Classification and analysis of a large collection of in vivo bioassay descriptions

U-Net based vessel segmentation for murine brains with small micro-magnetic resonance imaging reference datasets

Identification and quantitative segmentation of individual blood vessels in mice visualized with preclinical imaging techniques is a tedious, manual or semiautomated task that can require weeks of reviewing hundreds of levels of individual data sets. Preclinical imaging, such as micro-magnetic resonance imaging (μMRI) can produce tomographic datasets of murine vasculature across length scales and organs, which is of outmost importance to study tumor progression, angiogenesis, or vascular risk factors for diseases such as Alzheimer's. Training a neural network capable of accurate segmentation results requires a sufficiently large amount of labelled data, which takes a long time to compile. Recently, several reasonably automated approaches have emerged in the preclinical context but still require significant manual input and are less accurate than the deep learning approach presented in this paper-quantified by the Dice score. In this work, the implementation of a shallow, three-dimensional U-Net architecture for the segmentation of vessels in murine brains is presented, which is (1) open-source, (2) can be achieved with a small dataset (in this work only 8 μMRI imaging stacks of mouse brains were available), and (3) requires only a small subset of labelled training data. The presented model is evaluated together with two post-processing methodologies using a cross-validation, which results in an average Dice score of 61.34% in its best setup. The results show, that the methodology is able to detect blood vessels faster and more reliably compared to state-of-the-art vesselness filters with an average Dice score of 43.88% for the used dataset.

An extension of the BioAssay Ontology to include pharmacokinetic/pharmacodynamic terminology for the enrichment of scientific workflows

With the capacity to produce and record data electronically, Scientific research and the data associated with it have grown at an unprecedented rate. However, despite a decent amount of data now existing in an electronic form, it is still common for scientific research to be recorded in an unstructured text format with inconsistent context (vocabularies) which vastly reduces the potential for direct intelligent analysis. Research has demonstrated that the use of semantic technologies such as ontologies to structure and enrich scientific data can greatly improve this potential. However, whilst there are many ontologies that can be used for this purpose, there is still a vast quantity of scientific terminology that does not have adequate semantic representation. A key area for expansion identified by the authors was the pharmacokinetic/pharmacodynamic (PK/PD) domain due to its high usage across many areas of Pharma. As such we have produced a set of these terms and other bioassay related terms to be incorporated into the BioAssay Ontology (BAO), which was identified as the most relevant ontology for this work. A number of use cases developed by experts in the field were used to demonstrate how these new ontology terms can be used, and to set the scene for the continuation of this work with a look to expanding this work out into further relevant domains. The work done in this paper was part of Phase 1 of the SEED project (Semantically Enriching electronic laboratory notebook (eLN) Data).

Assessment of air toxicity in the megalopolis of Krasnoyarsk using long-term monitoring of suburban pine forests

The present study develops the application of suburban forests as bioindicators, with the industrial metropolis of Krasnoyarsk (Central Siberia, Russia) taken as an example. Huge forests, such as those found in large Siberian territories, are climate-forming for the entire planet. Hence, their conservation is essential at both the local and global scales. During the period 2002-2021, the vigor state of two pine forests was evaluated using several inventory and morphological parameters: needle damage, deterioration in tree condition, increased entropy, and tree mortality. Additionally, an original bioindication parameter was applied: episodic increase in the size of needles was analyzed. We hypothesized that this increase in needle size was related to the activation of tree protection at the initial stage of tree damage; the mechanism assumes a redirection of sugar transport into the crown to aid tree regeneration. All parameters were measured annually on six permanent sample plots; each plot included 200-300 numbered trees of similar age (approximately 60-80 years). The long-term parameter changes were analyzed and attributed to chronic exposure to industrial air pollution. Significant changes in pine-forest parameters observed over the past few years (2019-2021) may indicate an approaching stage of irreversible toxic damage that is the destruction of the entire forest system. The results encourage involving forest-based bioindication in the regional system of ecological monitoring. Forest-based bioindication can be used as a tool for evaluating the efficiency of long-term governmental activity on air quality in industrial metropolises. Integr Environ Assess Manag 2022;00:1-8. © 2022 SETAC.

The Hitchhiker's Guide to Human Therapeutic Nanoparticle Development

Nanomedicine plays an essential role in developing new therapies through novel drug delivery systems, diagnostic and imaging systems, vaccine development, antibacterial tools, and high-throughput screening. One of the most promising drug delivery systems are nanoparticles, which can be designed with various compositions, sizes, shapes, and surface modifications. These nanosystems have improved therapeutic profiles, increased bioavailability, and reduced the toxicity of the product they carry. However, the clinical translation of nanomedicines requires a thorough understanding of their properties to avoid problems with the most questioned aspect of nanosystems: safety. The particular physicochemical properties of nano-drugs lead to the need for additional safety, quality, and efficacy testing. Consequently, challenges arise during the physicochemical characterization, the production process, in vitro characterization, in vivo characterization, and the clinical stages of development of these biopharmaceuticals. The lack of a specific regulatory framework for nanoformulations has caused significant gaps in the requirements needed to be successful during their approval, especially with tests that demonstrate their safety and efficacy. Researchers face many difficulties in establishing evidence to extrapolate results from one level of development to another, for example, from an in vitro demonstration phase to an in vivo demonstration phase. Additional guidance is required to cover the particularities of this type of product, as some challenges in the regulatory framework do not allow for an accurate assessment of NPs with sufficient evidence of clinical success. This work aims to identify current regulatory issues during the implementation of nanoparticle assays and describe the major challenges that researchers have faced when exposing a new formulation. We further reflect on the current regulatory standards required for the approval of these biopharmaceuticals and the requirements demanded by the regulatory agencies. Our work will provide helpful information to improve the success of nanomedicines by compiling the challenges described in the literature that support the development of this novel encapsulation system. We propose a step-by-step approach through the different stages of the development of nanoformulations, from their design to the clinical stage, exemplifying the different challenges and the measures taken by the regulatory agencies to respond to these challenges.

Big Techs and startups in pharmaceutical R&D - A 2020 perspective on artificial intelligence

We investigated what kind of artificial intelligence (AI) technologies are utilized in pharmaceutical research and development (R&D) and which sources of AI-related competencies can be leveraged by pharmaceutical companies. First, we found that machine learning (ML) is the dominating AI technology currently used in pharmaceutical R&D. Second, both Big Techs and AI startups are competent knowledge bases for AI applications. Big Techs have long-lasting experience in the digital field and offer more general IT solutions to support pharmaceutical companies in cloud computing, health monitoring, diagnostics or clinical trial management, whereas startups can provide more specific AI services to address special issues in the drug-discovery space.

Bacteriocins: An Overview of Antimicrobial, Toxicity, and Biosafety Assessment by in vivo Models

The world is facing a significant increase in infections caused by drug-resistant infectious agents. In response, various strategies have been recently explored to treat them, including the development of bacteriocins. Bacteriocins are a group of antimicrobial peptides produced by bacteria, capable of controlling clinically relevant susceptible and drug-resistant bacteria. Bacteriocins have been studied to be able to modify and improve their physicochemical properties, pharmacological effects, and biosafety. This manuscript focuses on the research being developed on the biosafety of bacteriocins, which is a topic that has not been addressed extensively in previous reviews. This work discusses the studies that have tested the effect of bacteriocins against pathogens and assess their toxicity using in vivo models, including murine and other alternative animal models. Thus, this work concludes the urgency to increase and advance the in vivo models that both assess the efficacy of bacteriocins as antimicrobial agents and evaluate possible toxicity and side effects, which are key factors to determine their success as potential therapeutic agents in the fight against infections caused by multidrug-resistant microorganisms.

The role of gut microbiome in chemical-induced metabolic and toxicological murine disease models

The role of gut microbiome in human health and disease is well established. While evidence-based pharmacological studies utilize a variety of chemical-induced metabolic and toxicological disease models that in part recapitulate the natural mode of disease pathogenesis, the mode of actions of these disease models are likely underexplored. Conventionally, the mechanistic principles of these disease models are established as direct tissue toxicity through redox imbalance and pro-inflammatory injury. However, emerging evidences suggest that the mode of action of these chemicals could be largely associated with changes in gut microbial populations, diversity and metabolic functions, affecting pathological changes along the gut-liver and gut-pancreas axis. Especially in these disease models, reversal of disease severity or less sensitivity to induced disease pathogenesis has been observed when germ-free or antibiotic-supplemented microbiota-depleted rodents were treated with disease causing chemicals. Thus, by summarizing evidences from in vivo pharmacological interventions, this review revisits the mode of action of carbon tetrachloride-induced cirrhosis, diethylnitrosamine-induced hepatocellular carcinoma, acetaminophen-induced hepatotoxicity and alloxan- and streptozotocin-induced diabetes through the light of gut microbiota. How changes in gut microbiome affects tissue-level toxicity likely through intestinal-level mechanisms like gastrointestinal inflammation and gut barrier dysfunction has also been discussed. Additionally, this review discusses potential pitfalls of inconsistent experimental models that precludes defining the gut microbial effects in evidence-based pharmacology. Collectively, this review emphasizes the underexplored role of microbial intervention in experimental pharmacology and aims to provide direction towards redefining and establishing microbiome-centric alternative mode of action of chemical-induced metabolic and toxicological disease models in pharmacological research.

Extending the small-molecule similarity principle to all levels of biology with the Chemical Checker

Small molecules are usually compared by their chemical structure, but there is no unified analytic framework for representing and comparing their biological activity. We present the Chemical Checker (CC), which provides processed, harmonized and integrated bioactivity data on ~800,000 small molecules. The CC divides data into five levels of increasing complexity, from the chemical properties of compounds to their clinical outcomes. In between, it includes targets, off-targets, networks and cell-level information, such as omics data, growth inhibition and morphology. Bioactivity data are expressed in a vector format, extending the concept of chemical similarity to similarity between bioactivity signatures. We show how CC signatures can aid drug discovery tasks, including target identification and library characterization. We also demonstrate the discovery of compounds that reverse and mimic biological signatures of disease models and genetic perturbations in cases that could not be addressed using chemical information alone. Overall, the CC signatures facilitate the conversion of bioactivity data to a format that is readily amenable to machine learning methods.

Menagerie: A text-mining tool to support animal-human translation in neurodegeneration research

Discovery studies in animals constitute a cornerstone of biomedical research, but suffer from lack of generalizability to human populations. We propose that large-scale interrogation of these data could reveal patterns of animal use that could narrow the translational divide. We describe a text-mining approach that extracts translationally useful data from PubMed abstracts. These comprise six modules: species, model, genes, interventions/disease modifiers, overall outcome and functional outcome measures. Existing National Library of Medicine natural language processing tools (SemRep, GNormPlus and the Chemical annotator) underpin the program and are further augmented by various rules, term lists, and machine learning models. Evaluation of the program using a 98-abstract test set achieved F1 scores ranging from 0.75-0.95 across all modules, and exceeded F1 scores obtained from comparable baseline programs. Next, the program was applied to a larger 14,481 abstract data set (2008-2017). Expected and previously identified patterns of species and model use for the field were obtained. As previously noted, the majority of studies reported promising outcomes. Longitudinal patterns of intervention type or gene mentions were demonstrated, and patterns of animal model use characteristic of the Parkinson's disease field were confirmed. The primary function of the program is to overcome low external validity of animal model systems by aggregating evidence across a diversity of models that capture different aspects of a multifaceted cellular process. Some aspects of the tool are generalizable, whereas others are field-specific. In the initial version presented here, we demonstrate proof of concept within a single disease area, Parkinson's disease. However, the program can be expanded in modular fashion to support a wider range of neurodegenerative diseases.

Identifying antimicrobial peptides using word embedding with deep recurrent neural networks

MOTIVATION

Antibiotic resistance constitutes a major public health crisis, and finding new sources of antimicrobial drugs is crucial to solving it. Bacteriocins, which are bacterially produced antimicrobial peptide products, are candidates for broadening the available choices of antimicrobials. However, the discovery of new bacteriocins by genomic mining is hampered by their sequences' low complexity and high variance, which frustrates sequence similarity-based searches.

RESULTS

Here we use word embeddings of protein sequences to represent bacteriocins, and apply a word embedding method that accounts for amino acid order in protein sequences, to predict novel bacteriocins from protein sequences without using sequence similarity. Our method predicts, with a high probability, six yet unknown putative bacteriocins in Lactobacillus. Generalized, the representation of sequences with word embeddings preserving sequence order information can be applied to peptide and protein classification problems for which sequence similarity cannot be used.

AVAILABILITY AND IMPLEMENTATION

Data and source code for this project are freely available at: https://github.com/nafizh/NeuBI.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A large-scale dataset of in vivo pharmacology assay results

ChEMBL is a large-scale, open-access drug discovery resource containing bioactivity information primarily extracted from scientific literature. A substantial dataset of more than 135,000 in vivo assays has been collated as a key resource of animal models for translational medicine within drug discovery. To improve the utility of the in vivo data, an extensive data curation task has been undertaken that allows the assays to be grouped by animal disease model or phenotypic endpoint. The dataset contains previously unavailable information about compounds or drugs tested in animal models and, in conjunction with assay data on protein targets or cell- or tissue- based systems, allows the investigation of the effects of compounds at differing levels of biological complexity. Equally, it enables researchers to identify compounds that have been investigated for a group of disease-, pharmacology- or toxicity-relevant assays.