Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Mingchen Li
A New Secondary Decomposition–Ensemble Approach for Tourism Demand Forecasting
Conflicts of Interest The authors declare no conflicts interest. Data Availability Statement The data that support the findings of this study are openly available in Wind Database at https://www.wind.com.cn/. Supporting Information Filename Description for70223-sup-0001-Supplementary_material.docxWord 2007 document , 234.6 KB Table S1: RMSE results for benchmark models from eight source market datasets. Table S2: MASE results for benchmark models from eight source market datasets.
Mingchen Li session
Please note that we use cookies to improve the use of this website. By continuing to browse the site, you accept theCrag Site Usage Policy Wed Sep Mingchen Li logged 4 ascents from the past and attempted a route at 白河 Baihe. • 2202 2 Points • Logged 4 ascents from the past and attempted a route.
CancerLLM: a large language model in cancer domain - npj Digital Medicine
Abstract Medical large language models (LLMs) perform well on medical NLP tasks, but lack models tailored for cancer phenotyping and diagnosis. Moreover, having tens of billions of parameters increases the computational burden in healthcare settings. To this end, we present CancerLLM, a 7-billion-parameter Mistral-style model trained on 2.7 M clinical notes and 515 K pathology reports across 17 cancer types, followed by fine-tuning on cancer phenotype extraction and diagnosis generation tasks.
Spatio-temporal forecasting of tourism demand using graph Wavenet: evidence from the Hawaiian Islands
Tourism demand forecasting is essential for destination management and policy planning. This study develops a spatio-temporal deep learning framework based on Graph WaveNet to forecast daily tourist arrivals across the Hawaiian Islands. The proposed model jointly captures temporal dynamics and dynamic spatial dependencies among destinations, enabling more accurate multi-step demand prediction.
Optimizing furniture retail strategies:: Insights from cross-platform consumer sentiment and topic modeling
Ayuda Buscar en la ayuda Buscar en la ayuda Optimizing furniture retail strategies:: Insights from cross-platform consumer sentiment and topic modeling Yuanyuan Shi [1] ; Erlong Zhao [2] ; Mingchen Li [3] [1] Jiangxi Normal University, China [2] Xi’an University of Finance and Economics, China [3] China University of Mining and Technology, China Localización: Journal of Theoretical and Applied Electronic Commerce Research, ISSN-e 0718-1876, Vol. 20, Nº.
Impact of Production Temperatures on Blending Condition between Virgin and Aged Asphalt: Performance and Environmental Cost Analysis
Get full access to this article View all available purchase options and get full access to this article. Data Availability Statement All data, models, and code generated or used during the study appear in the published article. Acknowledgments The research is funded by a grant from the National Key R&D Program of China (Grant No. 2023YFB2603502) and Fundamental Research Funds for the Central Universities [Grant No. DUT24RC(3)100]. The sponsorships are gratefully acknowledged.
Benchmarking retrieval-augmented large language models in biomedical NLP: Application, robustness, and self-awareness
To reduce hallucinations in large language models (LLMs), retrieval-augmented LLMs (RALs) retrieve supporting knowledge from external databases. …
Conserved CD8 T cell vaccines without B cell epitopes drive robust protection against SARS-CoV-2 that is enhanced by intranasal boost
Abstract The emergence of SARS-CoV-2 variants has challenged the current spike protein–focused COVID-19 vaccine strategy due to neutralizing antibody escape and waning antibody-mediated immunity. In contrast, T cell–mediated immunity targeting conserved epitopes may offer broad and long-lasting protection. However, whether T cells alone can provide sufficient protection remains unclear.
Observation of proton tunneling correlated with phonons and electrons in Pd
Abstract Quantum-mechanical properties substantially affect the dynamics of light particles, including hydrogen. The temperature dependence of the tunneling rate provides a clue to understanding the quantum effects. Important physics behind quantum tunneling involves the correlation with surrounding environment, such as phonons and electrons. However, this correlation is not yet well understood due to the difficulty of directly probing hydrogen hopping.
Rapid cancer diagnosis using deep learning-powered label-free subcellular-resolution photoacoustic histology
Abstract Traditional hematoxylin and eosin staining in formalin-fixed paraffin-embedded sections, while essential for diagnostic pathology, is time-consuming, labor intensive, and prone to artifacts that can obscure critical histological details. Label-free ultraviolet photoacoustic microscopy (UV-PAM) has emerged as a promising alternative, offering fast histology-like images without the need for traditional staining and excessive tissue preparation.
Visualizing the strong field-induced molecular breakup of C60 via x-ray diffraction
Abstract Laser-driven dynamics in polyatomic molecules poses a complex many-body problem. Understanding intense light-matter interaction is crucial for steering intramolecular quantum dynamical processes. Here, we record time-resolved x-ray diffraction images of C60 molecules during and after their interaction with intense near-infrared fields, giving direct access to structural changes of the molecules and their fragmentation in real time.
A striosomal accumbens pathway drives stereotyped behavior through an aversive Esr1+ hypothalamic-habenula circuit
Abstract The lateral hypothalamic area (LHA) integrates external stimuli with internal states to drive the choice between competing innate or value-driven motivated behaviors. Here, we define a striosomal Tac1+/Tshz1+/Oprm1+ neuron subtype in the nucleus accumbens (ACB) that targets Esr1+ LHA neurons that project to the lateral habenula (LHb).
A rapid self-healing polymer mediated by ion aggregates achieves effective encapsulation of sustainable perovskite solar cells
Abstract Despite the rapid progress of perovskite solar cells (PSCs) toward commercialization, perovskite layers are unstable and contain toxic lead. Encapsulation represents an efficient strategy for improving the stability of PSCs as well as suppressing lead leakage. However, the damage to encapsulation materials during outdoor applications inevitably deteriorates the packaging effect and increases lead leakage.
A universal 2D-on-SiC platform for heterogeneous integration of epitaxial III-N membranes
Abstract Nonconventional epitaxial techniques, such as van der Waals epitaxy and remote epitaxy, have attracted substantial attention in the semiconductor research community for their capability to repeatedly produce high-quality freestanding films from a single mother wafer. Successful implementation of these techniques depends on creating a robust, uniform two-dimensional (2D) material surface.
Mitochondrial NAD+ gradient sustained by membrane potential and transport
Abstract SLC25A51 is required for the replenishment of free nicotinamide adenine dinucleotide (oxidized form) (NAD+) into mammalian mitochondria. However, it is not known how SLC25A51 imports this anionic molecule to sustain elevated NAD+ concentrations in the matrix. Understanding this would reveal regulatory mechanisms used to maintain critical bioenergetic gradients for cellular respiration, oxidative mitochondrial reactions, and mitochondrial adenosine triphosphate (ATP) production.
Two-photon induced coherence without induced emission
Abstract At the heart of recent advances in quantum imaging and spectroscopy with undetected photons is the quantum optical effect known as induced coherence without induced emission. This quantum interference effect has enabled access to challenging wavelength regimes for imaging and spectroscopic applications.
Nanofluidic-engineered carbon nanotube ion highways in hydrogels enable high-power aqueous zinc-ion batteries
Abstract Quasi-solid polymer electrolytes (QSPEs) for flexible batteries face critical limitations in ion transport efficiency at high currents. We address this with a design of nanofluidic polyacrylamide hydrogel integrating aligned single-walled carbon nanotubes (SWCNTs) as ion highways [SWCNT-embedded polyacrylamide(CPAM)]. Photo-polymerization ensures homogeneous SWCNT distribution, delivering a high ionic conductivity of 30.3 mS cm−1 while shielding polymer matrices from ion collision.
3D bioprinted human-scale intestine models for physiological and microbial insights through fluid-driven heterogeneity
Abstract The small intestine’s intricate structure enables vital functions such as nutrient absorption, microbial defense, and barrier protection, yet replicating its complexity in vitro remains a substantial challenge. We engineered a three-dimensional bioprinted intestinal model featuring biomimetic circular folds and zonated shear stress distribution to recapitulate native physiology.
An acyclic nucleoside phosphonate effectively blocks the egress of the malaria parasite by inhibiting the synthesis of cyclic GMP
Abstract The urgent need for original antimalarial therapies arises from the alarming spread of malaria parasite resistance to existing drugs. A promising candidate, UA2239, an acyclic nucleoside phosphonate with a guanine as nucleobase, demonstrates rapid and irreversible inhibitory effects on Plasmodium parasites. It blocks the active exit process, named egress, of merozoites and gametes from infected erythrocytes.
Double-sided annealing to reverse the crystallization direction for efficient and stable flexible FACs-perovskite solar modules
Abstract The application of methylammonium cations makes flexible perovskite solar modules (f-PSMs) unstable in long term. Here, we report flexible p-i-n structure perovskite modules made of methylammonium-free formamidinium cesium lead iodide (FA1−xCsxPbI3, x ≤ 0.1) to improve their stability. Interfacial voids between FA1−xCsxPbI3 layer and hole-transport layers, caused by the limited annealing temperature for f-PSMs, severely disrupt the film structural continuity.
Proximity-induced chirality at the achiral conductive interface by electrical control of enantiopure ion adsorption
Abstract Chirality manipulation of materials has attracted substantial interest in a wide variety of fields in science and technology. Chiral molecular adsorption is a distinct approach for inducing chirality in achiral systems such as organic-inorganic hybrid compounds and nanomaterials.
Mapping structures and dynamics with frequency-correlated diffusion exchange
Abstract Understanding molecular motion in diffusion-driven complex environments is critical for designing sustainable materials and improving chemical processes. Here, we introduce a multidimensional nuclear magnetic resonance (NMR) method that captures how molecular populations exchange across different dynamic regimes.
High-entropy nanoalloys anchored on entropy-compensating two-dimensional oxides for enhanced nanomagnetism
Abstract Mitigating detrimental surface effects in nanometals is crucial for advancing applications in quantum magnetic storage and integrated circuits, as size reduction often experiences atomic distortion and vacancy formation, disrupting magnetic domains and electronic transport. Herein, we synthesize nano–high-entropy alloys (HEAs) anchored on two-dimensional high-entropy oxide nanosheets.
Electrochemical C4 alkylation of pyridine derivatives: Enhanced regioselectivity via silane assistance
Abstract Pyridine derivatives are valuable biologically active compounds, materials, and ligands; however, traditional methods for site-selective direct functionalization are often hindered by multistep procedures and harsh conditions. Herein, we report the general and efficient electroreductive C4 alkylation of pyridine derivatives with various alkyl bromides with high regioselectivity and good yields.
Benchmarking retrieval-augmented large language models in biomedical NLP: Application, robustness, and self-awareness
Abstract To reduce hallucinations in large language models (LLMs), retrieval-augmented LLMs (RALs) retrieve supporting knowledge from external databases. However, their performance on biomedical natural language processing (NLP) tasks remains underexplored.
High-capacity directional information processor using all-optical multilayered neural networks
Abstract We propose a directional-diffractive deep neural network (D-D2NN) by encoding the wave propagation direction into a D2NN, introducing a new degree of freedom and enable high-capacity information processing. The unprecedented capability of metasurfaces in controlling light propagation provides a new opportunity to realize such a D-D2NN. We propose and demonstrate a versatile D-D2NN using three spin-decoupled metasurfaces.
Low-waste, single-step, sustainable extraction of critical metals from deep-sea polymetallic nodules
Abstract To support the green energy transition, sustainable supplies of critical metals—60 million (metric) tons of copper, 10 million tons of nickel, and 1 million tons of cobalt—annually by 2050 are essential. These metals are currently sourced from declining terrestrial reserves, making deep-sea polymetallic nodules a promising alternative.
Single atom-cluster synergy in Ag catalysts enables chiral glyceric acid from biomass
Abstract Accessing optically pure chemicals directly from biomass via chemical catalysis remains challenging because of the need for high selectivity across complex, multistep transformations. Here, we report a robust silver-based catalyst featuring synergistic single atoms and nanoclusters that function as complementary active sites in the anaerobic oxidative carbon-carbon cleavage of bio-derived feedstocks.
Antigen-specific B cell response regulation by IL-10-producing tolerogenic dendritic cells
Abstract B cells regulate immune responses via antibody production and antigen (Ag) presentation. Although B cell depletion is used therapeutically, it may be associated with side effects, highlighting the need for alternative B cell–targeted approaches. While tolerogenic dendritic cells (tolDC) are known to modulate T cell responses, their impact on B cells is poorly defined. We show that IL-10–producing tolDC (DCIL-10) regulate B cell responses through direct and indirect mechanisms.
Erratum for the Research Article “Heterochronic parabiosis uncovers AdipoR1 as a critical player in retinal rejuvenation” by Y. Liu et al.
Get Science’s award-winning newsletter with the latest news, commentary, and research, free to your inbox daily.
miRNA-loaded biomimetic nanoparticles orchestrate gut microbe to ameliorate inflammatory bowel disease
Abstract Modulation of gut microbiota has emerged as a promising therapeutic strategy for inflammatory bowel disease (IBD). However, current interventions such as probiotics and fecal microbiota transplantation remain limited by insufficient safety and efficacy. To address this, we engineered commensal Lactobacillus rhamnosus (LGG) using miRNA-loaded biomimetic nanoparticles to enhance its proliferation and indole-3-carboxaldehyde production.
Stable electron-irradiated [1-13C]alanine radicals for metabolic imaging with dynamic nuclear polarization
Abstract Dissolution dynamic nuclear polarization (dDNP) increases the sensitivity of magnetic resonance experiments by >104-fold, permitting isotopically labeled molecules to be transiently visible in magnetic resonance imaging scans. dDNP mechanistically takes place at ~1 K and requires unpaired electrons and microwaves. These electrons are usually chemical radicals, requiring removal by filtration prior to injection into humans.
Sabatier principle in designing CO2-philic but blocking membranes
Abstract Gas transport through polymers follows the sorption-diffusion mechanism, and gas-philic functional groups are often incorporated into polymers to enhance its solubility selectivity and thus separation efficiency.
A ubiquitin-like protein controls assembly of a bacterial type VIIb secretion system
Abstract Type VII secretion systems (T7SS) are protein translocation machines crucial for virulence and bacterial competition in Gram-positive bacteria. Despite their importance, the structural basis for assembly of type VIIb secretion systems (T7SSb), a widely distributed variant in Firmicutes, remains poorly understood.
Renal clearable CRISPR nanosensor targeting mitochondrial DNA mutation for noninvasive monitoring of tumor progression and metastasis
Abstract Mitochondrial DNA (mtDNA) mutations are emerging as important molecular features of tumorigenesis. Liquid biopsies, involving analysis of cell-free mtDNA, enable early cancer detection but suffer from low sensitivity due to scarce analytes. Here, we developed a CRISPR/Cas12a-mediated urinary biomarker, termed CasUber, for in vivo monitoring of tumor progression and metastasis.
Temporal Evolution Kinetics of Upconversion Population Distribution Resulting in Transient Luminescence Enhancement (Laser Photonics Rev. 19(22)/2025)
wiley.scienceconnect.io is blocked wiley.scienceconnect.io refused to connect.
Virgin Asphalt–Aged Asphalt Interface Diffusion Behavior: Molecular Dynamics Simulation and GPC Test Validation | Journal of Materials in Civil Engineering | Vol 38, No 2
Get full access to this article View all available purchase options and get full access to this article. Data Availability Statement All data, models, and code generated or used during the study appear in the published article. Acknowledgments The research is funded by a grant from the National Natural Science Foundation of China (Grant No. 51978521) and the National Natural Science Foundation of China (Grant No. 51778483). The sponsorships are gratefully acknowledged.
Preventing neuropathy and improving anticancer chemotherapy with a carbazole-based compound
Abstract While advances in cancer therapy have improved remission rates, chemotherapy-induced peripheral neuropathy (CIPN) remains a lasting and untreatable side effect. This study introduces Carba1, a bifunctional carbazole compound that protects against CIPN through two mechanisms. First, Carba1 interacts with tubulin, allowing for lower doses of taxanes, common chemotherapeutics known for causing CIPN, without reducing their anticancer effectiveness.
Hollywood Town: Long-Video Generation via Cross-Modal Multi-Agent Orchestration
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Harnessing protein language model for structure-based discovery of highly efficient and robust PET hydrolases - Nature Communications
Abstract Plastic waste, particularly polyethylene terephthalate (PET), presents significant environmental challenges, driving extensive research into enzymatic biodegradation. However, existing PET hydrolases (PETases) are limited by narrow sequence diversity and suboptimal performance. This study introduces VenusMine, a protein discovery pipeline that integrates protein language models (PLMs) with a representation tree to identify PETases based on structural similarity using sequence information.
Investigation on the Ageing Behaviour of High-Modulus Modified Bitumen Based on Rheological and Chemical Approaches
All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess.
Harnessing A Unified Multi-modal Sequence Modeling to unveil Protein-DNA Interdependency
Abstract The interdependent orchestration of proteins, coding DNA sequences (CDS), and adjacent regulatory DNA elements underpins biological functionality, where evolutionary constraints shape codon usage, transcriptional regulation, and structural stability. We present ProDMM, a multimodal framework that deciphers these systemic relationships through unified sequence modeling.
Unveiling Protein-DNA Interdependency: Harnessing Unified Multimodal Sequence Modeling, Understanding and Generation
Abstract The interactions between proteins and non-coding DNA remain underexplored in the context of large language models. In this study, we present a multimodal framework designed to investigate these critical interactions, utilizing a comprehensive pre-training dataset comprising over 129 million pairs of coding and non-coding sequences.
[2502.04951] The Rising Threat to Emerging AI-Powered Search Engines
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Publisher Correction: A multi-year campus-level smart meter database - Scientific Data
Correction to: Scientific Data https://doi.org/10.1038/s41597-024-04106-1, published online 26 November 2024 In this article, extraneous commas were inadvertently added to Equation 1. The original article has been corrected.
Discovery of Expression-Governing Residues in Proteins
Abstract Understanding how amino acids influence protein expression is crucial for advancements in biotechnology and synthetic biology. In this study, we introduce Venus-TIGER, a deep learning model designed to accurately identify amino acids critical for expression. By constructing a two-dimensional matrix that links model representations to experimental fitness, Venus-TIGER achieves improved predictive accuracy and enhanced extrapolation capability.
A multi-year campus-level smart meter database - Scientific Data
Abstract With the growing need for precise campus electricity management, understanding load patterns is crucial for improving energy efficiency and optimizing energy use. However, detailed electricity load data for campus buildings and their internal equipment is often lacking, hindering research.
How to select the best zero-shot model for the viral proteins?
Abstract Predicting the fitness of viral proteins holds notable implications for understanding viral evolution, advancing fundamental biological research, and informing drug discovery. However, the considerable variability and evolution of viral proteins make predicting mutant fitness a major challenge. This study introduces the ProPEC, a Perplexity-based Ensemble Model, aimed at improving the performance of zero-shot predictions for protein fitness across diverse viral datasets.
Unlearning Virus Knowledge Toward Safe and Responsible Mutation Effect Predictions
Abstract Pre-trained deep protein models have become essential tools in fields such as biomedical research, enzyme engineering, and therapeutics due to their ability to predict and optimize protein properties effectively. However, the diverse and broad training data used to enhance the generalizability of these models may also inadvertently introduce ethical risks and pose biosafety concerns, such as the enhancement of harmful viral properties like transmissibility or drug resistance.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Mingchen
Contact Mingchen, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack