AI-Assisted Processing Pipeline to Boost Protein Isoform Detection.

Proteomics, the study of proteins within biological systems, has seen remarkable advancements in recent years, with protein isoform detection emerging as one of the next major frontiers. One of the primary challenges is achieving the necessary peptide and protein coverage to confidently differentiate isoforms as a result of the protein inference problem and protein false discovery rate estimation challenge in large data. In this chapter, we describe the application of artificial intelligence-assisted peptide property prediction for database search engine rescoring by Oktoberfest, an approach that has proven effective, particularly for complex samples and extensive search spaces, which can greatly increase peptide coverage. Further, it illustrates a method for increasing isoform coverage by the PickedGroupFDR approach that is designed to excel when applied on large data. Real-world examples are provided to illustrate the utility of the tools in the context of rescoring, protein grouping, and false discovery rate estimation. By implementing these cutting-edge techniques, researchers can achieve a substantial increase in both peptide and isoform coverage, thus unlocking the potential of protein isoform detection in their studies and shedding light on their roles and functions in biological processes.

Deep Learning-Assisted Analysis of Immunopeptidomics Data.

Liquid chromatography-coupled mass spectrometry (LC-MS/MS) is the primary method to obtain direct evidence for the presentation of disease- or patient-specific human leukocyte antigen (HLA). However, compared to the analysis of tryptic peptides in proteomics, the analysis of HLA peptides still poses computational and statistical challenges. Recently, fragment ion intensity-based matching scores assessing the similarity between predicted and observed spectra were shown to substantially increase the number of confidently identified peptides, particularly in use cases where non-tryptic peptides are analyzed. In this chapter, we describe in detail three procedures on how to benefit from state-of-the-art deep learning models to analyze and validate single spectra, single measurements, and multiple measurements in mass spectrometry-based immunopeptidomics. For this, we explain how to use the Universal Spectrum Explorer (USE), online Oktoberfest, and offline Oktoberfest. For intensity-based scoring, Oktoberfest uses fragment ion intensity and retention time predictions from the deep learning framework Prosit, a deep neural network trained on a very large number of synthetic peptides and tandem mass spectra generated within the ProteomeTools project. The examples shown highlight how deep learning-assisted analysis can increase the number of identified HLA peptides, facilitate the discovery of confidently identified neo-epitopes, or provide assistance in the assessment of the presence of cryptic peptides, such as spliced peptides.

inSPIRE: An Open-Source Tool for Increased Mass Spectrometry Identification Rates Using Prosit Spectral Prediction.

Rescoring of mass spectrometry (MS) search results using spectral predictors can strongly increase peptide spectrum match (PSM) identification rates. This approach is particularly effective when aiming to search MS data against large databases, for example, when dealing with nonspecific cleavage in immunopeptidomics or inflation of the reference database for noncanonical peptide identification. Here, we present inSPIRE (in silico Spectral Predictor Informed REscoring), a flexible and performant open-source rescoring pipeline built on Prosit MS spectral prediction, which is compatible with common database search engines. inSPIRE allows large-scale rescoring with data from multiple MS search files, increases sensitivity to minor differences in amino acid residue position, and can be applied to various MS sample types, including tryptic proteome digestions and immunopeptidomes. inSPIRE boosts PSM identification rates in immunopeptidomics, leading to better performance than the original Prosit rescoring pipeline, as confirmed by benchmarking of inSPIRE performance on ground truth datasets. The integration of various features in the inSPIRE backbone further boosts the PSM identification in immunopeptidomics, with a potential benefit for the identification of noncanonical peptides.

Predicting fragment intensities and retention time of iTRAQ- and TMTPro-labeled peptides with Prosit-TMT.

Isobaric labeling increases the throughput of proteomics by enabling the parallel identification and quantification of peptides and proteins. Over the past decades, a variety of isobaric tags have been developed allowing the multiplexed analysis of up to 18 samples. However, experiments utilizing such tags often exhibit reduced identification rates and thus show decreased analytical depth. Re-scoring has been shown to rescue otherwise missed identifications but was not yet systematically applied on isobarically labeled data. Because iTRAQ 4/8-plex and the recently released TMTpro 16/18-plex share similar characteristics with TMT 6/10/11-plex, we hypothesized that Prosit-TMT, trained exclusively on 6/10/11-plex labeled peptides, may be applicable to these isobaric labeling strategies as well. To investigate this, we re-analyzed nine publicly available datasets covering iTRAQ and TMTpro labeling for samples with human and mouse origin. We highlight that Prosit-TMT shows remarkably good performance when comparing experimentally acquired and predicted fragmentation spectra (R of 0.84 - 0.9) and retention times (ΔRT95% of 3% - 10% gradient time) of peptides. Furthermore, re-scoring substantially increases the number of confidently identified spectra, peptides, and proteins.

How radical prostatectomy procedures have changed over the last 10 years in Italy: a comparative analysis based on more than 1500 patients participating in the MIRROR-SIU/LUNA and the Pros-IT CNR study.

PURPOSE: Therapeutic strategies for prostate cancer (PCa) have been evolving dramatically worldwide. The current article reports on the evolution of surgical management strategies for PCa in Italy. METHODS: The data from two independent Italian multicenter projects, the MIRROR-SIU/LUNA (started in 2007, holding data of 890 patients) and the Pros-IT-CNR project (started in 2014, with data of 692 patients), were compared. Differences in patients' characteristics were evaluated. Multivariable logistic regression models were used to identify characteristics associated with robot-assisted (RA) procedure, nerve sparing (NS) approach, and lymph node dissection (LND). RESULTS: The two cohorts did not differ in terms of age and prostate-specific antigen (PSA) levels at biopsy. Patients enrolled in the Pros-IT-CNR project more frequently were submitted to RA (58.8% vs 27.6%, p < 0.001) and NS prostatectomy (58.4% vs. 52.9%, p = 0.04), but received LND less frequently (47.7% vs. 76.7%, p < 0.001), as compared to the MIRROR-SIU/LUNA patients. At multivariate logistic models, Lower Gleason Scores (GS) and PSA levels were significantly associated with RA prostatectomy in both cohorts. As for the MIRROR-SIU/LUNA data, clinical T-stage was a predictor for NS (OR = 0.07 for T3, T4) and LND (OR = 2.41 for T2) procedures. As for Pros-IT CNR data, GS ≥ (4 + 3) and positive cancer cores ≥ 50% were decisive factors both for NS (OR 0.29 and 0.30) and LND (OR 7.53 and 2.31) strategies. CONCLUSIONS: PCa management has changed over the last decade in Italian centers: RA and NS procedures without LND have become the methods of choice to treat newly medium-high risk diagnosed PCa.

Deep Learning Neural Network Prediction Method Improves Proteome Profiling of Vascular Sap of Grapevines during Pierce's Disease Development.

Plant secretome studies highlight the importance of vascular plant defense proteins against pathogens. Studies on Pierce's disease of grapevines caused by the xylem-limited bacterium Xylella fastidiosa (Xf) have detected proteins and pathways associated with its pathobiology. Despite the biological importance of the secreted proteins in the extracellular space to plant survival and development, proteome studies are scarce due to methodological challenges. Prosit, a deep learning neural network prediction method is a powerful tool for improving proteome profiling by data-independent acquisition (DIA). We explored the potential of Prosit's in silico spectral library predictions to improve DIA proteomic analysis of vascular leaf sap from grapevines with Pierce's disease. The combination of DIA and Prosit-predicted libraries increased the total number of identified grapevine proteins from 145 to 360 and Xf proteins from 18 to 90 compared to gas-phase fractionation (GPF) libraries. The new proteins increased the range of molecular weights, assisted in the identification of more exclusive peptides per protein, and increased identification of low-abundance proteins. These improvements allowed identification of new functional pathways associated with cellular responses to oxidative stress, to be investigated further.

PROTEOFORMER 2.0: Further Developments in the Ribosome Profiling-assisted Proteogenomic Hunt for New Proteoforms.

PROTEOFORMER is a pipeline that enables the automated processing of data derived from ribosome profiling (RIBO-seq, i.e. the sequencing of ribosome-protected mRNA fragments). As such, genome-wide ribosome occupancies lead to the delineation of data-specific translation product candidates and these can improve the mass spectrometry-based identification. Since its first publication, different upgrades, new features and extensions have been added to the PROTEOFORMER pipeline. Some of the most important upgrades include P-site offset calculation during mapping, comprehensive data pre-exploration, the introduction of two alternative proteoform calling strategies and extended pipeline output features. These novelties are illustrated by analyzing ribosome profiling data of human HCT116 and Jurkat data. The different proteoform calling strategies are used alongside one another and in the end combined together with reference sequences from UniProt. Matching mass spectrometry data are searched against this extended search space with MaxQuant. Overall, besides annotated proteoforms, this pipeline leads to the identification and validation of different categories of new proteoforms, including translation products of up- and downstream open reading frames, 5' and 3' extended and truncated proteoforms, single amino acid variants, splice variants and translation products of so-called noncoding regions. Further, proof-of-concept is reported for the improvement of spectrum matching by including Prosit, a deep neural network strategy that adds extra fragmentation spectrum intensity features to the analysis. In the light of ribosome profiling-driven proteogenomics, it is shown that this allows validating the spectrum matches of newly identified proteoforms with elevated stringency. These updates and novel conclusions provide new insights and lessons for the ribosome profiling-based proteogenomic research field. More practical information on the pipeline, raw code, the user manual (README) and explanations on the different modes of availability can be found at the GitHub repository of PROTEOFORMER: https://github.com/Biobix/proteoformer.

Iloprost use and medical management of systemic sclerosis-related vasculopathy in Italian tertiary referral centers: results from the PROSIT study.

Vasculopathy is a crucial feature of systemic sclerosis (SSc), and Raynaud's phenomenon (RP) and digital ulcers (DU) have a deep impact on the quality of patients' life. The management of vascular disease can be challenging for the clinician because of the suboptimal tolerability of the treatments and lack of consensus on the best therapeutic approach. Intravenous iloprost, a synthetic analogue of prostacyclin, is broadly used for the treatment of RP and ischemic ulcers secondary to SSc. However, no standardized protocol on iloprost use is currently available and, consequently, the management of this treatment is largely based on the experience of each single center. The PROSIT project is an observational, multicenter study aiming to investigate the current treatments for SSc vasculopathy, the use of prostanoids, with special regard to iloprost, and the perception of the treatment from a patient's perspective. The study was conducted on a cohort of 346 patients from eight Italian centers and included a structured survey addressed to physicians, data collected from patient's medical records and two patient-administered questionnaires assessing the level of satisfaction, tolerability and perception of the efficacy of Iloprost. PROSIT data confirmed that in the contest of SSc iloprost represents the first-line choice for the management of severe RP and DU. Moreover, it is a well-tolerated treatment as reported by patients' experience. Although a standard protocol for the treatment of SSc-related vasculopathy is lacking, PROSIT study identified different therapeutic approaches largely supported by tertiary Italian centers. Further studies are needed in order to optimize the best treatment for SSc vascular diseases, in particular to improve the best iloprost schedule management.

Disease-specific and general health-related quality of life in newly diagnosed prostate cancer patients: the Pros-IT CNR study.

BACKGROUND: The National Research Council (CNR) prostate cancer monitoring project in Italy (Pros-IT CNR) is an observational, prospective, ongoing, multicentre study aiming to monitor a sample of Italian males diagnosed as new cases of prostate cancer. The present study aims to present data on the quality of life at time prostate cancer is diagnosed. METHODS: One thousand seven hundred five patients were enrolled. Quality of life is evaluated at the time cancer was diagnosed and at subsequent assessments via the Italian version of the University of California Los Angeles-Prostate Cancer Index (UCLA-PCI) and the Short Form Health Survey (SF-12). RESULTS: At diagnosis, lower scores on the physical component of the SF-12 were associated to older ages, obesity and the presence of 3+ moderate/severe comorbidities. Lower scores on the mental component were associated to younger ages, the presence of 3+ moderate/severe comorbidities and a T-score higher than one. Urinary and bowel functions according to UCLA-PCI were generally good. Almost 5% of the sample reported using at least one safety pad daily to control urinary loss; less than 3% reported moderate/severe problems attributable to bowel functions, and sexual function was a moderate/severe problem for 26.7%. Diabetes, 3+ moderate/severe comorbidities, T2 or T3-T4 categories and a Gleason score of eight or more were significantly associated with lower sexual function scores at diagnosis. CONCLUSIONS: Data collected by the Pros-IT CNR study have clarified the baseline status of newly diagnosed prostate cancer patients. A comprehensive assessment of quality of life will allow to objectively evaluate outcomes of different profile of care.