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

General General

Machine learning efficiently corrects LIBS spectrum variation due to change of laser fluence.

In Optics express

This work demonstrates the efficiency of machine learning in the correction of spectral intensity variations in laser-induced breakdown spectroscopy (LIBS) due to changes of the laser pulse energy, such changes can occur over a wide range, from 7.9 to 71.1 mJ in our experiment. The developed multivariate correction model led to a precise determination of the concentration of a minor element (magnesium for instance) in the samples (aluminum alloys in this work) with a precision of 6.3% (relative standard deviation, RSD) using the LIBS spectra affected by the laser pulse energy change. A comparison to the classical univariate corrections with laser pulse energy, total spectral intensity, ablation crater volume and plasma temperature, further highlights the significance of the developed method.

Yue Zengqi, Sun Chen, Gao Liang, Zhang Yuqing, Shabbir Sahar, Xu Weijie, Wu Mengting, Zou Long, Tan Yongqi, Chen Fengye, Yu Jin

2020-May-11

General General

NetMHCpan-4.1 and NetMHCIIpan-4.0: improved predictions of MHC antigen presentation by concurrent motif deconvolution and integration of MS MHC eluted ligand data.

In Nucleic acids research ; h5-index 217.0

Major histocompatibility complex (MHC) molecules are expressed on the cell surface, where they present peptides to T cells, which gives them a key role in the development of T-cell immune responses. MHC molecules come in two main variants: MHC Class I (MHC-I) and MHC Class II (MHC-II). MHC-I predominantly present peptides derived from intracellular proteins, whereas MHC-II predominantly presents peptides from extracellular proteins. In both cases, the binding between MHC and antigenic peptides is the most selective step in the antigen presentation pathway. Therefore, the prediction of peptide binding to MHC is a powerful utility to predict the possible specificity of a T-cell immune response. Commonly MHC binding prediction tools are trained on binding affinity or mass spectrometry-eluted ligands. Recent studies have however demonstrated how the integration of both data types can boost predictive performances. Inspired by this, we here present NetMHCpan-4.1 and NetMHCIIpan-4.0, two web servers created to predict binding between peptides and MHC-I and MHC-II, respectively. Both methods exploit tailored machine learning strategies to integrate different training data types, resulting in state-of-the-art performance and outperforming their competitors. The servers are available at http://www.cbs.dtu.dk/services/NetMHCpan-4.1/ and http://www.cbs.dtu.dk/services/NetMHCIIpan-4.0/.

Reynisson Birkir, Alvarez Bruno, Paul Sinu, Peters Bjoern, Nielsen Morten

2020-May-14

General General

A novel deep learning method for predictive modeling of microbiome data.

In Briefings in bioinformatics

With the development and decreasing cost of next-generation sequencing technologies, the study of the human microbiome has become a rapid expanding research field, which provides an unprecedented opportunity in various clinical applications such as drug response predictions and disease diagnosis. It is thus essential and desirable to build a prediction model for clinical outcomes based on microbiome data that usually consist of taxon abundance and a phylogenetic tree. Importantly, all microbial species are not uniformly distributed in the phylogenetic tree but tend to be clustered at different phylogenetic depths. Therefore, the phylogenetic tree represents a unique correlation structure of microbiome, which can be an important prior to improve the prediction performance. However, prediction methods that consider the phylogenetic tree in an efficient and rigorous way are under-developed. Here, we develop a novel deep learning prediction method MDeep (microbiome-based deep learning method) to predict both continuous and binary outcomes. Conceptually, MDeep designs convolutional layers to mimic taxonomic ranks with multiple convolutional filters on each convolutional layer to capture the phylogenetic correlation among microbial species in a local receptive field and maintain the correlation structure across different convolutional layers via feature mapping. Taken together, the convolutional layers with its built-in convolutional filters capture microbial signals at different taxonomic levels while encouraging local smoothing and preserving local connectivity induced by the phylogenetic tree. We use both simulation studies and real data applications to demonstrate that MDeep outperforms competing methods in both regression and binary classifications. Availability and Implementation: MDeep software is available at https://github.com/lichen-lab/MDeep Contact:chen61@iu.edu.

Wang Ye, Bhattacharya Tathagata, Jiang Yuchao, Qin Xiao, Wang Yue, Liu Yunlong, Saykin Andrew J, Chen Li

2020-May-14

deep learning, machine learning, microbiome, phylogeny, prediction

General General

Health Care Employees' Perceptions of the Use of Artificial Intelligence Applications: Survey Study.

In Journal of medical Internet research ; h5-index 88.0

BACKGROUND : The advancement of health care information technology and the emergence of artificial intelligence has yielded tools to improve the quality of various health care processes. Few studies have investigated employee perceptions of artificial intelligence implementation in Saudi Arabia and the Arabian world. In addition, limited studies investigated the effect of employee knowledge and job title on the perception of artificial intelligence implementation in the workplace.

OBJECTIVE : The aim of this study was to explore health care employee perceptions and attitudes toward the implementation of artificial intelligence technologies in health care institutions in Saudi Arabia.

METHODS : An online questionnaire was published, and responses were collected from 250 employees, including doctors, nurses, and technicians at 4 of the largest hospitals in Riyadh, Saudi Arabia.

RESULTS : The results of this study showed that 3.11 of 4 respondents feared artificial intelligence would replace employees and had a general lack of knowledge regarding artificial intelligence. In addition, most respondents were unaware of the advantages and most common challenges to artificial intelligence applications in the health sector, indicating a need for training. The results also showed that technicians were the most frequently impacted by artificial intelligence applications due to the nature of their jobs, which do not require much direct human interaction.

CONCLUSIONS : The Saudi health care sector presents an advantageous market potential that should be attractive to researchers and developers of artificial intelligence solutions.

Abdullah Rana, Fakieh Bahjat

2020-May-14

Saudi Arabia, artificial intelligence, employees, healthcare sector, perception

Public Health Public Health

Artificial Intelligence and Health Technology Assessment: Anticipating a New Level of Complexity.

In Journal of medical Internet research ; h5-index 88.0

Artificial Intelligence (AI) is seen as a strategic lever to improve access, quality and efficiency of care and services, and to build learning and value-based health systems. Many studies have examined the technical performance of AI within an experimental context. These studies provide limited insights into the issues that its use in a real-world context of care and services (RWCCS) raises. To help decision-makers address these issues in a systemic and holistic way, this viewpoint article relies on the Health Technology Assessment (HTA) core model to contrast the expectations of the health sector towards the use of AI with the risks that should be mitigated for its responsible deployment. The analysis adopts the perspective of payers (eg, health system organizations and agencies) because of their central role in regulating, financing and reimbursing novel technologies. This article suggests that AI-based systems should be seen as a health system transformation lever, rather than a discrete set of technological devices. Their use could bring significant changes and impacts at several levels: technological, clinical, human and cognitive (patient and clinician), professional and organizational, economic, legal and ethical. The assessment of the AI value proposition should thus go beyond technical performance and price logics by performing a holistic analysis of value in a RWCCS. In order to guide AI developments, generate knowledge and draw lessons that can be translated into action, the right political, regulatory, organizational, clinical and technological conditions for innovation should be created as a first step.

Alami Hassane, Lehoux Pascale, Auclair Yannick, de Guise Michèle, Gagnon Marie-Pierre, Shaw James, Roy Denis, Fleet Richard, Ag Ahmed Mohamed Ali, Fortin Jean-Paul

2020-May-13

General General

Interpret Neural Networks by Extracting Critical Subnetworks.

In IEEE transactions on image processing : a publication of the IEEE Signal Processing Society

In recent years, deep neural networks have achieved excellent performance in many fields of artificial intelligence. The requirements for the interpretability and robustness of neural networks are also increasing. In this paper, we propose to understand the functional mechanism of neural networks by extracting critical subnetworks. Specifically, we denote the critical subnetworks as a group of important channels across layers such that if they were suppressed to zeros, the final test performance would deteriorate severely. This novel perspective can not only reveal the layerwise semantic behavior within the model but also present more accurate visual explanations appearing in the data through attribution methods. Moreover, we propose two adversarial example detection methods based on the properties of sample-specific and class-specific subnetworks, which provides the possibility for increasing the model robustness.

Wang Yulong, Su Hang, Zhang Bo, Hu Xiaolin

2020-May-14