Biology subjects

Lähdesmäki, H.

Publications and source records attributed to Lähdesmäki, H..

At least 19 recordsLinked to original sources

bioRxiv2026

Peptide-HLA II interaction prediction for post-translationally modified peptides

CD4+ T cells recognize peptides presented by human leukocyte antigen (HLA) II, implementing a fundamental mediation mechanism of the adaptive immune system. Although post-translational modifications (PTMs) alter immune responses, PTM-peptide-HLA interaction prediction remains challenging due to data scarcity resulting from substoichiometric levels of PTMs. To overcome this, we developed PepChem, a deep learning model utilizing novel, molecular-level peptide representations that enable predictions for sidechain modifications. Using monoallelic datasets that we reanalyze for PTMs of interest, we show accurate predictions on PTMs that were unseen during training. Furthermore, we introduce a novel training protocol that improves PTM-peptide generalization compared to conventional methods. We predict and experimentally validate citrullination-induced binding increase of rheumatoid arthritis (RA)-linked peptides to HLA II risk allele DRB1*04:01. This framework bridges the critical gap in PTM-aware immune recognition prediction, with immediate applications in autoimmunity, cancer, and infectious disease.

bioinformatics↗

bioRxiv2026

LGTM: Gaussian Process Modulated Neural Topic Modeling for Longitudinal Microbiome

Longitudinal microbiome data are key to understanding the dynamics of microbial communities and their relationships with the host and environment. However, analysis of such data is challenging due to high dimensionality, compositionality, irregular sampling and temporal dependencies on external covariates. Existing analytical approaches typically address only subsets of these challenges, limiting their ability to yield biologically interpretable insights. We introduce LGTM, a probabilistic modeling framework that combines flexible non-linear longitudinal modeling with interpretable topic-based representations of the microbiome. LGTM simultaneously identifies microbial co-abundance patterns ("topics") and models how their proportions change over time and in relation to host and environmental covariates. Using multiple longitudinal human gut microbiome datasets, we demonstrate that LGTM identifies diverse microbial topics whose major patterns are reproducible across runs, while achieving competitive performance in imputation and forecasting tasks. A key strength of the framework is its interpretability: LGTM yields microbial topics with biologically interpretable taxonomic compositions and directly quantifies associations between covariates and microbial dynamics. LGTM is available at https://github.com/yuanx749/lgtm.

microbiology↗

bioRxiv2026

PepCABO: Latent-space Bayesian optimization for peptide-MHC binding using contrastive alignment

MotivationOptimizing peptide sequences for binding to specific MHC class I alleles is a central challenge in immunotherapy and vaccine design. The combinatorial size of peptide space, the nonlinear nature of peptide- MHC interactions, and limited experimental budgets make efficient optimization difficult. Latent-space Bayesian optimization (LSBO) provides a framework by embedding discrete sequences into a continuous space where Bayesian optimization can be applied. However, existing LSBO methods do not effectively leverage binding data from related alleles and often rely on inefficient random initialization. ResultsWe propose PepCABO, an LSBO framework for peptide-MHC binding using contrastive alignment, which utilizes a dual variational autoencoder framework that jointly learns peptide-allele alignment and a Gaussian process surrogate prior to Bayesian optimization. This simultaneous training induces a latent geometry that reflects the binding landscape and enables structured knowledge transfer across alleles. The pretrained model shapes a structured latent space in which peptides with high objective values regarding a specific MHC allele are geometrically organized, while the jointly trained Gaussian process defines an informative prior over the objective in this space, enabling principled and efficient exploration of promising regions during subsequent optimization. Across 12 target alleles without prior binding data and under both low- and high-budget settings, PepCABO consistently outperforms various baselines. We observe faster convergence, improved area under the optimization curve, and stronger best-found binding affinities, suggesting improved sample efficiency under experimentally constrained scenarios. Code availabilityThe source code is available at https://github.com/mohsen-g/PepCABO

bioinformatics↗

bioRxiv2026

Predicting single-cell responses to novel genetic perturbations with optimal transport

The combination of pooled genetic perturbation screening with single-cell RNA-sequencing has allowed for large-scale profiling of single-cell transcriptional responses, providing valuable insights into gene function and cellular behavior. There is a need for computational methods capable of predicting single-cell responses to novel genetic perturbations, thereby allowing for the efficient exploration of the vast combinatorial space of potential multi-gene perturbations. Optimal transport (OT) presents a compelling framework to model this type of data given the lack of true control-perturbed cell pairings. However, existing neural OT models are generally constrained to the perturbations already seen in training, while the use of OT theory in methods capable of modeling novel genetic perturbations remains limited. To bridge this gap, we present an OT-based method to predict single-cell transcriptional responses to novel genetic perturbations. Leveraging a flexible attention-based aggregation approach, our method integrates gene representations from multiple sources of prior knowledge, spanning from functional descriptions of genes to gene-gene relationships, producing a biologically informed representation of the perturbation. Moreover, we utilize an OT-based loss to align predicted and observed perturbed cell populations, avoiding the need to assign random control-perturbed cell pairings. Experiments on three benchmark datasets demonstrate the highly competitive performance of our model compared to state-of-the-art methods. Further evaluations on differential expression analysis and genetic interaction modeling demonstrate the biological relevance and potential utility of our model across diverse applications.

bioinformatics↗

bioRxiv2025

Incorporating Hierarchical Information into Multiple Instance Learning for Patient Phenotype Prediction with scRNA-seq Data

Multiple Instance Learning (MIL) provides a structured approach to patient phenotype prediction with single-cell RNA-sequencing (scRNA-seq) data. However, existing MIL methods tend to overlook the hierarchical structure inherent in scRNA-seq data, especially the biological groupings of cells, or cell types. This limitation may lead to suboptimal performance and poor interpretability at higher levels of cellular division. To address this gap, we present a novel approach to incorporate hierarchical information into the attentionbased MIL framework. Specifically, our model applies the attention-based aggregation mechanism over both cells and cell types, thus enforcing a hierarchical structure on the flow of information throughout the model. Across extensive experiments, our proposed approach consistently outperforms existing models and demonstrates robustness in data-constrained scenarios. Moreover, ablation test results show that simply applying the attention mechanism on cell types instead of cells leads to improved performance, underscoring the benefits of incorporating the hierarchical groupings. By identifying the critical cell types that are most relevant for prediction, we show that our model is capable of capturing biologically meaningful associations, thus facilitating biological discoveries.

bioinformatics↗

bioRxiv2024

Multispecies relations shape bird-feeding practices

While humans often feed birds in their backyards, there is growing awareness that this has positive and negative effects on local biodiversity. Whether the observed species assemblage shapes human activities has, however, rarely been investigated. We analyzed 15,088 open-ended answers from 9,473 Finnish respondents about why they have increased or reduced feeding birds. They mentioned 58 avian and non-avian species linked to changed practices. The main reasons for change were 1) respondents relation to non-human species, 2) respondents relation to other humans and 3) relations between non-human species. Most taxa and reasons could lead to both increase or decrease in feeding, although the direction was context-dependent. We suggest that bird-feeding is an interactive process where the species community strongly affects feeding practices, which in turn can affect community composition. Recognising this process is crucial for understanding the effects of bird-feeding on both humans and nature and providing more nuanced guidance.

scientific communication and education↗

bioRxiv2022

LuxHMM: DNA methylation analysis with genome segmentation via Hidden Markov Model

DNA methylation plays an important role in studying the epigenetics of various biological processes including many diseases. Although differential methylation of individual cytosines can be informative, given that methylation of neighboring CpGs are typically correlated, analysis of differentially methylated regions is often of more interest. We have developed a probabilistic method and software, LuxHMM, that uses hidden Markov model (HMM) to segment the genome into regions and a Bayesian regression model, which allows handling of multiple covariates, to infer differential methylation of regions. Moreover, our model includes experimental parameters that describe the underlying biochemistry in bisulfite sequencing and model inference is done using either variational inference for efficient genome-scale analysis or Hamiltonian Monte Carlo (HMC). Analyses of real and simulated bisulfite sequencing data demonstrate the competitive performance of LuxHMM compared with other published differential methylation analysis methods.

bioinformatics↗

bioRxiv2022

Single-cell functional genomics of natural killer cell evasion in blood cancers

Natural killer (NK) cells are emerging as a promising therapeutic option in cancer. To better understand how cancer cells evade NK cells, we studied interacting NK and blood cancer cells using single-cell and genome-scale functional genomics screens. At single-cell resolution, interaction of NK and cancer cells induced distinct activation states in both cell types depending on the cancer cell lineage and molecular phenotype, ranging from more sensitive myeloid to more resistant B-lymphoid cancers. CRISPR screens uncovered cancer cell-intrinsic genes driving sensitivity and resistance, including antigen presentation and death receptor signaling mediators, adhesion molecules, protein fucosylation genes, and transcriptional regulators. CRISPR screens with a single-cell transcriptomic readout revealed how these cancer cell genes influenced the gene expression landscape of both cell types, including regulation of activation states in both cancer and NK cells by IFN{gamma} signaling. Our findings provide a resource for rational design of NK cell-based therapies in blood cancers. HIGHLIGHTSO_LITranscriptomic states of interacting NK cells and cancer cells depend on cancer cell lineage C_LIO_LIMolecular correlates of increased sensitivity of myeloid compared to B-lymphoid cancers include activating receptor ligands NCR3LG1, PVR, and ULBP1 C_LIO_LINew regulators of NK cell resistance from 12 genome-scale CRISPR screens include blood cancer-specific regulators SELPLG, SPN, and MYB C_LIO_LISingle-cell transcriptomics CRISPR screens targeting 65 genome-wide screen hits identify MHC-I, IFNy, and NF-{kappa}B regulation as underlying mechanisms C_LI

immunology↗

bioRxiv2022

TSignal: A transformer model for signal peptide prediction

Signal peptides are short amino acid segments present at the N-terminus of newly synthesized proteins that facilitate protein translocation into the lumen of the endoplasmic reticulum, after which they are cleaved off. Specific regions of signal peptides influence the efficiency of protein translocation, and small changes in their primary structure can abolish protein secretion altogether. The lack of conserved motifs across signal peptides, sensitivity to mutations, and variability in the length of the peptides, make signal peptide prediction a challenging task that has been extensively pursued over the years. We introduce TSignal, a deep transformer-based neural network architecture that utilizes BERT language models (LMs) and dot-product attention techniques. TSignal predicts the presence of signal peptides (SPs) and the cleavage site between the SP and the translocated mature protein. We show improved accuracy in terms of cleavage site and SP presence prediction for most of the SP types and organism groups. We further illustrate that our fully data-driven trained model identifies useful biological information on heterogeneous test sequences.

bioinformatics↗

bioRxiv2022

Predicting recognition between T cell receptors and epitopes using contextualized motifs

We introduce TCRconv, a deep learning model for predicting recognition between T-cell receptors and epitopes. TCRconv uses a deep protein language model and convolutions to extract contextualized motifs and provides state-of-the-art TCR-epitope prediction accuracy. Using TCR repertoires from COVID-19 patients, we demonstrate that TCRconv can provide insight into T-cell dynamics and phenotypes during the disease.

bioinformatics↗

bioRxiv2022

ChromDMM: A Dirichlet-Multinomial Mixture Model For Clustering Heterogeneous Epigenetic Data

MotivationResearch on epigenetic modifications and other chromatin features at genomic regulatory elements elucidates essential biological mechanisms including the regulation of gene expression. Despite the growing number of epigenetic datasets, new tools are still needed to discover novel distinctive patterns of heterogeneous epigenetic signals at regulatory elements. ResultsWe introduce ChromDMM, a product Dirichlet-multinomial mixture model for clustering genomic regions that are characterised by multiple chromatin features. ChromDMM extends the mixture model framework by profile shifting and flipping that can probabilistically account for inaccuracies in the position and strand-orientation of the genomic regions. Owing to hyper-parameter optimisation, ChromDMM can also regularise the smoothness of the epigenetic profiles across the consecutive genomic regions. With simulated data, we demonstrate that ChromDMM clusters, shifts, and strand-orients the profiles more accurately than previous methods. With ENCODE data, we show that the clustering of enhancer regions in the human genome reveals distinct patterns in several chromatin features. We further validate the enhancer clusters by their enrichment for transcriptional regulatory factor binding sites. AvailabilityThe software is available at https://github.com/MariaOsmala/ChromDMM

bioinformatics↗

bioRxiv2021

Probabilistic modeling methods for cell-free DNA methylation based cancer classification

BackgroundcfMeDIP-seq is a low-cost method for determining the DNA methylation status of cell-free DNA and it has been successfully combined with statistical methods for accurate cancer diagnostics. We investigate the diagnostic classification aspect by applying statistical tests and dimension reduction techniques for feature selection and probabilistic modeling for the cancer type classification, and we also study the effect of sequencing depth. MethodsWe experiment with a variety of statistical methods that use different feature selection and feature extraction methods as well as probabilistic classifiers for diagnostic decision making. We test the (moderated) t-tests and the Fishers exact test for feature selection, principal component analysis (PCA) as well as iterative supervised PCA (ISPCA) for feature generation, and GLMnet and logistic regression methods with sparsity promoting priors for classification. Probabilistic programming language Stan is used to implement Bayesian inference for the probabilistic models. Results and conclusionsWe compare overlaps of differentially methylated genomic regions as chosen by different feature selection methods, and evaluate probabilistic classifiers by evaluating the area under the receiver operating characteristic (AUROC) scores on discovery and validation cohorts. While we observe that many methods perform equally well as, and occasionally considerably better than, GLMnet that was originally proposed for cfMeDIP-seq based cancer classification, we also observed that performance of different methods vary across sequencing depths, cancer types and study cohorts. Overall, methods that seem robust and promising include Fishers exact test and ISPCA for feature selection as well as a simple logistic regression model with the number of hyper and hypomethylated regions as features.

bioinformatics↗

bioRxiv2021

Permutation-based significance analysis reduces the type 1 error rate in bisulfite sequencing data analysis of human umbilical cord blood samples

BackgroundDNA methylation patterns are largely established in-utero and might mediate the impacts of in-utero conditions on later health outcomes. Associations between perinatal DNA methylation marks and pregnancy-related variables, such as maternal age and gestational weight gain, have been earlier studied with methylation microarrays, which typically cover less than 2 % of human CpG sites. To detect such associations outside these regions, we chose the bisulfite sequencing approach. MethodsWe collected and curated all available clinical data on 200 newborn infants; whose umbilical cord blood samples were analyzed with the reduced representation bisulfite sequencing (RRBS) method. A generalized linear mixed effects model was fit for each high coverage CpG site, followed by spatial and multiple testing adjustment of P values to identify differentially methylated cytosines (DMCs) and regions (DMRs) associated with clinical variables such as maternal age, mode of delivery, and birth weight. Type 1 error rate was then evaluated with a permutation analysis. ResultsWe discovered a strong inflation of spatially adjusted P values through the permutation analysis, which we then applied for empirical type 1 error control. Based on empirically estimated significance thresholds, very little differential methylation was associated with any of the studied clinical variables, other than sex. With this analysis workflow, the sex-associated differentially methylated regions were highly reproducible across studies, technologies, and statistical models. ConclusionsThe inflation of P values was caused by a common method for spatial adjustment and DMR detection, implemented in tools comb-p and RADMeth. With standard significance thresholds, type 1 error rates were high with both these implementations, across alternative parameter settings and analysis strategies. We conclude that comb-p and RADMeth are convenient methods for the detection of differentially methylated regions, but the statistical significance should either be determined empirically or before the spatial adjustment. Our RRBS data analysis workflow is available in https://github.com/EssiLaajala/RRBS_workflow.

bioinformatics↗

bioRxiv2020

PairGP: Gaussian process modeling of longitudinal data from paired multi-condition studies

We propose PairGP, a non-stationary Gaussian process method to compare gene expression timeseries across several conditions that can account for paired longitudinal study designs and can identify groups of conditions that have different gene expression dynamics. We demonstrate the method on both simulated data and previously unpublished RNA-seq time-series with five conditions. The results show the advantage of modeling the pairing effect to better identify groups of conditions with different dynamics. The implementations is available at https://github.com/michelevantini/PairGP

bioinformatics↗

bioRxiv2020

LuxHS: DNA methylation analysis with spatially varying correlation structure

Bisulfite sequencing (BS-seq) is a popular method for measuring DNA methylation in basepair-resolution. Many BS-seq data analysis tools utilize the assumption of spatial correlation among the neighboring cytosines methylation states. While being a fair assumption, most existing methods leave out the possibility of deviation from the spatial correlation pattern. Our approach builds on a method which combines a generalized linear mixed model (GLMM) with a likelihood that is specific for BS-seq data and that incorporates a spatial correlation for methylation levels. We propose a novel technique using a sparsity promoting prior to enable cytosines deviating from the spatial correlation pattern. The method is tested with both simulated and real BS-seq data and compared to other differential methylation analysis tools.

bioinformatics↗

bioRxiv2019

Enhancer prediction in the human genome by probabilistic modeling of the chromatin feature patterns

BackgroundThe binding sites of transcription factors (TFs) and the localisation of histone modifications in the human genome can be quantified by the chromatin immunoprecipitation assay coupled with next-generation sequencing (ChIP-seq). The resulting chromatin feature data has been successfully adopted for genome-wide enhancer identification by several unsupervised and supervised machine learning methods. However, the current methods predict different numbers and different sets of enhancers for the same cell type and do not utilise the pattern of the ChIP-seq coverage profiles efficiently. ResultsIn this work, we propose a PRobabilistic Enhancer PRedictIoN Tool (PREPRINT) that assumes characteristic coverage patterns of chromatin features at enhancers and employs a statistical model to account for their variability. PREPRINT defines probabilistic distance measures to quantify the similarity of the genomic query regions and the characteristic coverage patterns. The probabilistic scores of the enhancer and non-enhancer samples are utilised to train a kernel-based classifier. The performance of the method is demonstrated on ENCODE data for two cell lines. The predicted enhancers are computationally validated based on the transcriptional regulatory protein binding sites and compared to the predictions obtained by state-of-the-art methods. ConclusionPREPRINT performs favorably to the state-of-the-art methods, especially when requiring the methods to predict a larger set of enhancers. PREPRINT generalises successfully to data from cell type not utilised for training, and often the PREPRINT performs better than the previous methods. The PREPRINT enhancers are less sensitive to the choice of prediction threshold. PREPRINT identifies biologically validated enhancers not predicted by the competing methods. The enhancers predicted by PREPRINT can aid the genome interpretation in functional genomics and clinical studies. Availabilityhttps://github.com/MariaOsmala/preprint Contactmaria.osmala@aalto.fi

bioinformatics↗

bioRxiv2019

A personalised approach for identifying disease-relevant pathways in heterogeneous diseases

Numerous time-course gene expression datasets have been curated for studying the biological dynamics that drive disease progression; and nearly as many methods have been proposed to analyse them. However, barely any method exists that can appropriately model time-course data and at the same time account for heterogeneity that entails many complex diseases. Most methods manage to fulfil either one of those qualities, but not both. The lack of appropriate methods hinders our capability of understanding the disease process and pursuing preventive or curative treatments. Here, we present a method that models time-course data in a personalised manner, i.e. for each case-control pair individually, using Gaussian processes in order to identify differentially expressed genes (DEGs); and combines the lists of DEGs on a pathway-level using a permutation-based empirical hypothesis testing in order to overcome gene-level variability and inconsistencies prevalent to heterogeneous datasets from complex diseases. Our method can be applied to study the time-course dynamics as well as specific time-windows of heterogeneous diseases. We apply our personalised approach on two longitudinal type 1 diabetes (T1D) datasets to determine perturbations that take place during early prognosis of the disease as well as in time-windows before seroconversion and clinical onset of T1D. By comparing to non-personalised methods, we demonstrate that our approach is biologically motivated and can reveal more insights into progression of heterogeneous diseases. With its robust capabilities of identifying immunologically interesting and disease-relevant pathways, our approach could be useful for predicting certain events in the progression of heterogeneous diseases and even biomarker identification.\n\nAvailabilityThe implemented code of our personalised approach will be available online upon publication.

systems biology↗

bioRxiv2019

TCRGP: Determining epitope specificity of T cell receptors

T cell receptors (TCRs) can recognize various pathogens and consequently start immune responses. TCRs can be sequenced from individuals and methods analyzing the specificity of the TCRs can help us better understand individuals immune status in different diseases. We have developed TCRGP, a novel Gaussian process method to predict if TCRs recognize certain epitopes. This method can utilize CDR sequences from TCR and TCR{beta} chains and learn which CDRs are important in recognizing different epitopes. We have experimented with with epitope-specific data against 29 epitopes and performed a comprehensive evaluation with existing prediction methods. On this data, TCRGP outperforms other state-of-the-art methods in epitope-specificity predictions. We also propose a novel analysis approach for combined single-cell RNA and TCR{beta} (scRNA+TCR{beta}) sequencing data by quantifying epitope-specific TCRs with TCRGP in phenotypes identified from scRNA-seq data. With this approach, we find HBV-epitope specific T cells and their transcriptomic states in hepatocellular carcinoma patients.

bioinformatics↗