Development of a machine learning detector for North Atlantic humpback whale song.

The study of humpback whale song using passive acoustic monitoring devices requires bioacousticians to manually review hours of audio recordings to annotate the signals. To vastly reduce the time of manual annotation through automation, a machine learning model was developed. Convolutional neural networks have made major advances in the previous decade, leading to a wide range of applications, including the detection of frequency modulated vocalizations by cetaceans. A large dataset of over 60 000 audio segments of 4 s length is collected from the North Atlantic and used to fine-tune an existing model for humpback whale song detection in the North Pacific (see Allen, Harvey, Harrell, Jansen, Merkens, Wall, Cattiau, and Oleson (2021). Front. Mar. Sci. 8, 607321). Furthermore, different data augmentation techniques (time-shift, noise augmentation, and masking) are used to artificially increase the variability within the training set. Retraining and augmentation yield F-score values of 0.88 on context window basis and 0.89 on hourly basis with false positive rates of 0.05 on context window basis and 0.01 on hourly basis. If necessary, usage and retraining of the existing model is made convenient by a framework (AcoDet, acoustic detector) built during this project. Combining the tools provided by this framework could save researchers hours of manual annotation time and, thus, accelerate their research.

A Scalable Molecular Force Field Parameterization Method Based on Density Functional Theory and Quantum-Level Machine Learning.

Fast and accurate molecular force field (FF) parameterization is still an unsolved problem. Accurate FF are not generally available for all molecules, like novel druglike molecules. While methods based on quantum mechanics (QM) exist to parameterize them with better accuracy, they are computationally expensive and slow, which limits applicability to a small number of molecules. Here, we present an automated FF parameterization method which can utilize either density functional theory (DFT) calculations or approximate QM energies produced by different neural network potentials (NNPs), to obtain improved parameters for molecules. We demonstrate that for the case of torchani-ANI-1x NNP, we can parameterize small molecules in a fraction of time compared with an equivalent parameterization using DFT QM calculations while producing more accurate parameters than FF (GAFF2). We expect our method to be of critical importance in computational structure-based drug discovery (SBDD). The current version is available at PlayMolecule ( www.playmolecule.org ) and implemented in HTMD, allowing to parameterize molecules with different QM and NNP options.

Protocol for the Wessex AsThma CoHort of difficult asthma (WATCH): a pragmatic real-life longitudinal study of difficult asthma in the clinic.

BACKGROUND: Asthma is now widely recognised to be a heterogeneous disease. The last two decades have seen the identification of a number of biological targets and development of various novel therapies. Despite this, asthma still represents a significant health and economic burden worldwide. Why some individuals should continue to suffer remains unclear. METHODS: The Wessex Asthma Cohort of Difficult Asthma (WATCH) is an ongoing 'real-life', prospective study of patients in the University Hospital Southampton Foundation Trust (UHSFT) Difficult Asthma service. Research data capture is aligned with the extensive clinical characterisation required of a commissioned National Health Service (NHS) Specialist Centre for Severe Asthma. Data acquisition includes detailed clinical, health and disease-related questionnaires, anthropometry, allergy and lung function testing, radiological imaging (in a small subset) and collection of biological samples (blood, urine and sputum). Prospective data are captured in parallel to clinical follow up appointments, with data entered into a bespoke database. DISCUSSION: The pragmatic ongoing nature of the WATCH study allows comprehensive assessment of the real world clinical spectrum seen in a Specialist Asthma Centre and allows a longitudinal perspective of deeply phenotyped patients. It is anticipated that the WATCH cohort would act as a vehicle for potential collaborative asthma studies and will build upon our understanding of mechanisms underlying difficult asthma.

Molecular-Simulation-Driven Fragment Screening for the Discovery of New CXCL12 Inhibitors.

Fragment-based drug discovery (FBDD) has become a mainstream approach in drug design because it allows the reduction of the chemical space and screening libraries while identifying fragments with high protein-ligand efficiency interactions that can later be grown into drug-like leads. In this work, we leverage high-throughput molecular dynamics (MD) simulations to screen a library of 129 fragments for a total of 5.85 ms against the CXCL12 monomer, a chemokine involved in inflammation and diseases such as cancer. Our in silico binding assay was able to recover binding poses, affinities, and kinetics for the selected library and was able to predict 8 mM-affinity fragments with ligand efficiencies higher than 0.3. All of the fragment hits present a similar chemical structure, with a hydrophobic core and a positively charged group, and bind to either sY7 or H1S68 pockets, where they share pharmacophoric properties with experimentally resolved natural binders. This work presents a large-scale screening assay using an exclusive combination of thousands of short MD adaptive simulations analyzed with a Markov state model (MSM) framework.

Drug Discovery and Molecular Dynamics: Methods, Applications and Perspective Beyond the Second Timescale.

Bio-molecular dynamics (MD) simulations based on graphical processing units (GPUs) were first released to the public in the early 2009 with the code ACEMD. Almost 8 years after, applications now encompass a broad range of molecular studies, while throughput improvements have opened the way to millisecond sampling timescales. Based on an extrapolation of the amount of sampling in published literature, the second timescale will be reached by the year 2022, and therefore we predict that molecular dynamics is going to become one of the main tools in drug discovery in both academia and industry. Here, we review successful applications in the drug discovery domain developed over these recent years of GPU-based MD. We also retrospectively analyse limitations that have been overcome over the years and give a perspective on challenges that remain to be addressed.

RAPPORT: running scientific high-performance computing applications on the cloud.

Cloud computing infrastructure is now widely used in many domains, but one area where there has been more limited adoption is research computing, in particular for running scientific high-performance computing (HPC) software. The Robust Application Porting for HPC in the Cloud (RAPPORT) project took advantage of existing links between computing researchers and application scientists in the fields of bioinformatics, high-energy physics (HEP) and digital humanities, to investigate running a set of scientific HPC applications from these domains on cloud infrastructure. In this paper, we focus on the bioinformatics and HEP domains, describing the applications and target cloud platforms. We conclude that, while there are many factors that need consideration, there is no fundamental impediment to the use of cloud infrastructure for running many types of HPC applications and, in some cases, there is potential for researchers to benefit significantly from the flexibility offered by cloud platforms.

SPECTRa-T: machine-based data extraction and semantic searching of chemistry e-theses.

The SPECTRa-T project has developed text-mining tools to extract named chemical entities (NCEs), such as chemical names and terms, and chemical objects (COs), e.g., experimental spectral assignments and physical chemistry properties, from electronic theses (e-theses). Although NCEs were readily identified within the two major document formats studied, only the use of structured documents enabled identification of chemical objects and their association with the relevant chemical entity (e.g., systematic chemical name). A corpus of theses was analyzed and it is shown that a high degree of semantic information can be extracted from structured documents. This integrated information has been deposited in a persistent Resource Description Framework (RDF) triple-store that allows users to conduct semantic searches. The strength and weaknesses of several document formats are reviewed.

SPECTRa: the deposition and validation of primary chemistry research data in digital repositories.

The SPECTRa (Submission, Preservation and Exposure of Chemistry Teaching and Research Data) project has investigated the practices of chemists in archiving and disseminating primary chemical data from academic research laboratories. To redress the loss of the large amount of data never archived or disseminated, we have developed software for data publication into departmental and institutional Open Access digital repositories (DSpace). Data adhering to standard formats in selected disciplines (crystallography, NMR, computational chemistry) is transformed to XML (CML, Chemical Markup Language) which provides added validation. Context-specific chemical metadata and persistent Handle identifiers are added to enable long-term data reuse. It was found essential to provide an embargo mechanism, and policies for operating this and other processes are presented.

WEDS: a Web services-based environment for distributed simulation.

Web services have the potential to radically enhance the ability of researchers to make use of distributed computing resources, but jargon and a plethora of standards make their use almost impossible for the scientist without prior experience of the necessary technologies. A powerful and simple WSRF-based middleware scheme is presented, designed to let scientists remotely deploy single or multiple instances of a pre-existing code across multiple resources, and giving steering, visualization and workflow functionality with only simple modifications to program code. It is hoped that the development and implementation of such a toolkit will be relevant not only to the problem of deploying workstation-class codes in real time, but also the move towards more tractable alternatives to the Globus toolkit for deployment of processes in a high-performance computing environment.