A mechanism for SARS-CoV-2 RNA capping and its inhibition by nucleotide analog inhibitors.

Decoration of cap on viral RNA plays essential roles in SARS-CoV-2 proliferation. Here, we report a mechanism for SARS-CoV-2 RNA capping and document structural details at atomic resolution. The NiRAN domain in polymerase catalyzes the covalent link of RNA 5' end to the first residue of nsp9 (termed as RNAylation), thus being an intermediate to form cap core (GpppA) with GTP catalyzed again by NiRAN. We also reveal that triphosphorylated nucleotide analog inhibitors can be bonded to nsp9 and fit into a previously unknown "Nuc-pocket" in NiRAN, thus inhibiting nsp9 RNAylation and formation of GpppA. S-loop (residues 50-KTN-52) in NiRAN presents a remarkable conformational shift observed in RTC bound with sofosbuvir monophosphate, reasoning an "induce-and-lock" mechanism to design inhibitors. These findings not only improve the understanding of SARS-CoV-2 RNA capping and the mode of action of NAIs but also provide a strategy to design antiviral drugs.

Rational Design of the Alkali Metal Sn-Based Mixed Halides with Large Birefringence and Wide Transparent Range.

Birefringent materials are widely used in various advanced optical systems, owing to their vital role in creating and controlling polarized light. Currently, Sn2+-based compounds containing stereochemically active lone-pair (SCALP) cations are extensively investigated and considered as one class of promising birefringent materials. To solve the problem of relatively narrow bandgap of Sn2+-based compounds, alkali metals and multiple halogens are introduced to widen the bandgap during the research. Based on this strategy, four new Sn2+-based halides, A2Sn2F5Cl and ASnFCl2 (A = Rb and Cs), with large birefringence, short ultraviolet (UV) cutoff edge, and wide transparent range are successfully found. The birefringences of A2Sn2F5Cl (A = Rb and Cs) are 0.31 and 0.28 at 532 nm, respectively, which are among the largest in Sn-based halide family. Remarkably, A2Sn2F5Cl possess relatively shorter UV cutoff edge (<300 nm) and broad infrared (IR) transparent range (up to 16.6 µm), so they can become promising candidates as birefringent materials applied in both UV and IR regions. In addition, a comprehensive analysis on crystal structures and structure-property relationship of metal Sn2+-based halides is performed to fully understand this family. Therefore, this work provides insights into designing birefringent materials with balanced optical properties.

Electrical micro flow cytometry with LSTM and its application in leukocyte differential.

This paper developed an electrical micro flow cytometry to realize leukocyte differentials leveraging a constrictional microchannel and a deep neural network. Firstly, purified granulocytes, lymphocytes or monocytes traveled through the constrictional microchannel with a cross-sectional area marginally larger than individual cells and produced large impedance variations by blocking focused electric field lines. By optimizing key elements (e.g., normalization, learning rate, batch size and neuron number) of the recurrent neural network (RNN), electrical results of purified leukocytes were analyzed to establish a leukocyte differential system with a classification accuracy of 95.2%. Then the leukocyte mixtures were forced to travel through the same constrictional microchannel, producing mixed impedance profiles which were classified into granulocytes, lymphocytes and monocytes based on the aforementioned differential system. As to the classification results, two leukocyte mixtures from the same donor were processed, producing comparable classification results, which were 57% versus 59% of granulocytes, 37% versus 34% of lymphocytes and 6% versus 7% of monocytes. These results validated the established classification system based on the constrictional microchannel and the recurrent neural network, providing a new perspective of differentiating white blood cells by electrical flow cytometry.

Segmentation, feature extraction and classification of leukocytes leveraging neural networks, a comparative study.

The gold standard of leukocyte differentiation is a manual examination of blood smears, which is not only time and labor intensive but also susceptible to human error. As to automatic classification, there is still no comparative study of cell segmentation, feature extraction, and cell classification, where a variety of machine and deep learning models are compared with home-developed approaches. In this study, both traditional machine learning of K-means clustering versus deep learning of U-Net, U-Net + ResNet18, and U-Net + ResNet34 were used for cell segmentation, producing segmentation accuracies of 94.36% versus 99.17% for the dataset of CellaVision and 93.20% versus 98.75% for the dataset of BCCD, confirming that deep learning produces higher performance than traditional machine learning in leukocyte classification. In addition, a series of deep-learning approaches, including AlexNet, VGG16, and ResNet18, was adopted to conduct feature extraction and cell classification of leukocytes, producing classification accuracies of 91.31%, 97.83%, and 100% of CellaVision as well as 81.18%, 91.64% and 97.82% of BCCD, confirming the capability of the increased deepness of neural networks in leukocyte classification. As to the demonstrations, this study further conducted cell-type classification of ALL-IDB2 and PCB-HBC datasets, producing high accuracies of 100% and 98.49% among all literature, validating the deep learning model used in this study.

Leukocyte differential based on an imaging and impedance flow cytometry of microfluidics coupled with deep neural networks.

The differential of leukocytes functions as the first indicator in clinical examinations. However, microscopic examinations suffered from key limitations of low throughputs in classifying leukocytes while commercially available hematology analyzers failed to provide quantitative accuracies in leukocyte differentials. A home-developed imaging and impedance flow cytometry of microfluidics was used to capture fluorescent images and impedance variations of single cells traveling through constrictional microchannels. Convolutional and recurrent neural networks were adopted for data processing and feature extractions, which were then fused by a support vector machine to realize the four-part differential of leukocytes. The classification accuracies of the four-part leukocyte differential were quantified as 95.4% based on fluorescent images plus the convolutional neural network, 90.3% based on impedance variations plus the recurrent neural network, and 99.3% on the basis of fluorescent images, impedance variations, and deep neural networks. Based on single-cell fluorescent imaging and impedance variations coupled with deep neural networks, the four-part leukocyte differential can be realized with almost 100% accuracy.

Advance of microfluidic flow cytometry enabling high-throughput characterization of single-cell electrical and structural properties.

This paper reported a micro flow cytometer capable of high-throughput characterization of single-cell electrical and structural features based on constrictional microchannels and deep neural networks. When single cells traveled through microchannels with constricted cross-sectional areas, they effectively blocked concentrated electric field lines, producing large impedance variations. Meanwhile, the traveling cells were confined within the cross-sectional areas of the constrictional microchannels, enabling the capture of high-quality images without losing focuses. Then single-cell features from impedance profiles and optical images were extracted from customized recurrent and convolution networks (RNN and CNN), which were further fused for cell-type classification based on support vector machines (SVM). As a demonstration, two leukemia cell lines (e.g., HL60 vs. Jurkat) were analyzed, producing high-classification accuracies of 99.3% based on electrical features extracted from Long Short-Term Memory (LSTM) of RNN, 96.7% based on structural features extracted from Resnet18 of CNN and 100.0% based on combined features enabled by SVM. The microfluidic flow cytometry developed in this study may provide a new perspective for the field of single-cell analysis.

Fulvic acid alleviates the stress of low nitrogen on maize by promoting root development and nitrogen metabolism.

The potential of fulvic acid (FA) to improve plant growth has been acknowledged, but its effect on plant growth and nutrient uptake under nutrient stress remains unclear. This study investigated the effects of different FA application rates on maize growth and nitrogen utilization under low nitrogen stress. The results showed that under low nitrogen stress, FA significantly stimulated maize growth, particularly root development, biomass, and nitrogen content. The enhanced activity levels of key enzymes in nitrogen metabolism were observed, along with differential gene expression in maize, which enriched nitrogen metabolism, amino acid metabolism and plant hormone metabolism. The application of FA regulated the hormones' level, reduced abscisic acid content in leaves and Me-JA content in roots, and increased auxin and zeatin ribose content in leaves. This study concludes that, by promoting root development, nitrogen metabolism, and hormone metabolism, an appropriate concentration of FA can enhance plant tolerance to low nitrogen conditions and improve nitrogen use efficiency.

AX·(H2SeO3)n (A = K, Cs; X = Cl, Br; n = 1, 2): A Series of Ionic Cocrystals as Promising UV Birefringent Materials with Large Birefringence and Wide Band Gap.

The design and syntheses of new birefringent crystals will be of great importance in commercial applications and materials science. A series of ultraviolet (UV) birefringent crystals, AX·(H2SeO3)n (A = K, Cs; X = Cl, Br; n = 1, 2), with large sizes up to 23 × 6 × 3 mm3, was successfully synthesized by simple aqueous solution method. These four compounds belong to three different space groups. Isomorphic KCl·(H2SeO3)2 and CsCl·(H2SeO3)2 crystallize in the P1¯ space group, while CsBr·(H2SeO3)2 and CsCl·H2SeO3 crystallize in the P21/m and P21/c space groups, respectively. They exhibit cocrystal structures composed of [2(H2SeO3)]∞ and [AX]∞ frameworks, ingeniously inheriting the large optical anisotropy of selenite and the wide band gap of alkali metal halide. And it proves that these compounds indeed possess large birefringence (0.1-0.17 at 532 nm) and short UV cutoff edges (227-239 nm), achieving a balance of optical properties. This research affords a simple and viable strategy for the design and syntheses of new UV birefringent crystals. Besides, it is also found that the n value and ionic size (A and X ions) have important influences on the crystal structures and optical properties of AX·(H2SeO3)n. And this will promote further understanding of the alkali metal halide selenite family.

Na3K6(CO3)3(NO3)2X·6H2O (X = NO3, Cl, Br): Exploring High-Performance UV Birefringent Crystals Induced by Coplanar π-Conjugated CO3 and NO3 Groups.

Planar π-conjugated groups, like CO3, NO3, and BO3 triangles, are ideal functional units for designing birefringent materials due to their large optical anisotropy and wide band gap. The key point for designing birefringent crystals is to select appropriate functional building blocks (FBBs) and the proper arrangement mode. It is well known that the substitution strategy has proven to be a promising and accessible approach. In this work, alkali metals were chosen to regulate and control two different π-conjugated groups, CO3 and NO3, to build new compounds with large birefringence. Subsequently, three new compounds, Na3K6(CO3)3(NO3)2X·6H2O (X = NO3, Cl, Br), were successfully synthesized using the hydrothermal method. The aliovalent substitution between the [NO3]- anionic group and halogen anions [Cl]-/[Br]- has been achieved in these compounds. Na3K6(CO3)3(NO3)2X·6H2O feature the well-coplanar CO3 and NO3 groups in their crystal structure. This coplanar arrangement mode may effectively enhance the anisotropic polarizability of Na3K6(CO3)3(NO3)2X·6H2O. And their experimental birefringence can reach 0.094-0.131 at 546 nm. Diffuse reflectance spectra demonstrate that these compounds exhibit short ultraviolet (UV) absorption edges of ∼235 nm. Meanwhile, Na3K6(CO3)3(NO3)2X·6H2O also have an easily grown capacity under facile conditions. This work not only reports three new potential UV birefringent crystals but also provides a strategy to make the π-conjugated MO3 group coplanar.

[Developmental toxicity of Cry1Ab protein in the embryonic stem-cell model].

OBJECTIVE: To evaluate the developmental toxicity of Cry1Ab protein by studying its effects on cell proliferation and differentiation ability using a developmental toxicity assessment model based on embryonic stem-cell. METHODS: Cry1Ab protein was tested in seven dose groups (31.25, 62.50, 125.00, 250.00, 320.00, 1 000.00, and 2 000.00 µg/L) on mouse embryonic stem cells D3 (ES-D3) and 3T3 mouse fibroblast cells, with 5-fluorouracil (5-FU) used as the positive control and phosphate buffer saline (PBS) as the solvent control. Cell viability was detected by CCK-8 assay to calculate the 50% inhibitory concentration (IC50) of the test substance for different cells. Additionally, Cry1Ab protein was tested in five dose groups (125.00, 250.00, 320.00, 1 000.00, and 2 000.00 µg/L) on ES-D3 cells, with PBS as the solvent control and 5-FU used for model validation. After cell treatment, cardiac differentiation was induced using the embryonic bodies (EBs) culture method. The growth of EBs was observed under a microscope, and their diameters on the third and fifth days were measured. The proportion of EBs differentiating into beating cardiomyocytes was recorded, and the 50% inhibition concentration of differentiation (ID50) was calculated. Based on a developmental toxicity discrimination function, the developmental toxicity of the test substances was classified. Furthermore, at the end of the culture period, mRNA expression levels of cardiac differentiation-related markers (Oct3/4, GATA-4, Nkx2.5, and ß-MHC) were quantitatively detected using real-time quantitative polymerase chain reaction (qPCR) in the collected EBs samples. RESULTS: The IC50 of 5-FU was determined as 46.37 µg/L in 3T3 cells and 32.67 µg/L in ES-D3 cells, while the ID50 in ES-D3 cells was 21.28 µg/L. According to the discrimination function results, 5-FU was classified as a strong embryotoxic substance. There were no statistically significant differences in cell viability between different concentrations of Cry1Ab protein treatment groups and the control group in both 3T3 cells and ES-D3 cells (P>0.05). Moreover, there were no statistically significant differences in the diameter of EBs on the third and fifth days, as well as their morphology, between the Cry1Ab protein treatment groups and the control group (P>0.05). The cardiac differentiation rate showed no statistically significant differences between different concentrations of Cry1Ab protein treatment groups and the control group (P>0.05). 5-FU significantly reduced the mRNA expression levels of ß-MHC, Nkx2.5, and GATA-4 (P < 0.05), showing a dose-dependent trend (P < 0.05), while the mRNA expression levels of the pluripotency-associated marker Oct3/4 exhibited an increasing trend (P < 0.05). However, there were no statistically significant differences in the mRNA expression levels of mature cardiac marker ß-MHC, early cardiac differentiation marker Nkx2.5 and GATA-4, and pluripotency-associated marker Oct3/4 between the Cry1Ab protein treatment groups and the control group (P>0.05). CONCLUSION: No developmental toxicity of Cry1Ab protein at concentrations ranging from 31.25 to 2 000.00 µg/L was observed in this experimental model.

Interface Dipole Management of D-A-Type Molecules for Efficient Perovskite Solar Cells.

Interfacial engineering of perovskite films has been the main strategies in improving the efficiency and stability of perovskite solar cells (PSCs). In this study, three new donor-acceptor (D-A)-type interfacial dipole (DAID) molecules with hole-transporting and different anchoring units are designed and employed in PSCs. The formation of interface dipoles by the DAID molecules on the perovskite film can efficiently modulate the energy level alignment, improve charge extraction, and reduce non-radiative recombination. Among the three DAID molecules, TPA-BAM with amide group exhibits the best chemical and optoelectrical properties, achieving a champion PCE of 25.29 % with the enhanced open-circuit voltage of 1.174 V and fill factor of 84.34 %, due to the reduced defect density and improved interfacial hole extraction. Meanwhile, the operational stability of the unencapsulated device has been significantly improved. Our study provides a prospect for rationalized screening of interfacial dipole materials for efficient and stable PSCs.

Self-Polymerized Spiro-Type Interfacial Molecule toward Efficient and Stable Perovskite Solar Cells.

In the pursuit of highly efficient perovskite solar cells, spiro-OMeTAD has demonstrated recorded power conversion efficiencies (PCEs), however, the stability issue remains one of the bottlenecks constraining its commercial development. In this study, we successfully synthesize a novel self-polymerized spiro-type interfacial molecule, termed v-spiro. The linearly arranged molecule exhibits stronger intermolecular interactions and higher intrinsic hole mobility compared to spiro-OMeTAD. Importantly, the vinyl groups in v-spiro enable in situ polymerization, forming a polymeric protective layer on the perovskite film surface, which proves highly effective in suppressing moisture degradation and ion migration. Utilizing these advantages, poly-v-spiro-based device achieves an outstanding efficiency of 24.54 %, with an enhanced open-circuit voltage of 1.173 V and a fill factor of 81.11 %, owing to the reduced defect density, energy level alignment and efficient interfacial hole extraction. Furthermore, the operational stability of unencapsulated devices is significantly enhanced, maintaining initial efficiencies above 90 % even after 2000 hours under approximately 60 % humidity or 1250 hours under continuous AM 1.5G sunlight exposure. This work presents a comprehensive approach to achieving both high efficiency and long-term stability in PSCs through innovative interfacial design.

Quantitative flow cytometry leveraging droplet-based constriction microchannels with high reliability and high sensitivity.

This study presented a quantitative flow cytometry leveraging droplet-based constriction microchannels with high reliability and high sensitivity. Droplets encapsulating single cells and even distribution of fluorescein labeled antibodies removed from targeted cells deformed through the constriction microchannel where the excited fluorescent signals were sampled and interpreted into numbers of proteins based on volume equivalence in measurement of droplets and calibration of fluorescence. To improve the detection reliability, a comprehensive analysis and comparison of multiple stripping agents such as proteinase K, guanidine hydrochloride, and urea was conducted. To improve the detection sensitivity, light modulation was used to address electrical noises and quartz microchannels were fabricated to address optical noises. As a demonstration, based on this quantitative flow cytometry of droplet microfluidics, (1) mutant p53 expressions of single cells were quantified as 1.95 ± 0.60 × 105 (ncell  = 2918 of A431) and 1.30 ± 0.70 × 105 (ncell  = 3954 of T47D); (2) single-cell expressions of Ras, c-Myc, and ß-tubulin were quantified as 1.90 ± 0.59 × 105 , 4.39 ± 1.44 × 105 , and 2.97 ± 0.81 × 105 (ncell  = 3298 of CAL 27), 1.83 ± 0.58 × 105 , 2.08 ± 0.13 × 106 , and 1.96 ± 0.74 × 105 (ncell  = 5459 of WSU-HN6). As a microfluidic tool capable of quantitatively estimating single-cell protein expressions, this methodology may provide a new quantitative perspective for the field of flow cytometry.

Toward five-part differential of leukocytes based on electrical impedances of single cells and neural network.

The five-part differential of leukocytes plays key roles in the diagnosis of a variety of diseases and is realized by optical examinations of single cells, which is prone to various artifacts due to chemical treatments. The classification of leukocytes based on electrical impedances without cell treatments has not been demonstrated because of limitations in approaches of impedance acquisition and data processing. In this study, based on treatment-free single-cell impedance profiles collected from impedance flow cytometry leveraging constriction microchannels, two types of neural pattern recognition were conducted for comparisons with the purpose of realizing the five-part differential of leukocytes. In the first approach, 30 features from impedance profiles were defined manually and extracted automatically, and then a feedforward neural network was conducted, producing a classification accuracy of 84.9% in the five-part leukocyte differential. In the second approach, a customized recurrent neural network was developed to process impedance profiles directly and based on deep learning, a classification accuracy of 97.5% in the five-part leukocyte differential was reported. These results validated the feasibility of the five-part leukocyte differential based on label-free impedance profiles of single cells and thus provide a new perspective of differentiating white blood cells based on impedance flow cytometry.

Design method for a small F-number two-material uniform dispersion immersion grating imaging spectrometer.

Immersion gratings have high dispersion efficiency and have important application value in miniaturized imaging spectrometers, but its serious dispersion nonlinearity causes difficulties in calibration and image processing, which limits its application range. To solve this, this paper presents a design method for a two-material linear dispersion immersion grating device design method, and a compact small F-number immersion grating spectrometer based on it. First the vector form dispersion equation of the two-material immersion grating is derived and the linear spectral dispersion immersion grating design process is given, then a compact small F-number uniform dispersion imaging spectrometer is given as a design example using the proposed method. The results show that when the operating band of the system is 1590-1675 nm, the spectral resolution is better than 0.25 nm, and F-number can achieve better than 2. Compared with traditional single-material immersion grating imaging spectrometer, the designed imaging spectrometer dispersion linearity is significantly improved. Finally, the influence of prism materials, structure parameters and grating parameters on dispersion nonlinearity is analyzed. Design and analysis results show that the proposed two-material immersion grating device has much better spectral dispersion nonlinearity correction ability, and its design method can provide reference to the compact spectrometer design based on immersion gratings.

Blind light field image quality assessment based on deep meta-learning.

In recent years, the use of deep convolutional neural networks (DCNNs) for light field image quality assessment (LFIQA) has gained significant attention. Despite their notable successes, it is widely accepted that training DCNNs heavily depends on a large amount of annotated data. Additionally, convolutional network-based LFIQA methods show a limitation in capturing long-range dependencies. Unfortunately, LFIQA is essentially a typical small-sample problem, leading to existing DCNN-based LFIQA metrics requiring data augmentation but with unsatisfactory performance. To address these issues, this study proposes utilizing the self-attention capability of the Swin Transformer to efficiently capture spatial-angular information while employing meta-learning for small-sample learning in the LFIQA task. Specifically, a collection of LFIQA tasks is gathered, representing different distortions. Then, meta-learning is employed to acquire shared prior knowledge across diverse distortions. Finally, the quality prior model is fine-tuned on a target LFIQA task to obtain the final LFIQA model quickly. Experimental results show that the proposed LFIQA metric achieves high consistency with subjective scores, and outperforms several state-of-the-art LFIQA approaches.

RbCl·(H2SeO3)2: A Salt-Inclusion Selenite Featuring Short UV Cut-Off Edge and Large Birefringence.

Birefringent materials are key components to control the light polarization in laser science and technology as well as optical communication. However, the performance of current commercial birefringent materials has been limited by the magnitude of birefringence, optical transparency range, or the attainability of large-scale single crystals. To explore new birefringent materials, we strategically incorporated a lone pair cation (Se4+) with large optical anisotropy, an alkali metal, and halogen ions (Rb+ and Cl-) with superior UV transparent capacity; thus a new compound, RbCl·(H2SeO3)2, was successfully discovered with the aid of the facile hydrothermal method. Interestingly, Rb-Cl chains locate in the [H2SeO3]∞ skeleton, which makes RbCl·(H2SeO3)2 a salt-inclusion selenite. Millimeter-sized single crystals (up to 4 × 2 × 1 mm3) were obtained, and the transmittance spectrum revealed that its UV cut-off edge can be as low as 230 nm. In addition, the calculated birefringence of RbCl·(H2SeO3)2 is 0.14 at 589 nm that is similar to the birefringent value of famous α-BaB2O4. Wide UV transparency, large birefringence, and feasible crystal growth make RbCl·(H2SeO3)2 a new member of birefringent materials for UV light applications.

Genome-Wide Identification and Functional Analysis of Nitrate Transporter Genes (NPF, NRT2 and NRT3) in Maize.

Nitrate is the primary form of nitrogen uptake in plants, mainly transported by nitrate transporters (NRTs), including NPF (NITRATE TRANSPORTER 1/PEPTIDE TRANSPORTER FAMILY), NRT2 and NRT3. In this study, we identified a total of 78 NPF, seven NRT2, and two NRT3 genes in maize. Phylogenetic analysis divided the NPF family into eight subgroups (NPF1-NPF8), consistent with the results in Arabidopsis thaliana and rice. The NRT2 family appears to have evolved more conservatively than the NPF family, as NRT2 genes contain fewer introns. The promoters of all NRTs are rich in cis-acting elements responding to biotic and abiotic stresses. The expression of NRTs varies in different tissues and developmental stages, with some NRTs only expressed in specific tissues or developmental stages. RNA-seq analysis using Xu178 revealed differential expression of NRTs in response to nitrogen starvation and nitrate resupply. Moreover, the expression patterns of six key NRTs genes (NPF6.6, NPF6.8, NRT2.1, NRT2.5 and NRT3.1A/B) varied in response to alterations in nitrogen levels across distinct maize inbred lines with different nitrogen uptake rates. This work enhances our understanding of the structure and expression of NRTs genes, and their roles in nitrate response, paving the way for improving maize nitrogen efficiency through molecular breeding.

[Clinical and genetic analysis of three children with KBG syndrome due to novel variants of ANKRD11 gene].

OBJECTIVE: To explore the clinical and genetic characteristics of three children with KBG syndrome. METHODS: Clinical data of the three children from two families who have presented at the First Affiliated Hospital of Zhengzhou University between October 2019 and September 2020 and their family members were collected. Trio-whole exome sequencing (trio-WES) and Sanger sequencing were carried out. RESULTS: All children had feeding difficulties, congenital heart defects and facial dysmorphism. The sib- pair from family 1 was found to harbor a novel de novo heterozygous c.6270delT (p.Q2091Rfs*84) variant of the ANKRD11 gene, whilst the child from family 2 was found to harbor a novel heterozygous c.6858delC (p.D2286Efs*51) variant of the ANKRD11 gene, which was inherited from his mother who had a mild clinical phenotype. CONCLUSION: The heterozygous frameshift variants of the ANKRD11 gene probably underlay the disease in the three children. Above findings have enriched the spectrum of the ANKRD11 gene variants.

Road crash risk prediction during COVID-19 for flash crowd traffic prevention: The case of Los Angeles.

Road crashes are a major problem for traffic safety management, which usually causes flash crowd traffic with a profound influence on traffic management and communication systems. In 2020, the sudden outbreak of the novel coronavirus disease (COVID-19) pandemic led to significant changes in road traffic conditions. In this paper, by analyzing crash data from 2016 to 2020 and new COVID-19 case data in 2020, we find that the average crash severity and crash deaths during this period (a rapid increase of new COVID-19 cases in 2020) are higher than those in previous four years. Hence, it is necessary to exploit a novel road crash risk prediction model for such an emergency. We propose a novel data-adaptive fatigue focal loss (DA-FFL) method by fusing fatigue factors to establish a road crash risk prediction model under the scenario of large-scale emergencies. Finally, the experimental results demonstrate that DA-FFL performs better than the other typical methods in terms of area under curve (AUC) and false alarm rate (FAR) for imbalanced data. Furthermore, DA-FFL has better prediction performance in convolutional neural networks-long short-term memory (CNN-LSTM).