Clinically Applicable Deep Learning Algorithm Using Quantitative Proteomic Data

Early and swift identification of fungal-infection using infrared spectroscopy

Fungal pathogens pose significant threats to agricultural crops and food products, leading to economic losses, compromised food quality, and health hazards. Early detection is crucial for effective control and treatment. This study explores Fourier transform infrared-attenuated total reflectance (FTIR-ATR) spectroscopy for rapid fungal detection in bread. Using a machine learning algorithm (Random Forest), FTIR-ATR accurately distinguished between pure and infected bread samples, achieving 86% overall accuracy and 84% accuracy in identifying specific fungi like Rhizopus and Aspergillus on the first day of infection. These findings highlight FTIR-ATR's potential for early fungal infection detection, promising improved food quality and reduced economic losses through timely intervention.

Significant reduction of the culturing time required for bacterial identification and antibiotic susceptibility determination by infrared spectroscopy

Rapid testing of bacteria for antibiotic susceptibility is essential for effective treatment and curbing the emergence of multidrug-resistant bacteria. The misuse of antibiotics, coupled with the time-consuming classical testing methods, intensifies the threat of antibiotic resistance, a major global health concern. In this study, employing infrared spectroscopy-based machine learning techniques, we significantly shortened the time required for susceptibility testing to 10 hours, a significant improvement from the 24 hours in our previous studies as well as the conventional methods that typically take at least 48 hours. This remarkable reduction in turnaround time (from 48 hours to 10 hours), achieved by minimizing the culturing period, offers a game-changing advantage for clinical applications. Our study involves a dataset comprising 400 bacterial samples (200 E. coli, 100 Klebsiella pneumoniae, and 100 Pseudomonas aeruginosa) with an impressive 96% accuracy in the taxonomic classification at the species level and up to 82% accuracy in bacterial susceptibility to various antibiotics.

Applicability of selected reaction monitoring for precise screening tests

INTRODUCTION

The proactive identification of diseases through screening tests has long been endorsed as a means to preempt symptomatic onset. However, such screening endeavors are fraught with complications, such as diagnostic inaccuracies, procedural risks, and patient unease during examinations. These challenges are amplified when screenings for multiple diseases are administered concurrently. Selected Reaction Monitoring (SRM) offers a unique advantage, allowing for the high-throughput quantification of hundreds of analytes with minimal interferences.

AREAS COVERED

Our research posits that SRM-based assays, traditionally tailored for single-disease biomarker profiling, can be repurposed for multi-disease screening. This innovative approach has the potential to substantially alleviate time, labor, and cost demands on healthcare systems and patients alike. Nonetheless, there are formidable methodological hurdles to overcome. These include difficulties in detecting low-abundance proteins and the risk of model overfitting due to the multiple functionalities of single proteins across different disease spectrums - issues especially pertinent in blood-based assays where detection sensitivity is constrained. As we move forward, technological strides in sample preparation, online extraction, throughput, and automation are expected to ameliorate these limitations.

EXPERT OPINION

The maturation of mass spectrometry's integration into clinical laboratories appears imminent, positioning it as an invaluable asset for delivering highly sensitive, reproducible, and precise diagnostic results.

Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment

Research into the potential benefits of artificial intelligence for comprehending the intricate biology of cancer has grown as a result of the widespread use of deep learning and machine learning in the healthcare sector and the availability of highly specialized cancer datasets. Here, we review new artificial intelligence approaches and how they are being used in oncology. We describe how artificial intelligence might be used in the detection, prognosis, and administration of cancer treatments and introduce the use of the latest large language models such as ChatGPT in oncology clinics. We highlight artificial intelligence applications for omics data types, and we offer perspectives on how the various data types might be combined to create decision-support tools. We also evaluate the present constraints and challenges to applying artificial intelligence in precision oncology. Finally, we discuss how current challenges may be surmounted to make artificial intelligence useful in clinical settings in the future.

Realm of proteomics in breast cancer management and drug repurposing to alleviate intricacies of treatment

Breast cancer, a multi-networking heterogeneous disease, has emerged as a serious impediment to progress in clinical oncology. Although technological advancements and emerging cancer research studies have mitigated breast cancer lethality, a precision cancer-oriented solution has not been achieved. Thus, this review will persuade the acquiescence of proteomics-based diagnostic and therapeutic options in breast cancer management. Recently, the evidence of breast cancer health surveillance through imaging proteomics, single-cell proteomics, interactomics, and post-translational modification (PTM) tracking, to construct proteome maps and proteotyping for stage-specific and sample-specific cancer subtyping have outperformed conventional ways of dealing with breast cancer by increasing diagnostic efficiency, prognostic value, and predictive response. Additionally, the paradigm shift in applied proteomics for designing a chemotherapy regimen to identify novel drug targets with minor adverse effects has been elaborated. Finally, the potential of proteomics in alleviating the occurrence of chemoresistance and enhancing reprofiled drugs' effectiveness to combat therapeutic obstacles has been discussed. Owing to the enormous potential of proteomics techniques, the clinical recognition of proteomics in breast cancer management can be achievable and therapeutic intricacies can be surmountable.

Instant detection of extended-spectrum β-lactamase-producing bacteria from the urine of patients using infrared spectroscopy combined with machine learning

Antibiotics are considered the most effective treatment against bacterial infections. However, most bacteria have already developed resistance to a broad spectrum of commonly used antibiotics, mainly due to their uncontrolled use. Extended-spectrum beta-lactamase (ESBL)-producing bacteria are an essential class of multidrug-resistant (MDR) bacteria. It is of extreme urgency to develop a method that can detect ESBL-producing bacteria rapidly for the effective treatment of patients with bacterial infectious diseases. Fourier transform infrared (FTIR) microscopy is a sensitive method that can rapidly detect cellular molecular changes. In this study, we examined the potential of FTIR spectroscopy-based machine learning algorithms for the rapid detection of ESBL-producing bacteria obtained directly from a patient's urine. Using 591 ESBL-producing and 1658 non-ESBL-producing samples of Escherichia coli (E. coli) and Klebsiella pneumoniae, our results show that the FTIR spectroscopy-based machine learning approach can identify ESBL-producing bacteria within 40 minutes from receiving a patient's urine sample, with a success rate of 80%.

Rapid determination of Proteus mirabilis susceptibility to antibiotics using infrared spectroscopy in tandem with random forest

Bacterial infections cause serious illnesses that are treated with antibiotics. Currently used methods for detecting bacterial antibiotic susceptibility consume 48-72 h, leading to overuse of antibiotics. Thus, many bacterial species have acquired resistance to a broad range of available antibiotics. There is an urgent need to develop efficient methods for rapid determination of bacterial susceptibility to antibiotics. The combination of machine learning and Fourier-transform infrared (FTIR) spectroscopy has generated a promising diagnostic approach in medicine and biology. Our main goal is to examine the potential of FTIR spectroscopy to determine the susceptibility of urinary tract infection-Proteus mirabilis to a specific range of antibiotics, within about 20 min after 24 h culture and identification. We measured the infrared spectra of 489 different P. mirabilis isolates and used random forest to analyze this spectral database. A classification success rate of ~84% was achieved in differentiating between the resistant and sensitive isolates based on their susceptibility to ceftazidime, ceftriaxone, cefuroxime, cefuroxime axetil, cephalexin, ciprofloxacin, gentamicin, and sulfamethoxazole antibiotics in a time span of 24 h instead of 48 h.

Advances, obstacles, and opportunities for machine learning in proteomics

The fields of proteomics and machine learning are both large disciplines, each producing well over 5,000 publications per year. However, studies combining both fields are still relatively rare, with only about 2% of recent proteomics papers including machine learning. This review, which focuses on the intersection of the fields, is intended to inspire proteomics researchers to develop skills and knowledge in the application of machine learning. A brief tutorial introduction to machine learning is provided, and research advances that rely on both fields, particularly as they relate to proteomics tools development and biomarker discovery, are highlighted. Key knowledge gaps and opportunities for scientific advancement are also enumerated.

Sports Action Recognition Based on Deep Learning and Clustering Extraction Algorithm

This paper constructs a sports action recognition model based on deep learning (DL) and clustering extraction algorithm. For the input detection image frame, athletes' movements are detected through DL network, and then athletes' sports movements are fused. Moreover, it expands new knowledge and improves learning ability through automatic learning training set. The neural network (NN) is applied to the sample set containing images of nonathletes, and the negative training sample set is iteratively enhanced according to the generated false positives, and the results are optimized by clustering method. Simulation experiments show that compared with other algorithms, the clustering extraction algorithm in this paper has achieved superior performance in recognition rate and false alarm rate, and the recognition speed is faster. The aim is to extract the athletes' training postures through the analysis of sports movements, so as to assist coaches to train athletes more professionally and provide some reference for sports movement recognition.

A Review of Raman-Based Technologies for Bacterial Identification and Antimicrobial Susceptibility Testing

Antimicrobial resistance (AMR) is a global medical threat that seriously endangers human health. Rapid bacterial identification and antimicrobial susceptibility testing (AST) are key interventions to combat the spread and emergence of AMR. Although current clinical bacterial identification and AST provide comprehensive information, they are labor-intensive, complex, inaccurate, and slow (requiring several days, depending on the growth of pathogenic bacteria). Recently, Raman-based identification and AST technologies have played an increasingly important role in fighting AMR. This review summarizes major Raman-based techniques for bacterial identification and AST, including spontaneous Raman scattering, surface-enhanced Raman scattering (SERS), and coherent Raman scattering (CRS) imaging. Then, we discuss recent developments in rapid identification and AST methods based on Raman technology. Finally, we highlight the major challenges and potential future efforts to improve clinical outcomes through rapid bacterial identification and AST.

Managing of Unassigned Mass Spectrometric Data by Neural Network for Cancer Phenotypes Classification

Mass spectrometric profiling provides information on the protein and metabolic composition of biological samples. However, the weak efficiency of computational algorithms in correlating tandem spectra to molecular components (proteins and metabolites) dramatically limits the use of "omics" profiling for the classification of nosologies. The development of machine learning methods for the intelligent analysis of raw mass spectrometric (HPLC-MS/MS) measurements without involving the stages of preprocessing and data identification seems promising. In our study, we tested the application of neural networks of two types, a 1D residual convolutional neural network (CNN) and a 3D CNN, for the classification of three cancers by analyzing metabolomic-proteomic HPLC-MS/MS data. In this work, we showed that both neural networks could classify the phenotypes of gender-mixed oncology, kidney cancer, gender-specific oncology, ovarian cancer, and the phenotype of a healthy person by analyzing 'omics' data in 'mgf' data format. The created models effectively recognized oncopathologies with a model accuracy of 0.95. Information was obtained on the remoteness of the studied phenotypes. The closest in the experiment were ovarian cancer, kidney cancer, and prostate cancer/kidney cancer. In contrast, the healthy phenotype was the most distant from cancer phenotypes and ovarian and prostate cancers. The neural network makes it possible to not only classify the studied phenotypes, but also to determine their similarity (distance matrix), thus overcoming algorithmic barriers in identifying HPLC-MS/MS spectra. Neural networks are versatile and can be applied to standard experimental data formats obtained using different analytical platforms.

An Overview of EEG-based Machine Learning Methods in Seizure Prediction and Opportunities for Neurologists in this Field

The unpredictability of epileptic seizures is one of the most problematic aspects of the field of epilepsy. Methods or devices capable of detecting seizures minutes before they occur may help prevent injury or even death and significantly improve the quality of life. Machine learning (ML) is an emerging technology that can markedly enhance algorithm performance by interpreting data. ML has gained increasing attention from medical researchers in recent years. Its epilepsy applications range from the localization of the epileptic region, predicting the medical or surgical outcome of epilepsy, and automated electroencephalography (EEG) analysis to seizure prediction. While ML has good prospects with regard to detecting epileptic seizures via EEG signals, many clinicians are still unfamiliar with this field. This work briefly summarizes the history and recent significant progress made in this field and clarifies the essential components of the automatic seizure detection system using ML methodologies for clinicians. This review also proposes how neurologists can actively contribute to ensure improvements in seizure prediction using EEG-based ML.

Deep Learning in Proteomics

Proteomics, the study of all the proteins in biological systems, is becoming a data-rich science. Protein sequences and structures are comprehensively catalogued in online databases. With recent advancements in tandem mass spectrometry (MS) technology, protein expression and post-translational modifications (PTMs) can be studied in a variety of biological systems at the global scale. Sophisticated computational algorithms are needed to translate the vast amount of data into novel biological insights. Deep learning automatically extracts data representations at high levels of abstraction from data, and it thrives in data-rich scientific research domains. Here, a comprehensive overview of deep learning applications in proteomics, including retention time prediction, MS/MS spectrum prediction, de novo peptide sequencing, PTM prediction, major histocompatibility complex-peptide binding prediction, and protein structure prediction, is provided. Limitations and the future directions of deep learning in proteomics are also discussed. This review will provide readers an overview of deep learning and how it can be used to analyze proteomics data.

Computational advances of tumor marker selection and sample classification in cancer proteomics

Cancer proteomics has become a powerful technique for characterizing the protein markers driving transformation of malignancy, tracing proteome variation triggered by therapeutics, and discovering the novel targets and drugs for the treatment of oncologic diseases. To facilitate cancer diagnosis/prognosis and accelerate drug target discovery, a variety of methods for tumor marker identification and sample classification have been developed and successfully applied to cancer proteomic studies. This review article describes the most recent advances in those various approaches together with their current applications in cancer-related studies. Firstly, a number of popular feature selection methods are overviewed with objective evaluation on their advantages and disadvantages. Secondly, these methods are grouped into three major classes based on their underlying algorithms. Finally, a variety of sample separation algorithms are discussed. This review provides a comprehensive overview of the advances on tumor maker identification and patients/samples/tissues separations, which could be guidance to the researches in cancer proteomics.

BioDog, biomarker detection for improving identification power of breast cancer histologic grade in methylomics

Aim: Breast cancer histologic grade (HG) is a well-established prognostic factor. This study aimed to select methylomic biomarkers to predict breast cancer HGs. Materials & methods: The proposed algorithm BioDog firstly used correlation bias reduction strategy to eliminate redundant features. Then incremental feature selection was applied to find the features with a high HG prediction accuracy. The sequential backward feature elimination strategy was employed to further refine the biomarkers. A comparison with existing algorithms were conducted. The HG-specific somatic mutations were investigated. Results & conclusions: BioDog achieved accuracy 0.9973 using 92 methylomic biomarkers for predicting breast cancer HGs. Many of these biomarkers were within the genes and lncRNAs associated with the HG development in breast cancer or other cancer types.