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

General General

Self-healing bottlebrush polymer networks enabled via a side-chain interlocking design.

In Materials horizons

Exploring novel healing mechanisms is a constant impetus for the development of self-healing materials. Herein, we find that side-chain interlocking of bottlebrush polymers can form a dynamic network and thereby serve as a driving force for the self-healing process of the materials. Molecular dynamics simulation indicates that the interlocking is formed by the interpenetration between the long side chains of adjacent molecules and stabilized by van der Waals interactions and molecular entanglements of side chains. The interlocking can be tailored by changing the length and density of the side chains through atom transfer radical polymerization. As a result, the optimized bottlebrush polymer shows a healing efficiency of up to 100%. Unlike chemical interactions, side-chain interlocking eliminates the introduction of specific chemical groups. Therefore, bottlebrush polymers can even self-heal under harsh aqueous conditions, including acid and alkali solutions. Moreover, the highly dynamic side-chain interlocking enables bottlebrush polymers to efficiently dissipate vibration energy, and thus they can be used as damping materials. Collectively, side-chain interlocking expands the scope of physical interactions in self-healing materials and hews out a versatile way for polymers to accomplish self-healing capability in various environments.

Xiong Hui, Yue Tongkui, Wu Qi, Zhang Linjun, Xie Zhengtian, Liu Jun, Zhang Liqun, Wu Jinrong

2023-Mar-22

General General

A high-performance deep-learning-based pipeline for whole-brain vasculature segmentation at the capillary resolution.

In Bioinformatics (Oxford, England)

MOTIVATION : Reconstructing and analyzing all blood vessels throughout the brain is significant for understanding brain function, revealing the mechanisms of brain disease, and mapping the whole-brain vascular atlas. Vessel segmentation is a fundamental step in reconstruction and analysis. The whole-brain optical microscopic imaging method enables the acquisition of whole-brain vessel images at the capillary resolution. Due to the massive amount of data and the complex vascular features generated by high-resolution whole-brain imaging, achieving rapid and accurate segmentation of whole-brain vasculature becomes a challenge.

RESULTS : We introduce HP-VSP, a high-performance vessel segmentation pipeline based on deep learning. The pipeline consists of three processes: data blocking, block prediction, and block fusion. We used parallel computing to parallelize this pipeline to improve the efficiency of whole-brain vessel segmentation. We also designed a lightweight deep neural network based on multi-resolution vessel feature extraction to segment vessels at different scales throughout the brain accurately. We validated our approach on whole-brain vascular data from three transgenic mice collected by HD-fMOST. The results show that our proposed segmentation network achieves the state-of-the-art level under various evaluation metrics. In contrast, the parameters of the network are only 1% of those of similar networks. The established segmentation pipeline could be used on various computing platforms and complete the whole-brain vessel segmentation in 3 hours. We also demonstrated that our pipeline could be applied to the vascular analysis.

AVAILABILITY : The dataset is available at http://atlas.brainsmatics.org/a/li2301. The source code is freely available at https://github.com/visionlyx/HP-VSP.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Bioinformatics online.

Li Yuxin, Liu Xuhua, Jia Xueyan, Jiang Tao, Wu Jianghao, Zhang Qianlong, Li Junhuai, Li Xiangning, Li Anan

2023-Mar-22

General General

Profiling mechanisms that drive acute oral toxicity in mammals and its prediction via machine learning.

In Toxicological sciences : an official journal of the Society of Toxicology

We present a mechanistic machine-learning quantitative structure-activity relationship (QSAR) model to predict mammalian acute oral toxicity. We trained our model using a rat acute toxicity database compiled by the US National Toxicology Program. We profiled the database using new and published profilers and identified the most plausible mechanisms that drive high acute toxicity (LD50 ≤ 50 mg/kg; GHS categories 1 or 2). Our QSAR model assigns primary mechanisms to compounds, followed by predicting their acute oral LD50 using a random-forest machine-learning model. These predictions were further refined based on structural and mechanistic read-across to substances within the training set. Our model is optimized for sensitivity and aims to minimize the likelihood of under-predicting the toxicity of assessed compounds. It displays high sensitivity (76.1% or 76.6% for compounds in GHS 1-2 or GHS 1-3 categories, respectively), coupled with ≥73.7% balanced accuracy. We further demonstrate the utility of undertaking a mechanistic approach when predicting the toxicity of compounds acting via a rare mode of action (aconitase inhibition). The mechanistic profilers and framework of our QSAR model are route- and toxicity endpoint-agnostic, allowing for future applications to other endpoints and routes of administration. Furthermore, we present a preliminary exploration of the potential role of metabolic clearance in acute toxicity. To the best of our knowledge, this effort represents the first accurate mechanistic QSAR model for acute oral toxicity that combines machine-learning with mode of action (MOA) assignment, while also seeking to minimize under-prediction of more highly potent substances.

Wijeyesakere Sanjeeva J, Auernhammer Tyler, Parks Amanda, Wilson Dan

2023-Mar-22

QSAR, acute toxicity, mechanistic toxicology

General General

Blood quality evaluation via on-chip classification of cell morphology using a deep learning algorithm.

In Lab on a chip

The quality of red blood cells (RBCs) in stored blood has a direct impact on the recovery of patients treated by blood transfusion, which directly reflects the quality of blood. The traditional means for blood quality evaluation involve the use of reagents and multi-step and time-consuming operations. Here, a low-cost, multi-classification, label-free and high-precision method is developed, which combines microfluidic technology and a deep learning algorithm together to recognize and classify RBCs based on morphology. The microfluidic channel is designed to effectively and controllably solve the problem of cell overlap, which has a severe negative impact on the identification of cells. The object detection model in the deep learning algorithm is optimized and used to recognize multiple RBCs simultaneously in the whole field of view, so as to classify them into six morphological subcategories and count the numbers in each subgroup. The mean average precision of the developed object detection model reaches 89.24%. The blood quality can be evaluated by calculating the morphology index (MI) according to the numbers of cells in subgroups. The validation of the method is verified by evaluating three blood samples stored for 7 days, 21 days and 42 days, which have MIs of 84.53%, 73.33% and 24.34%, respectively, indicating good agreement with the actual blood quality. This method has the merits of cell identification in a wide channel, no need for single cell alignment as the image cytometry does and it is not only applicable to the quality evaluation of RBCs, but can also be used for general cell identifications with different morphologies.

Yang Yuping, He Hong, Wang Junju, Chen Li, Xu Yi, Ge Chuang, Li Shunbo

2023-Mar-22

General General

Artificial Intelligence Teaching as part of Medical Education: A Qualitative Analysis of Expert Interviews.

In JMIR medical education

BACKGROUND : The use of artificial intelligence in medicine is expected to increase significantly in the upcoming years. Advancements in AI technology have the potential to revolutionize healthcare, from aiding in the diagnosis of certain diseases to helping with treatment decisions. Current literature suggests the integration of the subject of AI in medicine as part of the medical curriculum to prepare medical students for the opportunities and challenges related to the use of the technology within the clinical context.

OBJECTIVE : The purpose of this study was to explore the relevant knowledge and understanding of the subject of AI in medicine, and to specify curricula teaching content within medical education.

METHODS : For this research, we conducted 12 guideline-based expert interviews. Experts were defined as individuals who have been engaged in full-time academic research, development, and/or teaching in the field of artificial intelligence in medicine for at least five years. As part of the data analysis, we recorded, transcribed, and analyzed the interviews using qualitative content analysis. We used the software QCAmap and inductive category formation to analyze the data.

RESULTS : The qualitative content analysis led to the formation of three main categories ("Knowledge," "Interpretation," and "Application") with a total of nine associated subcategories. The experts interviewed cited knowledge and an understanding of the fundamentals of AI, statistics, ethics, and privacy and regulation as necessary basic knowledge that should be part of medical education. The analysis also showed that medical students need to be able to interpret as well as critically reflect on the results provided by AI, taking into account the associated risks and data basis. To enable the application of AI in medicine, medical education should promote the acquisition of practical skills, including the need for basic technological skills, as well as the development of confidence in the technology and one's related competencies.

CONCLUSIONS : The analyzed expert interviews' results suggest that medical curricula should include the topic of AI in medicine to develop the knowledge, understanding, and confidence needed to use AI in the clinical context. The results further imply an imminent need for standardization of the definition of AI as the foundation to identify, define, and teach respective content on AI within medical curricula.

Weidener Lukas, Fischer Michael

2023-Mar-21

General General

Memristor-based neural networks: a bridge from device to artificial intelligence.

In Nanoscale horizons

Since the beginning of the 21st century, there is no doubt that the importance of artificial intelligence has been highlighted in many fields, among which the memristor-based artificial neural network technology is expected to break through the limitation of von Neumann so as to realize the replication of the human brain by enabling strong parallel computing ability and efficient data processing and become an important way towards the next generation of artificial intelligence. A new type of nanodevice, namely memristor, which is based on the variability of its resistance value, not only has very important applications in nonvolatile information storage, but also presents obsessive progressiveness in highly integrated circuits, making it one of the most promising circuit components in the post-Moore era. In particular, memristors can effectively simulate neural synapses and build neural networks; thus, they can be applied for the preparation of various artificial intelligence systems. This study reviews the research progress of memristors in artificial neural networks in detail and highlights the structural advantages and frontier applications of neural networks based on memristors. Finally, some urgent problems and challenges in current research are summarized and corresponding solutions and future development trends are put forward.

Cao Zelin, Sun Bai, Zhou Guangdong, Mao Shuangsuo, Zhu Shouhui, Zhang Jie, Ke Chuan, Zhao Yong, Shao Jinyou

2023-Mar-22