Robust COVID-19 Detection in CT Images with CLIP (preprint)

In the realm of medical imaging, particularly for COVID-19 detection, deep learning models face substantial challenges such as the necessity for extensive computational resources, the paucity of well-annotated datasets, and a significant amount of unlabeled data. In this work, we introduce the first lightweight detector designed to overcome these obstacles, leveraging a frozen CLIP image encoder and a trainable multilayer perception (MLP). Enhanced with Conditional Value at Risk (CVaR) for robustness and a loss landscape flattening strategy for improved generalization, our model is tailored for high efficacy in COVID-19 detection. Furthermore, we integrate a teacher-student framework to capitalize on the vast amounts of unlabeled data, enabling our model to achieve superior performance despite the inherent data limitations. Experimental results on the COV19-CT-DB dataset demonstrate the effectiveness of our approach, surpassing baseline by up to 10.6% in `macro' F1 score in supervised learning. The code is available at https://github.com/Purdue-M2/COVID-19_Detection_M2_PURDUE.

Impact of early in-hospital nutritional status on clinical outcomes in Coronavirus disease 2019 patients: A single-center retrospective analysis (preprint)

Background: ： This study investigated the effects of nutritional status at the time of admission on clinical outcomes in patients with Coronavirus disease 2019 (COVID-19). Methods：A retrospective analysis was performed on 54 patients diagnosed with COVID-19. Clinical data of admitted patients, albumin and pre-serum albumin levels, gastrointestinal intolerance, and general information were collected and analyzed. The primary clinical outcomes were length of hospital stay and hospitalization costs. Results：The results showed that albumin and pre-serum albumin levels of patients at admission were negatively associated with the length of hospital stay and hospitalization costs (P < 0.001). Patients with poor appetite had longer hospital stays (P < 0.001) and higher hospital costs (P = 0.022). Conclusion：These results indicated that the nutritional status at admission can directly influence the clinical outcomes of COVID-19.

SARS-CoV-2 N protein-induced Dicer, XPO5, SRSF3, and hnRNPA3 downregulation causes pneumonia (preprint)

Age is a major risk factor for coronavirus disease (COVID-19)-associated severe pneumonia and mortality; however, the underlying mechanism remains unclear. Herein, we investigated whether age-related deregulation of RNAi components and RNA splicing factors affects COVID-19 severity. Decreased expression of RNAi components (Dicer and XPO5) and splicing factors (SRSF3 and hnRNPA3) correlated with increased severity of COVID-19 and SARS-CoV-2 nucleocapsid (N) protein-induced pneumonia. N protein induced autophagic degradation of Dicer, XPO5, SRSF3, and hnRNPA3, repressing miRNA biogenesis and RNA splicing and inducing DNA damage, proteotoxic stress, and pneumonia. Dicer, XPO5, SRSF3, and hnRNPA3 were downregulated with age in mouse lung tissues. Older mice experienced more severe N protein-induced pneumonia than younger mice. However, treatment with a poly(ADP-ribose) polymerase inhibitor (PJ34) or aromatase inhibitor (anastrozole) relieved N protein-induced pneumonia by restoring Dicer, XPO5, SRSF3, and hnRNPA3 expression. These findings will aid in developing improved treatments for SARS-CoV-2-associated pneumonia.

Iterative In Silico Screening for Optimizing Stable Conformation of Anti-SARS-CoV-2 Nanobodies (preprint)

Abstract--Nanobodies (Nbs or VHHs) are single-domain antibodies (sdAbs) derived from camelid heavy-chain antibodies. The variable region of these nanobodies has special and unique characteristics, such as small size, good tissue penetration, and cost-effective production, making nanobodies a good candidate for the diagnosis and treatment of viruses. Identifying effective nanobodies against the COVID-19 would help us defeat this dangerous virus or other unknown variants in future. Herein, we introduce an in silico screening strategy for optimizing stable conformation of anti-SARS-CoV-2 nanobodies. Firstly, various complexes containing nanobodies were downloaded from the RCSB database, which were identified from immunized llamas. The primary docking between nanobodies and the SARS-CoV-2 spike protein receptor-binding domain was performed through ClusPro program, with the manually screening that leaving the reasonable conformation to the next step. Then, the binding distances of atoms between the antigen-antibody interfaces was measured through the Neighbor Search algorithm. Finally, filtered nanobodies were acquired according to HADDOCK scores through HADDOCK docking the Covid spike protein with nanobodies under restrictions of calculated molecular distance between active residues and antigenic epitopes less than 4.5 A. In this way, those nanobodies which with more reasonable conformation and with stronger neutralizing efficacy were acquired. This three-steps screening strategy iteratively in Silico greatly improved the accuracy of screening desired nanobodies compared to using only ClusPro docking or default HADDOCK docking settings. It provides new ideas for the screening of novel antibodies and computer-aided screening methods.

Online Education Isn’t the Best Choice: Evidence-Based Medical Education in the Post-epidemic Era—A Cross-Sectional Study (preprint)

Background The COVID-19 pandemic led many educational institutions to shift to online courses, making blended education a significant trend in teaching. We examined the effectiveness of blended learning in an evidence-based medicine course.Methods We compared the examination scores of a blended learning group, an online only group, and a traditional offline group and conducted a questionnaire survey on students’ preferences for different learning modes and the reasons for their preferences. A total of 2100 undergraduate students in clinical medicine were included in this cross-sectional study. Examination results were collected, and questionnaires were administered to the study participants. We compared the mean theoretical scores and exam pass rates of the three teaching groups using ANOVA and c2test for multiple comparisons.Results The blended group’s theoretical scores and pass rate were significantly higher than those of the offline and online groups. Furthermore, 71.6% preferred the blended teaching mode. Most students believed that blended teaching was the most effective mode—offline education: 7.86%; online education: 26.14%; blended education: 66%. Subsequently, in a questionnaire administered to a blended group of students, their foremost reason for liking online instruction was ‘flexible in time and space’ (99%), followed by ‘can be viewed repeatedly, facilitating a better understanding of knowledge points’ (98%). Their foremost reason for liking offline teaching was ‘helps to create a good learning atmosphere’ (97%), followed by ‘teachers can control students’ learning status in real time’ (89%).Conclusions This study explored the effectiveness of learning in evidence-based medicine courses by comparing the learning outcomes and personal perceptions of three different teaching modes. This is the first cross-sectional study in which three different teaching models are compared and discussed in an evidence-based medicine course. We also elaborate on the specific instructional protocols for each model. This study shows that using a blended education approach in evidence-based medicine courses can improve students’ learning motivation, autonomy, and satisfaction. It also enhances instructional efficiency, thereby improving students’ understanding of the course content.

Serum neutralization of SARS-CoV-2 Omicron BA.2, BA.2.75, BA.2.76, BA.5, BF.7, BQ.1.1 and XBB.1.5 in individuals receiving Evusheld (preprint)

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Omicron variant is undergoing continuous evolution and convergent mutation, which has led to the rapid emergence of several new variants. These new subvariants carry different mutations in theirreceptor-binding domain (RBD), raising concerns that they may evade neutralizing monoclonal antibodies (mAbs). In this study, we investigated the serum neutralization efficacy of Evusheld (cilgavimab and tixagevimab) antibody cocktails against SARS-CoV-2 Omicron sublineages BA.2, BA.2.75, BA.2.76, BA.5, BF.7, BQ.1.1 and XBB.1.5. Our results show that Evusheld retained neutralizing activity against BA.2, BA.2.75 and BA.5, albeit with somewhat reduced titers. However, the neutralizing activity of Evusheld against BA.2.76, BF.7, BQ.1.1 and XBB.1.5 significantly decreased, with XBB.1.5 showing the greatest escape activity among the subvariants, followed by BQ.1.1, BA.2.76 and BF.7. We also observed that recipients of Evusheld displayed elevated antibody levels in their serum, which efficiently neutralized the original variant, and exhibited different characteristics of infection than those who did not receive Evusheld. These findings provide important guidance for the application of Evusheld in treating SARS-CoV-2 subvariant infections.

Enhancing Food Supply Chain in Green Logistics with Multi-Level Processing Strategy under Disruptions

Food supply chains (FSCs) have long been exposed to environmental variability and shock events caused by various economic, political, and infrastructural factors. The outbreak of the COVID-19 pandemic has further exposed and identified the vulnerability of FSCs, and promoted integrated optimization approaches for building resilience. However, existing works focusing on general supply chains (SCs) and FSCs have not been fully aware of the distinct characteristics of FSCs in green logistics, i.e., the expiration of fresh products. In reality, perishable food materials can be processed into products of different processing levels (i.e., multi-level processing) for longer shelf lives, which can serve as a timely and economic strategy to increase safety stocks for mitigating disruption risks. Motivated by this fact, we study the problem of enhancing FSC with a multi-level processing strategy. An integrated location, inventory, and distribution planning model for a multi-echelon FSC under COVID-19-related disruptions is formulated to maximize the total profit over a finite planning horizon. Specifically, a two-stage stochastic programming model is presented to hedge against disruption risks, where scenarios are generated to characterize geographical impact induced by source-region disruptions. For small-scale problems, the model can be solved with commercial solvers. To exactly and efficiently solve the large-scale instances, we design an integer L-shaped method. Numerical experiments are conducted on a case study and randomly generated instances to show the efficiency of our model and solution method. Based on the case study, managerial insights are drawn.

Gaseous and Particulate Pollution in the Wu-Chang-Shi Urban ,Agglomeration on the Northern Slope of Tianshan Mountains from 2017 to 2021

Rapid social development has led to serious air pollution problems in cities, and air pollutants, including gaseous pollutants and particulate matter, have an important impact on climate, the environment, and human health. This study analyzed the characteristics, potential sources, and causes of air pollution in the Wu-Chang-Shi urban cluster. The results showed that NO2, CO, SO2, PM10, and PM2.5 had a tendency to decrease, while O3 showed an increasing trend. The concentrations of SO2, NO2, CO, PM2.5, and PM10 showed the highest values in winter and the lowest values in summer, with similar seasonal variations. However, the concentration of O3 was highest in the summer and lowest in the winter. Compared with the pollutant concentrations in other Chinese cities, PM2.5, PM10, and NO2 are more polluted in the Wu-Chang-Shi urban. Meteorological factors have a greater impact on pollutant concentrations, with higher concentrations of major pollutants observed when wind speeds are low and specific wind directions are observed, and higher secondary pollutant O3 concentrations observed when wind speeds are low and specific wind directions are observed. The backward trajectory and concentration weighting analysis show that the particulate pollutants in the Wu-Chang-Shi urban in winter mainly come from Central Asia and surrounding cities. O3 showed an increasing trend before and after the novel coronavirus outbreak, which may be related to changes in NOX, volatile organic compounds, and solar radiation intensity, and the concentrations of SO2, NO2, CO, PM10, and PM2.5 showed an overall decreasing trend after the outbreak and was smaller than before the outbreak, which is related to the reduction of industrial and anthropogenic source emissions during the outbreak.

Monkeypox virus quadrivalent mRNA vaccine induces antibody responses and cellular immunity and protects mice against Vaccinia virus (preprint)

There is an urgent need for efficient and safe vaccines against the monkeypox virus (MPXV) in response to the rapidly spreading monkeypox epidemic. In the age of COVID-19, mRNA vaccines have been highly successful and emerged as platforms enabling rapid development and large-scale preparation. Here, we have developed two MPXV quadrivalent mRNA vaccines, named mRNA-A-LNP and mRNA-B-LNP, based on two IMVs (A29L and M1R) and two EEVs (A35R and B6R). By administering mRNA-A-LNP and mRNA-B-LNP intramuscularly twice, mice have induced MPXV-specific IgG antibodies and potent Vaccinia virus (VACV)-specific neutralizing antibodies. Additionally, it elicited durable MPXV-specific killer memory T-cell immunity as well as memory B-cell immunity in mice. Furthermore, the passive transfer of sera from mRNA-A-LNP and mRNA-B-LNP-immunized mice protected nude mice against the VACV challenge. In addition, two doses of mRNA-A-LNP and mRNA-B-LNP were also protective against the VACV challenge in mice. Overall, our results demonstrated that mRNA-A-LNP and mRNA-B-LNP appear to be safe and effective vaccine candidates against monkeypox epidemics, as well as against outbreaks caused by other orthopoxviruses, including the smallpox virus.

Evaluating the Effect of SARS-CoV-2 Spike Mutations by Causal Inference (preprint)

Driven by various mutations on the viral Spike protein, diverse variants of SARS-CoV-2 have emerged and prevailed repeatedly, which necessitates the identification of key Spike mutations for fitness enhancement. To address the need, this manuscript formulates a principled framework of causal inference for evaluating Spike mutations. In the context of large-scale genomes of SARS-CoV-2, it estimates the contribution of mutations to viral fitness across lineages and validates mutational effects on the Spike stability, receptor-binding affinity, and potential for immune escape. Key fitness-enhancing mutations and protein regions are recognized and studied. The transmission capacity of any new variant possessing these mutations can be predicted based on our model, solely based on the viral sequence. This research produces an innovative and systematic insight into SARS-CoV-2 and promotes functional studies of its key mutations.

Transcriptome and targeted metabolome analysis revealed the effects of combined red and blue light on the growth and secondary metabolism of Scutellaria baicalensis Georgi

Scutellaria baicalensis Georgi is a medicinal plant commonly used in China and other parts of East Asia. A high flavonoid content endows it with multiple beneficial biological activities that have anti-inflammatory, antibacterial, antiviral, and anti-COVID19 properties. Light-emitting diodes (LEDs) have been recognized as effective artificial lights to enhance plant growth and the accumulation of secondary metabolites for commercial plant production. However, little is known regarding the effects of LEDs on S. baicalensis. Here, we explored the effects of monochromatic blue light (B, 460 nm), monochromatic red light (R, 660 nm), white light (CK), and different combinations of R and B (R9B1, R7B3, R5B5, R3B7, and R1B9) on the growth of, and flavonoid accumulation in S. baicalensis. The results revealed that under R:B ratios of 9:1 or 7:3, the whole plant and roots of S. baicalensis seedlings had a higher biomass and flavonoid content. Targeted metabolomics analysis showed that 48 differentially expressed metabolites (DEMs) were verified between different groups, and the number of upregulated DEMs, particularly flavonoids, were higher in the R9B1 and R7B3 groups compared with the CK. Transcriptome data identified 1412 and 1508 differentially expressed genes (DEGs) in the R9B1 and R7B3 groups, respectively, in contrast to the CK. KEGG pathway analysis indicated that DEGs in both the R9B1 and R7B3 groups were primarily enriched in the phenylpropane biosynthesis, plant hormone signal transduction, flavonoid biosynthesis, starch and sucrose metabolism, galactose metabolism, cartenoid biosynthesis, zeatin biosynthesis, and nitrogen metabolism pathways. The qRT-PCR results showed that SbPAL, SbCLL-7, SbCHI, SbFNS, and SbOMT encoding enzymes for the flavonoid biosynthesis pathway were significantly upregulated in S. baicalensis, which was consistent with the transcriptome data. Finally, based on correlation analysis between the main flavonoids in S. baicalensis and the genes encoding transcription factors and enzymes for the flavonoid metabolism pathway, a co-expression network map was developed, which provided a basis for the mining of light responsive genes related to flavonoids biosynthesis in S. baicalensis. This is the first report to articulate how the combination of red light and blue light influences the growth and secondary metabolism of S. baicalensis.

Automated de novo drug design and Anti-coronavirus activity studies of 3CLpro inhibitors (preprint)

Activity-based lead screening and druggability-based structure optimization are usually torn into two independent processes, although both are related to the chemical structure of target compounds. It leads to an unsatisfactory success ratio and inefficient drug development. DeepRLADS, a de novo molecular design assay, was established based on deep reinforcement learning training, integrating activity screening and structure optimization into a single artificial intelligence (AI)-based drug discovery module. Targeting the relatively easy-verified porcine epidemic diarrhea coronavirus (PEDV) main protease (Mpro, 3CLpro), a diverse virtual library of potential 3CLpro inhibitors was created by splitting existing inhibitors, digitizing fragments, and de novo design, focusing on their potential biological activities and pharmacological properties. The AI-designed compound 11b has a novel catechol-pyrazoline structure, presenting efficient inhibition against Mpro, surprising protection against PEDV infection, low toxicity, and favorable pharmacokinetic properties in vitro and in vivo. Low-dose oral 11b (5 mg/kg) reversed PEDV-induced diarrhea in 5-day-old piglets and greatly improved the survival rate (from 0% to 100%). A preclinical study (560 cases) in eight independent farms indicated an inspiring recovery rate (survival rate: 95.8% in treated piglets VS 9.1% in untreated piglets). Compound 11b is the first proven chemical efficiently protecting piglets in a large-scale preclinical study with multiple centers. It suggested that the novel strategy used by DeepRLADS was a hopeful approach for further AI-based drug design.

Impact of Coronavirus Disease of 2019 Vaccine on Health and Physical Activities Among Physical Education Students in China

Purpose This research focused primarily on the impact of the SARS-CoV-2 Vaccine (VeroCell) on Chinese physical education (PE) students' health and physical activity (PA) performance. Methods This study used quantitative methods and phenomenological procedures to collect and analyze data. Survey techniques were the main method used for collecting data from Chinese university students, using a self-designed questionnaire with a Cronbach's alpha α value of 0.76. To ensure the quality of the study, confirmatory factor analyses (CFA) were conducted, and the internal consistency reliability of the instrument was measured (alpha coefficient = 0.82). The determined sample size was 490 and around 90% as the minimum sample size was determined with the help of a sample size calculator. The author using factor loadings with h2 and an independent-sample t-test analyzed the responses of the remaining valid participants (n = 443 with a response rate of 90.40). Results Most participants (around 94%) did not experience any adverse reactions that impacted their daily life activities, health, or performance during physical activity. However, about 30–40% of students felt lethargy, weakness, muscle pain, or swelling. Regarding the impact of the vaccine on daily life, there was no difference in the responses between participants who had only received one shot of the coronavirus disease 2019 (COVID-19) vaccine and those who had received two shots (p > 0.05 in most cases). Conclusion The study concluded that the COVID-19 vaccine had no significant effect on PE students' daily activities, health, and PA performance. The results of this study could be used by policymakers to encourage people to get vaccinated and eradicate the isolation caused by COVID-19, which leads many people to develop various non-communicable diseases (NCDs).

Assessment on a blended teaching model for surgical laboratory course among international medical students in response to the COVID-19 pandemic: a case study in a Chinese university (preprint)

Background With the ongoing crisis of the COVID-19 pandemic in China and the increasing online teaching platforms, the blended teaching model for international medical students is necessary. Our study aims at assessing the effectiveness of the combination of online and classroom teaching in surgical laboratory course among international medical students in a Chinese university.Methods This was a cross-sectional study conducted in a Chinese university. All international medical students enrolled in 2016–2019 were included in our study and were all third year undergraduate students majoring in Clinical Medicine for a 5-year program. At the final stage of the surgical laboratory course learning, the scores of OSCE (Objective Structured Clinical Examination) and the performance of usual learning and the skills practice from 2019 to 2022 were used as measures to assess the effectiveness. STATA 14 software was applied to conduct the relevant descriptive and statistical analysis. The statistical significance was set at P < 0.05.Results A total of 29 international medical students from 14 developing countries were included in our study. The mean age of them was 25.5 ± 2.2 years. The mean scores of OSCE was 76.55 ± 21.91, and it was 76.80 ± 22.05 for the usual learning and skill practice among all the international medical students. The mean scores of OSCE was 75.69 ± 21.40 for the international medical students in the blended teaching model, close to that (77.47 ± 23.21) in the traditional teaching model. Besides, the mean scores of usual learning and skill practice for the international medical students in the blended teaching model was 74.40 ± 20.92, lower than that (77.43 ± 23.18) in the traditional teaching model (P > 0.0.05).Conclusions Our study as a preliminary study confirmed that a blended teaching model was effective like the traditional teaching model, which can reduce the disruption for the international medical students’ study during the COVID-19 pandemic. Online interactions between international medical students and instructors positively contribute to global health education. Better coordination of online and face-to-face blended teaching models is an important direction for global medical education.

Parenting Stress During COVID-19 Lockdown: Correlates with Family and Child Factors

In response to the COVID-19, a 76-day city-wide strict lockdown was imposed in Wuhan, China. This study aimed to document the family’s psychological status during the lockdown and test the role of family functioning, children’s mental health, child-parent relationship as well as parenting time during pandemic on parenting stress. The results showed that nearly 18% of the children exhibited clinical-level mental health problems. The children’s mental health and child-parent conflict fully mediated general family functioning’s impact on parenting stress. The change in childcaring time moderated the effect of the children’s mental health problems and child-parent conflict on parenting stress. Findings indicated that, during COVID-19 lockdown, children’s mental health and child-parent conflict contributed to parenting stress. More childrearing time would reduce the impact of children’s mental health on parenting stress.

Disentangling the common genetic architecture and causality of rheumatoid arthritis and systemic lupus erythematosus with COVID-19 outcomes: genome-wide cross trait analysis and bi-directional Mendelian randomization study (preprint)

COVID-19 may cause a dysregulation of the immune system and has complex relationships with multiple autoimmune diseases, including rheumatoid arthritis (RA) and systemic lupus erythematosus (SLE). However, little is known about their common genetic architecture. We analysed summary-level genetic data from the latest COVID-19 host genetics consortium and consortia on RA and SLE to examine the shared genetic etiology and causal relationship between COVID-19 and RA/SLE. The cross-trait meta-analysis identified 46, 47, and 19 shared genetic loci for severe COVID-19, COVID-19 hospitalization, and SARS-CoV-2 infection with RA, and 19, 24, and 11 shared loci with SLE, respectively. Shared genes were significantly enriched in the spleen, lung, whole blood, and small intestine, and involved in immune function, inflammation and coagulation process. Co-localization analysis identified eight shared loci in TYK2, IKZF3, COL11A2, PSORS1C1, MANEAL and COG6 genes for COVID-19 with RA, and four in CRHR1, FUT2 and NXPE3 genes for COVID-19 with SLE. Bi-directional Mendelian randomization analysis suggested RA is associated with a higher risk of COVID-19 hospitalization, and COVID-19 is not related to RA or SLE. Our novel findings improved the understanding of the common genetic aetiology shared by COVID-19, RA and SLE, and suggested an increased risk of COVID-19 hospitalization in people with higher genetic liability to RA.

A Structural Comparison of SARS-CoV-2 Main Protease and Animal Coronaviral Main Protease Reveals Species-Specific Ligand Binding and Dimerization Mechanism

Animal coronaviruses (CoVs) have been identified to be the origin of Severe Acute Respiratory Syndrome (SARS)-CoV, Middle East respiratory syndrome (MERS)-CoV, and probably SARS-CoV-2 that cause severe to fatal diseases in humans. Variations of zoonotic coronaviruses pose potential threats to global human beings. To overcome this problem, we focused on the main protease (Mpro), which is an evolutionary conserved viral protein among different coronaviruses. The broad-spectrum anti-coronaviral drug, GC376, was repurposed to target canine coronavirus (CCoV), which causes gastrointestinal infections in dogs. We found that GC376 can efficiently block the protease activity of CCoV Mpro and can thermodynamically stabilize its folding. The structure of CCoV Mpro in complex with GC376 was subsequently determined at 2.75 Å. GC376 reacts with the catalytic residue C144 of CCoV Mpro and forms an (R)- or (S)-configuration of hemithioacetal. A structural comparison of CCoV Mpro and other animal CoV Mpros with SARS-CoV-2 Mpro revealed three important structural determinants in a substrate-binding pocket that dictate entry and release of substrates. As compared with the conserved A141 of the S1 site and P188 of the S4 site in animal coronaviral Mpros, SARS-CoV-2 Mpro contains N142 and Q189 at equivalent positions which are considered to be more catalytically compatible. Furthermore, the conserved loop with residues 46–49 in animal coronaviral Mpros has been replaced by a stable α-helix in SARS-CoV-2 Mpro. In addition, the species-specific dimerization interface also influences the catalytic efficiency of CoV Mpros. Conclusively, the structural information of this study provides mechanistic insights into the ligand binding and dimerization of CoV Mpros among different species.

Research on the Cross-Chain Model of Rice Supply Chain Supervision Based on Parallel Blockchain and Smart Contracts

Rice is one of the three major staple foods in the world, and the quality and safety of rice are related to the development of human beings. The new crown epidemic, pesticide residues, insect pests, and heavy metal pollution have a certain security impact on the food supply chain. The rice supply chain is characterized by a long life cycle;complex roles in the main links;many types of hazards;and multidimensional, multisource, and heterogeneous information. To strengthen the rice supply chain’s supervision ability under the epidemic situation, a supervision cross-chain model suitable for the complicated data of the rice supply chain based on parallel blockchain theory and smart contract technology was built. Firstly, the data collected in the rice supply chain and different types of data stored in different parallel blockchains were analyzed. Secondly, based on data analysis, a collection/supervision cross-chain mechanism based on “hash lock + smart contract + relay chain”, a concurrency mechanism based on the K-means algorithm and a Bloom filter, and a consensus mechanism suitable for multichain consensus named the Supervision Practical Byzantine Fault Tolerance (SPBFT) were proposed. Furthermore, a cross-chain model of rice supply chain supervision was constructed. Finally, theoretical verification and simulation experiments were used to analyze the operation process, safety, cross-chain efficiency, and scalability of the model. The results showed that the application of parallel blockchains and smart contracts to supervision of rice supply chain information improved the convenience and security of information interaction between various links in the rice supply chain, the storage cost of supply chain data and the high latency of interaction was reduced, and the refined management of the rice supply chain data and personnel was realized. This research applied new information technology to the coordination and resource sharing of the food supply chain, and provides ideas for the digital transformation of the food industry.