LTK mutations responsible for resistance to lorlatinib in non-small cell lung cancer harboring CLIP1-LTK fusion.

The CLIP1-LTK fusion was recently discovered as a novel oncogenic driver in non-small cell lung cancer (NSCLC). Lorlatinib, a third-generation ALK inhibitor, exhibited a dramatic clinical response in a NSCLC patient harboring CLIP1-LTK fusion. However, it is expected that acquired resistance will inevitably develop, particularly by LTK mutations, as observed in NSCLC induced by oncogenic tyrosine kinases treated with corresponding tyrosine kinase inhibitors (TKIs). In this study, we evaluate eight LTK mutations corresponding to ALK mutations that lead to on-target resistance to lorlatinib. All LTK mutations show resistance to lorlatinib with the L650F mutation being the highest. In vitro and in vivo analyses demonstrate that gilteritinib can overcome the L650F-mediated resistance to lorlatinib. In silico analysis suggests that introduction of the L650F mutation may attenuate lorlatinib-LTK binding. Our study provides preclinical evaluations of potential on-target resistance mutations to lorlatinib, and a novel strategy to overcome the resistance.

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.

Developing a GNN-based AI model to predict mitochondrial toxicity using the bagging method.

Mitochondrial toxicity has been implicated in the development of various toxicities, including hepatotoxicity. Therefore, mitochondrial toxicity has become a major screening factor in the early discovery phase of drug development. Several models have been developed to predict mitochondrial toxicity based on chemical structures. However, they only provide a binary classification of positive or negative results and do not provide the substructures that contribute to a positive decision. Therefore, we developed an artificial intelligence (AI) model to predict mitochondrial toxicity and visualize structural alerts. To construct the model, we used the open-source software library kMoL, which employs a graph neural network approach that allows learning from chemical structure data. We also utilized the integrated gradient method, which enables the visualization of substructures that contribute to positive results. The dataset used to construct the AI model exhibited a significant imbalance, with significantly more negative than positive data. To address this, we employed the bagging method, which resulted in a model with high predictive performance, as evidenced by an F1 score of 0.839. This model can also be used to visualize substructures that contribute to mitochondrial toxicity using the integrated gradient method. Our AI model predicts mitochondrial toxicity based on chemical structures and may contribute to screening mitochondrial toxicity in the early stages of drug discovery.

Feature extraction of particle morphologies of pharmaceutical excipients from scanning electron microscope images using convolutional neural networks.

Scanning electron microscopy (SEM) images are the most widely used tool for evaluating particle morphology; however, quantitative evaluation using SEM images is time-consuming and often neglected. In this study, we aimed to extract features related to particle morphology of pharmaceutical excipients from SEM images using a convolutional neural network (CNN). SEM images of 67 excipients were acquired and used as models. A classification CNN model of the excipients was constructed based on the SEM images. Further, features were extracted from the middle layer of this CNN model, and the data was compressed to two dimensions using uniform manifold approximation and projection. Lastly, hierarchical clustering analysis (HCA) was performed to categorize the excipients into several clusters and identify similarities among the samples. The classification CNN model showed high accuracy, allowing each excipient to be identified with a high degree of accuracy. HCA revealed that the 67 excipients were classified into seven clusters. Additionally, the particle morphologies of excipients belonging to the same cluster were found to be very similar. These results suggest that CNN models are useful tools for extracting information and identifying similarities among the particle morphologies of excipients.

A macrocyclic kinase inhibitor overcomes triple resistant mutations in EGFR-positive lung cancer.

Brigatinib-based therapy was effective against osimertinib-resistant EGFR C797S mutants and is undergoing clinical studies. However, tumor relapse suggests additional resistance mutations might emerge. Here, we first demonstrated the binding mode of brigatinib to the EGFR-T790M/C797S mutant by crystal structure analysis and predicted brigatinib-resistant mutations through a cell-based assay including N-ethyl-N-nitrosourea (ENU) mutagenesis. We found that clinically reported L718 and G796 compound mutations appeared, consistent with their proximity to the binding site of brigatinib, and brigatinib-resistant quadruple mutants such as EGFR-activating mutation/T790M/C797S/L718M were resistant to all the clinically available EGFR-TKIs. BI-4020, a fourth-generation EGFR inhibitor with a macrocyclic structure, overcomes the quadruple and major EGFR-activating mutants but not the minor mutants, such as L747P or S768I. Molecular dynamics simulation revealed the binding mode and affinity between BI-4020 and EGFR mutants. This study identified potential therapeutic strategies using the new-generation macrocyclic EGFR inhibitor to overcome the emerging ultimate resistance mutants.

Idiopathic pulmonary fibrosis-specific Bayesian network integrating extracellular vesicle proteome and clinical information.

Idiopathic pulmonary fibrosis (IPF) is a progressive disease characterized by severe lung fibrosis and a poor prognosis. Although the biomolecules related to IPF have been extensively studied, molecular mechanisms of the pathogenesis and their association with serum biomarkers and clinical findings have not been fully elucidated. We constructed a Bayesian network using multimodal data consisting of a proteome dataset from serum extracellular vesicles, laboratory examinations, and clinical findings from 206 patients with IPF and 36 controls. Differential protein expression analysis was also performed by edgeR and incorporated into the constructed network. We have successfully visualized the relationship between biomolecules and clinical findings with this approach. The IPF-specific network included modules associated with TGF-ß signaling (TGFB1 and LRC32), fibrosis-related (A2MG and PZP), myofibroblast and inflammation (LRP1 and ITIH4), complement-related (SAA1 and SAA2), as well as serum markers, and clinical symptoms (KL-6, SP-D and fine crackles). Notably, it identified SAA2 associated with lymphocyte counts and PSPB connected with the serum markers KL-6 and SP-D, along with fine crackles as clinical manifestations. These results contribute to the elucidation of the pathogenesis of IPF and potential therapeutic targets.

Recent developments in machine learning modeling methods for hypertension treatment.

Hypertension is the leading cause of cardiovascular complications. This review focuses on the advancements in medical artificial intelligence (AI) models aimed at individualized treatment for hypertension, with particular emphasis on the approach to time-series big data on blood pressure and the development of interpretable medical AI models. The digitalization of daily blood pressure records and the downsizing of measurement devices enable the accumulation and utilization of time-series data. As mainstream blood pressure data shift from snapshots to time series, the clinical significance of blood pressure variability will be clarified. The time-series blood pressure prediction model demonstrated the capability to forecast blood pressure variabilities with a reasonable degree of accuracy for up to four weeks in advance. In recent years, various explainable AI techniques have been proposed for different purposes of model interpretation. It is essential to select the appropriate technique based on the clinical aspects; for example, actionable path-planning techniques can present individualized intervention plans to efficiently improve outcomes such as hypertension. Despite considerable progress in this field, challenges remain, such as the need for the prospective validation of AI-driven interventions and the development of comprehensive systems that integrate multiple AI methods. Future research should focus on addressing these challenges and refining the AI models to ensure their practical applicability in real-world clinical settings. Furthermore, the implementation of interdisciplinary collaborations among AI experts, clinicians, and healthcare providers are crucial to further optimizing and validate AI-driven solutions for hypertension management.

Enhanced Coarse-Grained Molecular Dynamics Simulation with a Smoothed Hybrid Potential Using a Neural Network Model.

In all-atom (AA) molecular dynamics (MD) simulations, the rugged energy profile of the force field makes it challenging to reproduce spontaneous structural changes in biomolecules within a reasonable calculation time. Existing coarse-grained (CG) models, in which the energy profile is set to a global minimum around the initial structure, are unsuitable to explore the structural dynamics between metastable states far away from the initial structure without any bias. In this study, we developed a new hybrid potential composed of an artificial intelligence (AI) potential and minimal CG potential related to the statistical bond length and excluded volume interactions to accelerate the transition dynamics while maintaining the protein character. The AI potential is trained by energy matching using a diverse structural ensemble sampled via multicanonical (Mc) MD simulation and the corresponding AA force field energy, profile of which is smoothed by energy minimization. By applying the new methodology to chignolin and TrpCage, we showed that the AI potential can predict the AA energy with significantly high accuracy, as indicated by a correlation coefficient (R-value) between the true and predicted energies exceeding 0.89. In addition, we successfully demonstrated that CGMD simulation based on the smoothed hybrid potential can significantly enhance the transition dynamics between various metastable states while preserving protein properties compared to those obtained with conventional CGMD and AAMD.

VGAE-MCTS: A New Molecular Generative Model Combining the Variational Graph Auto-Encoder and Monte Carlo Tree Search.

Molecular generation is crucial for advancing drug discovery, materials science, and chemical exploration. It expedites the search for new drug candidates, facilitates tailored material creation, and enhances our understanding of molecular diversity. By employing artificial intelligence techniques such as molecular generative models based on molecular graphs, researchers have tackled the challenge of identifying efficient molecules with desired properties. Here, we propose a new molecular generative model combining a graph-based deep neural network and a reinforcement learning technique. We evaluated the validity, novelty, and optimized physicochemical properties of the generated molecules. Importantly, the model explored uncharted regions of chemical space, allowing for the efficient discovery and design of new molecules. This innovative approach has considerable potential to revolutionize drug discovery, materials science, and chemical research for accelerating scientific innovation. By leveraging advanced techniques and exploring previously unexplored chemical spaces, this study offers promising prospects for the efficient discovery and design of new molecules in the field of drug development.

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.

Deep Learning-Based Differential Diagnosis of Follicular Thyroid Tumors Using Histopathological Images.

Deep learning systems (DLSs) have been developed for the histopathological assessment of various types of tumors, but none are suitable for differential diagnosis between follicular thyroid carcinoma (FTC) and follicular adenoma (FA). Furthermore, whether DLSs can identify the malignant characteristics of thyroid tumors based only on random views of tumor tissue histology has not been evaluated. In this study, we developed DLSs able to differentiate between FTC and FA based on 3 types of convolutional neural network architecture: EfficientNet, VGG16, and ResNet50. The performance of all 3 DLSs was excellent (area under the receiver operating characteristic curve = 0.91 ± 0.04; F1 score = 0.82 ± 0.06). Visual explanations using gradient-weighted class activation mapping suggested that the diagnosis of both FTC and FA was largely dependent on nuclear features. The DLSs were then trained with FTC images and linked information (presence or absence of recurrence within 10 years, vascular invasion, and wide capsular invasion). The ability of the DLSs to diagnose these characteristics was then determined. The results showed that, based on the random views of histology, the DLSs could predict the risk of FTC recurrence, vascular invasion, and wide capsular invasion with a certain level of accuracy (area under the receiver operating characteristic curve = 0.67 ± 0.13, 0.62 ± 0.11, and 0.65 ± 0.09, respectively). Further improvement of our DLSs could lead to the establishment of automated differential diagnosis systems requiring only biopsy specimens.

Establishment of an MR1 Presentation Reporter Screening System and Identification of Phenylpropanoid Derivatives as MR1 Ligands.

Mucosal-associated invariant T (MAIT) cells are innate-like T cells that are modulated by ligands presented on MHC class I-related proteins (MR1). These cells have attracted attention as potential drug targets because of their involvement in the initial response to infection and various disorders. Herein, we have established the MR1 presentation reporter assay system employing split-luciferase, which enables the efficient exploration of MR1 ligands. Using our screening system, we identified phenylpropanoid derivatives as MR1 ligands, including coniferyl aldehyde, which have an ability to inhibit the MR1-MAIT cell axis. Further, the structure-activity relationship study of coniferyl aldehyde analogs revealed the key structural features of ligands required for MR1 recognition. These results will contribute to identifying a broad range of endogenous and exogenous MR1 ligands and to developing novel MAIT cell modulators.

Individual health-disease phase diagrams for disease prevention based on machine learning.

Early disease detection and prevention methods based on effective interventions are gaining attention worldwide. Progress in precision medicine has revealed that substantial heterogeneity exists in health data at the individual level and that complex health factors are involved in chronic disease development. Machine-learning techniques have enabled precise personal-level disease prediction by capturing individual differences in multivariate data. However, it is challenging to identify what aspects should be improved for disease prevention based on future disease-onset prediction because of the complex relationships among multiple biomarkers. Here, we present a health-disease phase diagram (HDPD) that represents an individual's health state by visualizing the future-onset boundary values of multiple biomarkers that fluctuate early in the disease progression process. In HDPDs, future-onset predictions are represented by perturbing multiple biomarker values while accounting for dependencies among variables. We constructed HDPDs for 11 diseases using longitudinal health checkup cohort data of 3,238 individuals, comprising 3,215 measurement items and genetic data. The improvement of biomarker values to the non-onset region in HDPD remarkably prevented future disease onset in 7 out of 11 diseases. HDPDs can represent individual physiological states in the onset process and be used as intervention goals for disease prevention.

Ensemble-Learning and Feature Selection Techniques for Enhanced Antisense Oligonucleotide Efficacy Prediction in Exon Skipping.

Antisense oligonucleotide (ASO)-mediated exon skipping has become a valuable tool for investigating gene function and developing gene therapy. Machine-learning-based computational methods, such as eSkip-Finder, have been developed to predict the efficacy of ASOs via exon skipping. However, these methods are computationally demanding, and the accuracy of predictions remains suboptimal. In this study, we propose a new approach to reduce the computational burden and improve the prediction performance by using feature selection within machine-learning algorithms and ensemble-learning techniques. We evaluated our approach using a dataset of experimentally validated exon-skipping events, dividing it into training and testing sets. Our results demonstrate that using a three-way-voting approach with random forest, gradient boosting, and XGBoost can significantly reduce the computation time to under ten seconds while improving prediction performance, as measured by R2 for both 2'-O-methyl nucleotides (2OMe) and phosphorodiamidate morpholino oligomers (PMOs). Additionally, the feature importance ranking derived from our approach is in good agreement with previously published results. Our findings suggest that our approach has the potential to enhance the accuracy and efficiency of predicting ASO efficacy via exon skipping. It could also facilitate the development of novel therapeutic strategies. This study could contribute to the ongoing efforts to improve ASO design and optimize gene therapy approaches.

Improving Compound-Protein Interaction Prediction by Self-Training with Augmenting Negative Samples.

Identifying compound-protein interactions (CPIs) is crucial for drug discovery. Since experimentally validating CPIs is often time-consuming and costly, computational approaches are expected to facilitate the process. Rapid growths of available CPI databases have accelerated the development of many machine-learning methods for CPI predictions. However, their performance, particularly their generalizability against external data, often suffers from a data imbalance attributed to the lack of experimentally validated inactive (negative) samples. In this study, we developed a self-training method for augmenting both credible and informative negative samples to improve the performance of models impaired by data imbalances. The constructed model demonstrated higher performance than those constructed with other conventional methods for solving data imbalances, and the improvement was prominent for external datasets. Moreover, examination of the prediction score thresholds for pseudo-labeling during self-training revealed that augmenting the samples with ambiguous prediction scores is beneficial for constructing a model with high generalizability. The present study provides guidelines for improving CPI predictions on real-world data, thus facilitating drug discovery.

Exploring the mechanism of BK polyomavirus-associated nephropathy through consensus gene network approach.

BK polyomavirus-associated nephropathy occurs in kidney transplant recipients under immunosuppressive treatment. BK polyomavirus is implicated in cancer development and invasion, and case reports of renal cell carcinoma and urothelial carcinoma possibly associated with BK polyomavirus has been reported. Further, it has been suggested that the immune responses of KT-related diseases could play a role in the pathogenesis and progression of renal cell carcinoma. Thus, we thought to examine the relationship between BK polyomavirus-associated nephropathy and renal cell carcinoma in terms of gene expression. To identify the common and specific immune responses involved in kidney transplantation-related diseases with a specific focus on BK polyomavirus-associated nephropathy, we performed consensus weighted gene co-expression network analysis on gene profile datasets of renal biopsy samples from different institutions. After the identification of gene modules and validation of the obtained network by immunohistochemistry of the marker across kidney transplantation-related diseases, the relationship between prognosis of renal cell carcinoma and modules was assessed. We included the data from 248 patients and identified the 14 gene clusters across the datasets. We revealed that one cluster related to the translation regulating process and DNA damage response was specifically upregulated in BK polyomavirus-associated nephropathy. There was a significant association between the expression value of hub genes of the identified cluster including those related to cGAS-STING pathway and DNA damage response, and the prognosis of renal cell carcinoma. The study suggested the potential link between kidney transplantation-related diseases, especially specific transcriptomic signature of BK polyomavirus associated nephropathy and renal cell carcinoma.

Inhibition of the bone morphogenetic protein pathway suppresses tumor growth through downregulation of epidermal growth factor receptor in MEK/ERK-dependent colorectal cancer.

The bone morphogenetic protein (BMP) pathway promotes differentiation and induces apoptosis in normal colorectal epithelial cells. However, its role in colorectal cancer (CRC) is controversial, where it can act as context-dependent tumor promoter or tumor suppressor. Here we have found that CRC cells reside in a BMP-rich environment based on curation of two publicly available RNA-sequencing databases. Suppression of BMP using a specific BMP inhibitor, LDN193189, suppresses the growth of select CRC organoids. Colorectal cancer organoids treated with LDN193189 showed a decrease in epidermal growth factor receptor, which was mediated by protein degradation induced by leucine-rich repeats and immunoglobulin-like domains protein 1 (LRIG1) expression. Among 18 molecularly characterized CRC organoids, suppression of growth by BMP inhibition correlated with induction of LRIG1 gene expression. Notably, knockdown of LRIG1 in organoids diminished the growth-suppressive effect of LDN193189. Furthermore, in CRC organoids, which are susceptible to growth suppression by LDN193189, simultaneous treatment with LDN193189 and trametinib, an FDA-approved MEK inhibitor, resulted in cooperative growth inhibition both in vitro and in vivo. Taken together, the simultaneous inhibition of BMP and MEK could be a novel treatment option in CRC cases, and evaluating in vitro growth suppression and LRIG1 induction by BMP inhibition using patient-derived organoids could offer functional biomarkers for predicting potential responders to this regimen.

Development of a GCN-based model to predict in vitro phototoxicity from the chemical structure and HOMO-LUMO gap.

The interaction between sunlight and drugs can lead to phototoxicity in patients who have received such drugs. Phototoxicity assessment is a regulatory requirement globally and one of the main toxicity screening steps in the early stages of drug discovery. An in silico-in vitro approach has been utilized mainly for toxicology assessments at these stages. Although several quantitative structure-activity relationship (QSAR) models for phototoxicity have been developed, in silico technology to evaluate phototoxicity has not been well established. In this study, we attempted to develop an artificial intelligence (AI) model to predict the in vitro Neutral Red Uptake Phototoxicity Test results from a chemical structure and its derived information. To accomplish this, we utilized an open-source software library, kMoL. kMoL employs a graph convolutional neural networks (GCN) approach, which allows it to learn the data for the specified chemical structure. kMoL also utilizes the integrated gradient (IG) method, enabling it to visually display the substructures contributing to any positive results. To construct this AI model, we used only the chemical structure as a basis, then added the descriptors and the HOMO-LUMO gap, which was obtained from quantum chemical calculations. As a result, the assortment of chemical structures and the HOMO-LUMO gap produced an AI model with high discrimination performance, and an F1 score of 0.857. Additionally, our AI model could visualize the substructures involved in phototoxicity using the IG method. Our AI model can be applied as a toxicity screening method and could enhance productivity in drug development.

Mutual induced-fit mechanism drives binding between intrinsically disordered Bim and cryptic binding site of Bcl-xL.

The intrinsically disordered region (IDR) of Bim binds to the flexible cryptic site of Bcl-xL, a pro-survival protein involved in cancer progression that plays an important role in initiating apoptosis. However, their binding mechanism has not yet been elucidated. We have applied our dynamic docking protocol, which correctly reproduced both the IDR properties of Bim and the native bound configuration, as well as suggesting other stable/meta-stable binding configurations and revealed the binding pathway. Although the cryptic site of Bcl-xL is predominantly in a closed conformation, initial binding of Bim in an encounter configuration leads to mutual induced-fit binding, where both molecules adapt to each other; Bcl-xL transitions to an open state as Bim folds from a disordered to an α-helical conformation while the two molecules bind each other. Finally, our data provides new avenues to develop novel drugs by targeting newly discovered stable conformations of Bcl-xL.

Development and validation of ischemic heart disease and stroke prognostic models using large-scale real-world data from Japan.

BACKGROUND: Previous cardiovascular risk prediction models in Japan have utilized prospective cohort studies with concise data. As the health information including health check-up records and administrative claims becomes digitalized and publicly available, application of large datasets based on such real-world data can achieve prediction accuracy and support social implementation of cardiovascular disease risk prediction models in preventive and clinical practice. In this study, classical regression and machine learning methods were explored to develop ischemic heart disease (IHD) and stroke prognostic models using real-world data. METHODS: IQVIA Japan Claims Database was searched to include 691,160 individuals (predominantly corporate employees and their families working in secondary and tertiary industries) with at least one annual health check-up record during the identification period (April 2013-December 2018). The primary outcome of the study was the first recorded IHD or stroke event. Predictors were annual health check-up records at the index year-month, comprising demographic characteristics, laboratory tests, and questionnaire features. Four prediction models (Cox, Elnet-Cox, XGBoost, and Ensemble) were assessed in the present study to develop a cardiovascular disease risk prediction model for Japan. RESULTS: The analysis cohort consisted of 572,971 invididuals. All prediction models showed similarly good performance. The Harrell's C-index was close to 0.9 for all IHD models, and above 0.7 for stroke models. In IHD models, age, sex, high-density lipoprotein, low-density lipoprotein, cholesterol, and systolic blood pressure had higher importance, while in stroke models systolic blood pressure and age had higher importance. CONCLUSION: Our study analyzed classical regression and machine learning algorithms to develop cardiovascular disease risk prediction models for IHD and stroke in Japan that can be applied to practical use in a large population with predictive accuracy.