Dataset Information

Machine learning-augmented surface-enhanced spectroscopy toward next-generation molecular diagnostics.

ABSTRACT: The world today is witnessing the significant role and huge demand for molecular detection and screening in healthcare and medical diagnosis, especially during the outbreak of COVID-19. Surface-enhanced spectroscopy techniques, including Surface-Enhanced Raman Scattering (SERS) and Infrared Absorption (SEIRA), provide lattice and molecular vibrational fingerprint information which is directly linked to the molecular constituents, chemical bonds, and configuration. These properties make them an unambiguous, nondestructive, and label-free toolkit for molecular diagnostics and screening. However, new issues in molecular diagnostics, such as increasing molecular species, faster spread of viruses, and higher requirements for detection accuracy and sensitivity, have brought great challenges to detection technology. Advancements in artificial intelligence and machine learning (ML) techniques show promising potential in empowering SERS and SEIRA with rapid analysis and automatic data processing to jointly tackle the challenge. This review introduces the combination of ML and SERS/SEIRA by investigating how ML algorithms can be beneficial to SERS/SEIRA, discussing the general process of combining ML and SEIRA/SERS, highlighting the molecular diagnostics and screening applications based on ML-combined SEIRA/SERS, and providing perspectives on the future development of ML-integrated SEIRA/SERS. In general, this review offers comprehensive knowledge about the recent advances and the future outlook regarding ML-integrated SEIRA/SERS for molecular diagnostics and screening.

SUBMITTER: Zhou H

PROVIDER: S-EPMC9890940 | biostudies-literature | 2023 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning-augmented surface-enhanced spectroscopy toward next-generation molecular diagnostics.

Zhou Hong H Xu Liangge L Ren Zhihao Z Zhu Jiaqi J Lee Chengkuo C

Nanoscale advances 20221107 3

The world today is witnessing the significant role and huge demand for molecular detection and screening in healthcare and medical diagnosis, especially during the outbreak of COVID-19. Surface-enhanced spectroscopy techniques, including Surface-Enhanced Raman Scattering (SERS) and Infrared Absorption (SEIRA), provide lattice and molecular vibrational fingerprint information which is directly linked to the molecular constituents, chemical bonds, and configuration. These properties make them an u ...[more]

PMID: 36756499

Similar Datasets

Project description:Characterizing complex biofluids using surface-enhanced Raman spectroscopy (SERS) coupled with machine learning (ML) has been proposed as a powerful tool for point-of-care detection of clinical disease. ML is well-suited to categorizing otherwise uninterpretable, patient-derived SERS spectra that contain a multitude of low concentration, disease-specific molecular biomarkers among a dense spectral background of biological molecules. However, ML can generate false, non-generalizable models when data sets used for model training are inadequate. It is thus critical to determine how different SERS experimental methodologies and workflow parameters can potentially impact ML disease classification of clinical samples. In this study, a label-free, broadband, Ag nanoparticle-based SERS platform was coupled with ML to assess simulated clinical samples for cardiovascular disease (CVD), containing randomized combinations of five key CVD biomarkers at clinically relevant concentrations in serum. Raman spectra obtained at 532, 633, and 785 nm from up to 300 unique samples were classified into physiological and pathological categories using two standard ML models. Label-free SERS and ML could correctly classify randomized CVD samples with high accuracies of up to 90.0% at 532 nm using as few as 200 training samples. Spectra obtained at 532 nm produced the highest accuracies with no significant increase achieved using multiwavelength SERS. Sample preparation and measurement methodologies (e.g., different SERS substrate lots, sample volumes, sample sizes, and known variations in randomization and experimental handling) were shown to strongly influence the ML classification and could artificially increase classification accuracies by as much as 27%. This detailed investigation into the proper application of ML techniques for CVD classification can lead to improved data set acquisition required for the SERS community, such that ML on labeled and robust SERS data sets can be practically applied for future point-of-care testing in patients.

Project description:Next-generation T-cell-directed vaccines for COVID-19 aim to induce durable T-cell immunity against circulating and future hypermutated SARS-CoV-2 variants. Mass Spectrometry (MS)based immunopeptidomics holds promise for guiding vaccine design, but computational challenges impede the precise and unbiased identification of conserved T-cell epitopes crucial for vaccines against rapidly mutating viruses. We introduce a computational framework and analysis platform integrating a novel machine learning algorithm, immunopeptidomics, intra-host data, epitope immunogenicity, and geo-temporal CD8+ T-cell epitope conservation analyses. Central to our approach is MHCvalidator, a novel artificial neural network algorithm enhancing MS-based immunopeptidomics sensitivity by modeling antigen presentation and sequence features. MHCvalidator identified a novel nonconventional SARS-CoV-2 T-cell epitope presented by B7 supertype molecules, originating from a +1-frameshift in a truncated Spike (S) antigen, supported by ribo-seq data. Intra-host analysis of SARS-CoV-2 proteomes from ~100,000 COVID-19 patients revealed a prevalent S antigen truncation in ~51% of cases, exposing a rich source of frameshifted viral antigens. Our framework includes EpiTrack, a new computational pipeline tracking global mutational dynamics of MHCvalidator-identified SARS-CoV-2 CD8+ epitopes from vaccine BNT162b4. While most vaccine-encoded CD8+ epitopes exhibit global conservation from January 2020 to October 2023, a highly immunodominant A*01-associated epitope, especially in hospitalized patients, undergoes substantial mutations in Delta and Omicron variants. Our approach unveils unprecedented SARS-CoV-2 T-cell epitopes, elucidates novel antigenic features, and underscores mutational dynamics of vaccine-relevant epitopes. The analysis platform is applicable to any viruses, and underscores the need for continual vigilance in T-cell vaccine development against the evolving landscape of hypermutating SARS-CoV-2 variants.

Project description:OBJECTIVES:Culture-based diagnostics represent the standard of care in septic patients, but are highly insensitive and in many cases unspecific. We recently demonstrated the general feasibility of next-generation sequencing-based diagnostics using free circulating nucleic acids (cell-free DNA) in plasma samples of septic patients. Within the presented investigation, higher performance of next-generation sequencing-based diagnostics was validated by comparison to matched blood cultures. DESIGN:A secondary analysis of a prospective, observational, single-center study. SETTING:Surgical ICU of a university hospital and research laboratory. PATIENTS:Fifty patients with septic shock, 20 uninfected patients with elective surgery as control cohort. INTERVENTIONS:None. MEASUREMENTS AND MAIN RESULTS:From 256 plasma samples of 48 septic patients at up to seven consecutive time points within the 28-day observation period, cell-free DNA was isolated and analyzed by next-generation sequencing and relevance scoring. In parallel, results from culture-based diagnostics (e.g., blood culture) were obtained. Plausibility of blood culture and next-generation sequencing results as well as adequacy of antibiotic therapy was evaluated by an independent expert panel. In contrast to blood culture with a positivity rate of 33% at sepsis onset, the positivity rate for next-generation sequencing-based pathogen identification was 72%. Over the whole study period, blood culture positivity was 11%, and next-generation sequencing positivity was 71%. Ninety-six percent of positive next-generation sequencing results for acute sepsis time points were plausible and would have led to a change to a more adequate therapy in 53% of cases as assessed by the expert evaluation. CONCLUSIONS:Our results show that next-generation sequencing-based analyses of bloodstream infections provide a valuable diagnostic platform for the identification of clinically relevant pathogens with higher sensitivity and specificity than blood culture, indicating that patients might benefit from a more appropriate therapy based on next-generation sequencing-based diagnosis.

Project description:BackgroundRecently, a growing number of novel genetic defects underlying primary immunodeficiencies (PIDs) have been identified, increasing the number of PID up to more than 250 well-defined forms. Next-generation sequencing (NGS) technologies and proper filtering strategies greatly contributed to this rapid evolution, providing the possibility to rapidly and simultaneously analyze large numbers of genes or the whole exome.ObjectiveTo evaluate the role of targeted NGS and whole exome sequencing (WES) in the diagnosis of a case series, characterized by complex or atypical clinical features suggesting a PID, difficult to diagnose using the current diagnostic procedures.MethodsWe retrospectively analyzed genetic variants identified through targeted NGS or WES in 45 patients with complex PID of unknown etiology.ResultsForty-seven variants were identified using targeted NGS, while 5 were identified using WES. Newly identified genetic variants were classified into four groups: (I) variations associated with a well-defined PID, (II) variations associated with atypical features of a well-defined PID, (III) functionally relevant variations potentially involved in the immunological features, and (IV) non-diagnostic genotype, in whom the link with phenotype is missing. We reached a conclusive genetic diagnosis in 7/45 patients (~16%). Among them, four patients presented with a typical well-defined PID. In the remaining three cases, mutations were associated with unexpected clinical features, expanding the phenotypic spectrum of typical PIDs. In addition, we identified 31 variants in 10 patients with complex phenotype, individually not causative per se of the disorder.ConclusionNGS technologies represent a cost-effective and rapid first-line genetic approach for the evaluation of complex PIDs. WES, despite a moderate higher cost compared to targeted, is emerging as a valuable tool to reach in a timely manner, a PID diagnosis with a considerable potential to draw genotype-phenotype correlation. Nevertheless, a large fraction of patients still remains without a conclusive diagnosis. In these patients, the sum of non-diagnostic variants might be proven informative in future studies with larger cohorts of patients.

Dataset Information

Machine learning-augmented surface-enhanced spectroscopy toward next-generation molecular diagnostics.

Publications

Machine learning-augmented surface-enhanced spectroscopy toward next-generation molecular diagnostics.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets