How AI is making 2D materials stronger: An AI-driven framework to improve material design
Peer-Reviewed Publication
Updates every hour. Last Updated: 26-Jun-2025 22:10 ET (27-Jun-2025 02:10 GMT/UTC)
A research team from ShanghaiTech University has created a new method for designing two-dimensional patterned hollow structures (2D-PHS) with improved mechanical properties for aerospace and automotive applications. By using Conditional Generative Adversarial Networks (cGAN) and Deep Q-Networks (DQN), they optimized the design of 2D-PHS much faster than traditional finite element analysis (FEA). Their optimization enhanced stress uniformity by 4.3% and reduced maximum stress concentrations by 23.1%. These improvements were validated through simulations and tensile tests on 3D-printed samples, which showed tensile strength increased from 5.9 to 6.6 MPa. This study highlights the effectiveness of AI in efficient material design.
Precise tumor diagnosis and treatment require the support of abundant molecular information. However, conventional molecular diagnostic technologies gradually fail to satisfy the demands of clinical therapy due to limited detection performance. Benefiting from highly specific target sequence recognition and efficient cis/trans cleavage activity, CRISPR/Cas system has been widely employed to construct novel molecular diagnostic strategies, hailed as the “next-generation molecular diagnostic technology”. This review focuses on recent advances in CRISPR molecular diagnostic systems for the detection of tumor variant gene, protein, and liquid biopsy biomarker, and outlines strategies for CRISPR in situ molecular detection. In addition, we explore general principles and development trends in the construction of CRISPR molecular diagnostic system and emphasize the revolutionary impact that it has brought to the field of molecular diagnostics.
This review explores the interplay between COVID-19 and malaria, with a focus on pregnant women. The concurrent infection of SARS-CoV-2 and malaria presents significant challenges in diagnosis, treatment, and management due to overlapping symptoms and complex immune responses. Genetic factors, particularly variations in the angiotensin-converting enzyme 2 (ACE2) receptor, play a crucial role in determining disease susceptibility and severity. Malaria-induced immunomodulation may influence the clinical progression of COVID-19, though the precise impact remains uncertain. The review emphasizes the need for integrated diagnostic and therapeutic approaches to effectively manage co-infections and improve maternal and fetal health outcomes. It underscores the importance of timely intervention and enhanced diagnostic methods to better understand and address these interactions. This review aims to bridge gaps in current knowledge and pave the way for future research and targeted therapeutic interventions, addressing a significant yet often overlooked public health challenge.
In May 2025, the Journal for ImmunoTherapy of Cancer published a pioneering study entitled “NeoPred: dual-phase CT AI forecasts pathologic response to neoadjuvant chemo-immunotherapy in NSCLC”, led by Professor Jianxing He’s team from the First Affiliated Hospital of Guangzhou Medical University / National Center for Respiratory Medicine.
The study introduces NeoPred, a multimodal artificial intelligence model that combines dual-phase CT scans (pre-treatment and pre-surgery) and clinical features to predict major pathological response (MPR) before surgery in patients undergoing neoadjuvant chemo-immunotherapy for non-small cell lung cancer (NSCLC).
Corresponding Authors: Prof. Jianxing He, Dr. Hengrui Liang Co-First Authors: Dr. Jianqi Zheng, Mr. Zeping Yan, Mr. Runchen Wang Collaborating Institutions: Shanghai Chest Hospital, Liaoning Cancer Hospital, First Affiliated Hospital of Xi’an Jiaotong University
In order to explore recycling solutions for used lithium-ion batteries (LIBs), a tribocatalytic method is proposed by researchers. Using ZnO nanoparticles as catalysts, the leaching rates of lithium and cobalt in lithium cobaltate batteries reached 95% and 84%, respectively. In Li-Co-Mn-Ni batteries, the leaching rates of lithium, cobalt, manganese and nickel were 96.61%, 90.00%, 76.06% and 61.78%, respectively. In the acid leaching system, the lowest unoccupied molecular orbital (LUMO) and the highest occupied molecular orbital (HOMO) of citric acid (CA) were in more appropriate positions, indicating that CA is more prone to redox reactions when rubbed on the surface of zinc oxide. Compared to H2O, CA is more electrostatically polarized and can participate in more reactions through electron transfer on the ZnO surface. First-principle calculations of adsorption energies show that the interactions are stronger when CA molecules are located on the LCO (110) surface. The combination of theoretical calculations and experiments verified that the tribocatalytic weak acid leaching process is an effective ion leaching scheme. The free radicals generated during the catalytic process promoted the leaching of metal ions, thus enabling the recycling of cathode materials for lithium-ion batteries. In addition, this method has great potential for the reduction and leaching of ions.
Materials and Solidification, an international journal dedicated to advancing research in solidification theory, materials design, and processing technology, has officially launched its inaugural issue. Published by Tsinghua University Press and supported by the State Key Laboratory of Solidification Processing, Northwestern Polytechnical University, the journal is led by Editor-in-Chief Prof. Jinshan Li and Executive Editor Prof. Junjie Wang. It aims to serve as a high-level academic platform for global researchers and engineers to drive innovations in solidification science and its industrial applications.
A research team from Shanghai Jiao Tong University has achieved a groundbreaking feat in quantum materials by growing ultrathin CrTe2 films on NbSe2 substrates using molecular beam epitaxy (MBE). They created ultra-thin, stress-engineered structures that exhibit unique magnetic properties at the nanoscale. The study reveals how lattice mismatches induce periodic stress relief, leading to the formation of magnetic edge states that could be manipulated for future quantum technologies. This innovative approach opens new avenues for designing nanoscale spintronic devices and exploring topological quantum phenomena, paving the way for advancements in quantum computing and next-generation magnetic materials.