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.

Oktoberfest: Open-source spectral library generation and rescoring pipeline based on Prosit.

Machine learning (ML) and deep learning (DL) models for peptide property prediction such as Prosit have enabled the creation of high quality in silico reference libraries. These libraries are used in various applications, ranging from data-independent acquisition (DIA) data analysis to data-driven rescoring of search engine results. Here, we present Oktoberfest, an open source Python package of our spectral library generation and rescoring pipeline originally only available online via ProteomicsDB. Oktoberfest is largely search engine agnostic and provides access to online peptide property predictions, promoting the adoption of state-of-the-art ML/DL models in proteomics analysis pipelines. We demonstrate its ability to reproduce and even improve our results from previously published rescoring analyses on two distinct use cases. Oktoberfest is freely available on GitHub (https://github.com/wilhelm-lab/oktoberfest) and can easily be installed locally through the cross-platform PyPI Python package.

Data integration for prediction of weight loss in randomized controlled dietary trials.

Diet is an important component in weight management strategies, but heterogeneous responses to the same diet make it difficult to foresee individual weight-loss outcomes. Omics-based technologies now allow for analysis of multiple factors for weight loss prediction at the individual level. Here, we classify weight loss responders (N = 106) and non-responders (N = 97) of overweight non-diabetic middle-aged Danes to two earlier reported dietary trials over 8 weeks. Random forest models integrated gut microbiome, host genetics, urine metabolome, measures of physiology and anthropometrics measured prior to any dietary intervention to identify individual predisposing features of weight loss in combination with diet. The most predictive models for weight loss included features of diet, gut bacterial species and urine metabolites (ROC-AUC: 0.84-0.88) compared to a diet-only model (ROC-AUC: 0.62). A model ensemble integrating multi-omics identified 64% of the non-responders with 80% confidence. Such models will be useful to assist in selecting appropriate weight management strategies, as individual predisposition to diet response varies.

The effect of rehabilitation on health-care utilisation in COPD patients in Copenhagen.

INTRODUCTION: The Integrated Rehabilitation Programme for Chronic Conditions project (SIKS) implemented rehabilitation programmes for people with four chronic conditions in the local area within the Municipality of Copenhagen. OBJECTIVES: The objective of this study was to evaluate the impact of rehabilitation on health-care utilisation in chronic obstructive pulmonary disease (COPD) patients as a subgroup of SIKS. METHODS: For the analyses, data from Danish National Registers' were obtained. The following outcomes were analysed: (i) COPD hospital admissions, (ii) COPD bed days, (iii) COPD outpatient visits, (iv) COPD emergency room visits, (v) general practitioner visits, (vi) specialist visits, and (vii) COPD specific medication. The rehabilitation group consisted of 118 patients who completed the programme. The control group consisted of 236 COPD patients in Copenhagen who did not undergo rehabilitation and were matched with the intervention group according to propensity score calculated on the basis of patient socio-demographic characteristics and health-care utilisation pattern in 2 years prior to the rehabilitation programme. The effect was assessed by applying the principle of difference-in-difference analysis. RESULTS: Compared with their matched controls, the patients participating in the rehabilitation programme showed a statistically significantly smaller increase in hospital admissions, bed days and outpatient visits. CONCLUSIONS: The study provides the policy decision makers in the Municipality of Copenhagen with an assessment of the effect of a real-life intervention. It shows that the pulmonary rehabilitation programme introduced had the anticipated effects on health-care utilisation. The study also suggests that the methods used for evaluation were appropriate.

Integration of healthcare rehabilitation in chronic conditions.

INTRODUCTION: Quality of care provided to people with chronic conditions does not often fulfil standards of care in Denmark and in other countries. Inadequate organisation of healthcare systems has been identified as one of the most important causes for observed performance inadequacies, and providing integrated healthcare has been identified as an important organisational challenge for healthcare systems. Three entities-Bispebjerg University Hospital, the City of Copenhagen, and the GPs in Copenhagen-collaborated on a quality improvement project focusing on integration and implementation of rehabilitation programmes in four conditions. DESCRIPTION OF CARE PRACTICE: FOUR MULTIDISCIPLINARY REHABILITATION INTERVENTION PROGRAMMES, ONE FOR EACH CHRONIC CONDITION: chronic obstructive pulmonary disease, type 2 diabetes, chronic heart failure, and falls in elderly people were developed and implemented during the project period. The chronic care model was used as a framework for support of implementing and integration of the four rehabilitation programmes. CONCLUSION AND DISCUSSION: The chronic care model provided support for implementing rehabilitation programmes for four chronic conditions in Bispebjerg University Hospital, the City of Copenhagen, and GPs' offices. New management practices were developed, known practices were improved to support integration, and known practices were used for implementation purposes. Several barriers to integrated care were identified.