Detection of m6A from direct RNA sequencing using a multiple instance learning framework.

RNA modifications such as m6A methylation form an additional layer of complexity in the transcriptome. Nanopore direct RNA sequencing can capture this information in the raw current signal for each RNA molecule, enabling the detection of RNA modifications using supervised machine learning. However, experimental approaches provide only site-level training data, whereas the modification status for each single RNA molecule is missing. Here we present m6Anet, a neural-network-based method that leverages the multiple instance learning framework to specifically handle missing read-level modification labels in site-level training data. m6Anet outperforms existing computational methods, shows similar accuracy as experimental approaches, and generalizes with high accuracy to different cell lines and species without retraining model parameters. In addition, we demonstrate that m6Anet captures the underlying read-level stoichiometry, which can be used to approximate differences in modification rates. Overall, m6Anet offers a tool to capture the transcriptome-wide identification and quantification of m6A from a single run of direct RNA sequencing.

Beyond sequencing: machine learning algorithms extract biology hidden in Nanopore signal data.

Nanopore sequencing provides signal data corresponding to the nucleotide motifs sequenced. Through machine learning-based methods, these signals are translated into long-read sequences that overcome the read size limit of short-read sequencing. However, analyzing the raw nanopore signal data provides many more opportunities beyond just sequencing genomes and transcriptomes: algorithms that use machine learning approaches to extract biological information from these signals allow the detection of DNA and RNA modifications, the estimation of poly(A) tail length, and the prediction of RNA secondary structures. In this review, we discuss how developments in machine learning methodologies contributed to more accurate basecalling and lower error rates, and how these methods enable new biological discoveries. We argue that direct nanopore sequencing of DNA and RNA provides a new dimensionality for genomics experiments and highlight challenges and future directions for computational approaches to extract the additional information provided by nanopore signal data.

N-glycan profiles of acute myocardial infarction patients reveal potential biomarkers for diagnosis, severity assessment and treatment monitoring.

Acute myocardial infarction (AMI) is a leading cause of mortality and morbidity worldwide. Diagnostic challenges remain in this highly time-sensitive condition. Using capillary electrophoresis-laser-induced fluorescence, we analyzed the blood plasma N-glycan profile in a cohort study comprising 103 patients with AMI and 69 controls. Subsequently, the data generated was subjected to classification modeling to identify potential AMI biomarkers. An area under the Receiving Operating Characteristic curve (AUCROC) of 0.81 was obtained when discriminating AMI vs. non-MI patients. We postulate that the glycan profile involves a switch from a pro- to an anti-inflammatory state in the AMI pathophysiology. This was supported by significantly decreased levels in galactosylation, alongside increased levels in sialylation, afucosylation and GlcNAc bisection levels in the blood plasma of AMI patients. By substantiating the glycomics analysis with immunoglobulin G (IgG) protein measurements, robustness of the glycan-based classifiers was demonstrated. Changes in AMI-related IgG activities were also confirmed to be associated with alterations at the glycosylation level. Additionally, a glycan-biomarker panel derived from glycan features and current clinical biomarkers performed remarkably (AUCROC = 0.90, sensitivity = 0.579 at 5% false positive rate) when discriminating between patients with ST-segment elevation MI (n = 84) and non-ST-segment elevation MI (n = 19). Moreover, by applying the model trained using glycomics information, AMI and controls can still be discriminated at 1 and 6 months after baseline. Thus, glycomics biomarkers could potentially serve as a valuable complementary test to current diagnostic biomarkers. Additional research on their utility and associated biomechanisms via a large-scale study is recommended.

Identification of differential RNA modifications from nanopore direct RNA sequencing with xPore.

RNA modifications, such as N6-methyladenosine (m6A), modulate functions of cellular RNA species. However, quantifying differences in RNA modifications has been challenging. Here we develop a computational method, xPore, to identify differential RNA modifications from nanopore direct RNA sequencing (RNA-seq) data. We evaluate our method on transcriptome-wide m6A profiling data, demonstrating that xPore identifies positions of m6A sites at single-base resolution, estimates the fraction of modified RNA species in the cell and quantifies the differential modification rate across conditions. We apply xPore to direct RNA-seq data from six cell lines and multiple myeloma patient samples without a matched control sample and find that many m6A sites are preserved across cell types, whereas a subset exhibit significant differences in their modification rates. Our results show that RNA modifications can be identified from direct RNA-seq data with high accuracy, enabling analysis of differential modifications and expression from a single high-throughput experiment.