Isoelectric point barcode and similarity analysis with the earth mover's distance for identification of species origin of raw meat

Deep learning ResNet34 model-assisted diagnosis of sickle cell disease via microcolumn isoelectric focusing

Traditional methods for sickle cell disease (SCD) screening can be inaccurate and misleading, and the early and accurate diagnosis of SCD is crucial for effective management and treatment. Although microcolumn isoelectric focusing (mIEF) is effective, the hemoglobinopathies must be accurately identified, wherein skilled personnel are required to analyse the bands in mIEF. Further automating and standardizing the diagnostic methods via AI to identify abnormal Hbs would be a useful endeavor. In this study, we propose a novel approach for SCD diagnosis by integrating the high throughput capability of ResNet34 in image analysis, as a deep learning convolutional neural network, for the precise separation of Hb variants using mIEF. Initially, SCD blood samples were subjected to mIEF and the resulting patterns were then captured as digital images. The sensitivity and specificity of the mIEF analysis were 100% and 97.8%, respectively, with a 99.39% accuracy. Comparison with HPLC showed a strong linear correlation (R2 = 0.9934), good agreement with the Bland-Altman plot (average difference ± 1.96 SD, bias = 9.89%) and a 100% match with the DNA analysis. Subsequently, the mIEF images were then input into the ResNet34 model, pre-trained on a large dataset, for feature extraction and classification. The integration of ResNet34 with mIEF demonstrated promising results in terms of precision (90.1%) and accuracy in distinguishing between the various SCD conditions. Overall, the proposed method offers a more effective, automated, and reduced cost approach for SCD diagnosis, which could potentially streamline diagnostic workflows and mitigate the subjectivity and variability inherent in manual assessments.

Microstrip isoelectric focusing with deep learning for simultaneous screening of diabetes, anemia, and thalassemia

BACKGROUND

Hemoglobin (Hb) is an important protein in red blood cells and a crucial diagnostic indicator of diseases, e.g., diabetes, thalassemia, and anemia. However, there is a rare report on methods for the simultaneous screening of diabetes, anemia, and thalassemia. Isoelectric focusing (IEF) is a common separative tool for the separation and analysis of Hb. However, the current analysis of IEF images is time-consuming and cannot be used for simultaneous screening. Therefore, an artificial intelligence (AI) of IEF image recognition is desirable for accurate, sensitive, and low-cost screening.

RESULTS

Herein, we proposed a novel comprehensive method based on microstrip isoelectric focusing (mIEF) for detecting the relative content of Hb species. There was a good coincidence between the quantitation of Hb via a conventional automated hematology analyzer and the one via mIEF with R2 = 0.9898. Nevertheless, our results showed that the accuracy of disease diagnosis based on the quantification of Hb species alone is as low as 69.33 %, especially for the simultaneous screening of multiple diseases of diabetes, anemia, alpha-thalassemia, and beta-thalassemia. Therefore, we introduced a ResNet1D-based diagnosis model for the improvement of screening accuracy of multiple diseases. The results showed that the proposed model could achieve a high accuracy of more than 90 % and a good sensitivity of more than 96 % for each disease, indicating the overwhelming advantage of the mIEF method combined with deep learning in contrast to the pure mIEF method.

SIGNIFICANCE

Overall, the presented method of mIEF with deep learning enabled, for the first time, the absolute quantitative detection of Hb, relative quantitation of Hb species, and simultaneous screening of diabetes, anemia, alpha-thalassemia, and beta-thalassemia. The AI-based diagnosis assistant system combined with mIEF, we believe, will help doctors and specialists perform fast and precise disease screening in the future.

Real-time and quantitative protein detection via polyacrylamide gel electrophoresis and online intrinsic fluorescence imaging

The detection of intrinsic protein fluorescence is a powerful tool for studying proteins in their native state. Thanks to its label-free and stain-free feature, intrinsic fluorescence detection has been introduced to polyacrylamide gel electrophoresis (PAGE), a fundamental and ubiquitous protein analysis technique, to avoid the tedious detection process. However, the reported methods of intrinsic fluorescence detection were incompatible with online PAGE detection or standard slab gel. Here, we fulfilled online intrinsic fluorescence imaging (IFI) of the standard slab gel to develop a PAGE-IFI method for real-time and quantitative protein detection. To do so, we comprehensively investigated the arrangement of the deep-UV light source to obtain a large imaging area compatible with the standard slab gel, and then designed a semi-open gel electrophoresis apparatus (GEA) to scaffold the gel for the online UV irradiation and IFI with low background noise. Thus, we achieved real-time monitoring of the protein migration, which enabled us to determine the optimal endpoint of PAGE run to improve the sensitivity of IFI. Moreover, online IFI circumvented the broadening of protein bands to enhance the separation resolution. Because of the low background noise and the optimized endpoint, we showcased the quantitative detection of bovine serum albumin (BSA) with a limit of detection (LOD) of 20 ng. The standard slab gel provided a high sample loading volume that allowed us to attain a wide linear range of 0.03-10 μg. These results indicate that the PAGE-IFI method can be a promising alternative to conventional PAGE and can be widely used in molecular biology labs.

Marker-Free Isoelectric Focusing Patterns for Identification of Meat Samples via Deep Learning

Isoelectric focusing (IEF) is a powerful tool for resolving complex protein samples, which generates IEF patterns consisting of multiplex analyte bands. However, the interpretation of IEF patterns requires the careful selection of isoelectric point (pI) markers for profiling the pH gradient and a trivial process of pI labeling, resulting in low IEF efficiency. Here, we for the first time proposed a marker-free IEF method for the efficient and accurate classification of IEF patterns by using a convolutional neural network (CNN) model. To verify our method, we identified 21 meat samples whose IEF patterns comprised different bands of meat hemoglobin, myoglobin, and their oxygen-binding variants but no pI marker. Thanks to the high throughput and short assay time of the microstrip IEF, we efficiently collected 1449 IEF patterns to construct the data set for model training. Despite the absence of pI markers, we experimentally introduced the severe pH gradient drift into 189 IEF patterns in the data set, thereby omitting the need for profiling the pH gradient. To enhance the model robustness, we further employed data augmentation during the model training to mimic pH gradient drift. With the advantages of simple preprocessing, a rapid inference of 50 ms, and a high accuracy of 97.1%, the CNN model outperformed the traditional algorithm for simultaneously identifying meat species and cuts of meat of 105 IEF patterns, suggesting its great potential of being combined with microstrip IEF for large-scale IEF analyses of complicated protein samples.