Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Network effects govern the evolution of maritime trade.

In Proceedings of the National Academy of Sciences of the United States of America

Maritime transport accounts for over 80% of the world trade volume and is the backbone of the global economy. Global supply chains create a complex network of trade flows. The structure of this network impacts not only the socioeconomic development of the concerned regions but also their ecosystems. The movements of ships are a considerable source of CO2 emissions and contribute to climate change. In the wake of the announced development of Arctic shipping, the need to understand the behavior of the maritime trade network and to predict future trade flows becomes pressing. We use a unique database of daily movements of the world fleet over the period 1977-2008 and apply machine learning techniques on network data to develop models for predicting the opening of new shipping lines and for forecasting trade volume on links. We find that the evolution of this system is governed by a simple rule from network science, relying on the number of common neighbors between pairs of ports. This finding is consistent over all three decades of temporal data. We further confirm it with a natural experiment, involving traffic redirection from the port of Kobe after the 1995 earthquake. Our forecasting method enables researchers and industry to easily model effects of potential future scenarios at the level of ports, regions, and the world. Our results also indicate that maritime trade flows follow a form of random walk on the underlying network structure of sea connections, highlighting its pivotal role in the development of maritime trade.

Kosowska-Stamirowska Zuzanna


evolving networks, machine learning, maritime trade, network science, transport networks

Public Health Public Health

Simulating the Influence of Conjugative Plasmids Kinetic Values on the Multilevel Dynamics of Antimicrobial Resistance in a Membrane Computing Model.

In Antimicrobial agents and chemotherapy ; h5-index 79.0

Bacterial plasmids harboring antibiotic resistance genes are critical in the spread of antibiotic resistance. It is known that plasmids differ in their kinetic values i.e. conjugation rate, segregation rate by copy-number incompatibility with related plasmids, and rate of stochastic loss during replication. They also differ in cost to the cell in terms of reducing fitness and in the frequency of compensatory mutations compensating plasmid cost. However, we do not know how variation in these values influences the success of a plasmid and their resistance genes in complex ecosystems, as the microbiota. Genes are in plasmids, plasmids in cells, cells in bacterial populations and microbiotas, which are inside hosts, hosts in human communities at the hospital or the community, under various levels of cross-colonization and antibiotic exposure. Differences in plasmid kinetics might have consequences on the global spread of antibiotic resistance. New membrane computing methods help to predict these consequences. In our simulation, conjugation frequency of at least 10-3 influences the dominance of a strain with a resistance plasmid. Coexistence of different antibiotic resistances occur if host strains can maintain two copies of similar plasmids. Plasmid loss rates of 10-4 or 10-5 or plasmid fitness costs ≥0.06 favor plasmids located in the most abundant species. The beneficial effect of compensatory mutations for plasmid fitness cost is proportional to this cost at high mutation frequencies (10-3-10-5). The results of this computational model clearly show how changes in plasmid kinetics can modify the entire population ecology of antibiotic resistance in the hospital setting.

Campos Marcelino, San Millán Álvaro, Sempere José M, Lanza Val F, Coque Teresa M, Llorens Carlos, Baquero Fernando


General General

Pilot study: can machine learning analyses of movement discriminate between leg movements in sleep (LMS) with vs. without cortical arousals?

In Sleep & breathing = Schlaf & Atmung

PURPOSE : Clinical and animal studies indicate frequent small micro-arousals (McA) fragment sleep leading to health complications. McA in humans is defined by changes in EEG and EMG during sleep. Complex EEG recordings during the night are usually required to detect McA-limiting large-scale, prospective studies on McA and their impact on health. Even with the use of EEG, reliably measuring McA can be difficult because of low inter-scorer reliability. Surrogate measures in place of EEG could provide easier and possibly more reliable measures of McA. These have usually involved measuring heart rate and arm movements. They have not provided a reliable measurement of McA in part because they cannot adequately detect short wake periods and periods of wake after sleep onset. Leg movements in sleep (LMS) offer an attractive alternative. LMS and cortical arousal, including McA, commonly occur together. Not all McA occur with LMS, but the most clinically significant ones may be those with LMS [1]. Conversely, most LMS do not occur with McA, but LMS vary considerably in their characteristics. Evaluating LMS characteristics may serve to identify the LMS associated with McA. The use of standard machine learning approaches seems appropriate for this particular task. This proof-of-concept pilot project aims to determine the feasibility of detecting McA from machine learning methods analyzing movement characteristics of the LMS.

METHODS : This study uses a small but diverse group of subjects to provide a large variety of LMS and McA adequate for supervised machine learning. LMS measurements were obtained from a new advanced technology in the RestEaZe™ leg band that integrates gyroscope, accelerometer, and capacitance measurements. Eleven RestEaZe™ LMS features were selected for logistic regression analyses.

RESULTS : With the optimum logit probability threshold selected, the system accurately detected 76% of the McA matching the accuracy of trained visual inter-scorer reliability (71-76%). The classifier provided a sensitivity of 76% and a specificity of 86% for the identification of the LMS with McA. The classifier identified regions in sleep with high versus low rates of LMS with McA, indicating possible areas of fragmented versus undisturbed restful sleep.

CONCLUSION : These pilot data are encouraging as a preliminary proof-of-concept for using advanced machine learning analyses of LMS to identify sleep fragmented by McA.

Jha Amitanshu, Banerjee Nilanjan, Feltch Cody, Robucci Ryan, Earley Christopher J, Lam Janet, Allen Richard


Cortical arousal, Leg movements in sleep, Machine learning, Movement analyses, PLMS, RestEaZe™ analyses

General General

A review of epileptic seizure detection using machine learning classifiers.

In Brain informatics

Epilepsy is a serious chronic neurological disorder, can be detected by analyzing the brain signals produced by brain neurons. Neurons are connected to each other in a complex way to communicate with human organs and generate signals. The monitoring of these brain signals is commonly done using Electroencephalogram (EEG) and Electrocorticography (ECoG) media. These signals are complex, noisy, non-linear, non-stationary and produce a high volume of data. Hence, the detection of seizures and discovery of the brain-related knowledge is a challenging task. Machine learning classifiers are able to classify EEG data and detect seizures along with revealing relevant sensible patterns without compromising performance. As such, various researchers have developed number of approaches to seizure detection using machine learning classifiers and statistical features. The main challenges are selecting appropriate classifiers and features. The aim of this paper is to present an overview of the wide varieties of these techniques over the last few years based on the taxonomy of statistical features and machine learning classifiers-'black-box' and 'non-black-box'. The presented state-of-the-art methods and ideas will give a detailed understanding about seizure detection and classification, and research directions in the future.

Siddiqui Mohammad Khubeb, Morales-Menendez Ruben, Huang Xiaodi, Hussain Nasir


Applications of machine learning on epilepsy, Black-box and non-black-box classifiers, EEG signals, Epilepsy, Seizure detection, Seizure localization, Statistical features

General General

Genomic analysis of the natural history of attention-deficit/hyperactivity disorder using Neanderthal and ancient Homo sapiens samples.

In Scientific reports ; h5-index 158.0

Attention-deficit/hyperactivity disorder (ADHD) is an impairing neurodevelopmental condition highly prevalent in current populations. Several hypotheses have been proposed to explain this paradox, mainly in the context of the Paleolithic versus Neolithic cultural shift but especially within the framework of the mismatch theory. This theory elaborates on how a particular trait once favoured in an ancient environment might become maladaptive upon environmental changes. However, given the lack of genomic data available for ADHD, these theories have not been empirically tested. We took advantage of the largest GWAS meta-analysis available for this disorder consisting of over 20,000 individuals diagnosed with ADHD and 35,000 controls, to assess the evolution of ADHD-associated alleles in European populations using archaic, ancient and modern human samples. We also included Approximate Bayesian computation coupled with deep learning analyses and singleton density scores to detect human adaptation. Our analyses indicate that ADHD-associated alleles are enriched in loss of function intolerant genes, supporting the role of selective pressures in this early-onset phenotype. Furthermore, we observed that the frequency of variants associated with ADHD has steadily decreased since Paleolithic times, particularly in Paleolithic European populations compared to samples from the Neolithic Fertile Crescent. We demonstrate this trend cannot be explained by African admixture nor Neanderthal introgression, since introgressed Neanderthal alleles are enriched in ADHD risk variants. All analyses performed support the presence of long-standing selective pressures acting against ADHD-associated alleles until recent times. Overall, our results are compatible with the mismatch theory for ADHD but suggest a much older time frame for the evolution of ADHD-associated alleles compared to previous hypotheses.

Esteller-Cucala Paula, Maceda Iago, Børglum Anders D, Demontis Ditte, Faraone Stephen V, Cormand Bru, Lao Oscar


General General

PTB-XL, a large publicly available electrocardiography dataset.

In Scientific data

Electrocardiography (ECG) is a key non-invasive diagnostic tool for cardiovascular diseases which is increasingly supported by algorithms based on machine learning. Major obstacles for the development of automatic ECG interpretation algorithms are both the lack of public datasets and well-defined benchmarking procedures to allow comparison s of different algorithms. To address these issues, we put forward PTB-XL, the to-date largest freely accessible clinical 12-lead ECG-waveform dataset comprising 21837 records from 18885 patients of 10 seconds length. The ECG-waveform data was annotated by up to two cardiologists as a multi-label dataset, where diagnostic labels were further aggregated into super and subclasses. The dataset covers a broad range of diagnostic classes including, in particular, a large fraction of healthy records. The combination with additional metadata on demographics, additional diagnostic statements, diagnosis likelihoods, manually annotated signal properties as well as suggested folds for splitting training and test sets turns the dataset into a rich resource for the development and the evaluation of automatic ECG interpretation algorithms.

Wagner Patrick, Strodthoff Nils, Bousseljot Ralf-Dieter, Kreiseler Dieter, Lunze Fatima I, Samek Wojciech, Schaeffter Tobias