SARS-CoV-2, the causative agent of COVID-191, features a receptor-binding domain (RBD) for binding to the host cell ACE2 protein1–6. Neutralizing antibodies that block RBD-ACE2 interaction are candidates for the development of targeted therapeutics7–17. Llama-derived single-domain antibodies (nanobodies, ~15 kDa) offer advantages in bioavailability, amenability, and production and storage owing to their small sizes and high stability. Here, we report the rapid selection of 99 synthetic nanobodies (sybodies) against RBD by in vitro selection using three libraries. The best sybody, MR3 binds to RBD with high affinity (KD = 1.0 nM) and displays high neutralization activity against SARS-CoV-2 pseudoviruses (IC50 = 0.42 μg mL−1). Structural, biochemical, and biological characterization suggests a common neutralizing mechanism, in which the RBD-ACE2 interaction is competitively inhibited by sybodies. Various forms of sybodies with improved potency have been generated by structure-based design, biparatopic construction, and divalent engineering. Two divalent forms of MR3 protect hamsters from clinical signs after live virus challenge and a single dose of the Fc-fusion construct of MR3 reduces viral RNA load by 6 Log10. Our results pave the way for the development of therapeutic nanobodies against COVID-19 and present a strategy for rapid development of targeted medical interventions during an outbreak.

This study verifies the feasibility of using deep-learning algorithms for the binary classification as normal or abnormal of standard fetal ultrasound brain images in axial planes. What are the clinical implications of this work? Using deep-learning algorithms could help to reduce false-negative diagnoses. They are expected to help solve the shortage of sonologists for basic prenatal ultrasound in China and worldwide. This study lays the foundation for further multiclassification research on the diagnosis of fetal intracranial abnormalities and differential diagnosis using deep learning.

PurposeDynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is increasingly used for breast cancer diagnosis as supplementary to conventional imaging techniques. Combining of diffusion-weighted imaging (DWI) of morphology and kinetic features from DCE-MRI to improve the discrimination power of malignant from benign breast masses is rarely reported.Materials and MethodsThe study comprised of 234 female patients with 85 benign and 149 malignant lesions. Four distinct groups of features, coupling with pathological tests, were estimated to comprehensively characterize the pictorial properties of each lesion, which was obtained by a semi-automated segmentation method. Classical machine learning scheme including feature subset selection and various classification schemes were employed to build prognostic model, which served as a foundation for evaluating the combined effects of the multi-sided features for predicting of the types of lesions. Various measurements including cross validation and receiver operating characteristics were used to quantify the diagnostic performances of each feature as well as their combination.ResultsSeven features were all found to be statistically different between the malignant and the benign groups and their combination has achieved the highest classification accuracy. The seven features include one pathological variable of age, one morphological variable of slope, three texture features of entropy, inverse difference and information correlation, one kinetic feature of SER and one DWI feature of apparent diffusion coefficient (ADC). Together with the selected diagnostic features, various classical classification schemes were used to test their discrimination power through cross validation scheme. The averaged measurements of sensitivity, specificity, AUC and accuracy are 0.85, 0.89, 90.9% and 0.93, respectively.ConclusionMulti-sided variables which characterize the morphological, kinetic, pathological properties and DWI measurement of ADC can dramatically improve the discriminatory power of breast lesions.

Nanopore sequencing is promising because of its long read length and high speed. During sequencing, a strand of DNA/RNA passes through a biological nanopore, which causes the current in the pore to fluctuate. During basecalling, context-dependent current measurements are translated into the base sequence of the DNA/RNA strand. Accurate and fast basecalling is vital for downstream analyses such as genome assembly and detecting single-nucleotide polymorphisms and genomic structural variants. However, owing to the various changes in DNA/RNA molecules, noise during sequencing, and limitations of basecalling methods, accurate basecalling remains a challenge. In this paper, we propose Causalcall, which uses an end-to-end temporal convolution-based deep learning model for accurate and fast nanopore basecalling. Developed on a temporal convolutional network (TCN) and a connectionist temporal classification decoder, Causalcall directly identifies base sequences of varying lengths from current measurements in long time series. In contrast to the basecalling models using recurrent neural networks (RNNs), the convolution-based model of Causalcall can speed up basecalling by matrix computation. Experiments on multiple species have demonstrated the great potential of the TCN-based model to improve basecalling accuracy and speed when compared to an RNN-based model. Besides, experiments on genome assembly indicate the utility of Causalcall in reference-based genome assembly.