Feasibility study of stain-free classification of cell apoptosis based on diffraction imaging flow cytometry and supervised machine learning techniques

Machine learning implementation strategy in imaging and impedance flow cytometry

Imaging and impedance flow cytometry is a label-free technique that has shown promise as a potential replacement for standard flow cytometry. This is due to its ability to provide rich information and archive high-throughput analysis. Recently, significant efforts have been made to leverage machine learning for processing the abundant data generated by those techniques, enabling rapid and accurate analysis. Harnessing the power of machine learning, imaging and impedance flow cytometry has demonstrated its capability to address various complex phenotyping scenarios. Herein, we present a comprehensive overview of the detailed strategies for implementing machine learning in imaging and impedance flow cytometry. We initiate the discussion by outlining the commonly employed setup to acquire the data (i.e., image or signal) from the cell. Subsequently, we delve into the necessary processes for extracting features from the acquired image or signal data. Finally, we discuss how these features can be utilized for cell phenotyping through the application of machine learning algorithms. Furthermore, we discuss the existing challenges and provide insights for future perspectives of intelligent imaging and impedance flow cytometry.

Machine Learning Enhanced Optical Spectroscopy for Disease Detection

Optical spectroscopy plays an important role in disease detection. Improving the sensitivity and specificity of spectral detection has great importance in the development of accurate diagnosis. The development of artificial intelligence technology provides a great opportunity to improve the detection accuracy through machine learning methods. In this Perspective, we focus on the combination of machine learning methods with the optical spectroscopy methods widely used for disease detection, including absorbance, fluorescence, scattering, FTIR, terahertz, etc. By comparing the spectral analysis with different machine learning methods, we illustrate that the support vector machine and convolutional neural network are most effective, which have potential to further improve the classification accuracy to distinguish disease subtypes if these machine learning methods are used. This Perspective broadens the scope of optical spectroscopy enhanced by machine learning and will be useful for the development of disease detection.

Machine learning-based approaches for identifying human blood cells harboring CRISPR-mediated fetal chromatin domain ablations

Two common hemoglobinopathies, sickle cell disease (SCD) and β-thalassemia, arise from genetic mutations within the β-globin gene. In this work, we identified a 500-bp motif (Fetal Chromatin Domain, FCD) upstream of human ϒ-globin locus and showed that the removal of this motif using CRISPR technology reactivates the expression of ϒ-globin. Next, we present two different cell morphology-based machine learning approaches that can be used identify human blood cells (KU-812) that harbor CRISPR-mediated FCD genetic modifications. Three candidate models from the first approach, which uses multilayer perceptron algorithm (MLP 20-26, MLP26-18, and MLP 30-26) and flow cytometry-derived cellular data, yielded 0.83 precision, 0.80 recall, 0.82 accuracy, and 0.90 area under the ROC (receiver operating characteristic) curve when predicting the edited cells. In comparison, the candidate model from the second approach, which uses deep learning (T2D5) and DIC microscopy-derived imaging data, performed with less accuracy (0.80) and ROC AUC (0.87). We envision that equivalent machine learning-based models can complement currently available genotyping protocols for specific genetic modifications which result in morphological changes in human cells.

BCNet: A Novel Network for Blood Cell Classification

Aims: Most blood diseases, such as chronic anemia, leukemia (commonly known as blood cancer), and hematopoietic dysfunction, are caused by environmental pollution, substandard decoration materials, radiation exposure, and long-term use certain drugs. Thus, it is imperative to classify the blood cell images. Most cell classification is based on the manual feature, machine learning classifier or the deep convolution network neural model. However, manual feature extraction is a very tedious process, and the results are usually unsatisfactory. On the other hand, the deep convolution neural network is usually composed of massive layers, and each layer has many parameters. Therefore, each deep convolution neural network needs a lot of time to get the results. Another problem is that medical data sets are relatively small, which may lead to overfitting problems. Methods: To address these problems, we propose seven models for the automatic classification of blood cells: BCARENet, BCR5RENet, BCMV2RENet, BCRRNet, BCRENet, BCRSNet, and BCNet. The BCNet model is the best model among the seven proposed models. The backbone model in our method is selected as the ResNet-18, which is pre-trained on the ImageNet set. To improve the performance of the proposed model, we replace the last four layers of the trained transferred ResNet-18 model with the three randomized neural networks (RNNs), which are RVFL, ELM, and SNN. The final outputs of our BCNet are generated by the ensemble of the predictions from the three randomized neural networks by the majority voting. We use four multi-classification indexes for the evaluation of our model. Results: The accuracy, average precision, average F1-score, and average recall are 96.78, 97.07, 96.78, and 96.77%, respectively. Conclusion: We offer the comparison of our model with state-of-the-art methods. The results of the proposed BCNet model are much better than other state-of-the-art methods.

Cell morphology-based machine learning models for human cell state classification

Herein, we implement and access machine learning architectures to ascertain models that differentiate healthy from apoptotic cells using exclusively forward (FSC) and side (SSC) scatter flow cytometry information. To generate training data, colorectal cancer HCT116 cells were subjected to miR-34a treatment and then classified using a conventional Annexin V/propidium iodide (PI)-staining assay. The apoptotic cells were defined as Annexin V-positive cells, which include early and late apoptotic cells, necrotic cells, as well as other dying or dead cells. In addition to fluorescent signal, we collected cell size and granularity information from the FSC and SSC parameters. Both parameters are subdivided into area, height, and width, thus providing a total of six numerical features that informed and trained our models. A collection of logistical regression, random forest, k-nearest neighbor, multilayer perceptron, and support vector machine was trained and tested for classification performance in predicting cell states using only the six aforementioned numerical features. Out of 1046 candidate models, a multilayer perceptron was chosen with 0.91 live precision, 0.93 live recall, 0.92 live f value and 0.97 live area under the ROC curve when applied on standardized data. We discuss and highlight differences in classifier performance and compare the results to the standard practice of forward and side scatter gating, typically performed to select cells based on size and/or complexity. We demonstrate that our model, a ready-to-use module for any flow cytometry-based analysis, can provide automated, reliable, and stain-free classification of healthy and apoptotic cells using exclusively size and granularity information.

Secretion of Recombinant Human Annexin V in Fusion with the Super Folder GFP for Labelling Phosphatidylserine-Exposing Membranes

Annexin V (ANXV), mostly characterized by its ability to interact with biological membranes in a calcium-dependent manner. ANXV interacts mainly with phosphatidylserine (PS), for that fluorescent ANXV widely produced and used as a sensitive and specific probe to mark apoptotic cells or any PS-containing bilayers membranes. Many reports described the prokaryotic expression of recombinant human ANXV. To overcome some of E. coli expression limitations, we aimed in this work to investigate unconventional alternative expression system in mammalian cells for producing secreted human ANXV in fusion with the super folder green fluorescent protein (sfGFP). HEK239T cells were transfected using polyethylenimine (PEI) and pcDNA-sfGFP-ANXV plasmid. Forty-eight hours post transfection, direct fluorescence measurement, immunoblotting and ELISA confirmed the presence of secreted sfGFP-ANXV in cells supernatant. The yield of secreted 6 × His-tagged sfGFP-ANXV after affinity purification was estimated to be around 2 µg per 1 ml of cells supernatant. The secretion system was proper to produce a fully functional sfGFP-ANXV fusion protein in quantities enough to recognize and bind PS-containing surfaces or liposomes. Besides, biological assays such as flow cytometry and fluorescent microscopy confirmed the capacity of the secreted sfGFP-ANXV to detect PS exposure on apoptotic cells. Taken together, we present mammalian expression as a quick, affordable and endotoxin-free system to produce sfGFP-ANXV fusion protein. The secreted sfGFP-ANXV in eukaryotic system is a promising biotechnological tool, it opens up new horizons for additional applications in the detection of PS bearing surfaces and apoptosis in vitro and in vivo assays.

5-Fluorouracil enhances the chemosensitivity of gastric cancer to TRAIL via inhibition of the MAPK pathway

Tumor necrosis factor-related apoptosis-inducing ligand (TRAIL) has the ability to selectively trigger cancer cell apoptosis and can be used as a target for tumor therapy. However, gastric cancer cells are usually insensitive to TRAIL so reducing this drug resistance may improve the treatment of gastric cancer. In this study, we used Cell Counting Kit-8 (CCK-8) and 5-ethynyl-2'-deoxyuridine (EdU) experiments to determine the effects of 5-fluorouracil (5-FU) and TRAIL on the proliferation of gastric cancer cells. An Annexin V/propidium iodide (PI) staining experiment was used to detect apoptosis, and Western blotting was used to analyze the expression levels of apoptosis-related proteins and mitogen-activated protein kinase (MAPK) pathway proteins. The antitumor effects of 5-FU and TRAIL were verified in vivo using a nude mouse tumorigenesis experiment, and a TUNEL assay was performed to evaluate apoptosis in tumor tissue from the nude mice. We found the combination of 5-FU and TRAIL had a greater inhibitory effect on the proliferation of gastric cancer cells than 5-FU or TRAIL alone both in vivo and in vitro. 5-FU enhanced TRAIL-induced gastric cancer cell apoptosis by inactivating the MAPK pathway. Overall, our analysis firstly provided new insights into the role of 5-FU in increasing sensitivity to TRAIL. 5-FU can be used as a sensitizer for TRAIL, and its administration is a potential strategy for the treatment of gastric cancer.

Resveratrol modulates the apoptosis and autophagic death of human lung adenocarcinoma A549 cells via a p53‑dependent pathway: Integrated bioinformatics analysis and experimental validation

Resveratrol (RSV) has been reported to exhibit cytotoxic activity in multiple types of malignant cells; however, the mechanisms underlying the antitumor effects of RSV in non-small-cell lung cancer (NSCLC) cells remain undetermined. Combining bioinformatics analysis with experimental validation, the present study aimed to examine the effects of RSV on the apoptosis and autophagy of A549 NSCLC cells, and to determine the potential underlying molecular mechanisms. Bioinformatics analysis was used to determine the differentially expressed genes (DEGs) and identify the enriched biological functions and pathways associated with these DEGs following RSV treatment. Cell viability was determined by MTT assay, and flow cytometry and TUNEL assay were used to evaluate cell apoptosis. Monodansylcadaverine staining combined with a transmission electron microscope were used to evaluate the extent of autophagy. The expression levels of apoptosis-, autophagy-, or pathway-associated molecular markers were measured by reverse transcription-quantitative PCR and/or western blot analysis. By bioinformatics analysis, a total of 1,031 DEGs were identified in the RSV-treated A549 cells, which were enriched in apoptosis-, or autophagy-related biological functions and the p53 signaling pathway. In validation experiments, RSV significantly reduced cell viability and initiated apoptosis, with an increase in the number of apoptotic cells; it also upregulated cleaved caspase-3 expression and Bax expression, and downregulated the Bcl-2 expression levels. Additionally, there was an increase in the accumulation of green dot-like structures, indicative of autophagic vesicles, observed under a fluorescence microscope, and an increase in the presence of autophagic vacuoles observed using a transmission electron microscope following RSV treatment. Furthermore, the expression levels of the autophagy-related proteins, LC3-II/LC3-I and Beclin-1, were increased and p62 expression was decreased. 3-methyladenine (3-MA), an inhibitor of autophagy, partially reversed the RSV-induced cytotoxic effects, but did not significantly alter the number of apoptotic cells. RSV elevated the p53 levels and decreased the phosphorylated (p-)Mdm2 and p-Akt levels. Pifithrin-α, an inhibitor of p53, partially reduced RSV-induced apoptosis and autophagy. On the whole, the results of the present study demonstrated that RSV initiates the apoptosis and autophagic death of A549 cells via the activation of the p53 signaling pathway, further highlighting the potential of RSV for the treatment of NSCLC.

Targeted Prodrug-Based Self-Assembled Nanoparticles for Cancer Therapy

Background

Targeted prodrug has various applications as drug formulation for tumor therapy. Therefore, amphoteric small-molecule prodrug combined with nanoscale characteristics for the self-assembly of the nano-drug delivery system (DDS) is a highly interesting research topic.

Methods and Results

In this study, we developed a prodrug self-assembled nanoplatform, 2-glucosamine-fluorescein-5(6)-isothiocyanate-glutamic acid-paclitaxel (2DA-FITC-PTX NPs) by integration of targeted small molecule and nano-DDS with regular structure and perfect targeting ability. 2-glucosamine (DA) and paclitaxel were conjugated as the targeted ligand and anti-tumor chemotherapy drug by amino acid group. 2-DA molecular structure can enhance the targeting ability of prodrug-based 2DA-FITC-PTX NPs and prolong retention time, thereby reducing the toxicity of normal cell/tissue. The fluorescent dye FITC or near-infrared fluorescent dye ICG in prodrug-based DDS was attractive for in vivo optical imaging to study the behavior of 2DA-FITC-PTX NPs. In vitro and in vivo results proved that 2DA-FITC-PTX NPs exhibited excellent targeting ability, anticancer activity, and weak side effects.

Conclusion

This work demonstrates a new combination of nanomaterials for chemotherapy and may promote prodrug-based DDS clinical applications in the future.

Antitumor Effects of MRS5698, a Cordycepin Derivative, on Endometrial Cancer Cells

Endometrial cancer drug treatments often produce undesirable effects. Thus, discovering new drugs with fewer side effects is required. Cordycepin is a constituent of Cordyceps sinensis, which has been proven to inhibit tumor growth by stimulating the adenosine A3 receptor (A3R). However, cordycepin is rapidly degraded by adenosine deaminase (ADA) and has a clinically unacceptable short half-life. One of its derivatives, MRS5698, was predicted to exhibit antitumor effects with a poor affinity to ADA by our previous validated in silico experiments. The purpose of this study was to explore the possibilities of using MRS5698 as a novel antitumor agent through experiments on Ishikawa and HEC-1A cells. The detection of inhibition and apoptotic rate of MRS5698 and cisplatin, and their combination, on Ishikawa and HEC-1A cells were performed by MTT assays and flow cytometry, respectively. The inhibition rates of MRS5698 on Ishikawa and HEC-1A cells were both significantly higher than the control groups ( P < 0.05). MRS5698 produced a higher inhibitory effect on HEC-1A cells than on Ishikawa cells with IC50 values of 20.55 and 27.25 μg/mL, respectively. MRS5698 had a stronger inhibitory effect than cisplatin on HEC-1A cells. The Annexin V-FITC/propidium iodide assays demonstrated that the total rate of apoptosis of MRS5698 on HEC-1A cells was higher than that on Ishikawa cells. The results of MTT assay and cellular apoptosis showed that the combined use of MRS5698 and cisplatin produces dose-independent antagonistic effects. MRS5698 produced antitumor effects on both cell lines, which were better than that of cordycepin. However, the combined use of MRS5698 and cisplatin produced an antagonistic effect. A further in vivo study could be considered for investigating the antitumor effects of either MRS5698 monotherapy or MRS5698 in combination with other nonplatinum-based chemotherapeutic drugs in treating endometrial cancer.

Design, Synthesis and in Vitro Tumor Cytotoxicity Evaluation of 3,5-Diamino-N-substituted Benzamide Derivatives as Novel GSK-3β Small Molecule Inhibitors

Glycogen synthase kinase-3 (GSK-3) plays an important regulatory role in various signaling pathways; such as PI3 K/AKT, which is closely related to the occurrence and development of tumors. At present, the most reported active GSK-3 inhibitors have the same structure: lactam ring or amide structure. To find out the GSK-3β small molecule inhibitor with novel, safe, efficient and more uncomplicated synthesis method, we analyzed in-depth reported crystal-binding patterns of GSK-3β small molecule inhibitor with GSK-3β protein, and designed and synthesized 17 non-reported 3,5-diamino-N-substituted benzamide compounds. Their structures were confirmed by ¹ H-NMR, ¹³ C-NMR, and HR-MS. The preliminary screening of tumor cytotoxicity of compounds in vitro was detected by MTT, and their structure-activity relationships were illustrated. The results have shown that 3,5-diamino-N-[3-(trifluoromethyl)phenyl]benzamide (4d) exhibited significant tumor cytotoxicity against human colon cancer cells (HCT-116) with IC₅₀ of 8.3 μm and showed commendable selectivity to GSK-3β. In addition, Compound 4d induced apoptosis to some extent and possessed modest PK properties.

In Vitro Toxicity Study of a Porous Iron(III) Metal‒Organic Framework

A MIL series metal‒organic framework (MOF), MIL-100(Fe), was successfully synthesized at the nanoscale and fully characterized by TEM, TGA, XRD, FTIR, DLS, and BET. A toxicological assessment was performed using two different cell lines: human normal liver cells (HL-7702) and hepatocellular carcinoma (HepG2). In vitro cytotoxicity of MIL-100(Fe) was evaluated by the MTT assay, LDH releasing rate assay, DAPI staining, and annexin V/PI double staining assay. The safe dose of MIL-100(Fe) was 80 μg/mL. It exhibited good biocompatibility, low cytotoxicity, and high cell survival rate (HL-7702 cells' viability >85.97%, HepG2 cells' viability >91.20%). Therefore, MIL-100(Fe) has a potential application as a drug carrier.