Recent Developments in Machine Learning for Mass Spectrometry

ACS Measurement Science Au, Год журнала: 2024, Номер 4(3), С. 233 - 246

Опубликована: Фев. 21, 2024

Statistical analysis and modeling of mass spectrometry (MS) data have a long rich history with several modern MS-based applications using statistical chemometric methods. Recently, machine learning (ML) has experienced renaissance due to advents in computational hardware the development new algorithms for artificial neural networks (ANN) deep architectures. Moreover, recent successes ANN architectures areas science, engineering, society further strengthened ML field. Importantly, methods enabled approaches tasks related MS that are now widely adopted popular subdisciplines, such as imaging proteomics. Herein, we aim provide an introductory summary practical aspects methodology relevant MS. Additionally, seek up-to-date review most developments integration techniques while also providing critical insights into future direction

Язык: Английский

---

Mass Spectrometry Imaging of Lumpectomy Specimens Deciphers Diacylglycerols as Potent Biomarkers for the Diagnosis of Breast Cancer

Analytical Chemistry, Год журнала: 2023, Номер 95(20), С. 8054 - 8062

Опубликована: Май 11, 2023

Detecting breast tumor markers with a fast turnaround time from frozen sections should foster intraoperative histopathology in breast-conserving surgery, reducing the need for second operation. Hence, rapid label-free discrimination of spatially resolved molecular makeup between cancer and adjacent normal tissue is growing importance. We performed desorption electrospray ionization mass spectrometry imaging (DESI-MSI) fresh-frozen excision specimens, including paired sections, obtained lumpectomy 73 patients. The results demonstrate that posits sharp metabolic upregulation diacylglycerol, lipid messenger activates protein kinase C promoting growth. identified four specific sn-1,2-diacylglycerols outperformed all other lipids simultaneously mapped by positive ion mode DESI-MSI distinguishing cancers specimens. This result contrasts several previous studies probed dysregulation glycerophospholipids, sphingolipids, free fatty acids diagnoses. A random forest-based supervised machine learning considering detected signals also deciphered highest diagnostic potential these diacylglycerols top importance scores. led us to construct classifier 100% overall prediction accuracy using parsimonious set diacylglycerol biomarkers only. pathway analysis suggested increased catabolism phosphatidylcholine contributes overexpression. These open up opportunities mapping signaling context novel therapeutic developments, assessment margin status.

Язык: Английский

---

Mass Spectrometric Imaging of Anionic Phospholipids Desorbed from Human Hippocampal Sections: Discrimination between Temporal and Nontemporal Lobe Epilepsies

ACS Chemical Neuroscience, Год журнала: 2024, Номер 15(5), С. 983 - 993

Опубликована: Фев. 14, 2024

Temporal lobe epilepsy (TLE) is one of the most common neurological disorders, often accompanied by hippocampal sclerosis. The molecular processes underlying this epileptogenesis are poorly understood. To examine lipid profile, 39 fresh frozen sections human hippocampus obtained from surgery for TLE (n = 14) and non-TLE (control group; n 25) patients were subjected to desorption electrospray ionization mass spectrometry imaging in negative ion mode. In contrast our earlier report that showed striking downregulation positively charged phospholipids (e.g., phosphatidylcholine phosphatidylethanolamine, etc.) hippocampus, study finds complementary upregulation negatively phospholipids, notably, phosphatidylserine phosphatidylglycerol. This result may point an active metabolic pool produces these anionic at expense cationic phospholipids. shift could be due dysregulation Kennedy CDP-DG pathways responsible biosynthesizing lipids. Thus, further opens up opportunities investigate hallmarks potential therapeutic targets TLE.

Язык: Английский

---

Rapid and Reagent-Free Analysis of Dried Blood Spot by Paper Spray Mass Spectrometry Reveals Sex: Implications in Forensic Investigations

Journal of Proteome Research, Год журнала: 2025, Номер unknown

Опубликована: Янв. 22, 2025

Identifying sex from an unknown dried blood spot (DBS), especially when the corpse remains undiscovered, often provides valuable evidence in forensic casework. While DNA-based determination is a reliable method settings, it requires expensive reagents and time-consuming. To develop rapid reagent-free test for sex, we employed paper spray ionization mass spectrometry (PSI-MS) to capture sex-discriminatory lipid profiles 200 DBS samples comprising 100 males females. We conducted supervised machine learning (ML) analysis on all detected signals hunt biomarkers of within data set. This unveiled significant differences specific sphingomyelin phospholipid species levels between male female samples. Using parsimonious set 60 signals, constructed classifier that achieved 100% overall accuracy predicting paper. Additionally, assessed three-day-old air-exposed glass granite surfaces, simulating typical available investigations. Consequently, ∼92% prediction holdout surfaces. As highly sensitive detection tool, PSI-MS combined with ML has potential revolutionize methods by rapidly analyzing molecules encoding personal information.

Язык: Английский

---

Imaging and spatially resolved mass spectrometry applications in nephrology

Nature Reviews Nephrology, Год журнала: 2025, Номер unknown

Опубликована: Март 27, 2025

Язык: Английский

---

Mass Spectrometry Imaging Unveils the Fate of Azithromycin in Zebrafish: Uptake, Distribution, Transformation, and Metabolic Impact

Journal of environmental chemical engineering, Год журнала: 2025, Номер unknown, С. 117244 - 117244

Опубликована: Май 1, 2025

Язык: Английский

---

Advances in precision medicine for lupus nephritis: biomarker- and AI-driven diagnosis and treatment response prediction and targeted therapies

EBioMedicine, Год журнала: 2025, Номер 117, С. 105785 - 105785

Опубликована: Июнь 3, 2025

Язык: Английский

---

Systemic lupus in the era of machine learning medicine

Lupus Science & Medicine, Год журнала: 2024, Номер 11(1), С. e001140 - e001140

Опубликована: Март 1, 2024

Artificial intelligence and machine learning applications are emerging as transformative technologies in medicine. With greater access to a diverse range of big datasets, researchers turning these powerful techniques for data analysis. Machine can reveal patterns interactions between variables large complex datasets more accurately efficiently than traditional statistical methods. approaches open new possibilities studying SLE, multifactorial, highly heterogeneous disease. Here, we discuss how methods rapidly being integrated into the field SLE research. Recent reports have focused on building prediction models and/or identifying novel biomarkers using both supervised unsupervised understanding disease pathogenesis, early diagnosis prognosis In this review, will provide an overview current gaps, challenges opportunities studies. External validation most is still needed before clinical adoption. Utilisation deep models, alternative sources health increased awareness ethics, governance regulations surrounding use artificial medicine help propel exciting forward.

Язык: Английский

---

3D Mesh Animation Optimization Algorithm Based on Integer Programming and Nonlinear Constraints

IEEE Access, Год журнала: 2024, Номер 12, С. 86649 - 86661

Опубликована: Янв. 1, 2024

Язык: Английский

---

Glomerulopatia colapsante idiopática: bases moleculares e correlações entre parâmetros moleculares, proteômicos, clínicos e histológicos

Опубликована: Июль 20, 2023

em casos que não se identifica uma condição potencialmente associada à sua patogênese, a doença é denominada GC idiopática

---