Interpretable machine learning-based individual analysis of acute kidney injury in immune checkpoint inhibitor therapy.

BACKGROUND: Acute kidney injury (AKI) is a critical complication of immune checkpoint inhibitor therapy. Since the etiology of AKI in patients undergoing cancer therapy varies, clarifying underlying causes in individual cases is critical for optimal cancer treatment. Although it is essential to individually analyze immune checkpoint inhibitor-treated patients for underlying pathologies for each AKI episode, these analyses have not been realized. Herein, we aimed to individually clarify the underlying causes of AKI in immune checkpoint inhibitor-treated patients using a new clustering approach with Shapley Additive exPlanations (SHAP). METHODS: We developed a gradient-boosting decision tree-based machine learning model continuously predicting AKI within 7 days, using the medical records of 616 immune checkpoint inhibitor-treated patients. The temporal changes in individual predictive reasoning in AKI prediction models represented the key features contributing to each AKI prediction and clustered AKI patients based on the features with high predictive contribution quantified in time series by SHAP. We searched for common clinical backgrounds of AKI patients in each cluster, compared with annotation by three nephrologists. RESULTS: One hundred and twelve patients (18.2%) had at least one AKI episode. They were clustered per the key feature, and their SHAP value patterns, and the nephrologists assessed the clusters' clinical relevance. Receiver operating characteristic analysis revealed that the area under the curve was 0.880. Patients with AKI were categorized into four clusters with significant prognostic differences (p = 0.010). The leading causes of AKI for each cluster, such as hypovolemia, drug-related, and cancer cachexia, were all clinically interpretable, which conventional approaches cannot obtain. CONCLUSION: Our results suggest that the clustering method of individual predictive reasoning in machine learning models can be applied to infer clinically critical factors for developing each episode of AKI among patients with multiple AKI risk factors, such as immune checkpoint inhibitor-treated patients.

Modular Design Platform for Activatable Fluorescence Probes Targeting Carboxypeptidases Based on ProTide Chemistry.

Carboxypeptidases (CPs) are a family of hydrolases that cleave one or more amino acids from the C-terminal of peptides or proteins and play indispensable roles in various physiological and pathological processes. However, only a few highly activatable fluorescence probes for CPs have been reported, and there is a need for a flexibly tunable molecular design platform to afford a range of fluorescence probes for CPs for biological and medical research. Here, we focused on the unique activation mechanism of ProTide-based prodrugs and established a modular design platform for CP-targeting florescence probes based on ProTide chemistry. In this design, probe properties such as fluorescence emission wavelength, reactivity/stability, and target CP can be readily tuned and optimized by changing the four probe modules: the fluorophore, the substituent on the phosphorus atom, the linker amino acid at the P1 position, and the substrate amino acid at the P1' position. In particular, switching the linker amino acid at position P1 enabled us to precisely optimize the reactivity for target CPs. As a proof-of-concept, we constructed probes for carboxypeptidase M (CPM) and prostate-specific membrane antigen (also known as glutamate carboxypeptidase II). The developed probes were applicable for the imaging of CP activities in live cells and in clinical specimens from patients. This design strategy should be useful in studying CP-related biological and pathological phenomena.

Network-based prediction approach for cancer-specific driver missense mutations using a graph neural network.

BACKGROUND: In cancer genomic medicine, finding driver mutations involved in cancer development and tumor growth is crucial. Machine-learning methods to predict driver missense mutations have been developed because variants are frequently detected by genomic sequencing. However, even though the abnormalities in molecular networks are associated with cancer, many of these methods focus on individual variants and do not consider molecular networks. Here we propose a new network-based method, Net-DMPred, to predict driver missense mutations considering molecular networks. Net-DMPred consists of the graph part and the prediction part. In the graph part, molecular networks are learned by a graph neural network (GNN). The prediction part learns whether variants are driver variants using features of individual variants combined with the graph features learned in the graph part. RESULTS: Net-DMPred, which considers molecular networks, performed better than conventional methods. Furthermore, the prediction performance differed by the molecular network structure used in learning, suggesting that it is important to consider not only the local network related to cancer but also the large-scale network in living organisms. CONCLUSIONS: We propose a network-based machine learning method, Net-DMPred, for predicting cancer driver missense mutations. Our method enables us to consider the entire graph architecture representing the molecular network because it uses GNN. Net-DMPred is expected to detect driver mutations from a lot of missense mutations that are not known to be associated with cancer.

Rapid imaging of thymoma and thymic carcinoma with a fluorogenic probe targeting γ-glutamyltranspeptidase.

In recent years, thoracoscopic and robotic surgical procedures have increasingly replaced median sternotomy for thymoma and thymic carcinoma. In cases of partial thymectomy, the prognosis is greatly improved by ensuring a sufficient margin from the tumor, and therefore intraoperative fluorescent imaging of the tumor is especially valuable in thoracoscopic and robotic surgery, where tactile information is not available. γ-Glutamyl hydroxymethyl rhodamine green (gGlu-HMRG) has been applied for fluorescence imaging of some types of tumors in the resected tissues, and here we aimed to examine its validity for the imaging of thymoma and thymic carcinoma. 22 patients with thymoma or thymic carcinoma who underwent surgery between February 2013 and January 2021 were included in the study. Ex vivo imaging of specimens was performed, and the sensitivity and specificity of gGlu-HMRG were 77.3% and 100%, respectively. Immunohistochemistry (IHC) staining was performed to confirm expression of gGlu-HMRG's target enzyme, γ-glutamyltranspeptidase (GGT). IHC revealed high GGT expression in thymoma and thymic carcinoma in contrast to absent or low expression in normal thymic parenchyma and fat tissue. These results suggest the utility of gGlu-HMRG as a fluorescence probe for intraoperative visualization of thymomas and thymic carcinomas.

Rapid imaging of lung cancer using a red fluorescent probe to detect dipeptidyl peptidase 4 and puromycin-sensitive aminopeptidase activities.

Rapid identification of lung-cancer micro-lesions is becoming increasingly important to improve the outcome of surgery by accurately defining the tumor/normal tissue margins and detecting tiny tumors, especially for patients with low lung function and early-stage cancer. The purpose of this study is to select and validate the best red fluorescent probe for rapid diagnosis of lung cancer by screening a library of 400 red fluorescent probes based on 2-methyl silicon rhodamine (2MeSiR) as the fluorescent scaffold, as well as to identify the target enzymes that activate the selected probe, and to confirm their expression in cancer cells. The selected probe, glutamine-alanine-2-methyl silicon rhodamine (QA-2MeSiR), showed 96.3% sensitivity and 85.2% specificity for visualization of lung cancer in surgically resected specimens within 10 min. In order to further reduce the background fluorescence while retaining the same side-chain structure, we modified QA-2MeSiR to obtain glutamine-alanine-2-methoxy silicon rhodamine (QA-2OMeSiR). This probe rapidly visualized even borderline lesions. Dipeptidyl peptidase 4 and puromycin-sensitive aminopeptidase were identified as enzymes mediating the cleavage and consequent fluorescence activation of QA-2OMeSiR, and it was confirmed that both enzymes are expressed in lung cancer. QA-2OMeSiR is a promising candidate for clinical application.

Development of a fluorescent probe library enabling efficient screening of tumour-imaging probes based on discovery of biomarker enzymatic activities.

Fluorescent probes that can selectively detect tumour lesions have great potential for fluorescence imaging-guided surgery. Here, we established a library-based approach for efficient screening of probes for tumour-selective imaging based on discovery of biomarker enzymes. We constructed a combinatorial fluorescent probe library for aminopeptidases and proteases, which is composed of 380 probes with various substrate moieties. Using this probe library, we performed lysate-based in vitro screening and/or direct imaging-based ex vivo screening of freshly resected clinical specimens from lung or gastric cancer patients, and found promising probes for tumour-selective visualization. Further, we identified two target enzymes as novel biomarker enzymes for discriminating between tumour and non-tumour tissues. This library-based approach is expected to be an efficient tool to develop tumour-imaging probes and to discover new biomarker enzyme activities for various tumours and other diseases.

Evaluation of Kidney Histological Images Using Unsupervised Deep Learning.

INTRODUCTION: Evaluating histopathology via machine learning has gained research and clinical interest, and the performance of supervised learning tasks has been described in various areas of medicine. Unsupervised learning of histological images has the advantage of reproducibility for labeling; however, the relationship between unsupervised evaluation and clinical information remains unclear in nephrology. METHODS: We propose an unsupervised approach combining convolutional neural networks (CNNs) and a visualization algorithm to cluster the histological images and calculate the score for patients. We applied the approach to the entire images or patched images of the glomerulus of kidney biopsy samples stained with hematoxylin and eosin obtained from 68 patients with immunoglobulin A nephropathy. We assessed the relationship between the obtained scores and clinical variables of urinary occult blood, urinary protein, serum creatinine (SCr), systolic blood pressure, and age. RESULTS: The glomeruli of the patients were classified into 12 distinct classes and 10 patches. The output of the fine-tuned CNN, which we defined as the histological scores, had significant relationships with assessed clinical variables. In addition, the clustering and visualization results suggested that the defined clusters captured important findings when evaluating renal histopathology. For the score of the patch-based cluster containing crescentic glomeruli, SCr (coefficient = 0.09, P = 0.019) had a significant relationship. CONCLUSION: The proposed approach could successfully extract features that were related to the clinical variables from the kidney biopsy images along with the visualization for interpretability. The approach could aid in the quantified evaluation of renal histopathology.

Pericentromeric noncoding RNA changes DNA binding of CTCF and inflammatory gene expression in senescence and cancer.

Cellular senescence causes a dramatic alteration of chromatin organization and changes the gene expression profile of proinflammatory factors, thereby contributing to various age-related pathologies through the senescence-associated secretory phenotype (SASP). Chromatin organization and global gene expression are maintained by the CCCTC-binding factor (CTCF); however, the molecular mechanism underlying CTCF regulation and its association with SASP gene expression remains unclear. We discovered that noncoding RNA (ncRNA) derived from normally silenced pericentromeric repetitive sequences directly impairs the DNA binding of CTCF. This CTCF disturbance increases the accessibility of chromatin and activates the transcription of SASP-like inflammatory genes, promoting malignant transformation. Notably, pericentromeric ncRNA was transferred into surrounding cells via small extracellular vesicles acting as a tumorigenic SASP factor. Because CTCF blocks the expression of pericentromeric ncRNA in young cells, the down-regulation of CTCF during cellular senescence triggers the up-regulation of this ncRNA and SASP-related inflammatory gene expression. In this study, we show that pericentromeric ncRNA provokes chromosomal alteration by inhibiting CTCF, leading to a SASP-like inflammatory response in a cell-autonomous and non-cell-autonomous manner and thus may contribute to the risk of tumorigenesis during aging.

Fluorescence Probes for Imaging Basic Carboxypeptidase Activity in Living Cells with High Intracellular Retention.

Basic carboxypeptidases (basic CPs) cleave the C-terminal basic amino acid of peptides, and their activity is upregulated in some types of cancers. Therefore, detecting the activity of basic CPs in living cells would be important not only for studying the physiological functions of these enzymes but also for visualization of cancerous tissues. Here, we report two fluorescein diacetate (FDA)-based activatable fluorescence probes, named 5ArgAF-FDA and 5LysAF-FDA, in which the substrate amino acid arginine or lysine is conjugated to the benzene moiety via an azoformyl linker. In live-cell fluorescence imaging of CPM, one of the seven basic CPs, 5ArgAF-FDA showed a larger intracellular fluorescence increase than did 5LysAF-FDA within a few minutes. This increase was inhibited by coincubation with 2-mercaptomethyl-3-guanidinoethylthiopropanoic acid (MGTA), an inhibitor of basic CPs. When 5ArgAF-FDA was applied to a coculture of two breast cancer cell lines with different CPM activities, the fluorescence increase in individual cells was correlated with the expression level of CPM, suggesting that 5ArgAF-FDA has the ability to distinguish cell lines having different levels of CPM activity, owing to its high intracellular retention. We believe these probes will be useful for imaging cancers with upregulated basic CP activity.

γ-Glutamyltranspeptidase (GGT)-Activatable Fluorescence Probe for Durable Tumor Imaging.

γ-Glutamyltranspeptidase (GGT) is overexpressed in several types of cancer. Existing GGT-targeting fluorescence probes can image these cancers, but the fluorescent hydrolysis product leaks from the target cancer cells during prolonged incubation or fixation. Here, we present a functionalized fluorescence probe for GGT, 4-CH2 F-HMDiEtR-gGlu, which is designed to generate an azaquinone methide intermediate during activation by GGT; this intermediate reacts with intracellular nucleophiles to generate a fluorescent adduct that is trapped inside the cells, without loss of the target enzyme activity. Application of the probe to patient-derived xenograft (PDX) mice enabled in vivo cancer imaging for a prolonged period and was also compatible with fixation and immunostaining of the cancer tissue.

Rapid and Accurate Visualization of Breast Tumors with a Fluorescent Probe Targeting α-Mannosidase 2C1.

Accurate detection of breast tumors and discrimination of tumor from normal tissues during breast-conserving surgery are essential to reduce the risk of misdiagnosis or recurrence. However, existing probes show substantial background signals in normal breast tissues. In this study, we focus on glycosidase activities in breast tumors. We synthesized a series of 12 fluorescent probes and performed imaging-based evaluation on surgically resected human breast specimens. Among them, the α-mannosidase-reactive fluorescent probe HMRef-αMan detected breast cancer with 90% sensitivity and 100% specificity. We identified α-mannosidase 2C1 as the target enzyme and confirmed its overexpression in various breast tumors. We found that fibroadenoma, the most common benign breast lesion in young woman, tends to have higher α-mannosidase 2C1 activity than malignant cancer. Combined application of green-emitting HMRef-αMan and a red-emitting γ-glutamyltranspeptidase probe enabled efficient dual-color, dual-target optical discrimination of malignant and benign tumors.

Multicolor Activatable Raman Probes for Simultaneous Detection of Plural Enzyme Activities.

Raman probes based on alkyne or nitrile tags hold promise for highly multiplexed imaging. However, sensing of enzyme activities with Raman probes is difficult because few mechanisms are available to modulate the vibrational response. Here we present a general strategy to prepare activatable Raman probes that show enhanced Raman signals due to electronic preresonance (EPR) upon reaction with enzymes under physiological conditions. We identified a xanthene derivative bearing a nitrile group at position 9 (9CN-JCP) as a suitable scaffold dye, and synthesized four types of activatable Raman probes, which are targeted to different enzymes (three aminopeptidases and a glycosidase) and tuned to different vibrational frequencies by isotope editing of the nitrile group. We validated the activation of the Raman signals of these probes by the target enzymes and succeeded in simultaneous imaging of the four enzyme activities in live cells. Different cell lines showed different patterns of these enzyme activities.

Classification of glomerular pathological findings using deep learning and nephrologist-AI collective intelligence approach.

BACKGROUND: Automated classification of glomerular pathological findings is potentially beneficial in establishing an efficient and objective diagnosis in renal pathology. While previous studies have verified the artificial intelligence (AI) models for the classification of global sclerosis and glomerular cell proliferation, there are several other glomerular pathological findings required for diagnosis, and the comprehensive models for the classification of these major findings have not yet been reported. Whether the cooperation between these AI models and clinicians improves diagnostic performance also remains unknown. Here, we developed AI models to classify glomerular images for major findings required for pathological diagnosis and investigated whether those models could improve the diagnostic performance of nephrologists. METHODS: We used a dataset of 283 kidney biopsy cases comprising 15,888 glomerular images that were annotated by a total of 25 nephrologists. AI models to classify seven pathological findings: global sclerosis, segmental sclerosis, endocapillary proliferation, mesangial matrix accumulation, mesangial cell proliferation, crescent, and basement membrane structural changes, were constructed using deep learning by fine-tuning of InceptionV3 convolutional neural network. Subsequently, we compared the agreement to truth labels between majority decision among nephrologists with or without the AI model as a voter. RESULTS: Our model for global sclerosis showed high performance (area under the curve: periodic acid-Schiff, 0.986; periodic acid methenamine silver, 0.983); the models for the other findings also showed performance close to those of nephrologists. By adding the AI model output to majority decision among nephrologists, out of the 14 constructed models, the results of the majority decision showed improvement in sensitivity for 10 models (four of them were statistically significant) and specificity for eight models (five significant). CONCLUSION: Our study showed a proof-of-concept for the classification of multiple glomerular findings in a comprehensive method of deep learning and suggested its potential effectiveness in improving diagnostic accuracy of clinicians.

ɤ-glutamyl hydroxymethyl rhodamine green fluorescence as a prognostic indicator for lung cancer.

OBJECTIVE: ɤ-glutamyltranspeptidase is an enzyme expressed in various malignancies including lung cancer. It rapidly activates non-fluorescent ɤ-glutamyl hydroxymethyl rhodamine green to highly fluorescent hydroxymethyl rhodamine green. The resultant tumor fluorescence is therefore an indicator of cellular ɤ-glutamyltranspeptidase activity. We have explored the use of ɤ-glutamyl hydroxymethyl rhodamine green as an intraoperative imaging tool for visualizing cancers. Herein, we evaluated the potential of the tumor fluorescence as a postoperative prognostic indicator. METHODS: We included patients with non-small cell lung cancer who had undergone radical resection from 2012 to 2014 in the study. We assessed the fluorescence intensity of the resected tumor and normal lung tissue by ex vivo imaging using ɤ-glutamyl hydroxymethyl rhodamine green. RESULTS: Sixty-seven patients were eligible for the study (adenocarcinomas, n = 44; squamous cell carcinoma, n = 14; other histologies, n = 8). The pathological stages were I, II, III, and IV in 39, 15, 12, and 1 patient, respectively. Based on the fluorescence of the tumor tissue, the patients were divided into high fluorescence (n = 33) and low fluorescence (n = 34) groups. The 5-year overall survival rate was significantly higher in the high fluorescence group (72.7%) compared to the low fluorescence group (47.1%, P = 0.025). Similarly, pathological stage I patients of the high fluorescence group had higher 5-year overall survival (85.7% vs. 44.4%, P = 0.009) and recurrence-free survival (76.2% vs. 44.4% P = 0.044) rates compared to those of the low fluorescence group. CONCLUSIONS: ɤ-glutamyl hydroxymethyl rhodamine green fluorescence is a good postoperative prognostic indicator in patients with non-small cell lung cancer.

The relationship between cigarette smoking and the tongue microbiome in an East Asian population.

Background: The oral microbiome, which consists of various habitats, has been shown to be influenced by smoking. However, differences in the tongue microbiomes of current and former smokers, as well as their resultant functional consequences, have rarely been investigated in East Asian populations. Methods: We used 16S rRNA amplicon sequencing of tongue-coating samples obtained from East Asian subjects who were current, former, or never smokers to identify differences in their tongue microbiomes and related metagenomic functions. Two sets of participants from 2016 to 2017 (n = 657 and n = 187, respectively) were analyzed separately. Results: We found significant differences between the overall microbiome compositions of current versus never smokers (p = 0.0015), but not between former versus never smokers (p = 0.43) based on the weighted UniFrac distance. Twenty-nine of 43 investigated genera showed significantly different expression levels in current versus never smokers. Neisseria and Capnocytophaga were less abundant, and Streptococcus and Megasphaera were more abundant in current smokers. Moreover, the abundances of metagenomic pathways, including those related to nitrate reduction and the tricarboxylic acid cycle, were significantly different between current and never smokers. Conclusions: The tongue microbiomes and related metagenomic pathways of current smokers differ from those of never smokers among East Asians.

Spontaneously Blinking Fluorophores Based on Nucleophilic Addition/Dissociation of Intracellular Glutathione for Live-Cell Super-resolution Imaging.

Single-molecule localization microscopy (SMLM) allows the reconstruction of super-resolution images but generally requires prior intense laser irradiation and in some cases additives to induce blinking of conventional fluorophores. We previously introduced a spontaneously blinking rhodamine fluorophore based on an intramolecular spirocyclization reaction for live-cell SMLM under physiological conditions. Here, we report a novel principle of spontaneous blinking in living cells, which utilizes reversible ground-state nucleophilic attack of intracellular glutathione (GSH) upon a xanthene fluorophore. Structural optimization afforded two pyronine fluorophores with different colors, both of which exhibit equilibrium (between the fluorescent dissociated form and the nonfluorescent GSH adduct form) and blinking kinetics that enable SMLM of microtubules or mitochondria in living cells. Furthermore, by using spontaneously blinking fluorophores working in the near-infrared (NIR) and green ranges, we succeeded in dual-color live-cell SMLM without the need for optimization of the imaging medium.

An in silico Approach for Integrating Phenotypic and Target-based Approaches in Drug Discovery.

Phenotypic and target-based approaches are useful methods in drug discovery. The phenotypic approach is an experimental approach for evaluating the phenotypic response. The target-based approach is a rational approach for screening drug candidates targeting a biomolecule that causes diseases. These approaches are widely used for drug discovery. However, two serious problems of target deconvolution and polypharmacology are encountered in these conventional experimental approaches. To overcome these two problems, we developed a new in silico method using a probabilistic framework. This method integrates both the phenotypic and target-based approaches to estimate a relevant network from compound to phenotype. Our method can computationally execute target deconvolution considering polypharmacology and can provide keys for understanding the pathway and mechanism from compound to phenotype, thereby promoting drug discovery.

Fluorescence Detection of Prostate Cancer by an Activatable Fluorescence Probe for PSMA Carboxypeptidase Activity.

Prostate cancer (PCa) is a common malignant tumor among adult males, and convenient intraoperative detection of PCa would reduce the risk of leaving positive surgical margins, especially during nerve-sparing procedures. To achieve rapid, fluorescence-based visualization of PCa, we focused on the glutamate carboxypeptidase (CP) activity of prostate-specific membrane antigen (PSMA), a type II transmembrane glycoprotein that is attracting attention as a PCa biomarker. Based on our finding that aryl glutamate conjugates with an azoformyl linker are recognized by PSMA and have a sufficiently low LUMO (lowest unoccupied molecular orbital) energy level to quench the fluorophore through photoinduced electron transfer, we designed and synthesized a first-in-class activatable fluorescence probe for CP activity of PSMA. The developed probe allowed us to visualize the CP activity of PSMA in living cells and in clinical specimens from PCa patients and is expected to be useful for rapid intraoperative detection and diagnosis of PCa.

Synthetic Biology: Engineering Mammalian Cells To Control Cell-to-Cell Communication at Will.

Cell-to-cell communication plays a key role in the regulation of many natural biological processes. Recent advances in mammalian synthetic biology are making it possible to rationally engineer cell-to-cell communication for therapeutic and other purposes. Here, we review state-of-the-art engineering principles to control cell-to-cell communication, focusing on communication between mammalian cells with diffusible factors (e.g., small molecules or exosomes) or direct cell contact, and on interkingdom communication between mammalian cells and bacteria. Potential applications include construction of artificial tissues able to perform complex computations, sophisticated cell-based cancer therapies, use of mammalian cells as a new class of cargo delivery modality, development of design principles to control pattern formation of cell populations, and treatment of infectious diseases. We also discuss the challenges facing practical applications, and possible enabling technologies to overcome them.

Rapid detection of metastatic lymph nodes of colorectal cancer with a gamma-glutamyl transpeptidase-activatable fluorescence probe.

Rapid diagnosis of metastatic lymph nodes (mLNs) of colorectal cancer (CRC) is desirable either intraoperatively or in resected fresh specimens. We have developed a series of activatable fluorescence probes for peptidase activities that are specifically upregulated in various tumors. We aimed to discover a target enzyme for detecting mLNs of CRC. Among our probes, we found that gGlu-HMRG, a gamma-glutamyl transpeptidase (GGT)-activatable fluorescence probe, could detect mLNs. This was unexpected, because we have previously reported that gGlu-HMRG could not detect primary CRC. We confirmed that the GGT activity of mLNs was high, whereas that of non-metastatic lymph nodes and CRC cell lines was low. We investigated the reason why GGT activity was upregulated in mLNs, and found that GGT was induced under conditions of hypoxia or low nutritional status. We utilized this feature to achieve rapid detection of mLNs with gGlu-HMRG. GGT appears to be a promising candidate enzyme for fluorescence imaging of mLNs.