Hydrolysis-Induced Cu2O Networks and the Triggered Peroxidase-Mimic Activity by Cr6+ under Neutral Conditions.

The current small-scale synthesis and relatively large size of Cu2O have limited its practical applications. Herein, we developed a hydrolysis strategy to prepare phase-pure Cu2O networks composed of small granules (ca. 25 nm) on a gram scale. The preparation involves in situ hydrolyzing the Hx[CuxCl2x] complexes prereduced in N,N'-dimethylformamide (DMF). The DMF-soluble Hx[CuxCl2x] complexes are critical for the homogeneous nucleation of CuCl seeds and subsequent hydrolysis, allowing for separate control over the nucleation and growth stages to regulate the formation of Cu2O networks. The novel Cu2O networks possess numerous exposed active sites and hierarchical porosities, conferring high catalytic activity and fast mass transfer capability. The inherent peroxidase-mimic activity of Cu2O is severely inhibited under neutral conditions but can be triggered by Cr6+, enabling the colorimetric assay of Cr6+ with the assistance of the oxidation-induced color change of 3,3',5,5'-tetramethylbenzidine. Through density functional theory calculation, we confirmed that the attachment of Cr6+ on the Cu2O surface reduced the dissociation energy of H2O2, enhancing the enzyme-mimic activity. The colorimetric detection method demonstrated a sensitive and specific assay capability for Cr6+ (LOD = 0.095 µM). Our work offers a straightforward protocol for novel design of metal or metal-based nanomaterials for nanozymes or other applications.

Genetic Programming for Document Classification: A Transductive Transfer Learning System.

Document classification is a challenging task to the data being high-dimensional and sparse. Many transfer learning methods have been investigated for improving the classification performance by effectively transferring knowledge from a source domain to a target domain, which is similar to but different from the source domain. However, most of the existing methods cannot handle the case that the training data of the target domain does not have labels. In this study, we propose a transductive transfer learning system, utilizing solutions evolved by genetic programming (GP) on a source domain to automatically pseudolabel the training data in the target domain in order to train classifiers. Different from many other transfer learning techniques, the proposed system pseudolabels target-domain training data to retrains classifiers using all target-domain features. The proposed method is examined on nine transfer learning tasks, and the results show that the proposed transductive GP system has better prediction accuracy on the test data in the target domain than existing transfer learning approaches including subspace alignment-domain adaptation methods, feature-level-domain adaptation methods, and one latest pseudolabeling strategy-based method.

Amorphous copper(II)-cyanoimidazole frameworks as peroxidase mimics for hydrogen sulfide assay.

Metal-organic frameworks with hierarchical porosities and exposed active sites are promising for ideal enzyme mimics. In this work, we developed a simple and feasible air oxidation strategy to prepare amorphous Cu(II)-cyanoimidazole frameworks (aCu(II)-CIFs) using CuI as the metal source in dimethylsulfoxide. Benefiting from coordination unsaturation and hierarchical porosities, aCu(II)-CIFs exhibit inherent peroxidase-mimic activity for rapid colorimetric reaction of 3,3',5,5'-tetramethylbenzidine (TMB). aCu(II)-CIFs were utilized to develop a colorimetric platform for specific H2S assay in the range of 0.6-30 µM, achieving a limit of detection (LOD) of 0.071 µM. Structural collapse of aCu(II)-CIFs and subsequent generation of stable CuS particles, along with reducibility of H2S, are likely responsible for suppressing TMBox conversion. The proposed method successfully detected H2S in real water samples, with a relative standard deviation (RSD) lower than 8.4%. This contribution is expected to offer unique insights into the amorphization mechanisms of MOFs and their potential applications.

NCBP1 Improves Cognitive Function in Mice by Reducing Oxidative Stress, Neuronal Loss, and Glial Activation After Status Epilepticus.

Status epilepticus (SE) is a severe manifestation of epilepsy which can cause neurologic injury and death. This study aimed to identify key proteins involved in the pathogenesis of epilepsy and find a potential drug target for SE treatment. Tandem mass tag (TMT)-based quantitative proteomic analysis was applied to screen differentially expressed proteins (DEPs) in epilepsy. The adeno-associated virus was employed to overexpress candidate DEP in mice, and kainic acid (KA) was used to generate a mouse model of epilepsy. Then histopathological examination of the hippocampal tissue was performed, and the inflammatory factors levels in serum and hippocampus were measured. The IP-MS analysis was carried out to identify the interacting protein of nuclear cap-binding protein 1 (NCBP1). The results were that NCBP1 was downregulated in the epileptic hippocampus. NCBP1 overexpression alleviated KA-induced cognitive impairment in mice and reduced the apoptosis and damage of hippocampal neurons. Additionally, overexpressed NCBP1 increased the expression of NeuN and reduced the expression of GFAP and IBA-1 in the hippocampus of the mice. Further study indicated that NCBP1 overexpression inhibited the expression of IL-6, IL-1ß, and IFN-γ in serum and hippocampus as well as MDA and LDH in the hippocampus, whereas it increased the SOD levels, suggesting that overexpression of NCBP1 could diminish KA-induced inflammatory responses and oxidative stress. The IP-MS analysis identified that ELAVL4 was the NCBP1-interacting protein. In conclusion, this finding suggests that NCBP1 may potentially serve as a drug target for the treatment of epilepsy.

Three-Dimensional Coffee-Ring Effect Induced Deposition on Foam Surface for Enhanced Photothermal Conversion.

Uniformly depositing a thin layer of functional constituents on porous foam is attractive to realize their concentrated interfacial application. Here, a simple but robust polyvinyl alcohol (PVA)-mediated evaporation drying strategy to achieve uniform surface deposition on melamine foam (MF) is introduced. Solutes can be accumulated homogeneously to the surface periphery of MF due to the enhanced coffee-ring effect of PVA and its stabilizing effect on various functional constituents, including molecules and colloidal particles. The deposition thickness is positively correlated with the feeding amounts of PVA but seems to be independent of drying temperature. 3D outward capillary flow driven by the combination of contact surface pinning and continual interfacial evaporation induces the forming of core-shell foams. The enhanced interfacial photothermal effect and solar desalination performance using PVA/polypyrrole-coated MF as a Janus solar evaporator are demonstrated.

Microporous melamine-formaldehyde networks loaded on rice husks for dynamic removal of organic micropollutants.

The alteration of agricultural wastes into novel adsorbents can stimulate their scalability in realistic application, showing great economic and environmental advantages. Here, we proposed a strategy to engineer rice husk (RH) with microporous melamine-formaldehyde networks (MFNs) resins and the utilization for dynamic removal of organic micropollutants rapidly and efficiently. was pre-treated to acquire attractive surface and unique hierarchical porosity, endowing with surface functionalization and essential filtering properties. MFNs can be uniformly generated in-situ on the fully exposed cellulose backbones of the pre-treated RH. MFNs granules functionalized RH (RH@MFNs) exhibited high removal efficiencies over 90% within 30 min for the adsorption of hazardous organic compounds (e.g., phenolic and antibiotic micropollutants) in static tests. Experiment results and density functional theory (DFT) simulation revealed that the synergy of hydrogen bonding, π-πinteraction, and micropore preservation dominates the adsorption. Further dynamic adsorption experiments showed that the removal efficiency and equilibrium removal capacity towards bisphenol A by RH@MFNs packed bed up-flow column were 2.6 and 67 times higher than that of raw RH, respectively. The column adsorption fits well with the Thomas model and bed depth service time (BDST) kinetic model. The inherent macropores inside RH and the roughness caused by the spiky structures and mesopores outside RH, as well as the accumulated MFNs granules, can lead to local turbulence of water flow around RH@MFNs, enabling fast and efficient adsorption. This sustainable and cost-effective preparation of RH-based adsorbents sheds light on the rational design of biomass waste adsorbents for realistic wastewater.

Anti-α-synuclein c-terminal antibodies block PFF uptake and accumulation of phospho-synuclein in preclinical models of Parkinson's disease.

Parkinson's disease (PD), a neurodegenerative disease affecting dopaminergic (DA) neurons, is characterized by decline of motor function and cognition. Dopaminergic cell loss is associated with accumulation of toxic alpha synuclein aggregates. As DA neuron death occurs late in the disease, therapeutics that block the spread of alpha synuclein may offer functional benefit and delay disease progression. To test this hypothesis, we generated antibodies to the C terminal region of synuclein with high nanomolar affinity and characterized them in in vitro and in vivo models of spread. Interestingly, we found that only antibodies with high affinity to the distal most portion of the C-terminus robustly reduced uptake of alpha synuclein preformed fibrils (PFF) and accumulation of phospho (S129) alpha synuclein in cell culture. Additionally, the antibody treatment blocked the spread of phospho (S129) alpha synuclein associated-pathology in a mouse model of synucleinopathy. Blockade of neuronal PFF uptake by different antibodies was more predictive of in vivo activity than their binding potency to monomeric or oligomeric forms of alpha synuclein. These data demonstrate that antibodies directed to the C-terminus of the alpha synuclein have differential effects on target engagement and efficacy. Furthermore, our data provides additional support for the development of alpha synuclein antibodies as a therapeutic strategy for PD patients.

Th17-Related Cytokines Involved in Fluoride-Induced Cecal and Rectal Barrier Damage of Ovariectomized Rats.

To investigate fluoride (F)-induced intestine barrier damage and the role of estrogen deficiency in this progress, a rat model of estrogen deficiency was established through bilateral surgical removal of ovaries. The F exposure model was then continued by adding sodium fluoride (0, 25, 50, and 100 mg/L, calculated on a fluorine ion basis) to drinking water for 90 days. Afterward, intestinal mucosal structure, barrier function, and inflammatory cytokines were evaluated. The results showed that excessive F decreased the developmental parameters (crypt depth) of the cecum and rectum and inhibited the proliferation capacity of the intestinal epithelia, which are more obvious in the state of estrogen deficiency. The distribution of goblet cells and glycoproteins in the intestinal mucosa decreased with the increase in F concentration, and estrogen deficiency led to a further decline, especially in the rectum. Using the immunofluorescence method, the study showed that excessive F caused interleukin-17A (IL-17A) significantly decrease in the cecum and increase in the rectum. Meanwhile, F treatment remarkably upregulated the expression of intestinal IL-1ß, IL-23, and IL-22, while the level of IL-6 was downregulated. In addition, estrogen deficiency increased IL-1ß, IL-6, IL-23, and IL-22, but decreased IL-17A expression in the cecum and rectum. Collectively, F exposure damaged intestinal morphological structure, inhibited epithelial cell proliferation and mucus barrier function, and resulted in the disturbance of T helper (Th) 17 cell-related cytokines expression. Estrogen deficiency may further aggravate F-induced damage to the cecum and rectum.

Estrogen deficiency aggravates fluoride-induced small intestinal mucosa damage and junctional complexes proteins expression disorder in rats.

To investigate the effect of estrogen deficiency on the small intestinal mucosal barrier induced by fluoride (F), F exposure models of ovariectomy (OVX) rats (surgically removed ovaries) and non-OVX rats (normal condition) were established by adding sodium fluoride (NaF) (0, 25, 50, and 100 mg/L, calculated by F ion) in drinking water for 90 days. The intestinal mucosal histomorphology, mucosal barrier function, and protein expression levels of tight junctions (TJs), adhesion junctions (AJs), and desmosomes were evaluated in the duodenum, jejunum, and ileum. Hematoxylin-eosin (HE) staining and 5-Bromo-2-deoxyUridine (BrdU) measurement showed that excessive F-induced damage to intestinal epithelial cells and inhibited the proliferation of intestinal epithelial cells, eventually decreasing the number of goblet cells and decreasing glycoprotein secretion, as indicated by Alcian blue and periodic acid-Schiff (AB-PAS) and periodic acid-Schiff (PAS) staining. Further immunofluorescence analysis demonstrated that excessive F decreased the protein expression levels of occludin, zonula occludens-1 (ZO-1), E-cadherin, and desmoplakin (P < 0.05, P < 0.01) and enhanced the expression of claudin-2 (P < 0.01), suggesting that cell-to-cell junctions were disrupted. Collectively, F exposure impaired the small intestinal mucosal barrier by inducing damage to intestinal epithelial cells and inhibiting intestinal epithelial cell proliferation. Disorders in the junctional complex protein expression blocked the synergy between intercellular communication and aggravated mucosal injury. In particular, estrogen deficiency exacerbated F-induced enterotoxicity, which provides new explanations for the development and severity of intestinal disease in postmenopausal women with high-F areas.

Nitrogen-rich triazine-based porous polymers for efficient removal of bisphenol micropollutants.

Achieving both rapid adsorption rate and high adsorption capacity for bisphenol micropollutants from aquatic systems is critical for efficient adsorbents in water remediation. Here, we elaborately prepared three nitrogen-rich triazine-based porous polymers (NTPs) with similar geometric configurations and nitrogen contents (41.70-44.18 wt%) while tunable BET surface areas and micropore volumes in the range of 454.7-536.3 m2 g-1 and 0.20-0.84 cm3 g-1, respectively. It was systematically revealed that the synergy of hydrogen bonding, π-π electron-donor-acceptor interaction, and micropore preservation promoted the rapid (within 5 min) and high capacity adsorption of bisphenols by NTPs. Particularly, microporous-dominated NTPs-3 with the highest micro-pore volume (0.84 cm3 g-1) displays remarkable adsorption capacity towards bisphenol A as evidenced by the adsorption capacity of 182.23 mg g-1. A simple column filter constructed by NTPs-3 also expressed good dynamic adsorption and regeneration capacity. This work provided new insight into the rational design and engineering of nitrogen-rich porous polymers for the remediation of micropollutant wastewater.

The Covid-19 pandemic and its impact on socioeconomic inequality in psychological distress in the United Kingdom: An update.

This paper extends earlier on socioeconomic inequality in mental health, measured by the General Health Questionnaire, to include the second national lockdown up to March 2021.

Blood chromium exposure, immune inflammation and genetic damage: Exploring associations and mediation effects in chromate exposed population.

Both genetic damage and inappropriate immune function are relevant to cancer of hexavalent chromium [Cr(VI)]. However, its associations with immune response and genetic damage development are poorly understood. To explore their associations and mediating effects, 1249 participants were included from the Occupational Chromate Exposure Dynamic Cohort, and their blood Cr concentrations were measured as internal exposure. A set of biomarkers including urinary 8-hydroxy-2' - deoxyguanosine (8-OHdG), micronucleus frequency (MNF) and mitochondrial DNA copy number (mtCN) was developed to evaluate the landscape of genetic damage of Cr(VI). Serum C-reactive protein (CRP) and first component of complement q (C1q) were measured to reflect immune inflammation. Multivariate linear regression and mediation analyses were applied to assess the potential associations and mediation effects. It was found that blood Cr level showed significant dose-dependent relationships with increasing of MNF and urinary 8-OHdG, while negative association with CRP and C1q. Furthermore, a 1-unit increase in CRP was associated with decreases of - 0.765 to - 0.254 in MNF, - 0.400 to - 0.051 in urinary 8-OHdG. 4.97% of the association between blood Cr level and the increased MNF was mediated by CRP. 11.58% of the relationship between concentration of blood Cr and urinary 8-OHdG was mediated by C1q. These findings suggested that Cr(VI) exposures might prompt genetic damage, possibly partial via worsening immune inflammation.

Substituting clinical features using synthetic medical phrases: Medical text data augmentation techniques.

Biomedical natural language processing (NLP) has an important role in extracting consequential information in medical discharge notes. Detecting meaningful features from unstructured notes is a challenging task in medical document classification. The domain specific phrases and different synonyms within the medical documents make it hard to analyze them. Analyzing clinical notes becomes more challenging for short documents like abstract texts. All of these can result in poor classification performance, especially when there is a shortage of the clinical data in real life. Two new approaches (an ontology-guided approach and a combined ontology-based with dictionary-based approach) are suggested for augmenting medical data to enrich training data. Three different deep learning approaches are used to evaluate the classification performance of the proposed methods. The obtained results show that the proposed methods improved the classification accuracy in clinical notes classification.

Potential Early Identification of a Large Campylobacter Outbreak Using Alternative Surveillance Data Sources: Autoregressive Modelling and Spatiotemporal Clustering.

BACKGROUND: Over one-third of the population of Havelock North, New Zealand, approximately 5500 people, were estimated to have been affected by campylobacteriosis in a large waterborne outbreak. Cases reported through the notifiable disease surveillance system (notified case reports) are inevitably delayed by several days, resulting in slowed outbreak recognition and delayed control measures. Early outbreak detection and magnitude prediction are critical to outbreak control. It is therefore important to consider alternative surveillance data sources and evaluate their potential for recognizing outbreaks at the earliest possible time. OBJECTIVE: The first objective of this study is to compare and validate the selection of alternative data sources (general practice consultations, consumer helpline, Google Trends, Twitter microblogs, and school absenteeism) for their temporal predictive strength for Campylobacter cases during the Havelock North outbreak. The second objective is to examine spatiotemporal clustering of data from alternative sources to assess the size and geographic extent of the outbreak and to support efforts to attribute its source. METHODS: We combined measures derived from alternative data sources during the 2016 Havelock North campylobacteriosis outbreak with notified case report counts to predict suspected daily Campylobacter case counts up to 5 days before cases reported in the disease surveillance system. Spatiotemporal clustering of the data was analyzed using Local Moran's I statistics to investigate the extent of the outbreak in both space and time within the affected area. RESULTS: Models that combined consumer helpline data with autoregressive notified case counts had the best out-of-sample predictive accuracy for 1 and 2 days ahead of notified case reports. Models using Google Trends and Twitter typically performed the best 3 and 4 days before case notifications. Spatiotemporal clusters showed spikes in school absenteeism and consumer helpline inquiries that preceded the notified cases in the city primarily affected by the outbreak. CONCLUSIONS: Alternative data sources can provide earlier indications of a large gastroenteritis outbreak compared with conventional case notifications. Spatiotemporal analysis can assist in refining the geographical focus of an outbreak and can potentially support public health source attribution efforts. Further work is required to assess the location of such surveillance data sources and methods in routine public health practice.

DDI-PULearn: a positive-unlabeled learning method for large-scale prediction of drug-drug interactions.

BACKGROUND: Drug-drug interactions (DDIs) are a major concern in patients' medication. It's unfeasible to identify all potential DDIs using experimental methods which are time-consuming and expensive. Computational methods provide an effective strategy, however, facing challenges due to the lack of experimentally verified negative samples. RESULTS: To address this problem, we propose a novel positive-unlabeled learning method named DDI-PULearn for large-scale drug-drug-interaction predictions. DDI-PULearn first generates seeds of reliable negatives via OCSVM (one-class support vector machine) under a high-recall constraint and via the cosine-similarity based KNN (k-nearest neighbors) as well. Then trained with all the labeled positives (i.e., the validated DDIs) and the generated seed negatives, DDI-PULearn employs an iterative SVM to identify a set of entire reliable negatives from the unlabeled samples (i.e., the unobserved DDIs). Following that, DDI-PULearn represents all the labeled positives and the identified negatives as vectors of abundant drug properties by a similarity-based method. Finally, DDI-PULearn transforms these vectors into a lower-dimensional space via PCA (principal component analysis) and utilizes the compressed vectors as input for binary classifications. The performance of DDI-PULearn is evaluated on simulative prediction for 149,878 possible interactions between 548 drugs, comparing with two baseline methods and five state-of-the-art methods. Related experiment results show that the proposed method for the representation of DDIs characterizes them accurately. DDI-PULearn achieves superior performance owing to the identified reliable negatives, outperforming all other methods significantly. In addition, the predicted novel DDIs suggest that DDI-PULearn is capable to identify novel DDIs. CONCLUSIONS: The results demonstrate that positive-unlabeled learning paves a new way to tackle the problem caused by the lack of experimentally verified negatives in the computational prediction of DDIs.

Old drug repositioning and new drug discovery through similarity learning from drug-target joint feature spaces.

BACKGROUND: Detection of new drug-target interactions by computational algorithms is of crucial value to both old drug repositioning and new drug discovery. Existing machine-learning methods rely only on experimentally validated drug-target interactions (i.e., positive samples) for the predictions. Their performance is severely impeded by the lack of reliable negative samples. RESULTS: We propose a method to construct highly-reliable negative samples for drug target prediction by a pairwise drug-target similarity measurement and OCSVM with a high-recall constraint. On one hand, we measure the pairwise similarity between every two drug-target interactions by combining the chemical similarity between their drugs and the Gene Ontology-based similarity between their targets. Then we calculate the accumulative similarity with all known drug-target interactions for each unobserved drug-target interaction. On the other hand, we obtain the signed distance from OCSVM learned from the known interactions with high recall (≥0.95) for each unobserved drug-target interaction. After normalizing all accumulative similarities and signed distances to the range [0,1], we compute the score for each unobserved drug-target interaction via averaging its accumulative similarity and signed distance. Unobserved interactions with lower scores are preferentially served as reliable negative samples for the classification algorithms. The performance of the proposed method is evaluated on the interaction data between 1094 drugs and 1556 target proteins. Extensive comparison experiments using four classical classifiers and one domain predictive method demonstrate the superior performance of the proposed method. A better decision boundary has been learned from the constructed reliable negative samples. CONCLUSIONS: Proper construction of highly-reliable negative samples can help the classification models learn a clear decision boundary which contributes to the performance improvement.

Association of blood chromium and rare earth elements with the risk of DNA damage in chromate exposed population.

Pollution of heavy metals often occurs in combination with multiple metal ions. Whether the genetic damage among chromate exposed population correlated with rare earth elements (REEs) was still not well elucidated. A total of 291 participants from a chromate production plant were recruited in the present study. The DNA oxidative damage was evaluated by urinary 8-hydroxydeoxyguanosine (8-OHdG) and the concentrations of chromium (Cr) and 15 REEs accumulated in the peripheral blood of participants were determined. The results showed that significant DNA oxidative damage was observed in chromate exposed workers. Blood REEs levels in the exposed group were significantly higher than the control group and blood REEs increased in a concentration dependent manner with Cr. Additionally, significant correlations were observed between blood Cr and 10 REEs concentrations. Blood Cr had a significant positive correlation with urinary 8-OHdG. Blood Cr and Yttrium had a positive interactive effect on urinary 8-OHdG. Collectively, the results suggested workers who had been working in the chromate plant were simultaneously exposed to chromate and a variety of REEs, which could have interactive effects on the DNA damage of workers.

Visualization and quantification of cellular RNA production and degradation using a combined fluorescence and mass spectrometry characterization assay.

Here we report a combined fluorescence and mass spectrometry assay which is capable of stably visualizing and quantifying cellular nucleoside-labeled RNA production and degradation. The fluorescence and mass spectrometry signals from cellular labeled RNAs show a linear correlation. This simple and robust assay benefits the biological community to study RNA metabolism.

Adiponectin inhibits proliferation of vascular endothelial cells induced by Ox-LDL by promoting dephosphorylation of Caveolin-1 and depolymerization of eNOS and up-regulating release of NO.

Oxidized low density lipoprotein (ox-LDL) can induce the proliferation and differentiation of endothelial cells, which is one of the important mechanisms of ox-LDL atherosclerosis. Adiponectin is an endogenous bioactive polypeptide secreted by adipocytes, it participates in the metabolism of fat and glucose. It has the effect of reducing blood triglyceride and LDL content. Adiponectin also inhibits the abnormal proliferation and migration of endothelial cells, but its molecular mechanism is unclear. In this study, we used cell model of Ox-LDL-induced human aortic endothelial cells (HAECs) proliferation to analyze the molecular mechanism of APN inhibiting HAECs abnormal proliferation. The results showed that APN could inhibit the cell viability and DNA synthesis of HAECs after Ox-LDL treatment, up-regulate the apoptosis level and reduce the proportion of S + G2 phase cells. Further analysis showed that adiponectin could promote the dephosphorylation of Caveolin-1, which could dissociate eNOS and Caveolin-1, promote the phosphorylation of eNOS and enhance the synthesis of NO. NO increased expression levels of cleaved caspase 3 and p21 in the cells and inhibited the abnormal proliferation of HAECs. The regulation of phosphorylation and dephosphorylation of Caveolae-1 plays a key role in this process. Further study of the molecular mechanism of Caveolae-1 in the inhibition of HAECs abnormal proliferation by APN may reveal the potential of APN in the treatment of cardiovascular diseases.

CT-based radiomic signatures for prediction of pathologic complete response in esophageal squamous cell carcinoma after neoadjuvant chemoradiotherapy.

The objective of this study was to build models to predict complete pathologic response (pCR) after neoadjuvant chemoradiotherapy (nCRT) in esophageal squamous cell carcinoma (ESCC) patients using radiomic features. A total of 55 consecutive patients pathologically diagnosed as having ESCC were included in this study. Patients were divided into a training cohort (44 patients) and a testing cohort (11 patients). The logistic regression analysis using likelihood ratio forward selection was performed to select the predictive clinical parameters for pCR, and the least absolute shrinkage and selection operator (LASSO) with logistic regression to select radiomic predictors in the training cohort. Model performance in the training and testing groups was evaluated using the area under the receiver operating characteristic curves (AUC). The multivariate logistic regression analysis identified no clinical predictors for pCR. Thus, only radiomic features selected by LASSO were used to build prediction models. Three logistic regression models for pCR prediction were developed in the training cohort, and they were able to predict pCR well in both the training (AUC, 0.84-0.86) and the testing cohorts (AUC, 0.71-0.79). There were no differences between these AUCs. We developed three predictive models for pCR after nCRT using radiomic parameters and they demonstrated good model performance.