Finding the most potent compounds using active learning on molecular pairs.

Active learning allows algorithms to steer iterative experimentation to accelerate and de-risk molecular optimizations, but actively trained models might still exhibit poor performance during early project stages where the training data is limited and model exploitation might lead to analog identification with limited scaffold diversity. Here, we present ActiveDelta, an adaptive approach that leverages paired molecular representations to predict improvements from the current best training compound to prioritize further data acquisition. We apply the ActiveDelta concept to both graph-based deep (Chemprop) and tree-based (XGBoost) models during exploitative active learning for 99 Ki benchmarking datasets. We show that both ActiveDelta implementations excel at identifying more potent inhibitors compared to the standard exploitative active learning implementations of Chemprop, XGBoost, and Random Forest. The ActiveDelta approach is also able to identify more chemically diverse inhibitors in terms of their Murcko scaffolds. Finally, deep models such as Chemprop trained on data selected through ActiveDelta approaches can more accurately identify inhibitors in test data created through simulated time-splits. Overall, this study highlights the large potential for molecular pairing approaches to further improve popular active learning strategies in low data regimes by enabling faster and more accurate identification of more diverse molecular hits against critical drug targets.

Unraveling the molecular basis for effective regulation of integrin α5ß1 for enhanced therapeutic interventions.

Cell attachment to the extracellular matrix significantly impacts the integrity of tissues and human health. The integrin α5ß1 is a heterodimer of α5 and ß1 subunits and has been identified as a crucial modulator in several human carcinomas. Integrin α5ß1 significantly regulates cell proliferation, angiogenesis, inflammation, tumor metastasis, and invasion. This regulatory role of integrin α5ß1 in tumor metastasis makes it an appealing target for cancer therapy. The majority of the drugs targeting integrin α5ß1 are limited only to clinical trials. In our study, we have performed 94287 compounds screening to determine potential drugs against α5ß1 integrin. We have used ATN-161 as a reference and employed combined bioinformatic methodologies, including molecular modelling, virtual screening, MM-GBSA, cell-line cytotoxicity prediction, ADMET, Density Functional Theory (DFT), Non-covalent Interactions (NCI) and molecular simulation, to identify putative integrin α5ß1 inhibitors. We found Taxifolin, PD133053, and Acebutolol that possess inhibitory activity against α5ß1 integrin and could act as effective drug for the cancer treatment. Taxifolin, PD133053, and Acebutolol exhibited excellent binding to the druggable pocket of integrin α5ß1, and also maintained a unique binding mechanism with extra hydrophobic contacts at molecular level. Overall, our study gives new pharmacological candidates that may act as a potential drug against integrin α5ß1.

Remote Patient Monitoring and Machine Learning in Acute Exacerbations of Chronic Obstructive Pulmonary Disease: Dual Systematic Literature Review and Narrative Synthesis.

BACKGROUND: Acute exacerbations of chronic obstructive pulmonary disease (AECOPD) are associated with high mortality, morbidity, and poor quality of life and constitute a substantial burden to patients and health care systems. New approaches to prevent or reduce the severity of AECOPD are urgently needed. Internationally, this has prompted increased interest in the potential of remote patient monitoring (RPM) and digital medicine. RPM refers to the direct transmission of patient-reported outcomes, physiological, and functional data, including heart rate, weight, blood pressure, oxygen saturation, physical activity, and lung function (spirometry), directly to health care professionals through automation, web-based data entry, or phone-based data entry. Machine learning has the potential to enhance RPM in chronic obstructive pulmonary disease by increasing the accuracy and precision of AECOPD prediction systems. OBJECTIVE: This study aimed to conduct a dual systematic review. The first review focuses on randomized controlled trials where RPM was used as an intervention to treat or improve AECOPD. The second review examines studies that combined machine learning with RPM to predict AECOPD. We review the evidence and concepts behind RPM and machine learning and discuss the strengths, limitations, and clinical use of available systems. We have generated a list of recommendations needed to deliver patient and health care system benefits. METHODS: A comprehensive search strategy, encompassing the Scopus and Web of Science databases, was used to identify relevant studies. A total of 2 independent reviewers (HMGG and CM) conducted study selection, data extraction, and quality assessment, with discrepancies resolved through consensus. Data synthesis involved evidence assessment using a Critical Appraisal Skills Programme checklist and a narrative synthesis. Reporting followed PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. RESULTS: These narrative syntheses suggest that 57% (16/28) of the randomized controlled trials for RPM interventions fail to achieve the required level of evidence for better outcomes in AECOPD. However, the integration of machine learning into RPM demonstrates promise for increasing the predictive accuracy of AECOPD and, therefore, early intervention. CONCLUSIONS: This review suggests a transition toward the integration of machine learning into RPM for predicting AECOPD. We discuss particular RPM indices that have the potential to improve AECOPD prediction and highlight research gaps concerning patient factors and the maintained adoption of RPM. Furthermore, we emphasize the importance of a more comprehensive examination of patient and health care burdens associated with RPM, along with the development of practical solutions.

New Drinking Water Genome Catalog Identifies a Globally Distributed Bacterial Genus Adapted to Disinfected Drinking Water Systems.

Genome-resolved insights into the structure and function of the drinking water microbiome can advance the effective management of drinking water quality. To enable this, we constructed and curated thousands of metagenome-assembled and isolate genomes from drinking water distribution systems globally to develop a Drinking Water Genome Catalog (DWGC). The current DWGC disproportionately represents disinfected drinking water systems due to a paucity of metagenomes from nondisinfected systems. Using the DWGC, we identify core genera of the drinking water microbiome including a genus (UBA4765) within the order Rhizobiales that is frequently detected and highly abundant in disinfected drinking water systems. We demonstrate that this genus has been widely detected but incorrectly classified in previous amplicon sequencing-based investigations of the drinking water microbiome. Further, we show that a single genome variant (genomovar) within this genus is detected in 75% of drinking water systems included in this study. We propose a name for this uncultured bacterium as "Raskinella chloraquaticus" and describe the genus as "Raskinella" (endorsed by SeqCode). Metabolic annotation and modeling-based predictions indicate that this bacterium is capable of necrotrophic growth, is able to metabolize halogenated compounds, proliferates in a biofilm-based environment, and shows clear indications of disinfection-mediated selection.

Insights into electron transfer and bifurcation of the Synechocystis sp. PCC6803 hydrogenase reductase module.

The NAD+-reducing soluble [NiFe] hydrogenase (SH) is the key enzyme for production and consumption of molecular hydrogen (H2) in Synechocystis sp. PCC6803. In this study, we focused on the reductase module of the SynSH and investigated the structural and functional aspects of its subunits, particularly the so far elusive role of HoxE. We demonstrated the importance of HoxE for enzyme functionality, suggesting a regulatory role in maintaining enzyme activity and electron supply. Spectroscopic analysis confirmed that HoxE and HoxF each contain one [2Fe2S] cluster with an almost identical electronic structure. Structure predictions, alongside experimental evidence for ferredoxin interactions, revealed a remarkable similarity between SynSH and bifurcating hydrogenases, suggesting a related functional mechanism. Our study unveiled the subunit arrangement and cofactor composition essential for biological electron transfer. These findings enhance our understanding of NAD+-reducing [NiFe] hydrogenases in terms of their physiological function and structural requirements for biotechnologically relevant modifications.

Automated Identification of Postoperative Infections to Allow Prediction and Surveillance Based on Electronic Health Record Data: Scoping Review.

BACKGROUND: Postoperative infections remain a crucial challenge in health care, resulting in high morbidity, mortality, and costs. Accurate identification and labeling of patients with postoperative bacterial infections is crucial for developing prediction models, validating biomarkers, and implementing surveillance systems in clinical practice. OBJECTIVE: This scoping review aimed to explore methods for identifying patients with postoperative infections using electronic health record (EHR) data to go beyond the reference standard of manual chart review. METHODS: We performed a systematic search strategy across PubMed, Embase, Web of Science (Core Collection), the Cochrane Library, and Emcare (Ovid), targeting studies addressing the prediction and fully automated surveillance (ie, without manual check) of diverse bacterial infections in the postoperative setting. For prediction modeling studies, we assessed the labeling methods used, categorizing them as either manual or automated. We evaluated the different types of EHR data needed for the surveillance and labeling of postoperative infections, as well as the performance of fully automated surveillance systems compared with manual chart review. RESULTS: We identified 75 different methods and definitions used to identify patients with postoperative infections in studies published between 2003 and 2023. Manual labeling was the predominant method in prediction modeling research, 65% (49/75) of the identified methods use structured data, and 45% (34/75) use free text and clinical notes as one of their data sources. Fully automated surveillance systems should be used with caution because the reported positive predictive values are between 0.31 and 0.76. CONCLUSIONS: There is currently no evidence to support fully automated labeling and identification of patients with infections based solely on structured EHR data. Future research should focus on defining uniform definitions, as well as prioritizing the development of more scalable, automated methods for infection detection using structured EHR data.

Machine Learning and Vision: Advancing the Frontiers of Diabetic Cataract Management.

This comprehensive review explores the integration of machine learning (ML) in managing diabetic cataracts. It discusses the potential application of ML to identify novel methodologies for early detection, diagnosis, and therapeutic interventions. The review also addresses clinical translation challenges, including pharmacokinetics properties and ethical considerations. The approach toward cataractogenesis, therefore, has to be from a holistic viewpoint, bringing oxidative stress and metabolic disturbances to the top of importance. It outlines the important requirements, including continued research, diversified datasets, and uses interdisciplinary collaborations in making improvements in ML models and thereafter bridging the gap between computational promise and clinical implication, with the aim to help in the maximization of patient care in the management of diabetic cataract. A literature search through databases like PubMed and Scopus focusing on understanding of current innovations, challenges, and future directions in employing ML in diabetic cataract management was undertaken. This review has explored both recent and foundational studies in order to explain the development and gaps of current research with an aim to enhance outcomes of patient care by promoting future investigation. Key findings revealed a wide application of ML in ophthalmology including treatment identification, cataract detection and grading, and improving the surgical outcomes. However, this is accompanied by some obstacles, including risk of bias, concerns regarding artificial intelligence application as a diagnostic tool, and legal regulations. ML promises extraordinary developments in the treatment of diabetic cataracts through betterment in diagnosis, treatment, and patient care. With this, it is full of clinical translation and ethical challenges, yet there is recognition in general that continuous model refinement and interdisciplinary collaboration, along with the expansion of the two identified key elements in enhancing patient outcomes, are essential for this to continue.

Plastic particles and fluorescent brightener co-modify Chlorella pyrenoidosa photosynthesis and a machine learning approach predict algae growth.

Global release of plastics exerts various impacts on the ecological cycle, particularly on primary photosynthesis, while the impacts of plastic additives are unknown. As a carrier of fluorescent brightener, plastic particles co-modify Chlorella pyrenoidosa (C. pyrenoidosa) growth and its photosynthetic parameters. In general, adding to the oxidative damage induced by polystyrene, fluorescent brightener-doped polystyrene produces stronger visible light and the amount of negative charge is more likely to cause photodamage in C. pyrenoidosa leading to higher energy dissipation through conditioning than in the control group with a date of ETR (II) inhibition rate of 33 %, Fv/Fm inhibition rate of 8.3 % and Pm inhibition rate of 48.8 %. To elucidate the ecological effect of fluorescent brightener doping in plastic particles, a machine learning method is performed to establish a Gradient Boosting Machine model for predicting the impact of environmental factors on algal growth. Upon validation, the model achieved an average fitting degree of 88 %. Relative concentration of plastic particles and algae claimed the most significant factor by interpretability analysis of the machine learning. Additionally, both Gradient Boosting Machine prediction and experimental results indicate a matching result that plastic additives have an inhibitive effect on algal growth.

Data Analytics for Predicting Situational Developments in Smart Cities: Assessing User Perceptions.

The analysis of large volumes of data collected from heterogeneous sources is increasingly important for the development of megacities, the advancement of smart city technologies, and ensuring a high quality of life for citizens. This study aimed to develop algorithms for analyzing and interpreting social media data to assess citizens' opinions in real time and for verifying and examining data to analyze social tension and predict the development of situations during the implementation of urban projects. The developed algorithms were tested using an urban project in the field of transportation system development. The study's material included data from social networks, messenger channels and chats, video hosting platforms, blogs, microblogs, forums, and review sites. An interdisciplinary approach was utilized to analyze the data, employing tools such as Brand Analytics, TextAnalyst 2.32, GPT-3.5, GPT-4, GPT-4o, and Tableau. The results of the data analysis showed identical outcomes, indicating a neutral perception among users and the absence of social tension surrounding the project's implementation, allowing for the prediction of a calm development of the situation. Additionally, recommendations were developed to avert potential conflicts and eliminate sources of social tension for decision-making purposes.

Long-term changes of methane emissions from rice cultivation during 2000 - 2060 in China: Trends, driving factors, predictions and policy implications.

Regional budget assessments of methane (CH4) are critical for future climate and environmental management. CH4 emissions from rice cultivation (CH4-rice) constitute one of the most significant sources. However, previous studies mainly focus on historical emission estimates and lack consideration of future changes in CH4-rice under climate change or anthropogenic policy intervention, which hampers our understanding of long-term trends and the implementation of targeted emission reduction efforts. This study investigates the spatiotemporal variations of CH4-rice over the past two decades, using an integrated method to identify the major drivers and predict future emissions under climate change scenarios and policy perspectives. Results indicate that the CH4-rice emissions in China ranged between 6.21 and 6.57 Tg yr-1 over the past two decades, with a spatial distribution characterized by decreases in the south and increases in the north, associated with economic development, dietary shifts, technological advancements, and climate change. Factors such as the rate of straw added (RSA), fertilization, soil texture, temperature, and precipitation significantly influence CH4 emissions per unit rice production (CH4-urp), with RSA identified as the most significant tillage management factor, explaining 32 % of the variance. Lowering RSA to 8 % is beneficial for reducing CH4-urp. Scenario analysis indicates that under policies focusing on production or demand, CH4-rice is expected to increase by 0.3 % to 5.6 %, while adjusting RSA can reduce CH4-rice by 9.4 % to 10.0 %. Structural adjustments and regional cooperation serve as beneficial starting points for controlling and reducing CH4-rice in China, while optimizing industrial layouts contributes to regional development and CH4-rice control. Implementing policies related to maintaining field and crop yields can achieve a balance between rice supply and demand ahead of schedule. Dynamic adjustment of rice cultivation based on supply-demand balance can effectively reduce CH4-rice from excess rice production. By 2060, the reduction effect could reach 8.95 %-12.01 %. Introducing policy-driven tillage management measures as reference indicators facilitates the reduction of CH4-rice.

An App for Navigating Patient Transportation and Acute Stroke Care in Northwestern Ontario Using Machine Learning: Retrospective Study.

BACKGROUND: A coordinated care system helps provide timely access to treatment for suspected acute stroke. In Northwestern Ontario (NWO), Canada, communities are widespread with several hospitals offering various diagnostic equipment and services. Thus, resources are limited, and health care providers must often transfer patients with stroke to different hospital locations to ensure the most appropriate care access within recommended time frames. However, health care providers frequently situated temporarily (locum) in NWO or providing care remotely from other areas of Ontario may lack sufficient information and experience in the region to access care for a patient with a time-sensitive condition. Suboptimal decision-making may lead to multiple transfers before definitive stroke care is obtained, resulting in poor outcomes and additional health care system costs. OBJECTIVE: We aimed to develop a tool to inform and assist NWO health care providers in determining the best transfer options for patients with stroke to provide the most efficient care access. We aimed to develop an app using a comprehensive geomapping navigation and estimation system based on machine learning algorithms. This app uses key stroke-related timelines including the last time the patient was known to be well, patient location, treatment options, and imaging availability at different health care facilities. METHODS: Using historical data (2008-2020), an accurate prediction model using machine learning methods was developed and incorporated into a mobile app. These data contained parameters regarding air (Ornge) and land medical transport (3 services), which were preprocessed and cleaned. For cases in which Ornge air services and land ambulance medical transport were both involved in a patient transport process, data were merged and time intervals of the transport journey were determined. The data were distributed for training (35%), testing (35%), and validation (30%) of the prediction model. RESULTS: In total, 70,623 records were collected in the data set from Ornge and land medical transport services to develop a prediction model. Various learning models were analyzed; all learning models perform better than the simple average of all points in predicting output variables. The decision tree model provided more accurate results than the other models. The decision tree model performed remarkably well, with the values from testing, validation, and the model within a close range. This model was used to develop the "NWO Navigate Stroke" system. The system provides accurate results and demonstrates that a mobile app can be a significant tool for health care providers navigating stroke care in NWO, potentially impacting patient care and outcomes. CONCLUSIONS: The NWO Navigate Stroke system uses a data-driven, reliable, accurate prediction model while considering all variations and is simultaneously linked to all required acute stroke management pathways and tools. It was tested using historical data, and the next step will to involve usability testing with end users.

Beyond Step Count: Are We Ready to Use Digital Phenotyping to Make Actionable Individual Predictions in Psychiatry?

Some models for mental disorders or behaviors (eg, suicide) have been successfully developed, allowing predictions at the population level. However, current demographic and clinical variables are neither sensitive nor specific enough for making individual actionable clinical predictions. A major hope of the "Decade of the Brain" was that biological measures (biomarkers) would solve these issues and lead to precision psychiatry. However, as models are based on sociodemographic and clinical data, even when these biomarkers differ significantly between groups of patients and control participants, they are still neither sensitive nor specific enough to be applied to individual patients. Technological advances over the past decade offer a promising approach based on new measures that may be essential for understanding mental disorders and predicting their trajectories. Several new tools allow us to continuously monitor objective behavioral measures (eg, hours of sleep) and densely sample subjective measures (eg, mood). The promise of this approach, referred to as digital phenotyping, was recognized almost a decade ago, with its potential impact on psychiatry being compared to the impact of the microscope on biological sciences. However, despite the intuitive belief that collecting densely sampled data (big data) improves clinical outcomes, recent clinical trials have not shown that incorporating digital phenotyping improves clinical outcomes. This viewpoint provides a stepwise development and implementation approach, similar to the one that has been successful in the prediction and prevention of cardiovascular disease, to achieve clinically actionable predictions in psychiatry.

Unleashing the potential of cell painting assays for compound activities and hazards prediction.

The cell painting (CP) assay has emerged as a potent imaging-based high-throughput phenotypic profiling (HTPP) tool that provides comprehensive input data for in silico prediction of compound activities and potential hazards in drug discovery and toxicology. CP enables the rapid, multiplexed investigation of various molecular mechanisms for thousands of compounds at the single-cell level. The resulting large volumes of image data provide great opportunities but also pose challenges to image and data analysis routines as well as property prediction models. This review addresses the integration of CP-based phenotypic data together with or in substitute of structural information from compounds into machine (ML) and deep learning (DL) models to predict compound activities for various human-relevant disease endpoints and to identify the underlying modes-of-action (MoA) while avoiding unnecessary animal testing. The successful application of CP in combination with powerful ML/DL models promises further advances in understanding compound responses of cells guiding therapeutic development and risk assessment. Therefore, this review highlights the importance of unlocking the potential of CP assays when combined with molecular fingerprints for compound evaluation and discusses the current challenges that are associated with this approach.

CT-based multimodal deep learning for non-invasive overall survival prediction in advanced hepatocellular carcinoma patients treated with immunotherapy.

OBJECTIVES: To develop a deep learning model combining CT scans and clinical information to predict overall survival in advanced hepatocellular carcinoma (HCC). METHODS: This retrospective study included immunotherapy-treated advanced HCC patients from 52 multi-national in-house centers between 2018 and 2022. A multi-modal prognostic model using baseline and the first follow-up CT images and 7 clinical variables was proposed. A convolutional-recurrent neural network (CRNN) was developed to extract spatial-temporal information from automatically selected representative 2D CT slices to provide a radiological score, then fused with a Cox-based clinical score to provide the survival risk. The model's effectiveness was assessed using a time-dependent area under the receiver operating curve (AUC), and risk group stratification using the log-rank test. Prognostic performances of multi-modal inputs were compared to models of missing modality, and the size-based RECIST criteria. RESULTS: Two-hundred seven patients (mean age, 61 years ± 12 [SD], 180 men) were included. The multi-modal CRNN model reached the AUC of 0.777 and 0.704 of 1-year overall survival predictions in the validation and test sets. The model achieved significant risk stratification in validation (hazard ratio [HR] = 3.330, p = 0.008), and test sets (HR = 2.024, p = 0.047) based on the median risk score of the training set. Models with missing modalities (the single-modal imaging-based model and the model incorporating only baseline scans) can still achieve favorable risk stratification performance (all p < 0.05, except for one, p = 0.053). Moreover, results proved the superiority of the deep learning-based model to the RECIST criteria. CONCLUSION: Deep learning analysis of CT scans and clinical data can offer significant prognostic insights for patients with advanced HCC. CRITICAL RELEVANCE STATEMENT: The established model can help monitor patients' disease statuses and identify those with poor prognosis at the time of first follow-up, helping clinicians make informed treatment decisions, as well as early and timely interventions. KEY POINTS: An AI-based prognostic model was developed for advanced HCC using multi-national patients. The model extracts spatial-temporal information from CT scans and integrates it with clinical variables to prognosticate. The model demonstrated superior prognostic ability compared to the conventional size-based RECIST method.

A quantitative model of temperature-dependent diapause progression.

Winter diapause in insects is commonly terminated through cold exposure, which, like vernalization in plants, prevents development before spring arrives. Currently, quantitative understanding of the temperature dependence of diapause termination is limited, likely because diapause phenotypes are generally cryptic to human eyes. We introduce a methodology to tackle this challenge. By consecutively moving butterfly pupae of the species Pieris napi from several different cold conditions to 20 °C, we show that diapause termination proceeds as a temperature-dependent rate process, with maximal rates at relatively cold temperatures and low rates at warm and extremely cold temperatures. Further, we show that the resulting thermal reaction norm can predict P. napi diapause termination timing under variable temperatures. Last, we show that once diapause is terminated in P. napi, subsequent development follows a typical thermal performance curve, with a maximal development rate at around 31 °C and a minimum at around 2 °C. The sequence of these thermally distinct processes (diapause termination and postdiapause development) facilitates synchronous spring eclosion in nature; cold microclimates where diapause progresses quickly do not promote fast postdiapause development, allowing individuals in warmer winter microclimates to catch up, and vice versa. The unveiling of diapause termination as one temperature-dependent rate process among others promotes a parsimonious, quantitative, and predictive model, wherein winter diapause functions both as an adaptation against premature development during fall and winter and for synchrony in spring.

Machine Learning versus Cox Models for Predicting Overall Survival in Patients with Osteosarcoma: A Retrospective Analysis of the EURAMOS-1 Clinical Trial Data.

Since the mid-1980s, there has been little progress in improving survival of patients diagnosed with osteosarcoma. Survival prediction models play a key role in clinical decision-making, guiding healthcare professionals in tailoring treatment strategies based on individual patient risks. The increasing interest of the medical community in using machine learning (ML) for predicting survival has sparked an ongoing debate on the value of ML techniques versus more traditional statistical modelling (SM) approaches. This study investigates the use of SM versus ML methods in predicting overall survival (OS) using osteosarcoma data from the EURAMOS-1 clinical trial (NCT00134030). The well-established Cox proportional hazard model is compared to the extended Cox model that includes time-varying effects, and to the ML methods random survival forests and survival neural networks. The impact of eight variables on OS predictions is explored. Results are compared on different model performance metrics, variable importance, and patient-specific predictions. The article provides comprehensive insights to aid healthcare researchers in evaluating diverse survival prediction models for low-dimensional clinical data.

Actionable Predictions of Human Pharmacokinetics at the Drug Design Stage.

We present a novel computational approach for predicting human pharmacokinetics (PK) that addresses the challenges of early stage drug design. Our study introduces and describes a large-scale data set of 11 clinical PK end points, encompassing over 2700 unique chemical structures to train machine learning models. To that end multiple advanced training strategies are compared, including the integration of in vitro data and a novel self-supervised pretraining task. In addition to the predictions, our final model provides meaningful epistemic uncertainties for every data point. This allows us to successfully identify regions of exceptional predictive performance, with an absolute average fold error (AAFE/geometric mean fold error) of less than 2.5 across multiple end points. Together, these advancements represent a significant leap toward actionable PK predictions, which can be utilized early on in the drug design process to expedite development and reduce reliance on nonclinical studies.

Multifaceted computational profiling of thymol and geraniol against the human proteome for bio-repellent alternatives: Toxicity predictions, degradation analysis, and quantum mechanical approaches.

With growing interest in natural compounds as alternative mosquito repellents, assessing the toxicity and structure of potential repellent naturals like thymol (monoterpene phenol) and geraniol (monoterpene alcohol) is vital for understanding their stability and human impact. This study aimed to determine the structural, toxicity, and binding profiles of thymol and geraniol using computational predictions, xTB metadynamics, quantum mechanics, and principal component analysis. Toxicity studies using Protox-II, T.E.S.T, and SwissADME indicated that thymol and geraniol belong to toxicity class 4 and 5, respectively, with low toxicity predictions in other endpoints. Overall pharmacokinetic profile was generated via pkCSM. Off-target predictions via SwissTarget Predictions, LigTMap, Pharmapper, and SuperPred showed that these molecules can bind to 614 human proteins. The degradation of thymol and geraniol were performed using xTB metadynamics and the outcomes showed that the degradants for both compounds were stable and had lower toxicity profile. Nine tautomers were generated via quantum mechanics for thymol and four for geraniol, with RMSD ranging from 3.8 to 6.3 Å for thymol and 3.6 to 4 Å for geraniol after superimpositions. DFT studies found that HOMO-LUMO values and electronegativity parameters of thymol and geraniol did not differ significantly from their isomers. Binding affinity studies against 614 proteins, analysed via PCA and violin plots, highlighted the probable range of binding. These multifaceted in-silico findings corroborate the stability and potential utility of thymol and geraniol as safer alternatives in repellent applications.

Predicting Long COVID in the National COVID Cohort Collaborative Using Super Learner: Cohort Study.

BACKGROUND: Postacute sequelae of COVID-19 (PASC), also known as long COVID, is a broad grouping of a range of long-term symptoms following acute COVID-19. These symptoms can occur across a range of biological systems, leading to challenges in determining risk factors for PASC and the causal etiology of this disorder. An understanding of characteristics that are predictive of future PASC is valuable, as this can inform the identification of high-risk individuals and future preventative efforts. However, current knowledge regarding PASC risk factors is limited. OBJECTIVE: Using a sample of 55,257 patients (at a ratio of 1 patient with PASC to 4 matched controls) from the National COVID Cohort Collaborative, as part of the National Institutes of Health Long COVID Computational Challenge, we sought to predict individual risk of PASC diagnosis from a curated set of clinically informed covariates. The National COVID Cohort Collaborative includes electronic health records for more than 22 million patients from 84 sites across the United States. METHODS: We predicted individual PASC status, given covariate information, using Super Learner (an ensemble machine learning algorithm also known as stacking) to learn the optimal combination of gradient boosting and random forest algorithms to maximize the area under the receiver operator curve. We evaluated variable importance (Shapley values) based on 3 levels: individual features, temporal windows, and clinical domains. We externally validated these findings using a holdout set of randomly selected study sites. RESULTS: We were able to predict individual PASC diagnoses accurately (area under the curve 0.874). The individual features of the length of observation period, number of health care interactions during acute COVID-19, and viral lower respiratory infection were the most predictive of subsequent PASC diagnosis. Temporally, we found that baseline characteristics were the most predictive of future PASC diagnosis, compared with characteristics immediately before, during, or after acute COVID-19. We found that the clinical domains of health care use, demographics or anthropometry, and respiratory factors were the most predictive of PASC diagnosis. CONCLUSIONS: The methods outlined here provide an open-source, applied example of using Super Learner to predict PASC status using electronic health record data, which can be replicated across a variety of settings. Across individual predictors and clinical domains, we consistently found that factors related to health care use were the strongest predictors of PASC diagnosis. This indicates that any observational studies using PASC diagnosis as a primary outcome must rigorously account for heterogeneous health care use. Our temporal findings support the hypothesis that clinicians may be able to accurately assess the risk of PASC in patients before acute COVID-19 diagnosis, which could improve early interventions and preventive care. Our findings also highlight the importance of respiratory characteristics in PASC risk assessment. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1101/2023.07.27.23293272.

Climate change accelerates water and biogeochemical cycles in temperate agricultural catchments.

Climate change is expected to significantly deteriorate water quality in heavily managed agricultural landscapes, however, the exact mechanisms of these impacts are unknown. In this study we adopted a modelling approach to predict the multiple effects of climate change on hydrological and biogeochemical responses for dominant solutes and particulates in two agriculture-dominated temperate headwater catchments. We used climatic projections from three climatic models to simulate future flows, mobilisation and delivery of solutes and particulates. This allowed an examination of potential drivers by identifying changes in flow pathway distribution and key environmental variables. We found that future climate conditions will lead to a general increase in stream discharge as well as higher concentrations and loads of solutes and particulates. However, unlike previous studies, we observed a higher magnitude of change during the warmer part of the year. These changes will reduce the relative importance of winter flows on solute and particulate transport, leading to both higher and more evenly distributed concentrations and loads between seasons. We linked these changes to the higher importance of superficial flow pathways of tile and surface runoff driven by more rapid transition from extremely wet to dry conditions. Overall, the observed increase in solute and particulate mobilisation and delivery will lead to widespread water quality deterioration. Mitigation of this deterioration would require adequate management efforts to address the direct and indirect negative effects on stream biota and water scarcity.