Search

Acknowledgements: P.S. is a Royal Society University Research Fellow (URF\R1\201461). This work was partly funded by a Research Grant (RGS\R1\211126) from the Royal Society, by an Isaac Newton Trust/Wellcome Trust ISSF/University of Cambridge Joint Research Grant (MBAG/624 RG89305), and by UKRI EPSRC (EP/X024733/1). Biomolecular production and some of the characterisations were funded by Novo Nordisk. M.O. is a Ph.D. student funded by AstraZeneca. A.B. and M.M.M are Ph.D. students within the Novo Nordisk R&D STAR Fellowship programme and are partially funded by Innovation Fund Denmark., Funder: Isaac Newton Trust / Wellcome Trust ISSF / University of Cambridge Joint Research Grant (MBAG/624 RG89305), Biologics, such as antibodies and enzymes, are crucial in research, biotechnology, diagnostics, and therapeutics. Often, biologics with suitable functionality are discovered, but their development is impeded by developability issues. Stability and solubility are key biophysical traits underpinning developability potential, as they determine aggregation, correlate with production yield and poly-specificity, and are essential to access parenteral and oral delivery. While advances for the optimisation of individual traits have been made, the co-optimization of multiple traits remains highly problematic and time-consuming, as mutations that improve one property often negatively impact others. In this work, we introduce a fully automated computational strategy for the simultaneous optimisation of conformational stability and solubility, which we experimentally validate on six antibodies, including two approved therapeutics. Our results on 42 designs demonstrate that the computational procedure is highly effective at improving developability potential, while not affecting antigen-binding. We make the method available as a webserver at www-cohsoftware.ch.cam.ac.uk.

Much of the knowledge and information needed for enabling high-quality clinical research is stored in free-text format. Natural language processing (NLP) has been used to extract information from these sources at scale for several decades. This paper aims to present a comprehensive review of clinical NLP for the past 15 years in the UK to identify the community, depict its evolution, analyse methodologies and applications, and identify the main barriers. We collect a dataset of clinical NLP projects (n = 94; £ = 41.97 m) funded by UK funders or the European Union's funding programmes. Additionally, we extract details on 9 funders, 137 organisations, 139 persons and 431 research papers. Networks are created from timestamped data interlinking all entities, and network analysis is subsequently applied to generate insights. 431 publications are identified as part of a literature review, of which 107 are eligible for final analysis. Results show, not surprisingly, clinical NLP in the UK has increased substantially in the last 15 years: the total budget in the period of 2019-2022 was 80 times that of 2007-2010. However, the effort is required to deepen areas such as disease (sub-)phenotyping and broaden application domains. There is also a need to improve links between academia and industry and enable deployments in real-world settings for the realisation of clinical NLP's great potential in care delivery. The major barriers include research and development access to hospital data, lack of capable computational resources in the right places, the scarcity of labelled data and barriers to sharing of pretrained models.

Material extrusion is the most widespread additive manufacturing method but its application in end-use products is limited by vulnerability to errors. Humans can detect errors but cannot provide continuous monitoring or real-time correction. Existing automated approaches are not generalisable across different parts, materials, and printing systems. We train a multi-head neural network using images automatically labelled by deviation from optimal printing parameters. The automation of data acquisition and labelling allows the generation of a large and varied extrusion 3D printing dataset, containing 1.2 million images from 192 different parts labelled with printing parameters. The thus trained neural network, alongside a control loop, enables real-time detection and rapid correction of diverse errors that is effective across many different 2D and 3D geometries, materials, printers, toolpaths, and even extrusion methods. We additionally create visualisations of the network's predictions to shed light on how it makes decisions., This work has been funded by the Engineering and Physical Sciences Research Council, UK Ph.D. Studentship EP/N509620/1 to D.A.J.B., Royal Society award RGS/R2/192433 to S.W.P., Academy of Medical Sciences award SBF005/1014 to S.W.P., Engineering and Physical Sciences Research Council award EP/V062123/1 to S.W.P., and an Isaac Newton Trust award to S.W.P.

We present six datasets containing telemetry data of the Mars Express Spacecraft (MEX), a spacecraft orbiting Mars operated by the European Space Agency. The data consisting of context data and thermal power consumption measurements, capture the status of the spacecraft over three Martian years, sampled at six different time resolutions that range from 1 min to 60 min. From a data analysis point-of-view, these data are challenging even for the more sophisticated state-of-the-art artificial intelligence methods. In particular, given the heterogeneity, complexity, and magnitude of the data, they can be employed in a variety of scenarios and analyzed through the prism of different machine learning tasks, such as multi-target regression, learning from data streams, anomaly detection, clustering, etc. Analyzing MEX’s telemetry data is critical for aiding very important decisions regarding the spacecraft’s status and operation, extracting novel knowledge, and monitoring the spacecraft’s health, but the data can also be used to benchmark artificial intelligence methods designed for a variety of tasks.

Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses. However, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a considerable challenge for training a well-generalised model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the AI model can be distributedly trained and independently executed at each host institution under a federated learning framework (FL) without data sharing. Here we show that our FL model outperformed all the local models by a large yield (test sensitivity /specificity in China: 0.973/0.951, in the UK: 0.730/0.942), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals leaving out the FL) and heterogeneous (acquired with contrast materials) data, provided visual explanations for decisions made by the model, and analysed the trade-offs between the model performance and the communication costs in the federated training process. Our study is based on 9,573 chest computed tomography scans (CTs) from 3,336 patients collected from 23 hospitals located in China and the UK. Collectively, our work advanced the prospects of utilising federated learning for privacy-preserving AI in digital health., Nature Machine Intelligence

Funder: Gates Cambridge Trust; doi: http://dx.doi.org/10.13039/501100005370, Funder: Office of the Provost, Johns Hopkins University; doi: http://dx.doi.org/10.13039/100012800, Our goal is to explore quantitative motor features in critically ill patients with severe brain injury (SBI). We hypothesized that computational decoding of these features would yield information on underlying neurological states and outcomes. Using wearable microsensors placed on all extremities, we recorded a median 24.1 (IQR: 22.8-25.1) hours of high-frequency accelerometry data per patient from a prospective cohort (n = 69) admitted to the ICU with SBI. Models were trained using time-, frequency-, and wavelet-domain features and levels of responsiveness and outcome as labels. The two primary tasks were detection of levels of responsiveness, assessed by motor sub-score of the Glasgow Coma Scale (GCSm), and prediction of functional outcome at discharge, measured with the Glasgow Outcome Scale-Extended (GOSE). Detection models achieved significant (AUC: 0.70 [95% CI: 0.53-0.85]) and consistent (observation windows: 12 min-9 h) discrimination of SBI patients capable of purposeful movement (GCSm > 4). Prediction models accurately discriminated patients of upper moderate disability or better (GOSE > 5) with 2-6 h of observation (AUC: 0.82 [95% CI: 0.75-0.90]). Results suggest that time series analysis of motor activity yields clinically relevant insights on underlying functional states and short-term outcomes in patients with SBI.

Radiomic image features are becoming a promising non-invasive method to obtain quantitative measurements for tumour classification and therapy response assessment in oncological research. However, despite its increasingly established application, there is a need for standardisation criteria and further validation of feature robustness with respect to imaging acquisition parameters. In this paper, the robustness of radiomic features extracted from computed tomography (CT) images is evaluated for liver tumour and muscle, comparing the values of the features in images reconstructed with two different slice thicknesses of 2.0 mm and 5.0 mm. Novel approaches are presented to address the intrinsic dependencies of texture radiomic features, choosing the optimal number of grey levels and correcting for the dependency on volume. With the optimal values and corrections, feature values are compared across thicknesses to identify reproducible features. Normalisation using muscle regions is also described as an alternative approach. With either method, a large fraction of features (75–90%) was found to be highly robust (

Machine learning methods offer great promise for fast and accurate detection and prognostication of COVID-19 from standard-of-care chest radiographs (CXR) and computed tomography (CT) images. Many articles have been published in 2020 describing new machine learning-based models for both of these tasks, but it is unclear which are of potential clinical utility. In this systematic review, we search EMBASE via OVID, MEDLINE via PubMed, bioRxiv, medRxiv and arXiv for published papers and preprints uploaded from January 1, 2020 to October 3, 2020 which describe new machine learning models for the diagnosis or prognosis of COVID-19 from CXR or CT images. Our search identified 2,212 studies, of which 415 were included after initial screening and, after quality screening, 61 studies were included in this systematic review. Our review finds that none of the models identified are of potential clinical use due to methodological flaws and/or underlying biases. This is a major weakness, given the urgency with which validated COVID-19 models are needed. To address this, we give many recommendations which, if followed, will solve these issues and lead to higher quality model development and well documented manuscripts., 35 pages, 3 figures, 2 tables, updated to the period 1 January 2020 - 3 October 2020

Organic synthesis remains a major challenge in drug discovery. Although a plethora of machine learning models have been proposed as solutions in the literature, they suffer from being opaque black-boxes. It is neither clear if the models are making correct predictions because they inferred the salient chemistry, nor is it clear which training data they are relying on to reach a prediction. This opaqueness hinders both model developers and users. In this paper, we quantitatively interpret the Molecular Transformer, the state-of-the-art model for reaction prediction. We develop a framework to attribute predicted reaction outcomes both to specific parts of reactants, and to reactions in the training set. Furthermore, we demonstrate how to retrieve evidence for predicted reaction outcomes, and understand counterintuitive predictions by scrutinising the data. Additionally, we identify Clever Hans predictions where the correct prediction is reached for the wrong reason due to dataset bias. We present a new debiased dataset that provides a more realistic assessment of model performance, which we propose as the new standard benchmark for comparing reaction prediction models., Machine learning algorithms offer new possibilities for automating reaction procedures. The present paper investigates automated reaction’s prediction with Molecular Transformer, the state-of-the-art model for reaction prediction, proposing a new debiased dataset for a realistic assessment of the model’s performance.

Array programming provides a powerful, compact and expressive syntax for accessing, manipulating and operating on data in vectors, matrices and higher-dimensional arrays. NumPy is the primary array programming library for the Python language. It has an essential role in research analysis pipelines in fields as diverse as physics, chemistry, astronomy, geoscience, biology, psychology, materials science, engineering, finance and economics. For example, in astronomy, NumPy was an important part of the software stack used in the discovery of gravitational waves1 and in the first imaging of a black hole2. Here we review how a few fundamental array concepts lead to a simple and powerful programming paradigm for organizing, exploring and analysing scientific data. NumPy is the foundation upon which the scientific Python ecosystem is constructed. It is so pervasive that several projects, targeting audiences with specialized needs, have developed their own NumPy-like interfaces and array objects. Owing to its central position in the ecosystem, NumPy increasingly acts as an interoperability layer between such array computation libraries and, together with its application programming interface (API), provides a flexible framework to support the next decade of scientific and industrial analysis., NumPy is the primary array programming library for Python; here its fundamental concepts are reviewed and its evolution into a flexible interoperability layer between increasingly specialized computational libraries is discussed.

Gene expression profiling of tumours is an important source of information for cancer patient stratification. Detecting subtle alterations of gene expression remains a challenge, however. Here, we propose a novel tool for high-sensitivity detection of differential pathway activity in tumours. For a pathway defined by a collection of genes, the samples are projected onto a low-dimensional manifold in the subspace spanned by those genes. For each sample, a score is next found by calculating the distance between each projected sample and the projection of a subgroup of reference samples. Depending on the aim of the analysis and the available data, the reference samples may represent e.g. normal tissue or tumour samples with a particular genotype or phenotype. The proposed tool, PathTracer, is demonstrated on gene expression data from 1952 invasive breast cancer samples, 10 DCIS, 9 benign samples and 144 tumour adjacent normal breast tissue samples. PathTracer scores are shown to predict survival, clinical subtypes, cellular proliferation and genomic instability. Furthermore, predictions are shown to outperform those obtained with other comparable methods.

Cyber-physical systems embed software into the physical world. They appear in a wide range of applications such as smart grids, robotics, and intelligent manufacturing. Cyber-physical systems have proved resistant to modeling due to their intrinsic complexity arising from the combination of physical and cyber components and the interaction between them. This study proposes a general framework for discovering cyber-physical systems directly from data. The framework involves the identification of physical systems as well as the inference of transition logics. It has been applied successfully to a number of real-world examples. The novel framework seeks to understand the underlying mechanism of cyber-physical systems as well as make predictions concerning their state trajectories based on the discovered models. Such information has been proven essential for the assessment of the performance of cyber-physical systems; it can potentially help debug in the implementation procedure and guide the redesign to achieve the required performance., Discovery of hybrid dynamical models for real-world cyber-physical systems remains a challenge. This paper proposes a general framework for automating mechanistic modeling of hybrid dynamical systems from observed data with low computational complexity and noise resilience.

Machine learning methods offer great promise for fast and accurate detection and prognostication of coronavirus disease 2019 (COVID-19) from standard-of-care chest radiographs (CXR) and chest computed tomography (CT) images. Many articles have been published in 2020 describing new machine learning-based models for both of these tasks, but it is unclear which are of potential clinical utility. In this systematic review, we consider all published papers and preprints, for the period from 1 January 2020 to 3 October 2020, which describe new machine learning models for the diagnosis or prognosis of COVID-19 from CXR or CT images. All manuscripts uploaded to bioRxiv, medRxiv and arXiv along with all entries in EMBASE and MEDLINE in this timeframe are considered. Our search identified 2,212 studies, of which 415 were included after initial screening and, after quality screening, 62 studies were included in this systematic review. Our review finds that none of the models identified are of potential clinical use due to methodological flaws and/or underlying biases. This is a major weakness, given the urgency with which validated COVID-19 models are needed. To address this, we give many recommendations which, if followed, will solve these issues and lead to higher-quality model development and well-documented manuscripts.