Electro-Driven Multi-Enzymatic Cascade Conversion of CO2 to Ethylene Glycol in Nano-Reactor.

Multi-enzymatic cascade reaction provides a new avenue for C─C coupling directly from CO2 under mild conditions. In this study, a new pathway with four enzymes including formate dehydrogenase (PaFDH), formaldehyde dehydrogenase (BmFADH), glycolaldehyde synthase (PpGALS), and alcohol dehydrogenase (GoADH) is developed for directly converting CO2 gas molecules to ethylene glycol (EG) in vitro. A rhodium-based NADH regeneration electrode is constructed to continuously provide the proton and electron of this multi-enzymatic cascade reaction. The prepared electrode can reach the Faradaic Efficiency (FE) of 82.9% at -0.6 V (vs. Ag/AgCl) and the NADH productivity of 0.737 mM h-1. Shortening the reaction path is crucial for multi-enzymatic cascade reactions. Here, a hydrogen-bonded organic framework (HOF) nano-reactor is successfully developed to immobilize four enzymes in one pot with a striking enzyme loading capacity (990 mg enzyme g-1 material). Through integrating and optimization of NADH electro-regeneration and enzymatic catalysis in one pot, 0.15 mM EG is achieved with an average conversion rate of 7.15 × 10-7 mmol CO2 min-1 mg-1 enzymes in 6 h. These results shed light on electro-driven multi-enzymatic cascade conversion of C─C coupling from CO2 in the nano-reactor.

Genome-wide identification of Gα family in grass carp (Ctenopharyngodon idella) and reproductive regulation functional characteristics of Cignaq.

BACKGROUND: The Gα family plays a crucial role in the complex reproductive regulatory network of teleosts. However, the characterization and function of Gα family members, especially Gαq, remain poorly understood in teleosts. To analyze the characterization, expression, and function of grass carp (Ctenopharyngodon idella) Gαq, we identified the Gα family members in grass carp genome, and analyzed the expression, distribution, and signal transduction of Gαq/gnaq. We also explored the role of Gαq in the reproductive regulation of grass carp. RESULTS: Our results showed that the grass carp genome contains 27 Gα genes with 46 isoforms, which are divided into four subfamilies: Gαs, Gαi/o, Gαq/11, and Gα12/13. The expression level of Cignaq in the testis was the highest and significantly higher than in other tissues, followed by the hypothalamus and brain. The luteinizing hormone receptor (LHR) was mainly localized to the nucleus in grass carp oocytes, with signals also present in follicular cells. In contrast, Gαq signal was mainly found in the cytoplasm of oocytes, with no signal in follicular cells. In the testis, Gαq and LHR were co-localized in the cytoplasm. Furthermore, the grass carp Gαq recombinant protein significantly promoted Cipgr expression. CONCLUSIONS: These results provided preliminary evidence for understanding the role of Gαq in the reproductive regulation of teleosts.

Insights on the Contradiction between the Affinity and Capacity of Ferrihydrite toward As(III) and As(V): Surface Reaction Revisited.

Ferrihydrite is omnipresent in nature, and its adsorption of As(III/V) decides the migration of arsenic. Although As(III) is commonly recognized as the more mobile species of inorganic arsenic, it sometimes exhibits less mobility in ferrihydrite systems, which calls for further insights. In this study, we elucidated the adsorption behavior and mechanisms of As(III/V) on ferrihydrite under different loading levels (molar ratio As/Fe = 0-0.38), solution pH (3-10), and coexisting ions [P(V) and Ca(II)] based on batch adsorption experiments, surface complexation modeling, density functional theory calculations, and X-ray photoelectron spectroscopy. Our results show that As(III) exhibits weaker adsorption affinity but a larger capacity compared with that of As(V). On ferrihydrite, As(III) and As(V) are adsorbed mainly as bidentate mononuclear complexes at type-a sites [≡Fe(OH-0.5)2] and bidentate binuclear complexes at type-b sites (2≡FeOH-0.5), respectively. As the dosage increases, As(III) further forms mononuclear monodentate complexes at both surface sites, resulting in a higher site utilization efficiency, while As(V) does not due to repulsive electrostatic interaction. The difference in surface species of As(III/V) also leads to complex responses when coexisting with high concentrations of P(V) and Ca(II). This study helps us to understand environmental behavior of As(III/V) and develop remediation strategy in As(III/V) contaminated systems.

Screening and identification of reactive metabolic compounds of Cortex Periplocae based on glutathione capture-mass spectrometry.

As a traditional Chinese medicine (TCM), Cortex Periplocae (CP) has a wide range of pharmacological effects, as well as toxic side effects. The main toxic components of it are cardiac glycosides, which tend to cause cardiotoxicity. Currently, it has also been reported in studies to cause hepatotoxicity, but it is not clear whether the hepatotoxicity is related to the toxicity caused by the reactive metabolites. This study aims to investigate the target components of CP that generate reactive metabolic toxicity. The fluorescent probe method was used to detect glutathione (GSH)-trapped reactive metabolites in a co-incubation system of CP extract with rat liver microsomes. Identification of GSH conjugates was performed by LC-MS/MS and that of the possible precursor components that produce reactive metabolites was conducted by UPLC-Q-TOF/MS. Cell viability assays were performed on HepG2 and L02 cells to determine the cytotoxicity of the target components. The findings of our study demonstrate that the extract derived from CP has the ability to generate metabolites that exhaust the intracellular GSH levels, resulting in the formation of GSH conjugates and subsequent cytotoxic effects. Through the utilization of the UPLC-Q-TOF/MS technique, we were able to accurately determine the molecular weight of the precursor compound in CP to be 355.1023. The primary evidence to determining the GSH conjugetes relies on the appearance of characteristic product ions resulting from central neutral loss (CNL) scanning of 129 Da and product scanning of m/z 660 in the positive MS/MS spectrum. Through analysis, it was ultimately ascertained that the presence of chlorogenic acid (CGA) and its isomers, namely neochlorogenic acid (NCGA) and cryptochlorogenic acid (CCGA), could lead to the production of GSH conjugates, resulting in cytotoxicity at elevated levels. Taking these findings into consideration, the underlying cause for the potential hepatotoxicity of CP was initially determined.

Scattering approaches to unravel protein solution behaviors in ionic liquids and deep eutectic solvents: From basic principles to recent developments.

Proteins in ionic liquids (ILs) and deep eutectic solvents (DESs) have gained significant attention due to their potential applications in various fields, including biocatalysis, bioseparation, biomolecular delivery, and structural biology. Scattering approaches including dynamic light scattering (DLS) and small-angle X-ray and neutron scattering (SAXS and SANS) have been used to understand the solution behavior of proteins at the nanoscale and microscale. This review provides a thorough exploration of the application of these scattering techniques to elucidate protein properties in ILs and DESs. Specifically, the review begins with the theoretical foundations of the relevant scattering approaches and describes the essential solvent properties of ILs and DESs linked to scattering such as refractive index, scattering length density, ion-pairs, liquid nanostructure, solvent aggregation, and specific ion effects. Next, a detailed introduction is provided on protein properties such as type, concentration, size, flexibility and structure as observed through scattering methodologies. This is followed by a review of the literature on the use of scattering for proteins in ILs and DESs. It is highlighted that enhanced data analysis and modeling tools are necessary for assessing protein flexibility and structure, and for understanding protein hydration, aggregation and specific ion effects. It is also noted that complementary approaches are recommended for comprehensively understanding the behavior of proteins in solution due to the complex interplay of factors, including ion-binding, dynamic hydration, intermolecular interactions, and specific ion effects. Finally, the challenges and potential research directions for this field are proposed, including experimental design, data analysis approaches, and supporting methods to obtain fundamental understandings of complex protein behavior and protein systems in solution. We envisage that this review will support further studies of protein interface science, and in particular studies on solvent and ion effects on proteins.

Alleviation of arsenic stress in pakchoi by foliar spraying of engineered nanomaterials.

Addressing heavy metal contamination in leafy vegetables is critically important due to its adverse effects on human health. In this study, we investigated the inhibitory effects of foliar spraying with four nanoparticles (CeO2, ZnO, SiO2, and S NPs) on arsenic (As) stress in pakchoi (Brassica rapa var. Chinensis). The findings reveal that foliar application of ZnO NPs at 1 ~ 2.5 mg plant-1 and CeO2 NPs at 5 mg plant-1 significantly reduces As in shoots by 40.9 ~ 47.3% and 39.4%, respectively. Moreover, 5 mg plant-1 CeO2 NPs increased plant height by 6.06% and chlorophyll a (Chla) content by 30.2% under As stress. Foliar spraying of CeO2 NPs at 0.2-5 mg plant-1 also significantly enhanced superoxide dismutase (SOD) activity in shoots by 9.4 ~ 13.9%, lowered H2O2 content by 42.4 ~ 53.25%, and increased root protein contents by 79 ~ 109.2%. CeO2 NPs regulate the As(III)/As(V) ratio, aiding in As efflux from roots and thereby reducing As toxicity to plants. In vitro digestion experiments reveal that the consumption of CeO2 NPs carries the lowest health risk of As. In addition, foliar spraying of ZnO NPs at 1 ~ 2.5 mg plant-1 can suppress plant As uptake by modulating enzyme activity, reducing leaf damage, and enhancing chlorophyll content. The study demonstrates that high CeO2 NP concentrations and suitable ZnO NP concentrations can alleviate As toxicity in pakchoi, consequently reducing human health risks.

Simultaneous biodegradation of polycyclic aromatic hydrocarbons and phthalates by bacterial consortium and its bioremediation for complex polluted soil and sewage sludge.

Simultaneous biodegradation of multiple micropollutantslike polycyclic aromatic hydrocarbons (PAHs) and phthalates (PAEs) by microbial consortia remain unclear. Here, four distinct bacterial consortia capable of degrading PAHs and PAEs were domesticated from sludge and its composts. PAH-degrading consortium HS and PAE-degrading consortium EC2 displayed the highest degradation efficiencies for PAHs (37 %-99 %) and PAEs (98 %-99 %), respectively, being significantly higher than those of individual member strains. Consortia HS and EC2 could simultaneously degrade both PAHs and PAEs. Remarkably, a synthetic consortium Syn by co-culturing consortia HS and EC2 demonstrated proficient simultaneous biodegradation for both PAHs (65 %-98 %) and PAEs (91 %-97 %). These consortia changed their community structure with enriching pollutant-degrading genera and extracellular polymeric substance contents to promote simultaneous biodegradation of multiple pollutants. Moreover, consortium Syn significantly enhanced degradation of both PAHs and PAEs in soil and sludge. This study provides strong candidates for simultaneous bioremediation of complex polluted environments by PAHs and PAEs.

Vitamin D is involved in the effects of the intestinal flora and its related metabolite TMAO on perirenal fat and kidneys in mice with DKD.

BACKGROUND: Vitamin D was shown to directly exert a protective effect on diabetic kidney disease (DKD) in our previous study. However, whether it has an effect on perirenal adipose tissue (PRAT) or the intestinal flora and its metabolites (trimethylamine N-oxide, TMAO) is unclear. METHODS: DKD mice were received different concentrations of 1,25-(OH)2D3 for 2 weeks. Serum TNF-α levels and TMAO levels were detected. 16S rRNA sequencing was used to analyze gut microbiota. qPCR was used to detect the expression of TLR4, NF-Κb, PGC1α, and UCP-1 in kidney and adipose tissue. Histological changes in kidney and perirenal adipose tissue were observed using HE, PAS, Masson and oil red staining. Immunofluorescence and immunohistochemistry were used to detect the expression of VDR, PGC1α, podocin, and UCP-1 in kidney and adipose tissue. Electron microscopy was used to observe the pathological changes in the kidney. VDR knockout mice were constructed to observe the changes in the gut and adipose tissue, and immunofluorescence and immunohistochemistry were used to detect the expression of UCP-1 and collagen IV in the kidney. RESULTS: 1,25-(OH)2D3 could improve the dysbiosis of the intestinal flora of mice with DKD, increase the abundance of beneficial bacteria, decrease the abundance of harmful bacteria, reduce the pathological changes in the kidney, reduce fat infiltration, and downregulate the expression of TLR4 and NF-κB in kidneys. The serum TMAO concentration in mice with DKD was significantly higher than that of the control group, and was significantly positively correlated with the urine ACR. In addition, vitamin D stimulated the expression of the surface markers PGC1α, UCP-1 and VDR in the PRAT in DKD mice, and TMAO downregulated the expression of PRAT and renal VDR. CONCLUSIONS: The protective effect of 1,25-(OH)2D3 in DKD mice may affect the intestinal flora and its related metabolite TMAO on perirenal fat and kidneys.

A non-invasive artificial intelligence model for identifying axillary pathological complete response to neoadjuvant chemotherapy in breast cancer: a secondary analysis to multicenter clinical trial.

BACKGROUND: This study aims to develop a stacking model for accurately predicting axillary lymph node (ALN) response to neoadjuvant chemotherapy (NAC) using longitudinal MRI in breast cancer. METHODS: We included patients with node-positive breast cancer who received NAC following surgery from January 2012 to June 2022. We collected MRIs before and after NAC, and extracted radiomics features from the tumour, peritumour, and ALN regions. The Mann-Whitney U test, least absolute shrinkage and selection operator, and Boruta algorithm were used to select features. We utilised machine learning techniques to develop three single-modality models and a stacking model for predicting ALN response to NAC. RESULTS: This study consisted of a training cohort (n = 277), three external validation cohorts (n = 313, 164, and 318), and a prospective cohort (n = 81). Among the 1153 patients, 60.62% achieved ypN0. The stacking model achieved excellent AUCs of 0.926, 0.874, and 0.862 in the training, external validation, and prospective cohort, respectively. It also showed lower false-negative rates (FNRs) compared to radiologists, with rates of 14.40%, 20.85%, and 18.18% (radiologists: 40.80%, 50.49%, and 63.64%) in three cohorts. Additionally, there was a significant difference in disease-free survival between high-risk and low-risk groups (p < 0.05). CONCLUSIONS: The stacking model can accurately predict ALN status after NAC in breast cancer, showing a lower false-negative rate than radiologists. TRIAL REGISTRATION NUMBER: The clinical trial numbers were NCT03154749 and NCT04858529.

Unveiling the distinctive traits of functional rye centromeres: minisatellites, retrotransposons, and R-loop formation.

Centromeres play a vital role in cellular division by facilitating kinetochore assembly and spindle attachments. Despite their conserved functionality, centromeric DNA sequences exhibit rapid evolution, presenting diverse sizes and compositions across species. The functional significance of rye centromeric DNA sequences, particularly in centromere identity, remains unclear. In this study, we comprehensively characterized the sequence composition and organization of rye centromeres. Our findings revealed that these centromeres are primarily composed of long terminal repeat retrotransposons (LTR-RTs) and interspersed minisatellites. We systematically classified LTR-RTs into five categories, highlighting the prevalence of younger CRS1, CRS2, and CRS3 of CRSs (centromeric retrotransposons of Secale cereale) were primarily located in the core centromeres and exhibited a higher association with CENH3 nucleosomes. The minisatellites, mainly derived from retrotransposons, along with CRSs, played a pivotal role in establishing functional centromeres in rye. Additionally, we observed the formation of R-loops at specific regions of CRS1, CRS2, and CRS3, with both rye pericentromeres and centromeres exhibiting enrichment in R-loops. Notably, these R-loops selectively formed at binding regions of the CENH3 nucleosome in rye centromeres, suggesting a potential role in mediating the precise loading of CENH3 to centromeres and contributing to centromere specification. Our work provides insights into the DNA sequence composition, distribution, and potential function of R-loops in rye centromeres. This knowledge contributes valuable information to understanding the genetics and epigenetics of rye centromeres, offering implications for the development of synthetic centromeres in future plant modifications and beyond.

Longitudinal ultrasound-based AI model predicts axillary lymph node response to neoadjuvant chemotherapy in breast cancer: a multicenter study.

OBJECTIVES: Developing a deep learning radiomics model from longitudinal breast ultrasound and sonographer's axillary ultrasound diagnosis for predicting axillary lymph node (ALN) response to neoadjuvant chemotherapy (NAC) in breast cancer. METHODS: Breast cancer patients undergoing NAC followed by surgery were recruited from three centers between November 2016 and December 2022. We collected ultrasound images for extracting tumor-derived radiomics and deep learning features, selecting quantitative features through various methods. Two machine learning models based on random forest were developed using pre-NAC and post-NAC features. A support vector machine integrated these data into a fusion model, evaluated via the area under the curve (AUC), decision curve analysis, and calibration curves. We compared the fusion model's performance against sonographer's diagnosis from pre-NAC and post-NAC axillary ultrasonography, referencing histological outcomes from sentinel lymph node biopsy or axillary lymph node dissection. RESULTS: In the validation cohort, the fusion model outperformed both pre-NAC (AUC: 0.899 vs. 0.786, p < 0.001) and post-NAC models (AUC: 0.899 vs. 0.853, p = 0.014), as well as the sonographer's diagnosis of ALN status on pre-NAC and post-NAC axillary ultrasonography (AUC: 0.899 vs. 0.719, p < 0.001). Decision curve analysis revealed patient benefits from the fusion model across threshold probabilities from 0.02 to 0.98. The model also enhanced sonographer's diagnostic ability, increasing accuracy from 71.9% to 79.2%. CONCLUSION: The deep learning radiomics model accurately predicted the ALN response to NAC in breast cancer. Furthermore, the model will assist sonographers to improve their diagnostic ability on ALN status before surgery. CLINICAL RELEVANCE STATEMENT: Our AI model based on pre- and post-neoadjuvant chemotherapy ultrasound can accurately predict axillary lymph node metastasis and assist sonographer's axillary diagnosis. KEY POINTS: Axillary lymph node metastasis status affects the choice of surgical treatment, and currently relies on subjective ultrasound. Our AI model outperformed sonographer's visual diagnosis on axillary ultrasound. Our deep learning radiomics model can improve sonographers' diagnosis and might assist in surgical decision-making.

The impact of vedolizumab therapy on extraintestinal manifestations in patients with inflammatory bowel disease: A systematic review and meta-analysis.

BACKGROUND AND AIM: Extraintestinal manifestations (EIMs) pose a significant threat in inflammatory bowel disease (IBD) patients. Vedolizumab (VDZ) primarily affects the gastrointestinal tract. However, its impact on EIMs remains uncertain. Therefore, we conducted this meta-analysis to examine the effects of VDZ on EIMs during treatment. METHODS: Relevant studies were identified by conducting thorough searches across electronic databases, including PubMed, Ovid Embase, Medline, and Cochrane CENTRAL. Primary outcomes focused on the proportion of patients with resolution for pre-existing EIMs in IBD patients receiving VDZ. Secondary outcomes included the proportion of patients with EIM exacerbations and new onset EIMs during VDZ treatment. RESULTS: Our meta-analysis encompassed 21 studies. The proportion of patients with resolution of pre-existing EIMs in VDZ-treated IBD patients was 39% (150/386; 95% confidence interval [CI] 0.31-0.48). The proportion of patients with EIM exacerbations occurred at a rate of 28% (113/376; 95% CI 0.05-0.50), while new onset EIMs had a rate of 15% (397/2541; 95% CI 0.10-0.20). Subgroup analysis revealed a 40% (136/337) proportion of patients with resolution for articular-related EIMs and a 50% (9/18) rate for erythema nodosum. Exacerbation rates for arthritis/arthralgia, erythema nodosum/pyoderma gangrenosum, and aphthous stomatitis during VDZ use were 28% (102/328), 18% (7/38), and 11% (3/28), respectively. The incidence rate of newly developed EIMs during treatment was 11% (564/4839) for articular-related EIMs, with other EIMs below 2%. CONCLUSION: VDZ demonstrates efficacy in skin-related EIMs like erythema nodosum and joint-related EIMs including arthritis, arthralgia, spondyloarthritis, and peripheral joint diseases. Some joint and skin-related EIMs may experience exacerbation during VDZ therapy.

Fecal microbiota transplantation for irritable bowel syndrome: Current evidence and perspectives.

In this editorial we comment on the article published in the recent issue of the World journal of Gastroenterology. We focus specifically on the mechanisms un-derlying the effects of fecal microbiota transplantation (FMT) for irritable bowel syndrome (IBS), the factors which affect the outcomes of FMT in IBS patients, and challenges. FMT has emerged as a efficacious intervention for clostridium difficile infection and holds promise as a therapeutic modality for IBS. The utilization of FMT in the treatment of IBS has undergone scrutiny in numerous randomized controlled trials, yielding divergent outcomes. The current frontier in this field seeks to elucidate these variations, underscore the existing knowledge gaps that necessitate exploration, and provide a guideline for successful FMT imple-mentation in IBS patients. At the same time, the application of FMT as a treatment for IBS confronts several challenges.

Trends and risk factors for drug-resistant tuberculosis among children in Sichuan, China: A 10-year retrospective analysis, 2013-2022.

To investigate the status of the drug-resistant tuberculosis (DR-TB) among children in Sichuan, and to find out the risk factors and high-risk population related to drug resistance among children. The clinical data of tuberculosis patients ≤14 years old with culture-confirmed tuberculosis hospitalized in Chengdu Public Health Clinical Center from January 2013 through December 2022 were collected. Clinical data such as gender, age, ethnicity, history of anti-TB treatment, history of exposure to tuberculosis, nutritional status, and specific drug resistance of the children were collected and recorded. The drug resistance of children in different age groups (0-4 years old, 5-9 years old, 10-14 years old) and different periods (2013-2017 and 2018-2022) were grouped and compared. Logistic regression analysis was to analyze analysis of risk factors of drug resistance in children. A total of 438 children with culture-confirmed tuberculosis were screened. Among them, 26.19% (11/42) were 0 to 4 years old, 33.33% (22/66) were 5 to 9 years old, and 36.67% (121/330) were 10 to 14 years old among the resistant children. There was no statistically significant difference in the resistance rate among the 3 groups (P = .385). The proportions of DR-TB, monoresistant tuberculosis, polydrug-resistant tuberculosis were decreased during 2019 to 2022 compared with 2013 to 2017 (P < .0001). The resistance rates of drug resistant, monoresistant, polydrug-resistant, isoniazid-resistant, and rifampicin resistant during 2018 to 2022 were decreased compared with those from 2013 to 2017 (P < .05), but the multi-drug resistance rate was not decreased (P = .131, without statistical difference). The results of logistic regression analysis showed that male gender OR = 1.566 (95% CI 1.035-2.369), a history of antituberculosis therapy OR = 4.049 (95% CI 1.442-11.367), and pulmonary and extrapulmonary tuberculosis OR = 7.335 (95% CI 1.401-38.392) were risk factors for the development of drug resistance; but fever OR = 0.581 (95% CI 0.355-0.950) was Protective factor. The total drug resistance rate of children in Sichuan showed a downward trend, but the rate of multi-drug-resistant tuberculosis was still at a high level, and the form of drug resistance was still severe. Absence of fever, male, retreatment, and pulmonary concurrent with extrapulmonary tuberculosis are risk factors for DR-TB in children.

Non-B-form DNA is associated with centromere stability in newly-formed polyploid wheat.

Non-B-form DNA differs from the classic B-DNA double helix structure and plays a crucial regulatory role in replication and transcription. However, the role of non-B-form DNA in centromeres, especially in polyploid wheat, remains elusive. Here, we systematically analyzed seven non-B-form DNA motif profiles (A-phased DNA repeat, direct repeat, G-quadruplex, inverted repeat, mirror repeat, short tandem repeat, and Z-DNA) in hexaploid wheat. We found that three of these non-B-form DNA motifs were enriched at centromeric regions, especially at the CENH3-binding sites, suggesting that non-B-form DNA may create a favorable loading environment for the CENH3 nucleosome. To investigate the dynamics of centromeric non-B form DNA during the alloploidization process, we analyzed DNA secondary structure using CENH3 ChIP-seq data from newly formed allotetraploid wheat and its two diploid ancestors. We found that newly formed allotetraploid wheat formed more non-B-form DNA in centromeric regions compared with their parents, suggesting that non-B-form DNA is related to the localization of the centromeric regions in newly formed wheat. Furthermore, non-B-form DNA enriched in the centromeric regions was found to preferentially form on young LTR retrotransposons, explaining CENH3's tendency to bind to younger LTR. Collectively, our study describes the landscape of non-B-form DNA in the wheat genome, and sheds light on its potential role in the evolution of polyploid centromeres.

Noninvasive Artificial Intelligence System for Early Predicting Residual Cancer Burden during Neoadjuvant Chemotherapy in Breast Cancer.

OBJECTIVE: To develop an artificial intelligence (AI) system for the early prediction of residual cancer burden (RCB) scores during neoadjuvant chemotherapy (NAC) in breast cancer. SUMMARY BACKGROUND DATA: RCB III indicates drug resistance in breast cancer, and early detection methods are lacking. METHODS: This study enrolled 1048 patients with breast cancer from four institutions, who were all receiving NAC. Magnetic resonance images were collected at the pre- and mid-NAC stages, and radiomics and deep learning features were extracted. A multitask AI system was developed to classify patients into three groups (RCB 0-I, II, and III ) in the primary cohort (PC, n=335). Feature selection was conducted using the Mann-Whitney U- test, Spearman analysis, least absolute shrinkage and selection operator regression, and the Boruta algorithm. Single-modality models were developed followed by model integration. The AI system was validated in three external validation cohorts. (EVCs, n=713). RESULTS: Among the patients, 442 (42.18%) were RCB 0-I, 462 (44.08%) were RCB II and 144 (13.74%) were RCB III. Model-I achieved an area under the curve (AUC) of 0.975 in the PC and 0.923 in the EVCs for differentiating RCB III from RCB 0-II. Model-II distinguished RCB 0-I from RCB II-III, with an AUC of 0.976 in the PC and 0.910 in the EVCs. Subgroup analysis confirmed that the AI system was consistent across different clinical T stages and molecular subtypes. CONCLUSIONS: The multitask AI system offers a noninvasive tool for the early prediction of RCB scores in breast cancer, supporting clinical decision-making during NAC.