Toward universal cell embeddings: integrating single-cell RNA-seq datasets across species with SATURN

Analysis of single-cell datasets generated from diverse organisms offers unprecedented opportunities to unravel fundamental evolutionary processes of conservation and diversification of cell types. However, interspecies genomic differences limit the joint analysis of cross-species datasets to homologous genes. Here we present SATURN, a deep learning method for learning universal cell embeddings that encodes genes' biological properties using protein language models. By coupling protein embeddings from language models with RNA expression, SATURN integrates datasets profiled from different species regardless of their genomic similarity. SATURN can detect functionally related genes coexpressed across species, redefining differential expression for cross-species analysis. Applying SATURN to three species whole-organism atlases and frog and zebrafish embryogenesis datasets, we show that SATURN can effectively transfer annotations across species, even when they are evolutionarily remote. We also demonstrate that SATURN can be used to find potentially divergent gene functions between glaucoma-associated genes in humans and four other species.

ADMET-AI: A machine learning ADMET platform for evaluation of large-scale chemical libraries

Summary

The emergence of large chemical repositories and combinatorial chemical spaces, coupled with high-throughput docking and generative AI, have greatly expanded the chemical diversity of small molecules for drug discovery. Selecting compounds for experimental validation requires filtering these molecules based on favourable druglike properties, such as Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET). We developed ADMET-AI, a machine learning platform that provides fast and accurate ADMET predictions both as a website and as a Python package. ADMET-AI has the highest average rank on the TDC ADMET Benchmark Group leaderboard, and it is currently the fastest web-based ADMET predictor, with a 45% reduction in time compared to the next fastest ADMET web server. ADMET-AI can also be run locally with predictions for one million molecules taking just 3.1 hours.

Availability and Implementation

The ADMET-AI platform is freely available both as a web server at admet.ai.greenstonebio.com and as an open-source Python package for local batch prediction at github.com/swansonk14/admet_ai (also archived on Zenodo at doi.org/10.5281/zenodo.10372930 ). All data and models are archived on Zenodo at doi.org/10.5281/zenodo.10372418 .

Microbial communities are indicators of parasite infection status

Growing evidence suggests that microbiomes have been shaping the evolutionary pathways of macroorganisms for millennia and that these tiny symbionts can influence, and possibly even control, species interactions like host-parasite relationships. Yet, while studies have investigated host-parasites and microbiomes separately, little has been done to understand all three groups synergistically. Here, we collected infected and uninfected Eurypanopeus depressus crab hosts from a coastal North Carolina oyster reef three times over 4 months. Infected crabs demonstrated an external stage of the rhizocephalan parasite, Loxothylacus panopaei. Community analyses revealed that microbial richness and diversity were significantly different among tissue types (uninfected crab, infected crab, parasite externae and parasite larvae) and over time (summer and fall). Specifically, the microbial communities from parasite externae and larvae had similar microbiomes that were consistent through time. Infected crabs demonstrated microbial communities spanning those of their host and parasite, while uninfected crabs showed more distinctive communities with greater variability over time. Microbial communities were also found to be indicators of early-stage infections. Resolving the microbial community composition of a host and its parasite is an important step in understanding the microbiome's role in the host-parasite relationship and determining how this tripartite relationship impacts coevolutionary processes.

Deep learning-guided discovery of an antibiotic targeting Acinetobacter baumannii

Acinetobacter baumannii is a nosocomial Gram-negative pathogen that often displays multidrug resistance. Discovering new antibiotics against A. baumannii has proven challenging through conventional screening approaches. Fortunately, machine learning methods allow for the rapid exploration of chemical space, increasing the probability of discovering new antibacterial molecules. Here we screened ~7,500 molecules for those that inhibited the growth of A. baumannii in vitro. We trained a neural network with this growth inhibition dataset and performed in silico predictions for structurally new molecules with activity against A. baumannii. Through this approach, we discovered abaucin, an antibacterial compound with narrow-spectrum activity against A. baumannii. Further investigations revealed that abaucin perturbs lipoprotein trafficking through a mechanism involving LolE. Moreover, abaucin could control an A. baumannii infection in a mouse wound model. This work highlights the utility of machine learning in antibiotic discovery and describes a promising lead with targeted activity against a challenging Gram-negative pathogen.

Towards Universal Cell Embeddings: Integrating Single-cell RNA-seq Datasets across Species with SATURN

Analysis of single-cell datasets generated from diverse organisms offers unprecedented opportunities to unravel fundamental evolutionary processes of conservation and diversification of cell types. However, inter-species genomic differences limit the joint analysis of cross-species datasets to homologous genes. Here, we present SATURN, a deep learning method for learning universal cell embeddings that encodes genes' biological properties using protein language models. By coupling protein embeddings from language models with RNA expression, SATURN integrates datasets profiled from different species regardless of their genomic similarity. SATURN has a unique ability to detect functionally related genes co-expressed across species, redefining differential expression for cross-species analysis. We apply SATURN to three species whole-organism atlases and frog and zebrafish embryogenesis datasets. We show that cell embeddings learnt in SATURN can be effectively used to transfer annotations across species and identify both homologous and species-specific cell types, even across evolutionarily remote species. Finally, we use SATURN to reannotate the five species Cell Atlas of Human Trabecular Meshwork and Aqueous Outflow Structures and find evidence of potentially divergent functions between glaucoma associated genes in humans and other species.

7-UP: Generating in silico CODEX from a small set of immunofluorescence markers

Multiplex immunofluorescence (mIF) assays multiple protein biomarkers on a single tissue section. Recently, high-plex CODEX (co-detection by indexing) systems enable simultaneous imaging of 40+ protein biomarkers, unlocking more detailed molecular phenotyping, leading to richer insights into cellular interactions and disease. However, high-plex data can be slower and more costly to collect, limiting its applications, especially in clinical settings. We propose a machine learning framework, 7-UP, that can computationally generate in silico 40-plex CODEX at single-cell resolution from a standard 7-plex mIF panel by leveraging cellular morphology. We demonstrate the usefulness of the imputed biomarkers in accurately classifying cell types and predicting patient survival outcomes. Furthermore, 7-UP's imputations generalize well across samples from different clinical sites and cancer types. 7-UP opens the possibility of in silico CODEX, making insights from high-plex mIF more widely available.

Research needs, environmental concerns, and logistical considerations for incorporating livestock grazing into coastal upland habitat management

Along the Gulf of Mexico (GoM) coast, natural resource managers continually struggle with managing coastal uplands due to front-end costs, prolonged maintenance, and habitat-specific ecological needs. Prescribed fire, mechanical removal, and chemical treatments are common habitat management techniques used to remove invasive species, clear understory, and achieve other management goals. However, rapid development and changing climate exacerbate the difficulty in using these techniques. A potential alternative or complementary technique is using livestock for habitat management (i.e., targeted or controlled grazing). In other regions of the world, using livestock for conservation or restoration of managed lands has shown to be a less intrusive and more financially viable alternative. To better understand the research needs, logistical, and environmental concerns related to using livestock for habitat management in the coastal uplands of the GoM, we developed and distributed a survey to three groups of land users, including natural resource managers, researchers, and livestock producers in the region. Survey results show that over 96% of respondents are interested in using livestock for habitat management, but less than 10% of respondents were aware of any information that could be used to inform grazing practices for coastal upland habitat management along the Gulf of Mexico coast. There were differences among surveyed groups, but generally small-sized cattle breeds and goats were identified as the livestock with the most potential for environmental benefit and ease of containment. General concerns and areas for further investigation were implementation (e.g., which livestock type to use and grazing intensity), logistical considerations (e.g., fencing and rotational frequency), impacts of grazing on water quality, wildlife, vegetation, and livestock nutrition. Survey respondents overwhelmingly (at least 75% of each group) indicated that livestock grazing ideally would not be a standalone management practice and should be used in conjunction with other habitat management techniques such as prescribed burns, mechanical clearing, or chemical treatments. The results of the survey could be used to develop applied research projects and guidance documents that directly address informational needs related to using livestock for habitat management of coastal uplands along the Gulf of Mexico coast.

The timing versus resource problem in nonnative sentence processing: Evidence from a time-frequency analysis of anaphora resolution in successive wh-movement in native and nonnative speakers of French

Nonnative processing has been argued to reflect either reduced processing capacity or delayed timing of structural analysis compared to the extraction of lexical/semantic information. The current study simultaneously investigates timing and resource allocation through a time-frequency analysis of the intrinsic neural activity during syntactic processing in native and English-speaking nonnative speakers of French. It involved structurally constrained anaphora resolution in bi-clausal wh-filler-gap dependencies such as Quelle décision à propos de lui est-ce que Paul a dit que Lydie avait rejetée sans hésitation? 'Which decision about him did Paul say that Lydie rejected without hesitation?'. We tested the hypothesis that nonnative speakers may allocate greater resources than native speakers to the computation of syntactic representations based on the grammatical specifications encoded in lexical entries, though both native and nonnative processing involves the immediate application of structural constraints. This distinct resource allocation is likely to arise in response to higher activation thresholds for nonnative knowledge acquired after the first language grammar has been fully acquired. To examine this bias in nonnative neurocognitive processing, we manipulated the wh-filler to contain either a lexically specified noun complement such as à propos de lui 'about him' or a non-lexcially specified noun phrase modifier such as le concernant 'concerning him'. We focused on processing at the intermediate gap site, that is, the point of information exchange between the matrix and the embedded clauses by adopting a measurement window corresponding to the bridge verb dit 'said' and subordinator que 'that' introducing the embedded clause. Our results showed that structural constraints on anaphora produced event-related spectral perturbations at 13-14Hz early into the presentation of the bridge verb across groups. An interaction of structural constraints on anaphora with group was found at 18-19Hz early into the presentation of the bridge verb. In this interaction, the nonnative-speaker activity at 18-19Hz echoed the concurrent general patterns at 13-14Hz, whereas the native-speaker activity revealed distinct power at 18-19Hz and at 13-14Hz. There was no evidence of delay of structural constraints on intermediate gaps with respect to lexical access to the bridge verb and subordinator. However, nonnative speakers' allocation of power in cell assembly synchronizations of fillers and gaps at the intermediate gap site reflected the grammatical specifications lexically encoded in the fillers.

Cerebral Venous Sinus Thrombosis Associated With Coronavirus Disease 2019: Case Report and Review of the Literature

INTRODUCTION

Coronavirus disease 2019 (COVID-19) is associated with significant risk of acute thrombosis. We present a case report of a patient with cerebral venous sinus thrombosis (CVST) associated with COVID-19 and performed a literature review of CVST associated with COVID-19 cases.

CASE REPORT

A 38-year-old woman was admitted with severe headache and acute altered mental status a week after confirmed diagnosis of COVID-19. Magnetic resonance imaging brain showed diffuse venous sinus thrombosis involving the superficial and deep veins, and diffuse edema of bilateral thalami, basal ganglia and hippocampi because of venous infarction. Her neurological exam improved with anticoagulation (AC) and was subsequently discharged home. We identified 43 patients presenting with CVST associated with COVID-19 infection. 56% were male with mean age of 51.8±18.2 years old. The mean time of CVST diagnosis was 15.6±23.7 days after onset of COVID-19 symptoms. Most patients (87%) had thrombosis of multiple dural sinuses and parenchymal changes (79%). Almost 40% had deep cerebral venous system thrombosis. Laboratory findings revealed elevated mean D-dimer level (7.14/mL±12.23 mg/L) and mean fibrinogen level (4.71±1.93 g/L). Less than half of patients had prior thrombotic risk factors. Seventeen patients (52%) had good outcomes (mRS <=2). The mortality rate was 39% (13 patients).

CONCLUSION

CVST should be in the differential diagnosis when patients present with acute neurological symptoms in this COVID pandemic. The mortality rate of CVST associated with COVID-19 can be very high, therefore, early diagnosis and prompt treatment are crucial to the outcomes of these patients.

A Deep Learning Approach to Antibiotic Discovery

Due to the rapid emergence of antibiotic-resistant bacteria, there is a growing need to discover new antibiotics. To address this challenge, we trained a deep neural network capable of predicting molecules with antibacterial activity. We performed predictions on multiple chemical libraries and discovered a molecule from the Drug Repurposing Hub-halicin-that is structurally divergent from conventional antibiotics and displays bactericidal activity against a wide phylogenetic spectrum of pathogens including Mycobacterium tuberculosis and carbapenem-resistant Enterobacteriaceae. Halicin also effectively treated Clostridioides difficile and pan-resistant Acinetobacter baumannii infections in murine models. Additionally, from a discrete set of 23 empirically tested predictions from >107 million molecules curated from the ZINC15 database, our model identified eight antibacterial compounds that are structurally distant from known antibiotics. This work highlights the utility of deep learning approaches to expand our antibiotic arsenal through the discovery of structurally distinct antibacterial molecules.

Uncertainty Quantification Using Neural Networks for Molecular Property Prediction

Uncertainty quantification (UQ) is an important component of molecular property prediction, particularly for drug discovery applications where model predictions direct experimental design and where unanticipated imprecision wastes valuable time and resources. The need for UQ is especially acute for neural models, which are becoming increasingly standard yet are challenging to interpret. While several approaches to UQ have been proposed in the literature, there is no clear consensus on the comparative performance of these models. In this paper, we study this question in the context of regression tasks. We systematically evaluate several methods on five regression data sets using multiple complementary performance metrics. Our experiments show that none of the methods we tested is unequivocally superior to all others, and none produces a particularly reliable ranking of errors across multiple data sets. While we believe that these results show that existing UQ methods are not sufficient for all common use cases and further research is needed, we conclude with a practical recommendation as to which existing techniques seem to perform well relative to others.

Comparison of Kjeldahl Method for Determination of Crude Protein in Cereal Grains and Oilseeds with Generic Combustion Method: Collaborative Study

Seven laboratories participated in a collaborative study to extend the applicability of the AOAC generic combustion method for determination of crude protein in animal feed (990.03) to include determination in cereal grains and oilseeds. In the study, method 990.03 was compared with the AOAC mercury catalyst Kjeldahl method for determination of protein in grains (979.09) and crude protein in animal feed (954.01). The study also evaluated the effect on the results of fineness of grind. For determination of crude protein in grains and oilseeds by the combustion method, standard deviations for repeatability and reproducibility ranged from 0.10 to 0.37 and from 0.25 to 0.54, respectively, and relative standard deviations for repeatability and reproducibility ranged from 0.77 to 2.57% and from 1.24 to 3.15%, respectively. The combustion method was adopted first action by AOAC International for determination of crude protein in cereal grains and oilseeds containing 0.2- 20% nitrogen.

Deep learning for automated classification and characterization of amorphous materials

It is difficult to quantify structure-property relationships and to identify structural features of complex materials. The characterization of amorphous materials is especially challenging because their lack of long-range order makes it difficult to define structural metrics. In this work, we apply deep learning algorithms to accurately classify amorphous materials and characterize their structural features. Specifically, we show that convolutional neural networks and message passing neural networks can classify two-dimensional liquids and liquid-cooled glasses from molecular dynamics simulations with greater than 0.98 AUC, with no a priori assumptions about local particle relationships, even when the liquids and glasses are prepared at the same inherent structure energy. Furthermore, we demonstrate that message passing neural networks surpass convolutional neural networks in this context in both accuracy and interpretability. We extract a clear interpretation of how message passing neural networks evaluate liquid and glass structures by using a self-attention mechanism. Using this interpretation, we derive three novel structural metrics that accurately characterize glass formation. The methods presented here provide a procedure to identify important structural features in materials that could be missed by standard techniques and give unique insight into how these neural networks process data.

Effect of Feeding a Low Vitamin a Diet to Beef Steers on Calpain 1 Activation during Meat Aging

ObjectivesThe objective of the study was to determine if a vitamin A deficient diet during beef finishing influences calpain 1 activation during meat aging.Materials and MethodsSixty-four steers of approximately 7 mo of age were subjected to a 14-d acclimation period followed by a 95-d growing period on a low vitamin A diet (1017 IU vitamin A/kg DM) designed to deplete liver vitamin A stores. Steers were assigned to a randomized complete blocked design with a 2 × 2 arrangement of treatments (breed: commercial Angus, n = 32, and purebred Simmental, n = 32; and a Low Vitamin A diet or a control diet). The low Vitamin A (LVA) treatment was a finishing diet with no supplemental vitamin A (723 IU vitamin A/kg DM). The control (CON) treatment was the LVA diet plus supplementation with 2200 IU vitamin A/kg DM for a total of 2923 IU vitamin A/kg DM. Serum retinol concentrations were monitored at the beginning and end of treatment. Upon completion of finishing, steers were slaughtered in two groups at a commercial plant. After fabrication, boneless strip loins (IMPS 180) were collected and transported to NDSU. Samples (approximately 40 g) were collected from the anterior portion of the strip loin on d-2 and d-7 of aging and immediately frozen. Protein was extracted from meat samples in fractionation buffers to yield sarcoplasmic and myofibrillar portions, separated by SDS-PAGE, and transferred to PVDF membranes. Immunoblot analysis was done using anti-desmin (d-2 and d-7) and anti-calpain 1 (d-2) antibodies, and results were visualized and documented. A pooled control was run on all membranes and set to a value of one for normalizing results. All experimental data were analyzed using the Proc Mixed procedure of SAS with breed of steers, dietary treatments, their interaction and slaughter date used as a fixed effect.ResultsCalpain 1 autolysis in the sarcoplasmic protein fraction of the d-2 aged loin samples were not affected by treatment or breed. The myofibrillar protein fraction from Angus loins had greater (P = 0.02) accumulation of the 76 kDa calpain 1 autolysis product than that from the Simmental loins; the myofibrillar fraction of the loins from the LVA treatment tended (P = 0.07) to have more 76 kDa calpain 1 autolysis product than that from the CON. There were not any differences (P > 0.19) in the 80 kDa calpain 1 band or the 78 kDa calpain 1 intermediate autolysis product in the myofibrillar fraction. There was a treatment by breed interaction (P = 0.01) for desmin in the d-7 aged loins where Angus loins from the CON treatment had less accumulation of the 46 kDa band than Angus loins on the LVA treatment and Simmental loins from either treatment.ConclusionVitamin A restriction increased protein proteolysis in Angus but not in Simmental steers. The increased calpain 1 autolysis in Angus vs. Simmental, regardless of Vitamin A treatment, indicates a genetic difference that may be the driver for the increased protein degradation in steers a restricted vitamin A diet.

Minimizing Retraction by Pia-Arachnoidal 10-0 Sutures in Intrasulcal Dissection

BACKGROUND

In contemporary microneurosurgery reducing retraction-induced injury to the brain is essential. Self-retaining retractor systems are commonly used to improve visualization and decrease the repetitive microtrauma, but sometimes self-retaining retractor systems can be cumbersome and the force applied can cause focal ischemia or contusions. This may increase the morbidity and mortality. Here, we describe a technique of retraction using 10-0 sutures in the arachnoid.

OBJECTIVE

To evaluate the imaging and clinical results in patients where 10-0 suture retraction was used to aid the surgical procedure.

METHODS

Adjacent cortex was retracted by placing 10-0 nylon suture in the arachnoid of the bank or banks of the sulcus. The suture was secured to the adjacent dural edge by using aneurysm clips, allowing for easy adjustability of the amount of retraction. We retrospectively analyzed the neurological outcome, signal changes in postoperative imaging, and ease of performing surgery in 31 patients with various intracranial lesions including intracranial aneurysms, intra- and extra-axial tumors, and cerebral ischemia requiring arterial bypass.

RESULTS

Clinically, there were no injuries, vascular events, or neurological deficits referable to the relevant cortex. Postoperative imaging did not show changes consistent with ischemia or contusion due to the retraction. This technique improved the visualization and illumination of the surgical field in all cases.

CONCLUSION

Retraction of the arachnoid can be used safely in cases where trans-sulcal dissection is required. This technique may improve initial visualization and decrease the need for dynamic or static retraction.

Analyzing Learned Molecular Representations for Property Prediction

Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors and graph convolutional neural networks that construct a learned molecular representation by operating on the graph structure of the molecule. However, recent literature has yet to clearly determine which of these two methods is superior when generalizing to new chemical space. Furthermore, prior research has rarely examined these new models in industry research settings in comparison to existing employed models. In this paper, we benchmark models extensively on 19 public and 16 proprietary industrial data sets spanning a wide variety of chemical end points. In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary data sets. Our empirical findings indicate that while approaches based on these representations have yet to reach the level of experimental reproducibility, our proposed model nevertheless offers significant improvements over models currently used in industrial workflows.

Petawatt Laser Guiding and Electron Beam Acceleration to 8 GeV in a Laser-Heated Capillary Discharge Waveguide

Guiding of relativistically intense laser pulses with peak power of 0.85 PW over 15 diffraction lengths was demonstrated by increasing the focusing strength of a capillary discharge waveguide using laser inverse bremsstrahlung heating. This allowed for the production of electron beams with quasimonoenergetic peaks up to 7.8 GeV, double the energy that was previously demonstrated. Charge was 5 pC at 7.8 GeV and up to 62 pC in 6 GeV peaks, and typical beam divergence was 0.2 mrad.

Mammographic Breast Density Assessment Using Deep Learning: Clinical Implementation

Purpose To develop a deep learning (DL) algorithm to assess mammographic breast density. Materials and Methods In this retrospective study, a deep convolutional neural network was trained to assess Breast Imaging Reporting and Data System (BI-RADS) breast density based on the original interpretation by an experienced radiologist of 41 479 digital screening mammograms obtained in 27 684 women from January 2009 to May 2011. The resulting algorithm was tested on a held-out test set of 8677 mammograms in 5741 women. In addition, five radiologists performed a reader study on 500 mammograms randomly selected from the test set. Finally, the algorithm was implemented in routine clinical practice, where eight radiologists reviewed 10 763 consecutive mammograms assessed with the model. Agreement on BI-RADS category for the DL model and for three sets of readings-(a) radiologists in the test set, (b) radiologists working in consensus in the reader study set, and (c) radiologists in the clinical implementation set-were estimated with linear-weighted κ statistics and were compared across 5000 bootstrap samples to assess significance. Results The DL model showed good agreement with radiologists in the test set (κ = 0.67; 95% confidence interval [CI]: 0.66, 0.68) and with radiologists in consensus in the reader study set (κ = 0.78; 95% CI: 0.73, 0.82). There was very good agreement (κ = 0.85; 95% CI: 0.84, 0.86) with radiologists in the clinical implementation set; for binary categorization of dense or nondense breasts, 10 149 of 10 763 (94%; 95% CI: 94%, 95%) DL assessments were accepted by the interpreting radiologist. Conclusion This DL model can be used to assess mammographic breast density at the level of an experienced mammographer. © RSNA, 2018 Online supplemental material is available for this article . See also the editorial by Chan and Helvie in this issue.

Effects of hot boning and moisture enhancement on the eating quality of cull cow beef

The effects of chilling method and moisture enhancement were examined for improving eating quality of semimembranosus (SM) and longissimus lumborum (LL) from 62 cull beef cows. Chilling method included hot boning muscles after 45 to 60 min postmortem or conventional chilling for 24 h. Moisture enhancement included 1) a non-injected control (CONT) or injection processing (10% of product weight) using 2) Sodium Tripolyphosphate/salt (Na/STP), 3) Sodium Citrate (NaCIT), 4) Calcium Ascorbate (CaASC), or 5) Citrus Juices (CITRUS). Chilling method by moisture enhancement treatment interactions (P<0.09) were due to decreased hue, chroma and sarcomere length values in hot boned vs. conventionally chilled product (SM and LL) for CaASC vs. other moisture enhancement treatments. Chilling method by moisture enhancement treatment interactions (P<0.05) were due to decreased shear force and increased tenderness in conventionally chilled vs. hot boned LL using CaASC vs. Na/STP. Moisture enhancement can improve tenderness of cull cow beef depending on combinations of chilling method and moisture enhancement treatments used.