Biology subjects

Tolvanen, M.

Publications and source records attributed to Tolvanen, M..

4 recordsLinked to original sources

bioRxiv2025

TFBSFootprinter: a multiomics tool for prediction of transcription factor binding sites in vertebrate species

BackgroundTranscription factor (TF) proteins play a critical role in the regulation of eukaryotic gene expression via sequence-specific binding to genomic locations known as transcription factor binding sites (TFBSs). Accurate prediction of TFBSs is essential for understanding gene regulation, disease mechanisms, and drug discovery. These studies are therefore relevant not only in humans but also in model organisms and domesticated and wild animals. However, current tools for the automatic analysis of TFBSs in gene promoter regions are limited in their usability across multiple species. To our knowledge, no tools currently exist that allow for automatic analysis of TFBSs in gene promoter regions for many species. Methodology and FindingsThe TFBSFootprinter tool combines multiomic transcription-relevant data for more accurate prediction of functional TFBSs in 124 vertebrate species. In humans, this includes vertebrate sequence conservation (GERP), proximity to transcription start sites (FANTOM5), correlation of expression between target genes and TFs predicted to bind promoters (FANTOM5), overlap with ChIP-Seq TF metaclusters (GTRD), overlap with ATAC-Seq peaks (ENCODE), eQTLs (GTEx), and the observed/expected CpG ratio (Ensembl). TFBSFootprinter analyses are based on the Ensembl transcript ID for simplicity of use and require minimal setup steps. Benchmarking of the TFBSFootprinter on a manually curated and experimentally verified dataset of TFBSs produced superior results when using all multiomic data (average area under the receiver operating characteristic curve, 0.881), compared with DeepBind (0.798), FIMO (0.817) and traditional PWM (0.854). The results were further improved by selecting the best overall combination of multiomic data (0.910). Additionally, we determined combinations of multiomic data that provide the best model of binding for each TF. TFBSFootprinter is available as Conda and Python packages.

bioinformatics↗

bioRxiv2020

AutoCoEv: a high-throughput in silico pipeline for revealing novel protein-protein interactions

Protein-protein communications govern cellular processes via complex regulatory networks, that are still far from being understood. Thus, identifying novel interactions between proteins can significantly facilitate our comprehension of the mechanistic principles of protein functions. Co-evolution between proteins is a sign of functional communication and, as such, provides a powerful approach to search for novel direct or indirect molecular partners. However, evolutionary analysis of large arrays of proteins, in silico, is a highly time-consuming effort, which has limited the usage of this method to protein pairs or small protein groups. Here, we developed AutoCoEv, a user-friendly computational pipeline for the search of co-evolution between a large number of proteins. By driving 15 individual programs, culminating in CAPS2 as the software for detecting co-evolution, AutoCoEv achieves seamless automation and parallelization of the workflow. Importantly, we provide a patch to CAPS2 source code to strengthen its statistical output, allowing for multiple comparisons correction and enhanced analysis of the results. We apply the pipeline to inspect co-evolution among 324 proteins identified to locate at the vicinity of the lipid rafts of B lymphocytes. We successfully detected multiple strong coevolutionary relations between the proteins, predicting many novel partners and previously unidentified clusters of functionally related molecules. We conclude that AutoCoEv, available at https://github.com/mattilalab/autocoev, can be used to predict functional interactions from large datasets in a time and cost-efficient manner.

bioinformatics↗

bioRxiv2020

Evolution is in the details: Regulatory differences in modern human and Neandertal

Transcription factor proteins play a critical role in the regulation of eukaryote gene expression via sequence- specific binding to genomic locations known as transcription factor binding sites. We studied sites of genomic variation between modern human and Neanderthal promoters. We detected significant differences in the binding affinities of 110 transcription factors to the promoters of 74 target genes. The transcription factors were enriched for terms related to vision, motor neurons, homeobox, and brain, whereas the target genes and their direct interactors were enriched in terms related to autism, brain, connective tissue, trachea, prostate, skull morphology, and vision. Secondary analysis of single-cell data revealed that a subset of the identified transcription factors (CUX1, CUX2, ESRRG, FOXP1, FOXP2, MEF2C, POU6F2, PRRX1 and RORA) co-occur as marker genes in L4 glutamatergic neurons. The majority of these genes have known roles in autism and/or schizophrenia and are associated with human accelerated regions (elevated divergence in humans vs. other primates). These results support the value of gene regulation studies for the evolution of human cognitive abilities and the neuropsychiatric disorders that accompany it.

genomics↗

bioRxiv2019

Neural network and random forest models in protein function prediction

Over the past decade, the demand for automated protein function prediction has increased due to the volume of newly sequenced proteins. In this paper, we address the function prediction task by developing an ensemble system automatically assigning Gene Ontology (GO) terms to the given input protein sequence.\n\nWe develop an ensemble system which combines the GO predictions made by random forest (RF) and neural network (NN) classifiers. Both RF and NN models rely on features derived from BLAST sequence alignments, taxonomy and protein signature analysis tools. In addition, we report on experiments with a NN model that directly analyzes the amino acid sequence as its sole input, using a convolutional layer. The Swiss-Prot database is used as the training and evaluation data.\n\nIn the CAFA3 evaluation, which relies on experimental verification of the functional predictions, our submitted ensemble model demonstrates competitive performance ranking among top-10 best-performing systems out of over 100 submitted systems. In this paper, we evaluate and further improve the CAFA3-submitted system. Our machine learning models together with the data pre-processing and feature generation tools are publicly available as an open source software at https://github.com/TurkuNLP/CAFA3\n\nAuthor summaryUnderstanding the role and function of proteins in biological processes is fundamental for new biological discoveries. Whereas modern sequencing methods have led to a rapid growth of protein databases, the function of these sequences is often unknown and expensive to determine experimentally. This has spurred a lot of interest in predictive modelling of protein functions.\n\nWe develop a machine learning system for annotating protein sequences with functional definitions selected from a vast set of predefined functions. The approach is based on a combination of neural network and random forest classifiers with features covering structural and taxonomic properties and sequence similarity. The system is thoroughly evaluated on a large set of manually curated functional annotations and shows competitive performance in comparison to other suggested approaches. We also analyze the predictions for different functional annotation and taxonomy categories and measure the importance of different features for the task. This analysis reveals that the system is particularly efficient for bacterial protein sequences.

bioinformatics↗