Cell Painting-based bioactivity prediction boosts high-throughput screening hit-rates and compound diversity.

Identifying active compounds for a target is a time- and resource-intensive task in early drug discovery. Accurate bioactivity prediction using morphological profiles could streamline the process, enabling smaller, more focused compound screens. We investigate the potential of deep learning on unrefined single-concentration activity readouts and Cell Painting data, to predict compound activity across 140 diverse assays. We observe an average ROC-AUC of 0.744 ± 0.108 with 62% of assays achieving ≥0.7, 30% ≥0.8, and 7% ≥0.9. In many cases, the high prediction performance can be achieved using only brightfield images instead of multichannel fluorescence images. A comprehensive analysis shows that Cell Painting-based bioactivity prediction is robust across assay types, technologies, and target classes, with cell-based assays and kinase targets being particularly well-suited for prediction. Experimental validation confirms the enrichment of active compounds. Our findings indicate that models trained on Cell Painting data, combined with a small set of single-concentration data points, can reliably predict the activity of a compound library across diverse targets and assays while maintaining high hit rates and scaffold diversity. This approach has the potential to reduce the size of screening campaigns, saving time and resources, and enabling primary screening with more complex assays.

Environmental assessment of diets: overview and guidance on indicator choice.

Comprehensive but interpretable assessment of the environmental performance of diets involves choosing a set of appropriate indicators. Current knowledge and data gaps on the origin of dietary foodstuffs restrict use of indicators relying on site-specific information. This Personal View summarises commonly used indicators for assessing the environmental performance of diets, briefly outlines their benefits and drawbacks, and provides recommendations on indicator choices for actors across multiple fields involved in activities that include the environmental assessment of diets. We then provide recommendations on indicator choices for actors across multiple fields involved in activities that use environmental assessments, such as health and nutrition experts, policy makers, decision makers, and private-sector and public-sector sustainability officers. We recommend that environmental assessment of diets should include indicators for at least the five following areas: climate change, biosphere integrity, blue water consumption, novel entities, and impacts on natural resources (especially wild fish stocks), to capture important environmental trade-offs. If more indicators can be handled in the assessment, indicators to capture impacts related to land use quantity and quality and green water consumption should be used. For ambitious assessments, indicators related to biogeochemical flows, stratospheric ozone depletion, and energy use can be added.

Polymeric nanoparticle gel for intracellular mRNA delivery and immunological reprogramming of tumors.

Immuno-oncology therapies have been of great interest with the goal of inducing sustained tumor regression, but clinical results have demonstrated the need for improved and widely applicable methods. An antigen-free method of cancer immunotherapy can stimulate the immune system to recruit lymphocytes and produce immunostimulatory factors without prior knowledge of neoantigens, while local delivery reduces the risk of systemic toxicity. To improve the interactions between tumor cells and cytotoxic lymphocytes, a gene delivery nanoparticle platform was engineered to reprogram the tumor microenvironment (TME) in situ to be more immunostimulatory by inducing tumor-associated antigen-presenting cells (tAPCs) to activate cytotoxic lymphocytes against the tumor. Biodegradable, lipophilic poly (beta-amino ester) (PBAE) nanoparticles were synthesized and used to co-deliver mRNA constructs encoding a signal 2 co-stimulatory molecule (4-1BBL) and a signal 3 immuno-stimulatory cytokine (IL-12), along with a nucleic acid-based immunomodulatory adjuvant. Nanoparticles are combined with a thermoresponsive block copolymer for gelation at the injection site for local NP retention at the tumor. The reprogramming nanoparticle gel synergizes with immune checkpoint blockade (ICB) to induce tumor regression and clearance in addition to resistance to tumor rechallenge at a distant site. In vitro and in vivo studies reveal increases in immunostimulatory cytokine production and recruitment of immune cells as a result of the nanoparticles. Intratumoral injection of nanoparticles encapsulating mRNA encoding immunostimulatory agents and adjuvants via an injectable thermoresponsive gel has great translational potential as an immuno-oncology therapy that can be accessible to a wide range of patients.

Biodegradable lipophilic polymeric mRNA nanoparticles for ligand-free targeting of splenic dendritic cells for cancer vaccination.

Nanoparticle (NP)-based mRNA cancer vaccines hold great promise to realize personalized cancer treatments. To advance this technology requires delivery formulations for efficient intracellular delivery to antigen-presenting cells. We developed a class of bioreducible lipophilic poly(beta-amino ester) nanocarriers with quadpolymer architecture. The platform is agnostic to the mRNA sequence, with one-step self-assembly allowing for delivery of multiple antigen-encoding mRNAs as well as codelivery of nucleic acid-based adjuvants. We examined structure-function relationships for NP-mediated mRNA delivery to dendritic cells (DCs) and identified that a lipid subunit of the polymer structure was critical. Following intravenous administration, the engineered NP design facilitated targeted delivery to the spleen and preferential transfection of DCs without the need for surface functionalization with targeting ligands. Treatment with engineered NPs codelivering antigen-encoding mRNA and toll-like receptor agonist adjuvants led to robust antigen-specific CD8+ T cell responses, resulting in efficient antitumor therapy in in vivo models of murine melanoma and colon adenocarcinoma.

Detecting driver fatigue using heart rate variability: A systematic review.

Driver fatigue detection systems have potential to improve road safety by preventing crashes and saving lives. Conventional driver monitoring systems based on driving performance and facial features may be challenged by the application of automated driving systems. This limitation could potentially be overcome by monitoring systems based on physiological measurements. Heart rate variability (HRV) is a physiological marker of interest for detecting driver fatigue that can be measured during real life driving. This systematic review investigates the relationship between HRV measures and driver fatigue, as well as the performance of HRV based fatigue detection systems. With the applied eligibility criteria, 18 articles were identified in this review. Inconsistent results can be found within the studies that investigated differences of HRV measures between alert and fatigued drivers. For studies that developed HRV based fatigue detection systems, the detection performance showed a large variation, where the detection accuracy ranged from 44% to 100%. The inconsistency and variation of the results can be caused by differences in several key aspects in the study designs. Progress in this field is needed to determine the relationship between HRV and different fatigue causal factors and its connection to driver performance. To be deployed, HRV-based fatigue detection systems need to be thoroughly tested in real life conditions with good coverage of relevant driving scenarios and a sufficient number of participants.

Smaller farm size and ruminant animals are associated with increased supply of non-provisioning ecosystem services.

To balance trade-offs between livestock's negative environmental impacts and their positive contributions (e.g. maintaining semi-natural grasslands, varied agricultural landscapes and crop rotations), a better understanding is needed of how the supply of ecosystem services differs across farms. We analysed a suite of indicators for non-provisioning ecosystem services on a large subset of Swedish farms (71% of farms, covering 82% of agricultural land) and related these to farm type, farm size and livestock density. The analysed indicators exhibited clear geographical patterns with hotspots especially in less productive regions. Controlling for this spatial variation we still found that small-scale and ruminant farms were associated with more varied landscapes, small-scale habitats, semi-natural grasslands and better crop sequences compared to nearby farms specialised in crop production, while farms specialising in monogastric livestock were associated with less varied landscapes and inferior crop sequences. Results for cultural ecosystem services indicated that farms with more semi-natural grassland were associated with more visitors and more likely located within designated recreation or nature conservation areas.

Examining the Environmental Impacts of the Dairy and Baby Food Industries: Are First-Food Systems a Crucial Missing Part of the Healthy and Sustainable Food Systems Agenda Now Underway?

Food systems are increasingly being understood as driving various health and ecological crises and their transformation is recognised as a key opportunity for planetary health. First-food systems represent an underexplored aspect of this transformation. Despite breastfeeding representing the optimal source of infant nutrition, use of commercial milk formula (CMF) is high and growing rapidly. In this review, we examine the impact of CMF use on planetary health, considering in particular its effects on climate change, water use and pollution and the consequences of these effects for human health. Milk is the main ingredient in the production of CMF, making the role of the dairy sector a key area of attention. We find that CMF use has twice the carbon footprint of breastfeeding, while 1 kg of CMF has a blue water footprint of 699 L; CMF has a significant and harmful environmental impact. Facilitation and protection of breastfeeding represents a key part of developing sustainable first-food systems and has huge potential benefits for maternal and child health.

Photocrosslinked Bioreducible Polymeric Nanoparticles for Enhanced Systemic siRNA Delivery as Cancer Therapy.

Clinical translation of polymer-based nanocarriers for systemic delivery of RNA has been limited due to poor colloidal stability in the blood stream and intracellular delivery of the RNA to the cytosol. To address these limitations, this study reports a new strategy incorporating photocrosslinking of bioreducible nanoparticles for improved stability extracellularly and rapid release of RNA intracellularly. In this design, the polymeric nanocarriers contain ester bonds for hydrolytic degradation and disulfide bonds for environmentally triggered small interfering RNA (siRNA) release in the cytosol. These photocrosslinked bioreducible nanoparticles (XbNPs) have a shielded surface charge, reduced adsorption of serum proteins, and enable superior siRNA-mediated knockdown in both glioma and melanoma cells in high-serum conditions compared to non-crosslinked formulations. Mechanistically, XbNPs promote cellular uptake and the presence of secondary and tertiary amines enables efficient endosomal escape. Following systemic administration, XbNPs facilitate targeting of cancer cells and tissue-mediated siRNA delivery beyond the liver, unlike conventional nanoparticle-based delivery. These attributes of XbNPs facilitate robust siRNA-mediated knockdown in vivo in melanoma tumors colonized in the lungs following systemic administration. Thus, biodegradable polymeric nanoparticles, via photocrosslinking, demonstrate extended colloidal stability and efficient delivery of RNA therapeutics under physiological conditions, and thereby potentially advance systemic delivery technologies for nucleic acid-based therapeutics.

Nanoparticle designs for delivery of nucleic acid therapeutics as brain cancer therapies.

Glioblastoma (GBM) is an aggressive central nervous system cancer with a dismal prognosis. The standard of care involves surgical resection followed by radiotherapy and chemotherapy, but five-year survival is only 5.6% despite these measures. Novel therapeutic approaches, such as immunotherapies, targeted therapies, and gene therapies, have been explored to attempt to extend survival for patients. Nanoparticles have been receiving increasing attention as promising vehicles for non-viral nucleic acid delivery in the context of GBM, though delivery is often limited by low blood-brain barrier permeability, particle instability, and low trafficking to target brain structures and cells. In this review, nanoparticle design considerations and new advances to overcome nucleic acid delivery challenges to treat brain cancer are summarized and discussed.

Deep-learning models for lipid nanoparticle-based drug delivery.

Background: Early prediction of time-lapse microscopy experiments enables intelligent data management and decision-making. Aim: Using time-lapse data of HepG2 cells exposed to lipid nanoparticles loaded with mRNA for expression of GFP, the authors hypothesized that it is possible to predict in advance whether a cell will express GFP. Methods: The first modeling approach used a convolutional neural network extracting per-cell features at early time points. These features were then combined and explored using either a long short-term memory network (approach 2) or time series feature extraction and gradient boosting machines (approach 3). Results: Accounting for the temporal dynamics significantly improved performance. Conclusion: The results highlight the benefit of accounting for temporal dynamics when studying drug delivery using high-content imaging.

Effects of partially automated driving on the development of driver sleepiness.

The objective of this study was to compare the development of sleepiness during manual driving versus level 2 partially automated driving, when driving on a motorway in Sweden. The hypothesis was that partially automated driving will lead to higher levels of fatigue due to underload. Eighty-nine drivers were included in the study using a 2 × 2 design with the conditions manual versus partially automated driving and daytime (full sleep) versus night-time (sleep deprived). The results showed that night-time driving led to markedly increased levels of sleepiness in terms of subjective sleepiness ratings, blink durations, PERCLOS, pupil diameter and heart rate. Partially automated driving led to slightly higher subjective sleepiness ratings, longer blink durations, decreased pupil diameter, slower heart rate, and higher EEG alpha and theta activity. However, elevated levels of sleepiness mainly arose from the night-time drives when the sleep pressure was high. During daytime, when the drivers were alert, partially automated driving had little or no detrimental effects on driver fatigue. Whether the negative effects of increased sleepiness during partially automated driving can be compensated by the positive effects of lateral and longitudinal driving support needs to be investigated in further studies.

Halting European Union soybean feed imports favours ruminants over pigs and poultry.

The European Union (EU) livestock sector relies on imported soybean as a feed source, but feeding soybean to animals leads to a loss of macronutrients compared to direct human consumption, and soybean production is associated with deforestation. Here we show that 75-82% of current EU animal fat and protein production could be sustained without soybean imports while avoiding increased use of cropland for feed production within the EU. Reduced soybean feed exports, mainly from South America, would free up 11-14 million hectares outside the EU, but indirect land-use changes would increase demand for palm oil produced in southeast Asia. Avoiding imported soybean feeds would result in reduced EU pork and poultry production; increased plant-based food consumption would be required to maintain the supply of essential nutrients for human diets. Optimizing livestock production to overcome dependency on imported soybean feed can reduce cropland demand in deforestation-prone areas while supporting the nutritional requirements of EU diets-but will require progressive policies targeting all aspects of the food system.

Deep Learning With Conformal Prediction for Hierarchical Analysis of Large-Scale Whole-Slide Tissue Images.

With the increasing amount of image data collected from biomedical experiments there is an urgent need for smarter and more effective analysis methods. Many scientific questions require analysis of image sub-regions related to some specific biology. Finding such regions of interest (ROIs) at low resolution and limiting the data subjected to final quantification at full resolution can reduce computational requirements and save time. In this paper we propose a three-step pipeline: First, bounding boxes for ROIs are located at low resolution. Next, ROIs are subjected to semantic segmentation into sub-regions at mid-resolution. We also estimate the confidence of the segmented sub-regions. Finally, quantitative measurements are extracted at full resolution. We use deep learning for the first two steps in the pipeline and conformal prediction for confidence assessment. We show that limiting final quantitative analysis to sub-regions with full confidence reduces noise and increases separability of observed biological effects.

Poly(beta-amino ester)s as gene delivery vehicles: challenges and opportunities.

INTRODUCTION: Gene delivery technologies are being developed for an increasing number of biomedical applications, with delivery vehicles including viruses and non-viral materials. Among biomaterials used for non-viral gene delivery, poly(beta-amino ester)s (PBAEs), a class of synthetic, biodegradable polymers, have risen as a leading gene delivery vehicle that has been used for multiple applications in vitro and in vivo. AREAS COVERED: This review summarizes the key properties of PBAEs and their development, including a discussion of the advantages and disadvantages of PBAEs for gene delivery applications. The use of PBAEs to improve the properties of other drug delivery vehicles is also summarized. EXPERT OPINION: PBAEs are designed to have multiple characteristics that are ideal for gene delivery, including their reversible positive charge, which promotes binding to nucleic acids as well as imparting high buffering capacity, and their rapid degradability under mild conditions. Simultaneously, some of their properties also lead to nanoparticle instability and low transfection efficiency in physiological environments. The ease with which PBAEs can be chemically modified as well as non-covalently blended with other materials, however, allows them to be customized specifically to overcome delivery barriers for varied applications.

Cryptic diversity and species boundaries within the Paragalago zanzibaricus species complex.

The recently described genus Paragalago is a complex of several nocturnal and morphologically cryptic species distributed in the forests of eastern Africa. Species diversity within this genus has been mainly described using species-specific differences in their loud calls. However, molecular data are still lacking for this group and species boundaries remain unclear. In this study, we explore species diversity within the zanzibaricus-complex using a combination of mitochondrial and nuclear data and comparing multiple species delimitation methods. Our results consistently support the existence of three independent lineages, P. cocos, P. zanzibaricus, and P. granti, confirming previous hypotheses based on vocal data. We conclude that these three lineages represent valid cryptic species and we hypothesize that speciation within this complex was characterized by cycles of forest expansion and contraction in the Plio-Pleistocene.

Carboxylated branched poly(ß-amino ester) nanoparticles enable robust cytosolic protein delivery and CRISPR-Cas9 gene editing.

Efficient cytosolic protein delivery is necessary to fully realize the potential of protein therapeutics. Current methods of protein delivery often suffer from low serum tolerance and limited in vivo efficacy. Here, we report the synthesis and validation of a previously unreported class of carboxylated branched poly(ß-amino ester)s that can self-assemble into nanoparticles for efficient intracellular delivery of a variety of different proteins. In vitro, nanoparticles enabled rapid cellular uptake, efficient endosomal escape, and functional cytosolic protein release into cells in media containing 10% serum. Moreover, nanoparticles encapsulating CRISPR-Cas9 ribonucleoproteins (RNPs) induced robust levels of gene knock-in (4%) and gene knockout (>75%) in several cell types. A single intracranial administration of nanoparticles delivering a low RNP dose (3.5 pmol) induced robust gene editing in mice bearing engineered orthotopic murine glioma tumors. This self-assembled polymeric nanocarrier system enables a versatile protein delivery and gene editing platform for biological research and therapeutic applications.

Applications of Deep-Learning in Exploiting Large-Scale and Heterogeneous Compound Data in Industrial Pharmaceutical Research.

In recent years, the development of high-throughput screening (HTS) technologies and their establishment in an industrialized environment have given scientists the possibility to test millions of molecules and profile them against a multitude of biological targets in a short period of time, generating data in a much faster pace and with a higher quality than before. Besides the structure activity data from traditional bioassays, more complex assays such as transcriptomics profiling or imaging have also been established as routine profiling experiments thanks to the advancement of Next Generation Sequencing or automated microscopy technologies. In industrial pharmaceutical research, these technologies are typically established in conjunction with automated platforms in order to enable efficient handling of screening collections of thousands to millions of compounds. To exploit the ever-growing amount of data that are generated by these approaches, computational techniques are constantly evolving. In this regard, artificial intelligence technologies such as deep learning and machine learning methods play a key role in cheminformatics and bio-image analytics fields to address activity prediction, scaffold hopping, de novo molecule design, reaction/retrosynthesis predictions, or high content screening analysis. Herein we summarize the current state of analyzing large-scale compound data in industrial pharmaceutical research and describe the impact it has had on the drug discovery process over the last two decades, with a specific focus on deep-learning technologies.

Engineered nanoparticles for systemic siRNA delivery to malignant brain tumours.

Improved delivery materials are needed to enable siRNA transport across biological barriers, including the blood-brain barrier (BBB), to treat diseases like brain cancer. We engineered bioreducible nanoparticles for systemic siRNA delivery to patient-derived glioblastoma cells in an orthotopic mouse tumor model. We first utilized a newly developed biomimetic in vitro model to evaluate and optimize the performance of the engineered bioreducible nanoparticles at crossing the brain microvascular endothelium. We performed transmission electron microscopy imaging which indicated that the engineered nanoparticles are able to cross the BBB endothelium via a vesicular mechanism. The nanoparticle formulation engineered to best cross the BBB model in vitro led to safe delivery across the BBB to the brain in vivo. The nanoparticles were internalized by human brain cancer cells, released siRNA to the cytosol via environmentally-triggered degradation, and gene silencing was obtained both in vitro and in vivo. This study opens new frontiers for the in vitro evaluation and engineering of nanomedicines for delivery to the brain, and reports a systemically administered biodegradable nanocarrier for oligonucleotide delivery to treat glioma.

Species Boundaries within Morphologically Cryptic Galagos: Evidence from Acoustic and Genetic Data.

Describing primate biodiversity is one of the main goals in primatology. Species are the fundamental unit of study in phylogeny, behaviour, ecology and conservation. Identifying species boundaries is particularly challenging for nocturnal taxa where only subtle morphological variation is present. Traditionally, vocal signals have been used to identify species within nocturnal primates: species-specific signals often play a critical role in mate recognition, and they can restrict gene flow with other species. However, little research has been conducted to test whether different "acoustic forms" also represent genetically distinct species. Here, we investigate species boundaries between two putative highly cryptic species of Eastern dwarf galagos (Paragalago cocosand P. zanzibaricus). We combined vocal and genetic data: molecular data included the complete mitochondrial cytochrome b gene (1,140 bp) for 50 samples across 11 localities in Kenya and Tanzania, while vocal data comprised 221 vocalisations recorded across 8 localities. Acoustic analyses showed a high level of correct assignation to the putative species (approx. 90%), while genetic analyses identified two separate clades at the mitochondrial level. We conclude that P. cocos and P. zanzibaricus represent two valid cryptic species that probably underwent speciation in the Late Pliocene while fragmented in isolated populations in the eastern forests.

IA-Lab: A MATLAB framework for efficient microscopy image analysis development, applied to quantifying intracellular transport of internalized peptide-drug conjugate.

This work presents a MATLAB-based software package for high-throughput microscopy image analysis development, making such development more accessible for a large user community. The toolbox provides a GUI and a number of analysis workflows, and can serve as a general framework designed to allow for easy extension. For a new application, only a minor part of the object-oriented code needs to be replaced by new components, making development efficient. This makes it possible to quickly develop solutions for analysis not available in existing tools. We show its use in making a tool for quantifying intracellular transport of internalized peptide-drug conjugates. The code is freely available as open source on GitHub (https://github.com/amcorrigan/ia-lab).