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

General General

Interpretable detection of novel human viruses from genome sequencing data

bioRxiv Preprint

Viruses evolve extremely quickly, so reliable methods for viral host prediction are necessary to safeguard biosecurity and biosafety alike. Novel human-infecting viruses are difficult to detect with standard bioinformatics workflows. Here, we predict whether a virus can infect humans directly from next-generation sequencing reads. We show that deep neural architectures significantly outperform both shallow machine learning and standard, homology-based algorithms, cutting the error rates in half and generalizing to taxonomic units distant from those presented during training. Further, we develop a suite of interpretability tools and show that it can be applied also to other models beyond the host prediction task. We propose a new approach for convolutional filter visualization to disentangle the information content of each nucleotide from its contribution to the final classification decision. Nucleotide-resolution maps of the learned associations between pathogen genomes and the infectious phenotype can be used to detect regions of interest in novel agents, for example the SARS-CoV-2 coronavirus, unknown before it caused a COVID-19 pandemic in 2020. All methods presented here are implemented as easy-to-install packages enabling analysis of NGS datasets without requiring any deep learning skills, but also allowing advanced users to easily train and explain new models for genomics.

Bartoszewicz, J. M.; Seidel, A.; Renard, B. Y.


General General

Generating Longitudinal Atrophy Evaluation Datasets on Brain Magnetic Resonance Images Using Convolutional Neural Networks and Segmentation Priors.

In Neuroinformatics

Brain atrophy quantification plays a fundamental role in neuroinformatics since it permits studying brain development and neurological disorders. However, the lack of a ground truth prevents testing the accuracy of longitudinal atrophy quantification methods. We propose a deep learning framework to generate longitudinal datasets by deforming T1-w brain magnetic resonance imaging scans as requested through segmentation maps. Our proposal incorporates a cascaded multi-path U-Net optimised with a multi-objective loss which allows its paths to generate different brain regions accurately. We provided our model with baseline scans and real follow-up segmentation maps from two longitudinal datasets, ADNI and OASIS, and observed that our framework could produce synthetic follow-up scans that matched the real ones (Total scans= 584; Median absolute error: 0.03 ± 0.02; Structural similarity index: 0.98 ± 0.02; Dice similarity coefficient: 0.95 ± 0.02; Percentage of brain volume change: 0.24 ± 0.16; Jacobian integration: 1.13 ± 0.05). Compared to two relevant works generating brain lesions using U-Nets and conditional generative adversarial networks (CGAN), our proposal outperformed them significantly in most cases (p < 0.01), except in the delineation of brain edges where the CGAN took the lead (Jacobian integration: Ours - 1.13 ± 0.05 vs CGAN - 1.00 ± 0.02; p < 0.01). We examined whether changes induced with our framework were detected by FAST, SPM, SIENA, SIENAX, and the Jacobian integration method. We observed that induced and detected changes were highly correlated (Adj. R2 > 0.86). Our preliminary results on harmonised datasets showed the potential of our framework to be applied to various data collections without further adjustment.

Bernal Jose, Valverde Sergi, Kushibar Kaisar, Cabezas Mariano, Oliver Arnau, Lladó Xavier


Brain MRI, Cerebral atrophy, Convolutional neural networks, Image generation, Longitudinal atrophy synthesis

General General

A bibliometric analysis of comparative research on the evolution of international and Chinese green supply chain research hotspots and frontiers.

In Environmental science and pollution research international

Green supply chain (GSC), one of the most vital sub-topics of sustainable development, indicates people provoking on the rationality of business practices and resource consumption patterns. Under the background of economy globalization, developing countries, especially China, severely affected by green barriers became the global focus. A systematic review of articles about GSC which published in leading journals of Web of Science Core Collection (WoSCC) and China Knowledge Resource Infrastructure (CNKI) is proposed for exploring publishing trends, the distribution of authors and journals, research topics, and hotspots and predicting frontiers by utilizing VOSviewer, Sci2, and CiteSpace. The results show that (1) there are differences in the attention of GSC between international and Chinese academia. (2) "Green" is referred to environmental friendly practices in international academia. Scholars advocate to promote management to strengthen cooperation among GSC members and boost technology investment to improve the comprehensive performance; however, specific practices such as "low-carbon," "emission reduction," "recycling," and "remanufacture" are referred to environmental friendly behaviors in Chinese academia. Scholars expect to avoid enterprises' short-term profit compression relying on government subsidies and make contracts to share environment protection cost equally out for ensuring GSC stable operation. (3) Exploring collaboration among GSC members using complex operation research and artificial intelligence will be international research frontier. Relevant papers are to provide Chinese research with merely innovation in methodology. Besides, the "government-enterprise-university-research institute-customer-economy" management mode proposed by development countries like China will enrich the international GSC research scope, leading international GSC knowledge structure to change. The contribution of this study is to afford reference for future research on GSC.

Zhou Xinyu, Li Tuochen, Ma Xiaoqi


Bibliometrics, Evolution of frontiers, Green supply chain, Mapping knowledge domain, Research hotspots, Visualization

Ophthalmology Ophthalmology

Evaluation of a novel artificial intelligence-based screening system for diabetic retinopathy in community of China: a real-world study.

In International ophthalmology

PURPOSE : To evaluate the performance of an AI-based diabetic retinopathy (DR) grading model in real-world community clinical setting.

METHODS : Participants with diabetes on record in the chosen community were recruited by health care staffs in a primary clinic of Zhengzhou city, China. Retinal images were prospectively collected during December 2018 and April 2019 based on intent-to-screen principle. A pre-validated AI system based on deep learning algorithm was deployed to screen DR graded according to the International Clinical Diabetic Retinopathy scale. Kappa value of DR severity, the sensitivity, specificity of detecting referable DR (RDR) and any DR were generated based on the standard of the majority manual grading decision of a retina specialist panel.

RESULTS : Of the 193 eligible participants, 173 (89.6%) were readable with at least one eye image. Mean [SD] age was 69.3 (9.0) years old. Total of 321 eyes (83.2%) were graded both by AI and the specialist panel. The κ value in eye image grading was 0.715. The sensitivity, specificity and area under curve for detection of RDR were 84.6% (95% CI: 54.6- 98.1%), 98.0% (95% CI: 94.3-99.6%) and 0.913 (95% CI: 0.797-1.000), respectively. For detection of any DR, the upper indicators were 90.0% (95% CI: 68.3-98.8), 96.6% (95% CI: 92.1-98.9) and 0.933 (95% CI: 0.933-1.000), respectively.

CONCLUSION : The AI system showed relatively good consistency with ophthalmologist diagnosis in DR grading, high specificity and acceptable sensitivity for identifying RDR and any DR.

TRANSLATIONAL RELEVANCE : It is feasible to apply AI-based DR screening in community.

PRECIS : Deployed in community real-world clinic setting, AI-based DR screening system showed high specificity and acceptable sensitivity in identifying RDR and any DR. Good DR diagnostic consistency was found between AI and manual grading. These prospective evidences were essential for regulatory approval.

Ming Shuai, Xie Kunpeng, Lei Xiang, Yang Yingrui, Zhao Zhaoxia, Li Shuyin, Jin Xuemin, Lei Bo


Artificial intelligence, Deep neural network, Diabetic retinopathy, Fundus photography, Rreal-world study

General General

Estimating aortic thoracic aneurysm rupture risk using tension-strain data in physiological pressure range: an in vitro study.

In Biomechanics and modeling in mechanobiology ; h5-index 36.0

Previous studies have shown that the rupture properties of an ascending thoracic aortic aneurysm (ATAA) are strongly correlated with the pre-rupture response features. In this work, we present a two-step machine learning method to predict where the rupture is likely to occur in ATAA and what safety reserve the structure may have. The study was carried out using ATAA specimens from 15 patients who underwent surgical intervention. Through inflation test, full-field deformation data and post-rupture images were collected, from which the wall tension and surface strain distributions were computed. The tension-strain data in the pressure range of 9-18 kPa were fitted to a third-order polynomial to characterize the response properties. It is hypothesized that the region where rupture is prone to initiate is associated with a high level of tension buildup. A machine learning method is devised to predict the peak risk region. The predicted regions were found to match the actual rupture sites in 13 samples out of the total 15. In the second step, another machine learning model is utilized to predict the tissue's rupture strength in the peak risk region. Results suggest that the ATAA rupture risk can be reasonably predicted using tension-strain response in the physiological range. This may open a pathway for evaluating the ATAA rupture propensity using information of in vivo response.

He Xuehuan, Avril Stephane, Lu Jia


ATAA, Machine learning, Rupture, Strength

Surgery Surgery

New modalities and directions for dystonia care.

In Journal of neural transmission (Vienna, Austria : 1996)

Dystonia is an abnormal involuntary movement or posture owing to sustained or intermittent muscle contraction. Standard treatment for dystonia includes medications, such as levodopa, anticholinergic and antiepileptic drugs, botulinum toxin, and baclofen pump, and surgeries, such as lesioning surgery and deep-brain stimulation. New treatment modalities aimed toward improving dystonia care in the future are under investigation. There are two main axes to improve dystonia care; one is non-invasive neuromodulation, such as transcranial magnetic stimulation, transcranial electrical stimulation, and transcutaneous electrical nerve stimulation. The other is a quantitative evaluation of dystonia using a wearable device and motion-capturing system, which can be empowered by artificial intelligence. In this article, the current status of these axes will be reviewed.

Oyama Genko, Hattori Nobutaka


AI, Quantitative analysis, TBS, TENS, Wearable device, rTMS, tDCDS