An automated workflow for MALDI-ToF mass spectra pattern identification on large data sets: An application to detect aneuploidies from pregnancy urine

Artificial intelligence for prenatal chromosome analysis

This review article delves into the rapidly advancing domain of prenatal diagnostics, with a primary focus on the detection and management of chromosomal abnormalities such as trisomy 13 ("Patau syndrome)", "trisomy 18 (Edwards syndrome)", and "trisomy 21 (Down syndrome)". The objective of the study is to examine the utilization and effectiveness of novel computational methodologies, such as "machine learning (ML)", "deep learning (DL)", and data analysis, in enhancing the detection rates and accuracy of these prenatal conditions. The contribution of the article lies in its comprehensive examination of advancements in "Non-Invasive Prenatal Testing (NIPT)", prenatal screening, genomics, and medical imaging. It highlights the potential of these techniques for prenatal diagnosis and the contributions of ML and DL to these advancements. It highlights the application of ensemble models and transfer learning to improving model performance, especially with limited datasets. This also delves into optimal feature selection and fusion of high-dimensional features, underscoring the need for future research in these areas. The review finds that ML and DL have substantially improved the detection and management of prenatal conditions, despite limitations such as small sample sizes and issues related to model generalizability. It recognizes the promising results achieved through the use of ensemble models and transfer learning in prenatal diagnostics. The review also notes the increased importance of feature selection and high-dimensional feature fusion in the development and training of predictive models. The findings underline the crucial role of AI and machine learning techniques in early detection and improved therapeutic strategies in prenatal diagnostics, highlighting a pressing need for further research in this area.

Predictive Modelling in Clinical Bioinformatics: Key Concepts for Startups

Clinical bioinformatics is a newly emerging field that applies bioinformatics techniques for facilitating the identification of diseases, discovery of biomarkers, and therapy decision. Mathematical modelling is part of bioinformatics analysis pipelines and a fundamental step to extract clinical insights from genomes, transcriptomes and proteomes of patients. Often, the chosen modelling techniques relies on either statistical, machine learning or deterministic approaches. Research that combines bioinformatics with modelling techniques have been generating innovative biomedical technology, algorithms and models with biotech applications, attracting private investment to develop new business; however, startups that emerge from these technologies have been facing difficulties to implement clinical bioinformatics pipelines, protect their technology and generate profit. In this commentary, we discuss the main concepts that startups should know for enabling a successful application of predictive modelling in clinical bioinformatics. Here we will focus on key modelling concepts, provide some successful examples and briefly discuss the modelling framework choice. We also highlight some aspects to be taken into account for a successful implementation of cost-effective bioinformatics from a business perspective.

A Rapid and Affordable Screening Tool for Early-Stage Ovarian Cancer Detection Based on MALDI-ToF MS of Blood Serum

Ovarian cancer is a worldwide health issue that grows at a rate of almost 250,000 new cases every year. Its early detection is key for a good prognosis and even curative surgery. However, current medical examination methods and tests have been inefficient in detecting ovarian cancer at the early stage, leading to preventable death. So far, new screening tests based on molecular biomarker analysis techniques have not resulted in any substantial improvement in early-stage diagnosis and increased survival. Thus, whilst there remains clear potential to improve outcomes through early detection, novel approaches are needed. Here, we postulated that MALDI-ToF-mass-spectrometry-based tests can be a solution for effective screening of ovarian cancer. In this retrospective cohort study, we generated and analyzed the mass spectra of 181 serum samples of women with and without ovarian cancer. Using bioinformatics pipelines for analysis, including predictive modeling and machine learning, we found distinct mass spectral patterns composed of 9–20 key combinations of peak intensity or peak enrichment features for each stage of ovarian cancer. Based on a scoring algorithm and obtained patterns, the optimal sensitivity for detecting each stage of cancer was 95–97% with a specificity of 97%. Scoring all algorithms simultaneously could detect all stages of ovarian cancer at 99% sensitivity and 92% specificity. The results further demonstrate that the matrix and mass range analyzed played a key role in improving the mass spectral data quality and diagnostic power. Altogether, with the results reported here and increasing evidence of the MS assay’s diagnostic accuracy and instrument robustness, it has become imminent to consider MS in the clinical application for ovarian cancer screening.

High-resolution mass spectrometry (HRMS): Focus on the m/z values estimated by the Savitzky-Golay first derivative

RATIONALE

The calculation of centroids from profile mass spectra is one of the very first steps in the processing of mass spectra. The output is a signal and a m/z value. We focus on the accuracy of the prediction of the centroids' m/z values.

METHODS

A calculation based on the Savizky-Golay algorithm was evaluated on an Orbitrap mass spectrum. Reference m/z values were identified manually. Experimental centroids were extracted (1) automatically using our algorithm or the MSconvert algorithm and (2) manually using the Xcalibur software from Thermo. The three series of experimental m/z values were compared with the reference m/z values.

RESULTS

Our algorithm improved the determination of the m/z values compared with MSconvert. However, no improvement was observed over Xcalibur.

CONCLUSIONS

Our algorithm improved the automatic estimation of m/z values in the profile-to-centroid calculation. This is of importance when the goal is to determine raw compositions from the experimental m/z values. Nevertheless, the algorithms led to almost the same m/z values on a higher resolution mass spectrum.

Current Advancements in Noninvasive Profiling of the Embryo Culture Media Secretome

There have been over 8 million babies born through in vitro fertilization (IVF) and this number continues to grow. There is a global trend to perform elective single embryo transfers, avoiding risks associated with multiple pregnancies. It is therefore important to understand where current research of noninvasive testing for embryos stands, and what are the most promising techniques currently used. Furthermore, it is important to identify the potential to translate research and development into clinically applicable methods that ultimately improve live birth and reduce time to pregnancy. The current focus in the field of human reproductive medicine is to develop a more rapid, quantitative, and noninvasive test. Some of the most promising fields of research for noninvasive assays comprise cell-free DNA analysis, microscopy techniques coupled with artificial intelligence (AI) and omics analysis of the spent blastocyst media. High-throughput proteomics and metabolomics technologies are valuable tools for noninvasive embryo analysis. The biggest advantages of such technology are that it can differentiate between the embryos that appear morphologically identical and has the potential to identify the ploidy status noninvasively prior to transfer in a fresh cycle or before vitrification for a later frozen embryo transfer.

Bioinformatic identification of euploid and aneuploid embryo secretome signatures in IVF culture media based on MALDI-ToF mass spectrometry

PURPOSE

Embryo genotyping in IVF clinics aims to identify aneuploid embryos, and current methodologies rely on costly, invasive and time-consuming approaches such as PGT-A screening. MALDI-ToF-based mass spectral analysis of embryo culture has been demonstrated to be a non-invasive, affordable and accurate technique that is able to capture secretome profiles from embryo culture media extremely quick. Thus, aneuploid embryo genotypes can be distinguished from euploids from these profiles towards the development of novel embryo selection tools.

METHODS

A retrospective cohort study, including 292 spent media samples from embryo cultures collected from a single IVF clinic in USA. There were 149 euploid and 165 aneuploid embryos previously analysed by PGT-A next-generation sequencing techniques. Secretome mass spectra of embryos were generated using MALDI-ToF mass spectrometry in the UK. Data was systematically analysed using a fully automated and ultra-fast bioinformatic pipeline developed for the identification of mass spectral signatures.

RESULTS

Distinct spectral patterns were found for euploid and aneuploid genotypes in embryo culture media. We identified 12 characteristic peak signatures for euploid and 17 for aneuploid embryos. Data analysis also revealed a high degree of complementarity among regions showing that 22 regions are required to differentiate between genotypes with a sensitivity of 84% and a false positive rate of 18%.

CONCLUSION

Ultra-fast and fully automated screening of an embryo genotype is possible based on multiple combinations of specific mass spectral peak signatures. This constitutes a breakthrough towards the implementation of non-invasive and ultra-fast tools for embryo selection immediately prior to transfer.