The convergence of robotics and virtual reality (VR) has enabled safer and more efficient workflows in high-risk laboratory settings, particularly virology labs. As biohazard complexity increases, minimizing direct human exposure while maintaining precision becomes essential. We propose GAMORA (Gesture Articulated Meta Operative Robotic Arm), a novel VR-guided robotic system that enables remote execution of hazardous tasks using natural hand gestures. Unlike existing scripted automation or traditional teleoperation, GAMORA integrates the Oculus Quest 2, NVIDIA Jetson Nano, and Robot Operating System (ROS) to provide real-time immersive control, digital twin simulation, and inverse kinematics-based articulation. The system supports VR-based training and simulation while executing precision tasks in physical environments via a 3D-printed robotic arm. Inverse kinematics ensure accurate manipulation for delicate operations such as specimen handling and pipetting. The pipeline includes Unity-based 3D environment construction, real-time motion planning, and hardware-in-the-loop testing. GAMORA achieved a mean positional discrepancy of 2.2 mm (improved from 4 mm), pipetting accuracy within 0.2 mL, and repeatability of 1.2 mm across 50 trials. Integrated object detection via YOLOv8 enhances spatial awareness, while energy-efficient operation (50% reduced power output) ensures sustainable deployment. The system's digital-physical feedback loop enables safe, precise, and repeatable automation of high-risk lab tasks. GAMORA offers a scalable, immersive solution for robotic control and biosafety in biomedical research environments.
AI safety systems face a dual-use dilemma. Since the same request can be either harmless or harmful depending on who made it and why, if the system makes decisions based solely on the request's content, it will refuse some legitimate queries and let pass harmful ones. To address this, we propose a conceptual access control framework, based on verified user credentials (such as institutional affiliation) and classifiers that assign model outputs to risk categories (such as advanced virology). The system permits responses only when the user's verified credentials match the category's requirements. For implementation of the model output classifiers, we introduce a theoretical approach utilizing small, gated expert modules integrated into the generator model, trained with gradient routing, that enable efficient risk detection without the capability gap problems of external monitors. While open questions remain about the verification mechanisms, risk categories, and the technical implementation, our framework makes the first step toward enabling granular governance of AI capabilities: verified users gain access to specialized knowledge without arbitrary restrictions, while adversaries are blocked from it. This contextual approach reconciles model utility with robust safety, addressing the dual-use dilemma.
This study systematically evaluates 27 frontier Large Language Models on eight biology benchmarks spanning molecular biology, genetics, cloning, virology, and biosecurity. Models from major AI developers released between November 2022 and April 2025 were assessed through ten independent runs per benchmark. The findings reveal dramatic improvements in biological capabilities. Top model performance increased more than 4-fold on the challenging text-only subset of the Virology Capabilities Test over the study period, with OpenAI's o3 now performing twice as well as expert virologists. Several models now match or exceed expert-level performance on other challenging benchmarks, including the biology subsets of GPQA and WMDP and LAB-Bench CloningScenarios. Contrary to expectations, chain-of-thought did not substantially improve performance over zero-shot evaluation, while extended reasoning features in o3-mini and Claude 3.7 Sonnet typically improved performance as predicted by inference scaling. Benchmarks such as PubMedQA and the MMLU and WMDP biology subsets exhibited performance plateaus well below 100%, suggesting benchmark saturation and errors in the underlying benchmark data. The analysis highlights the need for more sophisticated evaluation methodologies as AI systems continue to advance.
We present the Virology Capabilities Test (VCT), a large language model (LLM) benchmark that measures the capability to troubleshoot complex virology laboratory protocols. Constructed from the inputs of dozens of PhD-level expert virologists, VCT consists of $322$ multimodal questions covering fundamental, tacit, and visual knowledge that is essential for practical work in virology laboratories. VCT is difficult: expert virologists with access to the internet score an average of $22.1\%$ on questions specifically in their sub-areas of expertise. However, the most performant LLM, OpenAI's o3, reaches $43.8\%$ accuracy, outperforming $94\%$ of expert virologists even within their sub-areas of specialization. The ability to provide expert-level virology troubleshooting is inherently dual-use: it is useful for beneficial research, but it can also be misused. Therefore, the fact that publicly available models outperform virologists on VCT raises pressing governance considerations. We propose that the capability of LLMs to provide expert-level troubleshooting of dual-use virology work should be integrated into existing frameworks for handling dual-use technologies in the life sciences.
In this work, we introduce Virology-Informed Neural Networks (VINNs), a powerful tool for capturing the intricate dynamics of viral infection when data of some compartments of the model are not available. VINNs, an extension of the widely known Physics-Informed Neural Networks (PINNs), offer an alternative approach to traditional numerical methods for solving system of differential equations. We apply this VINN technique on a recently proposed hepatitis B virus (HBV) infection dynamics model to predict the transmission of the infection within the liver more accurately. This model consists of four compartments, namely uninfected and infected hepatocytes, rcDNA-containing capsids, and free viruses, along with the consideration of capsid recycling. Leveraging the power of VINNs, we study the impacts of variations in parameter range, experimental noise, data variability, network architecture, and learning rate in this work. In order to demonstrate the robustness and effectiveness of VINNs, we employ this approach on the data collected from nine HBV-infceted chimpanzees, and it is observed that VINNs can effectively estimate the model parameters. VINNs reliably capture the dynamics of infection spread and accurately predict their future progression using real-world data. Furthermore, VINNs efficiently identify the most influential parameters in HBV dynamics based solely on experimental data from the capsid component. It is also expected that this framework can be extended beyond viral dynamics, providing a powerful tool for uncovering hidden patterns and complex interactions across various scientific and engineering domains.
HIV-1 replication can be suppressed with antiretroviral therapy (ART), but individuals who stop taking ART soon become viremic again. Some people experience extended times of detectable viremia despite optimal adherence to ART. In the issue of the JCI, White, Wu, and coauthors elucidate a source of nonsuppressible viremia (NSV) in treatment-adherent patients clonally expanded T cells harboring HIV-1 proviruses with small deletions or mutations in the 5'-leader, the UTR that includes the major splice donor site of viral RNA. These mutations altered viral RNA-splicing efficiency and RNA dimerization and packaging, yet still allowed production of detectable levels of noninfectious virus particles. These particles lacked the HIV-1 Env surface protein required for cell entry and failed to form the mature capsid cone required for infectivity. These studies improve our understanding of NSV and the regulation of viral functions in the 5'-leader with implications for rationalized care in individuals with NSV.
Large Language Models (LLMs) have shown remarkable performance across various tasks, yet significant disparities remain for non-English languages, and especially native African languages. This paper addresses these disparities by creating approximately 1 million human-translated words of new benchmark data in 8 low-resource African languages, covering a population of over 160 million speakers of: Amharic, Bambara, Igbo, Sepedi (Northern Sotho), Shona, Sesotho (Southern Sotho), Setswana, and Tsonga. Our benchmarks are translations of Winogrande and three sections of MMLU: college medicine, clinical knowledge, and virology. Using the translated benchmarks, we report previously unknown performance gaps between state-of-the-art (SOTA) LLMs in English and African languages. Finally, using results from over 400 fine-tuned models, we explore several methods to reduce the LLM performance gap, including high-quality dataset fine-tuning (using an LLM-as-an-Annotator), cross-lingual transfer, and cultural appropriateness adjustments. Key findings include average mono-lingual improvements of 5.6% with fine-tuning (with 5.4% average mono-lingual improvements when using high-quality data over low-quality data), 2.9% average gains from cross-lingual transfer, and a 3.0% out-of-the-box performance boost on culturally appropriate questions. The publicly available benchmarks, translations, and code from this study support further research and development aimed at creating more inclusive and effective language technologies.
Maybe not. We identify and analyse errors in the popular Massive Multitask Language Understanding (MMLU) benchmark. Even though MMLU is widely adopted, our analysis demonstrates numerous ground truth errors that obscure the true capabilities of LLMs. For example, we find that 57% of the analysed questions in the Virology subset contain errors. To address this issue, we introduce a comprehensive framework for identifying dataset errors using a novel error annotation protocol. Then, we create MMLU-Redux, which is a subset of 5,700 manually re-annotated questions across all 57 MMLU subjects. We estimate that 6.49% of MMLU questions contain errors. Using MMLU-Redux, we demonstrate significant discrepancies with the model performance metrics that were originally reported. Our results strongly advocate for revising MMLU's error-ridden questions to enhance its future utility and reliability as a benchmark. https://huggingface.co/datasets/edinburgh-dawg/mmlu-redux-2.0.
This demo will present the Research Assistant (RA) tool developed to assist with six main types of research tasks defined as standardized instruction templates, instantiated with user input, applied finally as prompts to well-known--for their sophisticated natural language processing abilities--AI tools, such as ChatGPT (https://chat.openai.com/) and Gemini (https://gemini.google.com/app). The six research tasks addressed by RA are: creating FAIR research comparisons, ideating research topics, drafting grant applications, writing scientific blogs, aiding preliminary peer reviews, and formulating enhanced literature search queries. RA's reliance on generative AI tools like ChatGPT or Gemini means the same research task assistance can be offered in any scientific discipline. We demonstrate its versatility by sharing RA outputs in Computer Science, Virology, and Climate Science, where the output with the RA tool assistance mirrored that from a domain expert who performed the same research task.
In this paper, we champion the use of structured and semantic content representation of discourse-based scholarly communication, inspired by tools like Wikipedia infoboxes or structured Amazon product descriptions. These representations provide users with a concise overview, aiding scientists in navigating the dense academic landscape. Our novel automated approach leverages the robust text generation capabilities of LLMs to produce structured scholarly contribution summaries, offering both a practical solution and insights into LLMs' emergent abilities. For LLMs, the prime focus is on improving their general intelligence as conversational agents. We argue that these models can also be applied effectively in information extraction (IE), specifically in complex IE tasks within terse domains like Science. This paradigm shift replaces the traditional modular, pipelined machine learning approach with a simpler objective expressed through instructions. Our results show that finetuned FLAN-T5 with 1000x fewer parameters than the state-of-the-art GPT-davinci is competitive for the task.
Cancer progression and monotonic accumulation models were developed to discover dependencies in the irreversible acquisition of binary traits from cross-sectional data. They have been used in computational oncology and virology but also in widely different problems such as malaria progression. These methods have been applied to predict future states of the system, identify routes of feature acquisition, and improve patient stratification, and they hold promise for evolutionary-based treatments. New methods continue to be developed. But these methods have shortcomings, which are yet to be systematically critiqued, regarding key evolutionary assumptions and interpretations. After an overview of the available methods, we focus on why inferences might not be about the processes we intend. Using fitness landscapes, we highlight difficulties that arise from bulk sequencing and reciprocal sign epistasis, from conflating lines of descent, path of the maximum, and mutational profiles, and from ambiguous use of the idea of exclusivity. We examine how the previous concerns change when bulk sequencing is explicitly considered, and underline opportunities for addressing dependencies due to frequency-dependent selection. This review identifies major standing issues, and should encourage the use of these methods in other areas with a better alignment between entities and model assumptions.
The COVID-19 pandemic has changed the research agendas of most scientific communities, resulting in an overwhelming production of research articles in a variety of domains, including medicine, virology, epidemiology, economy, psychology, and so on. Several open-access corpora and literature hubs were established; among them, the COVID-19 Open Research Dataset (CORD-19) has systematically gathered scientific contributions for 2.5 years, by collecting and indexing over one million articles. Here, we present the CORD-19 Topic Visualizer (CORToViz), a method and associated visualization tool for inspecting the CORD-19 textual corpus of scientific abstracts. Our method is based upon a careful selection of up-to-date technologies (including large language models), resulting in an architecture for clustering articles along orthogonal dimensions and extraction techniques for temporal topic mining. Topic inspection is supported by an interactive dashboard, providing fast, one-click visualization of topic contents as word clouds and topic trends as time series, equipped with easy-to-drive statistical testing for analyzing the significance of topic emergence along arbitrarily selected time windows. The processes of data preparation and results visualization are completely general and virtually applicable to any corpus of textual documents - thus suited for effective adaptation to other contexts.
The COVID-19 pandemic has given rise to numerous articles from different scientific fields (epidemiology, virology, immunology, airflow physics...) without any effort to link these different insights. In this review, we aim to establish relationships between epidemiological data and the characteristics of the virus strain responsible for the epidemic wave concerned. We have carried out this study on the Wuhan, Alpha, Delta and Omicron strains allowing us to illustrate the evolution of the relationships we have highlighted according to these different viral strains. We addressed the following questions: 1) How can the mean infectious dose (one quantum, by definition in epidemiology) be measured and expressed as an amount of viral RNA molecules (in genome units, GU) or as a number of replicative viral particles (in plaque-forming units, PFU)? 2) How many infectious quanta are exhaled by an infected person per unit of time? 3) How many infectious quanta are exhaled, on average, integrated over the whole contagious period? 4) How do these quantities relate to the epidemic reproduction rate R as measured in epidemiology, and to the viral load, as measured by molecular biological methods? 5) How has the infectious dose evolved with the different strains of SARS-CoV-2? We make use of state-of-the-art modelling, reviewed and explained in the appendix of the article (Supplemental Information, SI), to answer these questions using data from the literature in both epidemiology and virology. We have considered the modification of these relationships according to the vaccination status of the population. We hope that this work will allow a better integration of data from different fields (virology, epidemiology, and immunology) to anticipate the evolution of the epidemic in the case of COVID-19, but also in respiratory pathologies transmissible in an airborne manner.
High order structures (cavities and cliques) of the gene network of influenza A virus reveal tight associations among viruses during evolution and are key signals that indicate viral cross-species infection and cause pandemics. As indicators for sensing the dynamic changes of viral genes, these higher order structures have been the focus of attention in the field of virology. However, the size of the viral gene network is usually huge, and searching these structures in the networks introduces unacceptable delay. To mitigate this issue, in this paper, we propose a simple-yet-effective model named HyperSearch based on deep learning to search cavities in a computable complex network for influenza virus genetics. Extensive experiments conducted on a public influenza virus dataset demonstrate the effectiveness of HyperSearch over other advanced deep-learning methods without any elaborated model crafting. Moreover, HyperSearch can finish the search works in minutes while 0-1 programming takes days. Since the proposed method is simple and easy to be transferred to other complex networks, HyperSearch has the potential to facilitate the monitoring of dynamic changes in viral genes and help humans keep up with the pace of virus mutations.
We present a rapid and stain-free quantitative viral plaque assay using lensfree holographic imaging and deep learning. This cost-effective, compact, and automated device significantly reduces the incubation time needed for traditional plaque assays while preserving their advantages over other virus quantification methods. This device captures ~0.32 Giga-pixel/hour phase information of the objects per test well, covering an area of ~30x30 mm^2, in a label-free manner, eliminating staining entirely. We demonstrated the success of this computational method using vesicular stomatitis virus (VSV), herpes simplex virus (HSV-1) and encephalomyocarditis virus (EMCV). Using a neural network, this stain-free device automatically detected the first cell lysing events due to the VSV viral replication as early as 5 hours after the incubation, and achieved >90% detection rate for the VSV plaque-forming units (PFUs) with 100% specificity in <20 hours, providing major time savings compared to the traditional plaque assays that take at least 48 hours. Similarly, this stain-free device reduced the needed incubation time by ~48 hours for HSV-1 and ~20 hours for EMCV, achieving >90% detection rate with 100% specificity. We also demonstrated that this data-driven plaque assay offers the capability of quantifying the infected area of the cell monolayer, performing automated counting and quantification of PFUs and virus-infected areas over a 10-fold larger dynamic range of virus concentration than standard viral plaque assays. This compact, low-cost, automated PFU quantification device can be broadly used in virology research, vaccine development, and clinical applications.
Raman spectroscopy provides a vibrational profile of the molecules and thus can be used to uniquely identify different kind of materials. This sort of fingerprinting molecules has thus led to widespread application of Raman spectrum in various fields like medical dignostics, forensics, mineralogy, bacteriology and virology etc. Despite the recent rise in Raman spectra data volume, there has not been any significant effort in developing generalized machine learning methods for Raman spectra analysis. We examine, experiment and evaluate existing methods and conjecture that neither current sequential models nor traditional machine learning models are satisfactorily sufficient to analyze Raman spectra. Both has their perks and pitfalls, therefore we attempt to mix the best of both worlds and propose a novel network architecture RamanNet. RamanNet is immune to invariance property in CNN and at the same time better than traditional machine learning models for the inclusion of sparse connectivity. Our experiments on 4 public datasets demonstrate superior performance over the much complex state-of-the-art methods and thus RamanNet has the potential to become the defacto standard in Raman spectra data analysis
A possible explanation based on first principles for the appearance of the Omicron variant of the SARS-CoV-2 virus is proposed involving coinfection with HIV. The gist is that the resultant HIV-induced immunocompromise allows SARS-CoV-2 greater latitude to explore its own mutational space. This latitude is not withoutr estriction, and a specific biophysical constraint is explored. Specifically, a nearly two- to five-fold discrepancy in backbone hydrogen bonding is observed between sub-molecules in Protein Data Bank files of the spike glycoprotein yielding two conclusions: mutagenic residues in the receptor-binding subunit of the spike much more frequently do not participate in backbone hydrogen bonds; and a technique of viral escape is therefore to remove such bonds within physico-chemical and functional constraints. Earlier work, from which the previous discussion is entirely independent, explains these phenomena from general principles of free energy, namely, the metastability of the glycoprotein. The conclusions therefore likely hold more generally as principles in virology.
Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based language model performance across a wide range of model scales -- from models with tens of millions of parameters up to a 280 billion parameter model called Gopher. These models are evaluated on 152 diverse tasks, achieving state-of-the-art performance across the majority. Gains from scale are largest in areas such as reading comprehension, fact-checking, and the identification of toxic language, but logical and mathematical reasoning see less benefit. We provide a holistic analysis of the training dataset and model's behaviour, covering the intersection of model scale with bias and toxicity. Finally we discuss the application of language models to AI safety and the mitigation of downstream harms.
This paper is devoted to the multidisciplinary modelling of a pandemic initiated by an aggressive virus, specifically the so-called \textit{SARS--CoV--2 Severe Acute Respiratory Syndrome, corona virus n.2}. The study is developed within a multiscale framework accounting for the interaction of different spatial scales, from the small scale of the virus itself and cells, to the large scale of individuals and further up to the collective behaviour of populations. An interdisciplinary vision is developed thanks to the contributions of epidemiologists, immunologists and economists as well as those of mathematical modellers. The first part of the contents is devoted to understanding the complex features of the system and to the design of a modelling rationale. The modelling approach is treated in the second part of the paper by showing both how the virus propagates into infected individuals, successfully and not successfully recovered, and also the spatial patterns, which are subsequently studied by kinetic and lattice models. The third part reports the contribution of research in the fields of virology, epidemiology, immune competition, and economy focused also on social behaviours. Finally, a critical analysis is proposed looking ahead to research perspectives.
Inclusion of high throughput technologies in the field of biology has generated massive amounts of biological data in the recent years. Now, transforming these huge volumes of data into knowledge is the primary challenge in computational biology. The traditional methods of data analysis have failed to carry out the task. Hence, researchers are turning to machine learning based approaches for the analysis of high-dimensional big data. In machine learning, once a model is trained with a training dataset, it can be applied on a testing dataset which is independent. In current times, deep learning algorithms further promote the application of machine learning in several field of biology including plant virology. Considering a significant progress in the application of machine learning in understanding plant virology, this review highlights an introductory note on machine learning and comprehensively discusses the trends and prospects of machine learning in diagnosis of viral diseases, understanding host-virus interplay and emergence of plant viruses.