Biology subjects

Waegeman, W.

Publications and source records attributed to Waegeman, W..

At least 19 recordsLinked to original sources

bioRxiv2026

Reliable Molecular Retrieval from Mass Spectra using Conformal Prediction

A key task in the computational analysis of liquid chromatography-tandem mass spectrometry (LC- MS/MS) data is identifying the molecular structure underlying a measured spectrum. A common approach ranks candidate molecules retrieved from chemical databases using predicted fingerprint similarities, yet standard metrics such as top-k accuracy summarize performance only at the dataset level and provide no spectrum-specific reliability statement. In this work, we apply conformal prediction to candidate-based molecular retrieval to construct spectrum-specific prediction sets that contain the true molecule with a user-specified probability. We evaluate marginal and conditional conformal prediction across three experimental scenarios representing in-distribution, partially shifted, and fully out-of-distribution settings on the MassSpecGym benchmark. When calibration and test data are aligned, conformal prediction attains the target coverage with small candidate sets for most spectra. Under distribution shift, prediction sets become larger as rankings grow more ambiguous, although candidates can still be reduced when calibration remains representative. Conditional conformal prediction improves subgroup reliability across spectra of different difficulty, with the best gains obtained using confidence-based grouping. Overall, conformal prediction turns candidate rankings into reliable, spectrum-specific candidate sets with an explicit reliability-efficiency trade-off.

bioinformatics↗

bioRxiv2025

Harnessing machine learning to predict antibiotic susceptibility in Pseudomonas aeruginosa biofilms

Standard antibiotic susceptibility tests (ASTs) often fail to accurately predict treatment outcomes because they do not account for biofilm-specific mechanisms of reduced susceptibility. In the present study, we explored alternative approaches to predict tobramycin susceptibility of Pseudomonas aeruginosa biofilms that were experimentally evolved in physiologically relevant conditions. To this end, we used four analytical methods - whole-genome sequencing (WGS), matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS), isothermal microcalorimetry (IMC) and multi-excitation Raman spectroscopy (MX-Raman). Machine learning models were trained on data outputs from these methods to predict tobramycin susceptibility of our evolved strains and subsequently validated with a collection of clinical isolates. For minimal inhibitory concentration (MIC) predictions of the evolved strains, the highest accuracy{+/-}1 was achieved with MALDI-TOF MS (97.83 %), while for biofilm prevention concentration (BPC) predictions, Raman spectroscopy performed best with an accuracy{+/-}1 of 80.43 %. Overall, all analytical methods demonstrated comparable predictive performance, showing their potential for improving biofilm AST.

microbiology↗

bioRxiv2025

A systematic assessment of single-cell language model configurations

Transformers pre-trained on single-cell transcriptomic data have recently been applied to a series of tasks, earning them the title of foundation models. As all currently published models in this class employ vastly different pre-training strategies, it is impossible to determine which practices drive their success (or failure). Here, we present a large-scale study of pre-training components for single-cell transcriptomic transformers: bento-sc (BENchmarking Transformer-Obtained Single-Cell representations). By isolating (and tuning) parts of the pre-training scheme one by one, we define best practices for single-cell language model (scLM) construction. While comparisons with baselines indicate that scLMs do not yet offer the generational leap in prediction performances promised by many foundation models, we identify key design choices leading to their improved performance. Namely, the best scLMs are obtained by: (1) minimally processing counts at the input level, (2) using reconstruction losses that exploit known count distributions, (3) masking (up to high rates), and (4) combining different pre-training tasks/losses. All code supporting this study is distributed on PyPI and is packaged under: https://github.com/gdewael/bento-sc.

bioinformatics↗

bioRxiv2025

Evaluation of out-of-distribution detection methods for data shifts in single-cell transcriptomics

Automatic cell type annotation methods assign cell type labels to new, unlabeled datasets by leveraging relationships from a reference RNA-seq atlas. However, new datasets may include labels absent from the reference dataset or exhibit feature distributions that diverge from it. These scenarios can significantly affect the reliability of annotation predictions, a factor often overlooked in current automatic annotation methods. The field of out-of-distribution detection (OOD), primarily focused on computer vision, addresses the identification of instances that differ from the training distribution. Implementing OOD methods in the context of novel cell type annotation and data shift detection for single-cell transcriptomics may enhance annotation accuracy and trustworthiness. We evaluate 6 OOD detection methods: LogitNorm, MC dropout, Ensembles, Energy- based OOD, Deep NN and Posterior networks, for their annotation and OOD detection performance in both synthetical and real-life application settings. We show that OOD detection methods are able to accurately detect novel cell types and show their promise to detect severe data shifts on non-integrated datasets. Moreover, integration of the OOD datasets improves annotation performance, but interferes with OOD detection, diminishing novel cell type capabilities of the OOD methods.

bioinformatics↗

bioRxiv2024

Pre-trained Maldi Transformers improve MALDI-TOF MS-based prediction

For the last decade, matrix-assisted laser desportion/ionization time-of-flight mass spectrometry (MALDI-TOF MS) has been the reference method for species identification in clinical microbiology. Hampered by a historical lack of open data, machine learning research towards models specifically adapted to MALDI-TOF MS remains in its infancy. Given the growing complexity of available datasets (such as large-scale antimicrobial resistance prediction), a need for models that (1) are specifically designed for MALDI-TOF MS data, and (2) have high representational capacity, presents itself. Here, we introduce Maldi Transformer, an adaptation of the state-of-the-art transformer architecture to the MALDI-TOF mass spectral domain. We propose the first self-supervised pre-training technique specifically designed for mass spectra. The technique is based on shuffling peaks across spectra, and pre-training the transformer as a peak discriminator. Extensive benchmarks confirm the efficacy of this novel design. The final result is a model exhibiting state-of-the-art (or competitive) performance on downstream prediction tasks. In addition, we show that Maldi Transformers identification of noisy spectra may be leveraged towards higher predictive performance. All code supporting this study is distributed on PyPI and is packaged under: https://github.com/gdewael/maldi-nn

bioinformatics↗

bioRxiv2023

An antimicrobial drug recommender system using MALDI-TOF MS and dual-branch neural networks

Timely and effective use of antimicrobial drugs can improve patient outcomes, as well as help safeguard against resistance development. Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) is currently routinely used in clinical diagnostics for rapid species identification. Mining additional data from said spectra in the form of antimicrobial resistance (AMR) profiles is, therefore, highly promising. Such AMR profiles could serve as a drop-in solution for drastically improving treatment efficiency, effectiveness, and costs. This study endeavours to develop the first machine learning models capable of predicting AMR profiles for the whole repertoire of species and drugs encountered in clinical microbiology. The resulting models can be interpreted as drug recommender systems for infectious diseases. We find that our dual-branch method delivers considerably higher performance compared to previous approaches. In addition, experiments show that the models can be efficiently fine-tuned to data from other clinical laboratories. MALDI-TOF-based AMR recommender systems can, hence, greatly extend the value of MALDI-TOF MS for clinical diagnostics. All code supporting this study is distributed on PyPI and is packaged under: https://github.com/gdewael/maldi-nn

bioinformatics↗

bioRxiv2023

A Comparison of Embedding Aggregation Strategies in Drug-Target Interaction Prediction

The prediction of interactions between novel drugs and biological targets is a vital step in the early stage of the drug discovery pipeline. Many deep learning approaches have been proposed over the last decade, with a substantial fraction of them sharing the same underlying two-branch architecture. Their distinction is limited to the use of different types of feature representations and branches (multi-layer perceptrons, convolutional neural networks, graph neural networks and transformers). In contrast, the strategy used to combine the outputs (embeddings) of the branches has remained mostly the same. The same general architecture has also been used extensively in the area of recommender systems, where the choice of an aggregation strategy is still an open question. In this work, we investigate the effectiveness of three different embedding aggregation strategies in the area of drug-target interaction (DTI) prediction. We formally define these strategies and prove their universal approximator capabilities. We then present experiments that compare the different strategies on benchmark datasets from the area of DTI prediction, showcasing conditions under which specific strategies could be the obvious choice.

bioinformatics↗

bioRxiv2023

Uncertainty-aware single-cell annotation with a hierarchical reject option

AbstractAutomatic cell type annotation methods assign cell type labels to new datasets by extracting relationships from a reference RNA-seq dataset. However, due to the limited resolution of gene expression features, there is always uncertainty present in the label assignment. To enhance the reliability and robustness of annotation, most machine learning methods address this uncertainty by providing a full reject option, i.e. when the predicted confidence score of a cell type label falls below a user-defined threshold, no label is assigned and no prediction is made. As a better alternative, some methods deploy hierarchical models and consider a so-called partial rejection by returning internal nodes of the hierarchy as label assignment. However, because a detailed experimental analysis of various rejection approaches is missing in the literature, there is no consensus on best practices, superiority of certain methods, and potential drawbacks associated with rejection. We evaluate three annotation approaches (1) full rejection (2) partial rejection and (3) no rejection for both flat and hierarchical probabilistic classifiers. Our findings indicate that hierarchical classifiers are superior when rejection is applied, with partial rejection being the preferred rejection approach, as it preserves a significant amount of label information. For optimal rejection implementation, the rejection threshold should be determined through careful examination of a methods rejection behavior. Without rejection, flat and hierarchical annotation perform equally well, as long as the cell type hierarchy accurately captures transcriptomic relationships.

bioinformatics↗

bioRxiv2021

CpG Transformer for imputation of single-cell methylomes

AO_SCPLOWBSTRACTC_SCPLOWO_ST_ABSMotivationC_ST_ABSThe adoption of current single-cell DNA methylation sequencing protocols is hindered by incomplete coverage, outlining the need for effective imputation techniques. The task of imputing single-cell (methylation) data requires models to build an understanding of underlying biological processes. ResultsWe adapt the transformer neural network architecture to operate on methylation matrices through combining axial attention with sliding window self-attention. The obtained CpG Transformer displays state-of-the-art performances on a wide range of scBS-seq and scRRBS-seq datasets. Further-more, we demonstrate the interpretability of CpG Transformer and illustrate its rapid transfer learning properties, allowing practitioners to train models on new datasets with a limited computational and time budget. Availability and ImplementationCpG Transformer is freely available at https://github.com/gdewael/cpg-transformer.

bioinformatics↗

bioRxiv2021

Predicting the presence and abundance of bacterial taxa in environmental communities through flow cytometric fingerprinting

Microbiome management research and applications rely on temporally-resolved measurements of community composition. Current technologies to assess community composition either make use of cultivation or sequencing of genomic material, which can become time consuming and/or laborious in case high-throughput measurements are required. Here, using data from a shrimp hatchery as an economically relevant case study, we combined 16S rRNA gene amplicon sequencing and flow cytometry data to develop a computational workflow that allows the prediction of taxon abundances based on flow cytometry measurements. The first stage of our pipeline consists of a classifier to predict the presence or absence of the taxon of interest, with yields an average accuracy of 88.13{+/-}4.78 % across the top 50 OTUs of our dataset. In the second stage, this classifier was combined with a regression model to predict the relative abundances of the taxon of interest, which yields an average R2 of 0.35{+/-}0.24 across the top 50 OTUs of our dataset. Application of the models on flow cytometry time series data showed that the generated models can predict the temporal dynamics of a large fraction of the investigated taxa. Using cell-sorting we validated that the model correctly associates taxa to regions in the cytometric fingerprint where they are detected using 16S rRNA gene amplicon sequencing. Finally, we applied the approach of our pipeline on two other datasets of microbial ecosystems. This pipeline represents an addition to the expanding toolbox for flow cytometry-based monitoring of bacterial communities and complements the current plating- and marker gene-based methods. ImportanceMonitoring of microbial community composition is crucial for both microbiome management research and applications. Existing technologies, such as plating and amplicon sequencing, can become laborious and expensive when high-throughput measurements are required. Over the recent years, flow cytometry-based measurements of community diversity have been shown to correlate well to those derived from 16S rRNA gene amplicon sequencing in several aquatic ecosystems, suggesting there is a link between the taxonomic community composition and phenotypic properties as derived through flow cytometry. Here, we further integrated 16S rRNA gene amplicon sequencing and flow cytometry survey data in order to construct models that enable the prediction of both the presence and the abundance of individual bacterial taxa in mixed communities using flow cytometric fingerprinting. The developed pipeline holds great potential to be integrated in routine monitoring schemes and early warning systems for biotechnological applications.

microbiology↗

bioRxiv2020

An in-depth evaluation of annotated transcription start sites in E. coli using deep learning

The effectiveness of deep learning methods can be largely attributed to the automated extraction of relevant features from raw data. In the field of functional genomics, this generally comprises the automatic selection of relevant nucleotide motifs from DNA sequences. To benefit from automated learning methods, new strategies are required that unveil the decision-making process of trained models. In this paper, we present several methods that can be used to gather insights on biological processes that drive any genome annotation task. This work builds upon a transformer-based neural network framework designed for prokaryotic genome annotation purposes. We find that the majority of sub-units (attention heads) of the model are specialized towards identifying DNA binding sites. Working with a neural network trained to detect transcription start sites in E. coli, we successfully characterize both locations and consensus sequences of transcription factor binding sites, including both well-known and potentially novel elements involved in the initiation of the transcription process.

genomics↗

bioRxiv2019

Novel transformer networks for improved sequence labeling in genomics

In genomics, a wide range of machine learning methodologies have been investigated to annotate biological sequences for positions of interest such as transcription start sites, translation initiation sites, methylation sites, splice sites and promoter start sites. In recent years, this area has been dominated by convolutional neural networks, which typically outperform previously-designed methods as a result of automated scanning for influential sequence motifs. However, those architectures do not allow for the efficient processing of the full genomic sequence. As an improvement, we introduce transformer architectures for whole genome sequence labeling tasks. We show that these architectures, recently introduced for natural language processing, are better suited for processing and annotating long DNA sequences. We apply existing networks and introduce an optimized method for the calculation of attention from input nucleotides. To demonstrate this, we evaluate our architecture on several sequence labeling tasks, and find it to achieve state-of-the-art performances when comparing it to specialized models for the annotation of transcription start sites, translation initiation sites and 4mC methylation in E. coli.

genetics↗

bioRxiv2019

Cytometric fingerprints of gut microbiota predict Crohn’s disease state

Variations in the gut microbiome have been associated with changes in health state such as Crohns disease. Most surveys characterize the microbiome through analysis of the 16S rRNA gene. An alternative technology that can be used is flow cytometry. In this report we analyzed a disease cohort that has been characterized by both technologies. Changes in microbial community structure are reflected in both types of data. We demonstrate that cytometric fingerprints can be used as a diagnostic tool in order to classify samples according to Crohns disease state. These results highlight the potential of flow cytometry to perform rapid diagnostics of microbiome-associated diseases.

microbiology↗

bioRxiv2019

PhenoGMM: Gaussian mixture modelling of microbial cytometry data enables efficient predictions of biodiversity

Microbial flow cytometry allows to rapidly characterize microbial communities. Recent research has demonstrated a moderate to strong connection between the cytometric diversity and taxonomic diversity based on 16S rRNA gene amplicon sequencing data. This creates the opportunity to integrate both types of data to study and predict the microbial community diversity in an automated and efficient way. However, microbial flow cytometry data results in a number of unique challenges that need to be addressed. The results of our work are threefold: i) We expand current microbial cytometry fingerprinting approaches by proposing and validating a model-based fingerprinting approach based upon Gaussian Mixture Models, which we called PhenoGMM. ii) We show that microbial diversity can be rapidly estimated by PhenoGMM. In combination with a supervised machine learning model, diversity estimations based on 16S rRNA gene amplicon sequencing data can be predicted. iii) We evaluate our method extensively by using multiple datasets from different ecosystems and compare its predictive power with a generic binning fingerprinting approach that is commonly used in microbial flow cytometry. These results demonstrate the strong connection between the genetic make-up of a microbial community and its phenotypic properties as measured by flow cytometry. Our workflow facilitates the study of microbial diversity and community dynamics using flow cytometry in a fast and quantitative way. ImportanceMicroorganisms are vital components in various ecoystems on Earth. In order to investigate the microbial diversity, researchers have largely relied on the analysis of 16S rRNA gene sequences from DNA. Flow cytometry has been proposed as an alternative technique to characterize microbial community diversity and dynamics. It is an optical technique, able to rapidly characterize a number of phenotypic properties of individual cells. So-called fingerprinting techniques are needed in order to describe microbial community diversity and dynamics based on flow cytometry data. In this work, we propose a more advanced fingerprinting strategy based on Gaussian Mixture Models. When samples have been analyzed by both flow cytometry and 16S rRNA gene amplicon sequencing, we show that supervised machine learning models can be used to find the relationship between the two types of data. We evaluate our workflow on datasets from different ecosystems, illustrating its general applicability for the analysisof microbial flow cytometry data. PhenoGMM facilitates the rapid characterization and predictive modelling of microbial diversity using flow cytometry.

microbiology↗

bioRxiv2019

Characterizing phenotypic heterogeneity in isogenic bacterial populations using flow cytometry and Raman spectroscopy

Investigating phenotypic heterogeneity can help to better understand and manage microbial communities. However, characterizing phenotypic heterogeneity remains a challenge, as there is no standardized analysis framework. Several optical tools are available, which often describe properties of the individual cell. In this work, we compare Raman spectroscopy and flow cytometry to study phenotypic heterogeneity in bacterial populations. The growth phase of E. coli populations was characterized using both technologies. Our findings show that flow cytometry detects and quantifies shifts in phenotypic heterogeneity at the population level due to its high-throughput nature. Raman spectroscopy, on the other hand, offers a much higher resolution at the single-cell level (i.e. more biochemical information is recorded). Therefore, it is capable of identifying distinct phenotypic populations when coupled with standardized data analysis. In addition, it provides information about biomolecules that are present, which can be linked to cell functionality. We propose an automated workflow to distinguish between bacterial phenotypic populations using Raman spectroscopy and validated this approach with an external dataset. We recommend to apply flow cytometry to characterize phenotypic heterogeneity at the population level, and Raman spectroscopy to perform a more in-depth analysis of heterogeneity at the single-cell level. ImportanceSingle-cell techniques are frequently applied tools to study phenotypic characteristics of bacterial populations. As flow cytometry and Raman spectroscopy gain popularity in the field, there is a need to understand their advantages and limitations, as well as to create a more standardized data analysis framework. Our work shows that flow cytometry allows to study and quantify shifts at the bacterial population level, but since its resolution is limited for microbial purposes, distinct phenotypic populations cannot be distinguished at the single-cell level. Raman spectroscopy, combined with appropriate data analysis, has sufficient resolving power at the single-cell level, enabling the identification of distinct phenotypic populations. As regions in a Raman spectrum are associated with specific (bio)molecules, it is possible to link these to the cell state and/or its function.

bioengineering↗

bioRxiv2018

Coculturing bacteria leads to reduced phenotypic heterogeneities

Isogenic bacterial populations are known to exhibit phenotypic heterogeneity at the single cell level. Because of difficulties in assessing the phenotypic heterogeneity of a single taxon in a mixed community, the importance of this deeper level of organisation remains relatively unknown for natural communities. In this study, we have used membrane-based microcosms that allow the probing of the phenotypic heterogeneity of a single taxon while interacting with a synthetic or natural community. Individual taxa were studied under axenic conditions, as members of a coculture with physical separation, and as a mixed culture. Phenotypic heterogeneity was assessed through both flow cytometry and Raman spectroscopy. Using this setup, we investigated the effect of microbial interactions on the individual phenotypic heterogeneities of two interacting drinking water isolates. We have demonstrated that interactions between these bacteria lead to an adjustment of their individual phenotypic diversities, and that this adjustment is conditional on the bacterial taxon.\n\nImportanceLaboratory studies have shown the impact of phenotypic heterogeneity on the survival and functionality of isogenic populations. As phenotypic heterogeneity is known to play an important role in pathogenicity and virulence, antibiotics resistance, biotechnological applications and ecosystem properties, it is crucial to understand its influencing factors. An unanswered question is whether bacteria in mixed communities influence the phenotypic heterogeneity of their community partners. We found that coculturing bacteria leads to a reduction in their individual phenotypic heterogeneities, which led us to the hypothesis that the individual phenotypic diversity of a taxon is dependent on the community composition.

microbiology↗

bioRxiv2018

Using machine learning to associate bacterial taxa with functional groups through flow cytometry, 16S rRNA gene sequencing, and productivity data

High-(HNA) and low-nucleic acid (LNA) bacteria are two operational groups identified by flow cytometry (FCM) in aquatic systems. HNA cell density often correlates strongly with heterotrophic production, while LNA cell density does not. However, which taxa are specifically associated with these groups, and by extension, productivity has remained elusive. Here, we addressed this knowledge gap by using a machine learning-based variable selection approach that integrated FCM and 16S rRNA gene sequencing data collected from 14 freshwater lakes spanning a broad range in physicochemical conditions. There was a strong association between bacterial heterotrophic production and HNA absolute cell abundances (R2 = 0.65), but not with the more abundant LNA cells. This solidifies findings, mainly from marine systems, that HNA and LNA could be considered separate functional groups, the former contributing a disproportionately large share of carbon cycling. Taxa selected by the models could predict HNA and LNA absolute cell abundances at all taxonomic levels, with the highest performance at the OTU level. Selected OTUs ranged from low to high relative abundance and were mostly lake system-specific (89.5%-99.2%). A subset of selected OTUs was associated with both LNA and HNA groups (12.5%-33.3%) suggesting either phenotypic plasticity or within-OTU genetic and physiological heterogeneity. These findings may lead to the identification of systems-specific putative ecological indicators for heterotrophic productivity. Generally, our approach allows for the association of OTUs with specific functional groups in diverse ecosystems in order to improve our understanding of (microbial) biodiversity-ecosystem functioning relationships. ImportanceA major goal in microbial ecology is to understand how microbial community structure influences ecosystem functioning. Research is limited by the ability to readily culture most bacteria present in the environment and the difference in bacterial physiology in situ compared to in laboratory culture. Various methods to directly associate bacterial taxa to functional groups in the environment are being developed. In this study, we applied machine learning methods to relate taxonomic data obtained from marker gene surveys to functional groups identified by flow cytometry. This allowed us to identify the taxa that are associated with heterotrophic productivity in freshwater lakes and indicated that the key contributors were highly system-specific, regularly rare members of the community, and that some could switch between being low and high contributors. Our approach provides a promising framework to identify taxa that contribute to ecosystem functioning and can be further developed to explore microbial contributions beyond heterotrophic production.

ecology↗

bioRxiv2018

DeepRibo: precise gene annotation of prokaryotes using deep learning and ribosome profiling data

Annotation of gene expression in prokaryotes often finds itself corrected due to small variations of the annotated gene regions observed between different (sub-species. It has become apparent that traditional sequence alignment algorithms, used for the curation of genomes, are not able to map the full complexity of the genomic landscape. We present DeepRibo, a novel neural network applying ribosome profiling data that shows to be a precise tool for the delineation and annotation of expressed genes in prokaryotes. The neural network combines recurrent memory cells and convolutional layers, adapting the information gained from both the high-throughput ribosome profiling data and Shine-Dalgarno region into one model. DeepRibo is designed as a single model trained on a variety of ribosome profiling experiments, and is therefore evaluated on independent datasets. Through extensive validation of the model, including the use of multiple species sequence similarity and mass spectrometry, the effectiveness of the model is highlighted.

bioinformatics↗