Phenotype Classification using Proteome Data in a Data-Independent Acquisition Tensor Format

ProteoNet: A CNN-based framework for analyzing proteomics MS-RGB images

Proteomics is crucial in clinical research, yet the clinical application of proteomic data remains challenging. Transforming proteomic mass spectrometry (MS) data into red, green, and blue color (MS-RGB) image formats and applying deep learning (DL) techniques has shown great potential to enhance analysis efficiency. However, current DL models often fail to extract subtle, crucial features from MS-RGB data. To address this, we developed ProteoNet, a deep learning framework that refines MS-RGB data analysis. ProteoNet incorporates semantic partitioning, adaptive average pooling, and weighted factors into the Convolutional Neural Network (CNN) model, thus enhancing data analysis accuracy. Our experiments with proteomics data from urine, blood, and tissue samples related to liver, kidney, and thyroid diseases demonstrate that ProteoNet outperforms existing models in accuracy. ProteoNet also provides a direct conversion method for MS-RGB data, enabling a seamless workflow. Moreover, its compatibility with various CNN architectures, including lightweight models like MobileNetV2, underscores its scalability and clinical potential.

A deep learning framework for hepatocellular carcinoma diagnosis using MS1 data

Clinical proteomics analysis is of great significance for analyzing pathological mechanisms and discovering disease-related biomarkers. Using computational methods to accurately predict disease types can effectively improve patient disease diagnosis and prognosis. However, how to eliminate the errors introduced by peptide precursor identification and protein identification for pathological diagnosis remains a major unresolved issue. Here, we develop a powerful end-to-end deep learning model, termed "MS1Former", that is able to classify hepatocellular carcinoma tumors and adjacent non-tumor (normal) tissues directly using raw MS1 spectra without peptide precursor identification. Our model provides accurate discrimination of subtle m/z differences in MS1 between tumor and adjacent non-tumor tissue, as well as more general performance predictions for data-dependent acquisition, data-independent acquisition, and full-scan data. Our model achieves the best performance on multiple external validation datasets. Additionally, we perform a detailed exploration of the model's interpretability. Prospectively, we expect that the advanced end-to-end framework will be more applicable to the classification of other tumors.

Acquisition and Analysis of DIA-Based Proteomic Data: A Comprehensive Survey in 2023

Data-independent acquisition (DIA) mass spectrometry (MS) has emerged as a powerful technology for high-throughput, accurate, and reproducible quantitative proteomics. This review provides a comprehensive overview of recent advances in both the experimental and computational methods for DIA proteomics, from data acquisition schemes to analysis strategies and software tools. DIA acquisition schemes are categorized based on the design of precursor isolation windows, highlighting wide-window, overlapping-window, narrow-window, scanning quadrupole-based, and parallel accumulation-serial fragmentation-enhanced DIA methods. For DIA data analysis, major strategies are classified into spectrum reconstruction, sequence-based search, library-based search, de novo sequencing, and sequencing-independent approaches. A wide array of software tools implementing these strategies are reviewed, with details on their overall workflows and scoring approaches at different steps. The generation and optimization of spectral libraries, which are critical resources for DIA analysis, are also discussed. Publicly available benchmark datasets covering global proteomics and phosphoproteomics are summarized to facilitate performance evaluation of various software tools and analysis workflows. Continued advances and synergistic developments of versatile components in DIA workflows are expected to further enhance the power of DIA-based proteomics.

Proteome Landscapes of Human Hepatocellular Carcinoma and Intrahepatic Cholangiocarcinoma

Liver cancer is among the top leading causes of cancer mortality worldwide. Particularly, hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (CCA) have been extensively investigated from the aspect of tumor biology. However, a comprehensive and systematic understanding of the molecular characteristics of HCC and CCA remains absent. Here, we characterized the proteome landscapes of HCC and CCA using the data-independent acquisition (DIA) mass spectrometry (MS) method. By comparing the quantitative proteomes of HCC and CCA, we found several differences between the two cancer types. In particular, we found an abnormal lipid metabolism in HCC and activated extracellular matrix-related pathways in CCA. We next developed a three-protein classifier to distinguish CCA from HCC, achieving an area under the curve (AUC) of 0.92, and an accuracy of 90% in an independent validation cohort of 51 patients. The distinct molecular characteristics of HCC and CCA presented in this study provide new insights into the tumor biology of these two major important primary liver cancers. Our findings may help develop more efficient diagnostic approaches and new targeted drug treatments.

Artificial intelligence defines protein-based classification of thyroid nodules

Determination of malignancy in thyroid nodules remains a major diagnostic challenge. Here we report the feasibility and clinical utility of developing an AI-defined protein-based biomarker panel for diagnostic classification of thyroid nodules: based initially on formalin-fixed paraffin-embedded (FFPE), and further refined for fine-needle aspiration (FNA) tissue specimens of minute amounts which pose technical challenges for other methods. We first developed a neural network model of 19 protein biomarkers based on the proteomes of 1724 FFPE thyroid tissue samples from a retrospective cohort. This classifier achieved over 91% accuracy in the discovery set for classifying malignant thyroid nodules. The classifier was externally validated by blinded analyses in a retrospective cohort of 288 nodules (89% accuracy; FFPE) and a prospective cohort of 294 FNA biopsies (85% accuracy) from twelve independent clinical centers. This study shows that integrating high-throughput proteomics and AI technology in multi-center retrospective and prospective clinical cohorts facilitates precise disease diagnosis which is otherwise difficult to achieve by other methods.

Rapid Screening of COVID-19 Directly from Clinical Nasopharyngeal Swabs Using the MasSpec Pen

The outbreak of COVID-19 has created an unprecedent global crisis. While the polymerase chain reaction (PCR) is the gold standard method for detecting active SARS-CoV-2 infection, alternative high-throughput diagnostic tests are of a significant value to meet universal testing demands. Here, we describe a new design of the MasSpec Pen technology integrated to electrospray ionization (ESI) for direct analysis of clinical swabs and investigate its use for COVID-19 screening. The redesigned MasSpec Pen system incorporates a disposable sampling device refined for uniform and efficient analysis of swab tips via liquid extraction directly coupled to an ESI source. Using this system, we analyzed nasopharyngeal swabs from 244 individuals including symptomatic COVID-19 positive, symptomatic negative, and asymptomatic negative individuals, enabling rapid detection of rich lipid profiles. Two statistical classifiers were generated based on the lipid information acquired. Classifier 1 was built to distinguish symptomatic PCR-positive from asymptomatic PCR-negative individuals, yielding a cross-validation accuracy of 83.5%, sensitivity of 76.6%, and specificity of 86.6%, and validation set accuracy of 89.6%, sensitivity of 100%, and specificity of 85.3%. Classifier 2 was built to distinguish symptomatic PCR-positive patients from negative individuals including symptomatic PCR-negative patients with moderate to severe symptoms and asymptomatic individuals, yielding a cross-validation accuracy of 78.4%, specificity of 77.21%, and sensitivity of 81.8%. Collectively, this study suggests that the lipid profiles detected directly from nasopharyngeal swabs using MasSpec Pen-ESI mass spectrometry (MS) allow fast (under a minute) screening of the COVID-19 disease using minimal operating steps and no specialized reagents, thus representing a promising alternative high-throughput method for screening of COVID-19.

Deep learning neural network tools for proteomics

Mass-spectrometry-based proteomics enables quantitative analysis of thousands of human proteins. However, experimental and computational challenges restrict progress in the field. This review summarizes the recent flurry of machine-learning strategies using artificial deep neural networks (or "deep learning") that have started to break barriers and accelerate progress in the field of shotgun proteomics. Deep learning now accurately predicts physicochemical properties of peptides from their sequence, including tandem mass spectra and retention time. Furthermore, deep learning methods exist for nearly every aspect of the modern proteomics workflow, enabling improved feature selection, peptide identification, and protein inference.