Machine learning for active matter published on Nature Machine Intelligence

Active-matter systems and phenomena: interaction with complex environments.

Machine learning for active matter
Frank Cichos, Kristian Gustavsson, Bernhard Mehlig & Giovanni Volpe
Nature Machine Intelligence 2, 94–103 (2020)
doi: https://doi.org/10.1038/s42256-020-0146-9

The availability of large datasets has boosted the application of machine learning in many fields and is now starting to shape active-matter research as well. Machine learning techniques have already been successfully applied to active-matter data—for example, deep neural networks to analyse images and track objects, and recurrent nets and random forests to analyse time series. Yet machine learning can also help to disentangle the complexity of biological active matter, helping, for example, to establish a relation between genetic code and emergent bacterial behaviour, to find navigation strategies in complex environments, and to map physical cues to animal behaviours. In this Review, we highlight the current state of the art in the application of machine learning to active matter and discuss opportunities and challenges that are emerging. We also emphasize how active matter and machine learning can work together for mutual benefit.

An algorithm that learns to diagnose a genetic disease

Researchers at the University of Gothenburg, together with researchers from Portugal, have now found a way to estimate the probability that a patient will suffer from a common genetic disease by training an algorithm using patient data. Continue reading (in English)

Press release:
Algoritm lär sig diagnostisera genetisk sjukdom (in Swedish)
An algorithm that learns to diagnose genetic disease (in English)

Article: Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning

Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning published in European Journal of Preventive Cardiology

Take home figure. We have exploited machine learning to obtain a reliable way to perform genetic diagnosis of familial hypercholesterolemia (FH) with a virtual genotyping in the lipid clinic.

Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning
Anna Pina, Saga Helgadottir, Rosellina Margherita Mancina, Chiara Pavanello, Carlo Pirazzi, Tiziana Montalcini, Roberto Henriques, Laura Calabresi, Olov Wiklund, M Paula Macedo, Luca Valenti, Giovanni Volpe, Stefano Romeo
European Journal of Preventive Cardiology (2020)
doi: https://doi.org/10.1177/2047487319898951

Aims

Familial hypercholesterolemia (FH) is the most common genetic disorder of lipid metabolism. The gold standard for FH diagnosis is genetic testing, available, however, only in selected university hospitals. Clinical scores – for example, the Dutch Lipid Score – are often employed as alternative, more accessible, albeit less accurate FH diagnostic tools. The aim of this study is to obtain a more reliable approach to FH diagnosis by a “virtual” genetic test using machine-learning approaches.

Methods and results

We used three machine-learning algorithms (a classification tree (CT), a gradient boosting machine (GBM), a neural network (NN)) to predict the presence of FH-causative genetic mutations in two independent FH cohorts: the FH Gothenburg cohort (split into training data (N = 174) and internal test (N = 74)) and the FH-CEGP Milan cohort (external test, N = 364). By evaluating their area under the receiver operating characteristic (AUROC) curves, we found that the three machine-learning algorithms performed better (AUROC 0.79 (CT), 0.83 (GBM), and 0.83 (NN) on the Gothenburg cohort, and 0.70 (CT), 0.78 (GBM), and 0.76 (NN) on the Milan cohort) than the clinical Dutch Lipid Score (AUROC 0.68 and 0.64 on the Gothenburg and Milan cohorts, respectively) in predicting carriers of FH-causative mutations.

Conclusion

In the diagnosis of FH-causative genetic mutations, all three machine-learning approaches we have tested outperform the Dutch Lipid Score, which is the clinical standard. We expect these machine-learning algorithms to provide the tools to implement a virtual genetic test of FH. These tools might prove particularly important for lipid clinics without access to genetic testing.