomics Platform (formerly known as OMXWare), a comprehensive database relating genotype to phenotype for bacterial life. Continually updated, the Functional Genomics Platform today contains data derived from 200,000 curated, self-consistently assembled genomes. The database stores functional data for over 68 million genes, 52 million proteins, and 239 million domains with associated biological activity annotations from Gene Ontology, KEGG, MetaCyc, and Reactome. The Functional Genomics Platform maps all of the many-to-many connections between each biological entity including the originating genome, gene, protein, and protein domain. Various microbial studies, from infectious disease to environmental health, can benefit from the rich data and connections. We describe the data selection, the pipeline to create and update the Functional Genomics Platform, and the developer tools (Python SDK and REST APIs)which allow researchers to efficiently study microbial life at scale.

Epitopes are short amino acid sequences that define the antigen signature to which an antibody or T cell receptor binds. In light of the current pandemic, epitope analysis and prediction are paramount to improving serological testing and developing vaccines. In this paper, known epitope sequences from SARS-CoV, SARS-CoV-2, and other Coronaviridae were leveraged to identify additional antigen regions in 62K SARS-CoV-2 genomes. Additionally, we present epitope distribution across SARS-CoV-2 genomes, locate the most commonly found epitopes, and discuss where epitopes are located on proteins and how epitopes can be grouped into classes. The mutation density of different protein regions is presented using a big data approach. It was observed that there are 112 B cell and 279 T cell conserved epitopes between SARS-CoV-2 and SARS-CoV, with more diverse sequences found in Nucleoprotein and Spike glycoprotein.

Patient Electronic Health Records (EHRs) typically contain a substantial amount of data, which can lead to information overload for clinicians, especially in high-throughput fields like radiology. Thus, it would be beneficial to have a mechanism for summarizing the most clinically relevant patient information pertinent to the needs of clinicians. This study presents a novel approach for the curation of clinician EHR data preference information towards the ultimate goal of providing robust EHR summarization. Clinicians first provide a list of data items of interest across multiple EHR categories. Since this data is manually dictated, it has limited coverage and may not cover all the important terms relevant to a concept. To address this problem, we have developed a knowledge-driven semantic concept expansion approach by leveraging rich biomedical knowledge from the UMLS. The approach expands 1094 seed concepts to 22,325 concepts with 92.69% of the expanded concepts identified as relevant by clinicians.

Although a plethora of research articles on AI methods on COVID-19 medical imaging are published, their clinical value remains unclear. We conducted the largest systematic review of the literature addressing the utility of AI in imaging for COVID-19 patient care. By keyword searches on PubMed and preprint servers throughout 2020, we identified 463 manuscripts and performed a systematic meta-analysis to assess their technical merit and clinical relevance. Our analysis evidences a significant disparity between clinical and AI communities, in the focus on both imaging modalities (AI experts neglected CT and ultrasound, favoring X-ray) and performed tasks (71.9% of AI papers centered on diagnosis). The vast majority of manuscripts were found to be deficient regarding potential use in clinical practice, but 2.7% (n = 12) publications were assigned a high maturity level and are summarized in greater detail. We provide an itemized discussion of the challenges in developing clinically relevant AI solutions with recommendations and remedies.

Rapid tests for active SARS-CoV-2 infections rely on reverse transcription polymerase chain reaction (RT-PCR). RT-PCR uses reverse transcription of RNA into complementary DNA (cDNA) and amplification of specific DNA (primer and probe) targets using polymerase chain reaction (PCR). The technology makes rapid and specific identification of the virus possible based on sequence homology of nucleic acid sequence and is much faster than tissue culture or animal cell models. However the technique can lose sensitivity over time as the virus evolves and the target sequences diverge from the selective primer sequences. Different primer sequences have been adopted in different geographic regions. As we rely on these existing RT-PCR primers to track and manage the spread of the Coronavirus, it is imperative to understand how SARS-CoV-2 mutations, over time and geographically, diverge from existing primers used today. In this study, we analyze the performance of the SARS-CoV-2 primers in use today by measuring the number of mismatches between primer sequence and genome targets over time and spatially. We find that there is a growing number of mismatches, an increase by 2% per month, as well as a high specificity of virus based on geographic location.

SARS-CoV-2 genomic sequencing efforts have scaled dramatically to address the current global pandemic and aid public health. However, autonomous genome annotation of SARS-CoV-2 genes, proteins, and domains is not readily accomplished by existing methods and results in missing or incorrect sequences. To overcome this limitation, we developed a novel semi-supervised pipeline for automated gene, protein, and functional domain annotation of SARS-CoV-2 genomes that differentiates itself by not relying on the use of a single reference genome and by overcoming atypical genomic traits that challenge traditional bioinformatic methods. We analyzed an initial corpus of 66,000 SARS-CoV-2 genome sequences collected from labs across the world using our method and identified the comprehensive set of known proteins with 98.5% set membership accuracy and 99.1% accuracy in length prediction, compared to proteome references, including Replicase polyprotein 1ab (with its transcriptional slippage site). Compared to other published tools, such as Prokka (base) and VAPiD, we yielded a 6.4- and 1.8-fold increase in protein annotations. Our method generated 13,000,000 gene, protein, and domain sequences-some conserved across time and geography and others representing emerging variants. We observed 3362 non-redundant sequences per protein on average within this corpus and described key D614G and N501Y variants spatiotemporally in the initial genome corpus. For spike glycoprotein domains, we achieved greater than 97.9% sequence identity to references and characterized receptor binding domain variants. We further demonstrated the robustness and extensibility of our method on an additional 4000 variant diverse genomes containing all named variants of concern and interest as of August 2021. In this cohort, we successfully identified all keystone spike glycoprotein mutations in our predicted protein sequences with greater than 99% accuracy as well as demonstrating high accuracy of the protein and domain annotations. This work comprehensively presents the molecular targets to refine biomedical interventions for SARS-CoV-2 with a scalable, high-accuracy method to analyze newly sequenced infections as they arise.

Lung opacities on CT scans, such as ground-glass opacities (GGOs) and consolidation, can manifest with various conditions, including lung cancers, pulmonary edema and COVID-19. Presentation of these non-specific findings can vary from isolated focal to diffuse opacities in all lobes. Moreover, disease distributions and progressions vary across disease types and patients. This unpredictability can challenge one's ability to accurately quantify and compare the percentage of infected lung within and across patients. Despite the promise of AI models for image segmentation, the inconsistency of lung opacities, and limited access to large annotated datasets affect generalization performance of models to the cohort of lung diseases. In this paper, we developed a single-stage system to jointly localize the lung and opacifications in CT scans using a diverse real-world dataset with sparse annotations. A multi-class Dense U-Net model was designed to segment the lungs and two classes of opacity regions (GGOs and consolidations) in CT images. The model was trained on 4075 slices from 495 sparsely annotated CT studies and evaluated on 18625 slices from 103 densely annotated studies (37 positive). A comparative analysis of different training data subsets and loss functions was performed to determine optimal model design. Performance was evaluated by comparing manual and automated lung opacity percentages via Pearson Correlation Coefficient. The optimal model achieved a Pearson Correlation Coefficient of 0.99. These findings suggest the potential of developing an accurate method to localize lung opacification, unspecific to a particular disease.

We developed a rich dataset of Chest X-Ray (CXR) images to assist investigators in artificial intelligence. The data were collected using an eye-tracking system while a radiologist reviewed and reported on 1,083 CXR images. The dataset contains the following aligned data: CXR image, transcribed radiology report text, radiologist’s dictation audio and eye gaze coordinates data. We hope this dataset can contribute to various areas of research particularly towards explainable and multimodal deep learning/machine learning methods. Furthermore, investigators in disease classification and localization, automated radiology report generation, and human-machine interaction can benefit from these data. We report deep learning experiments that utilize the attention maps produced by the eye gaze dataset to show the potential utility of this dataset.