Biology subjects

Pahikkala, T.

Publications and source records attributed to Pahikkala, T..

7 recordsLinked to original sources

bioRxiv2024

Targeted and Untargeted Amine Metabolite Quantitation in Single Cells with Isobaric Multiplexing

We developed a single cell amine analysis approach utilizing isobarically multiplexed samples of 6 individual cells along with analyte abundant carrier. This methodology was applied for absolute quantitation of amino acids and untargeted relative quantitation of amines in a total of 108 individual cells using nanoflow LC with high-resolution mass spectrometry. Together with individually determined cell sizes, this provides the first absolute quantification of intracellular metabolites within individual cells. The targeted method was partially validated for 10 amino acids with limits of detection in low attomoles, linear calibration range covering analyte amounts typically from 30 amol to 120 fmol, and correlation coefficients (R) above 0.99. Using the cell sizes determined during dispensing, millimolar intracellular concentrations were determined. The untargeted approach yielded 249 features that were detected in at least 25% of the single cells, providing modest cell type separation on principal component analysis. Using Greedy forward selection with regularized least squares, a sub-selection of 100 features explaining most of the difference, was determined. These features were annotated using MS2 from analyte standards and accurate mass with library search. The approach provides accessible, sensitive, and high-throughput method with the potential to be expanded also to other forms of ultrasensitive analysis.

biochemistry↗

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↗

bioRxiv2021

Modeling drug combination effects via latent tensor reconstruction

AO_SCPLOWBSTRACTC_SCPLOWO_ST_ABSMotivationC_ST_ABSCombination therapies have emerged as a powerful treatment modality to overcome drug resistance and improve treatment efficacy. However, the number of possible drug combinations increases very rapidly with the number of individual drugs in consideration which makes the comprehensive experimental screening infeasible in practice. Machine learning models offer time- and cost-efficient means to aid this process by prioritising the most effective drug combinations for further pre-clinical and clinical validation. However, the complexity of the underlying interaction patterns across multiple drug doses and in different cellular contexts poses challenges to the predictive modelling of drug combination effects. ResultsWe introduce comboLTR, highly time-efficient method for learning complex, nonlinear target functions for describing the responses of therapeutic agent combinations in various doses and cancer cell-contexts. The method is based on a polynomial regression via powerful latent tensor reconstruction. It uses a combination of recommender system-style features indexing the data tensor of response values in different contexts, and chemical and multi-omics features as inputs. We demonstrate that comboLTR outperforms state-of-the-art methods in terms of predictive performance and running time, and produces highly accurate results even in the challenging and practical inference scenario where full dose-response matrices are predicted for completely new drug combinations with no available combination and monotherapy response measurements in any training cell line. Availability and implementationcomboLTR code is available at https://github.com/aalto-ics-kepaco/ComboLTR Contacttianduanyi.wang@aalto.fi; juho.rousu@aalto.fi

bioinformatics↗

bioRxiv2020

comboFM: leveraging multi-way interactions for systematic prediction of drug combination effects

We present comboFM, a machine learning framework for predicting the responses of drug combinations in preclinical studies, such as those based on cell lines or patient-derived cells. comboFM models the cell context-specific drug interactions through higher-order tensors, and efficiently learns latent factors of the tensor using powerful factorization machines. The approach enables comboFM to leverage information from previous experiments performed on similar drugs and cells when predicting responses of new combinations in so far untested cells; thereby, it achieves highly accurate predictions despite sparsely populated data tensors. We demonstrated high predictive performance of comboFM in various prediction scenarios using data from cancer cell line drug screening. Subsequent experimental validation of a set of previously untested drug combinations further supported the practical and robust applicability of comboFM. For instance, we confirmed a novel synergy between anaplastic lymphoma kinase (ALK) inhibitor crizotinib and proteasome inhibitor bortezomib in lymphoma cells. Overall, our results demonstrate that comboFM provides an effective means for systematic pre-screening of drug combinations to support precision oncology applications.

bioinformatics↗

bioRxiv2020

Resting state EEG as a biomarker of Parkinson's disease: Influence of measurement conditions

Resting state electroencephalographic (EEG) recording could provide cost-effective means to aid in the detection of neurological disorders such as Parkinsons disease (PD). We examined how many electrodes are needed for classification of PD based on EEG, which electrode locations provide most value for classification, and whether data recorded eyes open or closed yield comparable results. We used a nested cross-validated classifier which included a budget-based search algorithm for selecting the optimal electrodes for classification. By iterating over variable budgets, we show that with eyes open recording, only 10 electrodes, localized over motor and occipital areas enable relatively accurate classification (AUC = .82) between PD patients (N=20) and age-matched healthy control participants (N=20). Classification accuracy only slightly increased when all 64 electrodes were included (AUC = .85). With the data recorded eyes closed, classification was not statistically significantly above chance even with full set of 64 electrodes (AUC = .55). These results show that classification based on small number of EEG electrodes is a promising tool for classifying PD, but measurement conditions and electrode locations can have a significant effect on classifier performance.

neuroscience↗

bioRxiv2018

Molecular atlas of postnatal mouse heart development

RationaleMammals lose the ability to regenerate their hearts within one week after birth. During this regenerative window, cardiac energy metabolism shifts from glycolysis to fatty acid oxidation, and recent evidence suggests that metabolism may participate in controlling cardiomyocyte cell cycle. However, the molecular mechanisms mediating the loss of postnatal cardiac regeneration are not fully understood.\n\nObjectiveThis study aims at providing an integrated resource of mRNA, protein and metabolite changes in the neonatal heart to identify metabolism-related mechanisms associated with the postnatal loss of regenerative capacity.\n\nMethods and ResultsMouse ventricular tissue samples taken on postnatal days 1, 4, 9 and 23 (P01, P04, P09 and P23, respectively) were analyzed with RNA sequencing (RNAseq) and global proteomics and metabolomics. Differential expression was observed for 8547 mRNAs and for 1199 of the 2285 quantified proteins. Furthermore, 151 metabolites with significant changes were identified. Gene ontology analysis, KEGG pathway analysis and fuzzy c-means clustering were used to identify biological processes and metabolic pathways either up- or downregulated on all three levels. Among these were branched chain amino acid degradation (upregulated at P23) and production of free saturated and monounsaturated medium- to long-chain fatty acids (upregulated at P04 and P09; downregulated at P23). Moreover, the HMG-CoA synthase (HMGCS)-mediated mevalonate pathway and ketogenesis were transiently activated. Pharmacological inhibition of HMGCS in primary neonatal rat ventricular cardiomyocytes reduced the percentage of BrdU+ cardiomyocytes, providing evidence that the mevalonate and ketogenesis routes may participate in regulating cardiomyocyte cell cycle.\n\nConclusionsThis is the first systems-level resource combining data from genome-wide transcriptomics with global quantitative proteomics and untargeted metabolomics analyses of the mouse heart throughout the early postnatal period. This integrated multi-level data of molecular changes associated with the loss of cardiac regeneration may open up new possibilities for the development of regenerative therapies.

systems biology↗

bioRxiv2018

Algebraic Shortcuts for Leave-One-Out Cross-Validation in Supervised Network Inference

MotivationSupervised machine learning techniques have traditionally been very successful at reconstructing biological networks, such as protein-ligand interaction, protein-protein interaction and gene regulatory networks. Recently, much emphasis has been placed on the correct evaluation of such supervised models. It is vital to distinguish between using the model to either predict new interactions in a given network or to predict interactions for a new vertex not present in the original network. Specific cross-validation schemes need to be used to assess the performance in such different prediction settings.\n\nResultsWe present a series of leave-one-out cross-validation shortcuts to rapidly estimate the performance of state-of-the-art kernel-based network inference techniques.\n\nAvailabilityThe machine learning techniques with the algebraic shortcuts are implemented in the RLScore software package.

systems biology↗