Quantifying the Benefits of Imputation over QSAR Methods in Toxicology Data Modeling.

Imputation machine learning (ML) surpasses traditional approaches in modeling toxicity data. The method was tested on an open-source data set comprising approximately 2500 ingredients with limited in vitro and in vivo data obtained from the OECD QSAR Toolbox. By leveraging the relationships between different toxicological end points, imputation extracts more valuable information from each data point compared to well-established single end point methods, such as ML-based Quantitative Structure Activity Relationship (QSAR) approaches, providing a final improvement of up to around 0.2 in the coefficient of determination. A significant aspect of this methodology is its resilience to the inclusion of extraneous chemical or experimental data. While additional data typically introduces a considerable level of noise and can hinder performance of single end point QSAR modeling, imputation models remain unaffected. This implies a reduction in the need for laborious manual preprocessing tasks such as feature selection, thereby making data preparation for ML analysis more efficient. This successful test, conducted on open-source data, validates the efficacy of imputation approaches in toxicity data analysis. This work opens the way for applying similar methods to other types of sparse toxicological data matrices, and so we discuss the development of regulatory authority guidelines to accept imputation models, a key aspect for the wider adoption of these methods.

Potential for redistribution of post-moult habitat for Eudyptes penguins in the Southern Ocean under future climate conditions.

Anthropogenic climate change is resulting in spatial redistributions of many species. We assessed the potential effects of climate change on an abundant and widely distributed group of diving birds, Eudyptes penguins, which are the main avian consumers in the Southern Ocean in terms of biomass consumption. Despite their abundance, several of these species have undergone population declines over the past century, potentially due to changing oceanography and prey availability over the important winter months. We used light-based geolocation tracking data for 485 individuals deployed between 2006 and 2020 across 10 of the major breeding locations for five taxa of Eudyptes penguins. We used boosted regression tree modelling to quantify post-moult habitat preference for southern rockhopper (E. chrysocome), eastern rockhopper (E. filholi), northern rockhopper (E. moseleyi) and macaroni/royal (E. chrysolophus and E. schlegeli) penguins. We then modelled their redistribution under two climate change scenarios, representative concentration pathways RCP4.5 and RCP8.5 (for the end of the century, 2071-2100). As climate forcings differ regionally, we quantified redistribution in the Atlantic, Central Indian, East Indian, West Pacific and East Pacific regions. We found sea surface temperature and sea surface height to be the most important predictors of current habitat for these penguins; physical features that are changing rapidly in the Southern Ocean. Our results indicated that the less severe RCP4.5 would lead to less habitat loss than the more severe RCP8.5. The five taxa of penguin may experience a general poleward redistribution of their preferred habitat, but with contrasting effects in the (i) change in total area of preferred habitat under climate change (ii) according to geographic region and (iii) the species (macaroni/royal vs. rockhopper populations). Our results provide further understanding on the regional impacts and vulnerability of species to climate change.

Imputation of sensory properties using deep learning.

Predicting the sensory properties of compounds is challenging due to the subjective nature of the experimental measurements. This testing relies on a panel of human participants and is therefore also expensive and time-consuming. We describe the application of a state-of-the-art deep learning method, Alchemite™, to the imputation of sparse physicochemical and sensory data and compare the results with conventional quantitative structure-activity relationship methods and a multi-target graph convolutional neural network. The imputation model achieved a substantially higher accuracy of prediction, with improvements in R2 between 0.26 and 0.45 over the next best method for each sensory property. We also demonstrate that robust uncertainty estimates generated by the imputation model enable the most accurate predictions to be identified and that imputation also more accurately predicts activity cliffs, where small changes in compound structure result in large changes in sensory properties. In combination, these results demonstrate that the use of imputation, based on data from less expensive, early experiments, enables better selection of compounds for more costly studies, saving experimental time and resources.

Practical Applications of Deep Learning To Impute Heterogeneous Drug Discovery Data.

Contemporary deep learning approaches still struggle to bring a useful improvement in the field of drug discovery because of the challenges of sparse, noisy, and heterogeneous data that are typically encountered in this context. We use a state-of-the-art deep learning method, Alchemite, to impute data from drug discovery projects, including multitarget biochemical activities, phenotypic activities in cell-based assays, and a variety of absorption, distribution, metabolism, and excretion (ADME) endpoints. The resulting model gives excellent predictions for activity and ADME endpoints, offering an average increase in R2 of 0.22 versus quantitative structure-activity relationship methods. The model accuracy is robust to combining data across uncorrelated endpoints and projects with different chemical spaces, enabling a single model to be trained for all compounds and endpoints. We demonstrate improvements in accuracy on the latest chemistry and data when updating models with new data as an ongoing medicinal chemistry project progresses.

Accurate characterization of the IFITM locus using MiSeq and PacBio sequencing shows genetic variation in Galliformes.

BACKGROUND: Interferon inducible transmembrane (IFITM) proteins are effectors of the immune system widely characterized for their role in restricting infection by diverse enveloped and non-enveloped viruses. The chicken IFITM (chIFITM) genes are clustered on chromosome 5 and to date four genes have been annotated, namely chIFITM1, chIFITM3, chIFITM5 and chIFITM10. However, due to poor assembly of this locus in the Gallus Gallus v4 genome, accurate characterization has so far proven problematic. Recently, a new chicken reference genome assembly Gallus Gallus v5 was generated using Sanger, 454, Illumina and PacBio sequencing technologies identifying considerable differences in the chIFITM locus over the previous genome releases. METHODS: We re-sequenced the locus using both Illumina MiSeq and PacBio RS II sequencing technologies and we mapped RNA-seq data from the European Nucleotide Archive (ENA) to this finalized chIFITM locus. Using SureSelect probes capture probes designed to the finalized chIFITM locus, we sequenced the locus of a different chicken breed, namely a White Leghorn, and a turkey. RESULTS: We confirmed the Gallus Gallus v5 consensus except for two insertions of 5 and 1 base pair within the chIFITM3 and B4GALNT4 genes, respectively, and a single base pair deletion within the B4GALNT4 gene. The pull down revealed a single amino acid substitution of A63V in the CIL domain of IFITM2 compared to Red Jungle fowl and 13, 13 and 11 differences between IFITM1, 2 and 3 of chickens and turkeys, respectively. RNA-seq shows chIFITM2 and chIFITM3 expression in numerous tissue types of different chicken breeds and avian cell lines, while the expression of the putative chIFITM1 is limited to the testis, caecum and ileum tissues. CONCLUSIONS: Locus resequencing using these capture probes and RNA-seq based expression analysis will allow the further characterization of genetic diversity within Galliformes.

Modelling the nicotine pharmacokinetic profile for e-cigarettes using real time monitoring of consumers' physiological measurements and mouth level exposure.

Pharmacokinetic (PK) studies can provide essential information on abuse liability of nicotine and tobacco products but are intrusive and must be conducted in a clinical environment. The objective of the study was to explore whether changes in plasma nicotine levels following use of an e-cigarette can be predicted from real time monitoring of physiological parameters and mouth level exposure (MLE) to nicotine before, during, and after e-cigarette vaping, using wearable devices. Such an approach would allow an -effective pre-screening process, reducing the number of clinical studies, reducing the number of products to be tested and the number of blood draws required in a clinical PK study Establishing such a prediction model might facilitate the longitudinal collection of data on product use and nicotine expression among consumers using nicotine products in their normal environments, thereby reducing the need for intrusive clinical studies while generating PK data related to product use in the real world.An exploratory machine learning model was developed to predict changes in plasma nicotine levels following the use of an e-cigarette; from real time monitoring of physiological parameters and MLE to nicotine before, during, and after e-cigarette vaping. This preliminary study identified key parameters, such as heart rate (HR), heart rate variability (HRV), and physiological stress (PS) that may act as predictors for an individual's plasma nicotine response (PK curve). Relative to baseline measurements (per participant), HR showed a significant increase for nicotine containing e-liquids and was consistent across sessions (intra-participant). Imputing missing values and training the model on all data resulted in 57% improvement from the original'learning' data and achieved a median validation R2 of 0.70.The study is in its exploratory phase, with limitations including a small and non-diverse sample size and reliance on data from a single e-cigarette product. These findings necessitate further research for validation and to enhance the model's generalisability and applicability in real-world settings. This study serves as a foundational step towards developing non-intrusive PK models for nicotine product use.

Isolated pulmonary valve endocarditis in a patient without structural heart disease or a history of intravenous drug use.

We present a case of a febrile patient in his 70s who was found to have isolated native pulmonary valve vegetations on echocardiography, and Enterococcus faecalis on blood cultures. Of note, our patient had none of the typical risk factors associated with this rare form of endocarditis previously described in only a handful of case reports.

An Open Drug Discovery Competition: Experimental Validation of Predictive Models in a Series of Novel Antimalarials.

The Open Source Malaria (OSM) consortium is developing compounds that kill the human malaria parasite, Plasmodium falciparum, by targeting PfATP4, an essential ion pump on the parasite surface. The structure of PfATP4 has not been determined. Here, we describe a public competition created to develop a predictive model for the identification of PfATP4 inhibitors, thereby reducing project costs associated with the synthesis of inactive compounds. Competition participants could see all entries as they were submitted. In the final round, featuring private sector entrants specializing in machine learning methods, the best-performing models were used to predict novel inhibitors, of which several were synthesized and evaluated against the parasite. Half possessed biological activity, with one featuring a motif that the human chemists familiar with this series would have dismissed as "ill-advised". Since all data and participant interactions remain in the public domain, this research project "lives" and may be improved by others.

Use of Digital Technology among Adolescents Attending Schools in Bissau, Guinea-Bissau.

Digital technology plays an important role in achieving many of the Sustainable Development Goals. However, access is uneven, with 80% of those in high-income countries being online compared to 20% of those in the 47 least developed countries. This study aimed to describe and analyse adolescents' access to and usage of digital technology in Guinea-Bissau and its implications. In June 2017, a survey with a locally adapted Planet Youth questionnaire was implemented in the capital, Bissau, whereby classes in 16 secondary schools were surveyed on a variety of issues. In total, 2039 randomly selected students participated; the survey included ten questions specifically on the access to and use of digital technology. Half of the respondents had access to desktop/laptops, and one-third used mobile internet daily; about two-thirds had an experience of social media. Explanatory variables included educational institution, parental education, economic situation, and gender. Furthermore, students' experience of social media was significantly linked to bullying, anxiety, depression, smoking and alcohol consumption. Many adolescents in Bissau have no experience of using digital technology, including for schoolwork. Access improvements are necessary so that young Bissau-Guineans are not to be left behind in developing their capabilities and can benefit from proficiency in the use of digital technologies. At the same time, potential harmful usage of the media requires the implementation of preventive measures.

Ventilator-associated lung injury.

Mechanical ventilation is indispensable in support of patients with respiratory failure who are critically ill. However, use of this technique has adverse effects, including increased risk of pneumonia, impaired cardiac performance, and difficulties associated with sedation and paralysis. Moreover, application of pressure to the lung, whether positive or negative, can cause damage known as ventilator-associated lung injury (VALI). Despite difficulties in distinguishing the effects of mechanical ventilation from those of the underlying disorder, VALI greatly assists patients with the most severe form of lung injury, acute respiratory distress syndrome (ARDS). Moreover, modification of mechanical ventilation so that VALI is kept to a minimum improves survival of patients with ARDS. Here, we outline the effects of mechanical ventilation on injured lungs and explore the underlying mechanisms.

Effect of mechanical ventilation on cytokine response to intratracheal lipopolysaccharide.

BACKGROUND: Mechanical ventilation may cause lung injury through the excitation of an inflammatory response and the release of mediators, such as cytokines. The authors tested the hypothesis that intratracheal lipopolysaccharide amplifies the cytokine response to mechanical ventilation. METHODS: Rat lungs were intratracheally instilled with lipopolysaccharide followed by ex vivo mechanical ventilation for 2 h with low tidal volume of 7 ml/kg with 3 cm H2O positive end-expiratory pressure (PEEP), high tidal volume of 40 ml/kg with zero PEEP, medium tidal volume of 15 ml/kg with 3 cm H2O PEEP, or medium tidal volume and zero PEEP. RESULTS: In the absence of lipopolysaccharide, lung lavage concentrations of tumor necrosis factor and interleukin 1 beta but not macrophage inflammatory protein 2 were significantly higher in lungs ventilated at high tidal volume/zero PEEP than at low tidal volume. There was a marked increase in lavage tumor necrosis factor and macrophage inflammatory protein 2 concentrations in lungs ventilated at low tidal volume after exposure to intratracheal lipopolysaccharide at doses of 100 ng/ml or greater. However, in lungs ventilated at high tidal volume, this response to lipopolysaccharide was markedly reduced. In addition, the number of alveolar macrophages recovered in the lavage was significantly lower in lungs ventilated at high tidal volume. CONCLUSION: Ventilation strategy can modify lung cytokine responses to lipopolysaccharide, likely through an effect on the alveolar macrophage population.

Intercellular adhesion molecule-1 mediates cellular cross-talk between parenchymal and immune cells after lipopolysaccharide neutralization.

The mechanisms by which parenchymal cells interact with immune cells, particularly after removal of LPS, remain unknown. Lung explants from rats, mice deficient in the TNF gene, or human lung epithelial A549 cells were treated with LPS and washed, before naive alveolar macrophages, bone marrow monocytes, or PBMC, respectively, were added to the cultures. When the immune cells were cocultured with LPS-challenged explants or A549 cells, TNF production was greatly enhanced. This was not affected by neutralization of LPS with polymyxin B. The LPS-induced increase in the expression of ICAM-1 on A549 cells correlated with TNF production by PBMC. The cellular cross talk leading to the TNF response was blunted by an anti-ICAM-1 Ab and an ICAM-1 antisense oligonucleotide. In A549 cells, a persistent decrease in the concentration of intracellular cAMP was associated with colocalization of LPS into Toll-like receptor 4 and the Golgi apparatus, resulting in increased ICAM-1 expression. Inhibition of LPS internalization by cytochalasin D or treatment with dibutyryl cAMP attenuated ICAM-1 expression and TNF production by PBMC. In conclusion, lung epithelial cells are not bystanders, but possess memory of LPS through the expression of ICAM-1 that interacts with and activates leukocytes. This may provide an explanation for the failure of anti-LPS therapies in sepsis trials.