Clinlabomics is a methodology-driven approach that leverages clinical laboratory data through advanced data mining strategies. Our lab focuses on developing innovative computational methods and tools to extract meaningful insights from routine clinical laboratory tests, enabling more accurate disease diagnosis, monitoring, and personalized treatment strategies.
By integrating machine learning, statistical analysis, and bioinformatics approaches, we aim to transform conventional laboratory data into actionable clinical knowledge, ultimately improving patient care and outcomes.
BMC Bioinformatics, 2022 Sep 24;23(1):387
This paper introduces the concept of Clinlabomics as a novel approach to extract valuable insights from routine clinical laboratory data. We present a comprehensive framework for data mining strategies that can be applied to laboratory test results, demonstrating how these methods can enhance disease diagnosis and monitoring.
BMC Cancer, 2023 Jun 1;23(1):496
This study explores how high-order features derived from routine blood tests can be used to predict non-small cell lung cancer prognosis. By applying advanced data mining techniques to standard laboratory data, we demonstrate the potential of Clinlabomics approaches in improving cancer management and patient stratification.
Comput Struct Biotechnol J, 2024 May 11;24:404-411
In this research, we developed a clinical-information-free method using neural networks to diagnose lung cancer in patients with pulmonary nodules. This work exemplifies the Clinlabomics approach by demonstrating how computational models can extract diagnostic information from laboratory data without requiring additional clinical information.
Our laboratory is at the forefront of basic research on platelets and their role in various diseases, particularly cancer. We investigate the fundamental mechanisms of platelet biology and how platelets interact with tumor cells, contributing to cancer progression, metastasis, and treatment resistance.
Through comprehensive studies of platelet-related biomarkers, we aim to develop novel diagnostic tools and therapeutic strategies targeting platelet-cancer interactions, ultimately improving cancer detection and treatment outcomes.
Genomics Proteomics Bioinformatics, 2025 Apr 12:qzaf031
This paper introduces PlateletBase, a comprehensive knowledgebase dedicated to platelet research. The database integrates diverse data types related to platelets, including genomics, proteomics, and clinical information, providing a valuable resource for researchers studying platelet biology and platelet-related diseases.
J Cell Mol Med, 2025 Apr;29(7):e70544
This study identifies the FLNA gene in tumor-educated platelets as a potential biomarker for identifying high-risk populations for non-small cell lung cancers. Our findings highlight the importance of platelet-derived molecular signatures in cancer diagnosis and risk assessment.
J Cell Mol Med, 2024 Dec;28(24):e70233
This research investigates the significance of the platelet-derived chloride ion channel gene (BEST3) in non-small cell lung cancer. Through platelet-related subtype mining, we reveal how platelet-specific molecular features can contribute to cancer classification and potentially guide personalized treatment approaches.
Pharmacol Res, 2023 May;191:106777
This review explores the interaction between oxidative stress and platelets in the context of cancer. We discuss how oxidative stress affects platelet function and how these changes may contribute to cancer development and progression, highlighting potential therapeutic targets in the platelet-cancer axis.
Our laboratory is dedicated to addressing clinical challenges in lung cancer through interdisciplinary research approaches. We focus on developing innovative diagnostic methods, understanding disease mechanisms, and improving treatment strategies for lung cancer patients.
By integrating AI-driven multimodal diagnostics with molecular and clinical data, we aim to enhance early detection, personalized treatment, and monitoring of lung cancer, ultimately improving patient outcomes and quality of life.
Signal Transduct Target Ther, 2022 Oct 10;7(1):348
This study investigates the characteristics and significance of peripheral blood T-cell receptor repertoire features in patients with indeterminate lung nodules. Our findings reveal how immune signatures can help distinguish between benign and malignant lung nodules, providing a novel approach for early lung cancer detection.
J Cancer, 2022 May 9;13(8):2515-2527
In this research, we developed a new classifier using platelet features to distinguish between malignant and benign pulmonary nodules. Based on prospective real-world data, our classifier demonstrates the potential of platelet-related biomarkers in improving lung cancer diagnosis and reducing unnecessary invasive procedures.
iScience, 2023 Apr 23;26(5):106693
This study explores the use of serum laser Raman spectroscopy as a potential diagnostic tool for distinguishing between benign and malignant pulmonary nodules. Our findings demonstrate how advanced spectroscopic techniques can provide non-invasive methods for lung cancer detection, potentially improving early diagnosis and treatment outcomes.
Int J Med Sci, 2024 Jan 1;21(2):234-252
This comprehensive review examines metabolomics analysis in lung cancer diagnosis using diverse sample types. We discuss how metabolomic approaches can provide valuable insights into lung cancer biology and potentially lead to the development of novel diagnostic biomarkers and therapeutic targets.
Heliyon, 2024 Jan 15;10(1):e23830
This study investigates the usefulness of the baseline immature reticulocyte fraction to mature reticulocyte fraction ratio (IMR) as a prognostic predictor for patients with small cell lung cancer. Our findings suggest that this simple blood test parameter may serve as a valuable tool for risk stratification and treatment planning in lung cancer patients.