Biology subjects

Konstantakos, V.

Publications and source records attributed to Konstantakos, V..

7 recordsLinked to original sources

bioRxiv2026

DeepSCENIC: transfer learning from sequence-to-function models enables causal gene regulatory network inference

Sequence-to-function (S2F) deep learning models have become an important aid to decipher the genomic cis-regulatory code. However, current S2F models do not take the cellular trans-environment of transcription factors (TF) into account. Conversely, methods for gene regulatory network (GRN) inference often rely on heuristics or simple position weight matrices (PWMs), without exploiting the combinatorial grammar of genomic enhancers. Here, we present DeepSCENIC, a deep learning framework that enables causal GRN inference by performing transfer learning from S2F models to single-cell multiome atlases. We first test and validate DeepSCENIC on ENCODE cell lines, demonstrating that the framework accurately predicts single-cell gene expression and chromatin accessibility by leveraging pretrained S2F models like Enformer and Borzoi. We show that DeepSCENIC recovers TF-region (TF-RE) interactions with high fidelity, and captures de novo TF binding motifs without prior PWM knowledge. The model improves enhancer-gene associations (RE-TG) over correlation-based baselines when benchmarked against large-scale CRISPRi screens. After training a DeepSCENIC model, it enables the prediction of perturbation effects during cell state changes by acting as a mechanistic simulator. In a melanoma cell line atlas, the model accurately recapitulates the transcriptional shift from melanocytic to mesenchymal states, and predicted knock-down effects show high concordance with experimental time series data. Finally, we use DeepSCENIC to identify mouse-human cortex conserved GRNs, finding high cross-species concordance in TF activity programs across matched neuronal subclasses and validating top-ranked enhancers against experimental reporter assays. By unifying S2F enhancer representations with single-cell multiomics, DeepSCENIC provides a new paradigm for jointly modeling and simulating cis-sequence and trans-cellular perturbations.

bioinformatics↗

bioRxiv2026

Microglial lipid signaling drives glioblastoma invasion and represents a therapeutic vulnerability

Glioblastoma (GBM) is characterized by diffuse infiltration into the surrounding brain, which precludes complete surgical resection, the strongest determinant of patient survival. The mechanisms that drive this invasive growth remain incompletely understood. Here we identify a lipid-mediated paracrine signaling axis through which microglia, the resident macrophages of the brain, promote glioma invasion. Integrating single-cell transcriptomics, spatial lipidomics, and functional perturbation across mouse models and human GBM samples, we show that invading tumor cells engage and reprogram microglia via CSF1R-PI3K signaling. This induces a metabolic switch in microglia, leading to the secretion of bioactive lipids, including lysophosphatidylcholines (LPCs) and lysophosphatidic acids (LPAs), which act as pro-invasive cues across GBM subtypes through distinct downstream pathways. Disruption of the microglia-GBM axis, either by inhibiting CSF1R signaling or by blocking lipid mobilization, reduces lipid secretion and suppresses tumor invasion. Targeting downstream LPA-LPAR or YAP/TAZ signaling further constrains invasion in a context-dependent manner. Together, these findings define a lipid-driven signaling circuit that links the tumor microenvironment to glioma invasion and identify therapeutic strategies to limit tumor infiltration and improve surgical resectability.

cancer biology↗

bioRxiv2026

Modeling cis-regulatory variation in human brain enhancers across a large Parkinson's Disease cohort

Genome-wide association studies (GWAS) have linked more than a hundred non-coding genomic loci to Parkinsons disease (PD) risk. Deciphering their functional impact on gene regulation requires cell type-aware modeling approaches to assess the effects of sequence variation on enhancer function and target gene expression. To address this challenge, we generated a comprehensive matched dataset from 190 human donors (115 controls and 75 PD), comprising long-read whole-genome sequencing alongside single nucleus multiome atlases (snATAC-seq and snRNA-seq for 3.1 and 1.1 million nuclei respectively) of the anterior cingulate cortex and substantia nigra. By integrating chromatin accessibility quantitative trait loci (caQTL), DNA methylation QTL (meQTL), and allele-specific chromatin accessibility (ASCA), we identified 53,841 high-confidence cis-acting genetic variants that modulate cell type-specific enhancer accessibility in one or both brain regions. We further demonstrate that sequence-to-function models can accurately predict the impact of these variants directly from the genomic sequence. Novel explainability approaches allowed stratifying these variants according to their regulatory function, with the majority disrupting specific transcription factor binding sites in a cell type specific manner. Integrating these "enhancer variants" (EV) with eQTL mapping and gene locus modeling linked a subset of EVs to their target genes. Finally, we applied these models to prioritize regulatory variants at known PD GWAS loci, bypassing statistical limitations in rare disease-relevant populations like dopaminergic neurons. All together, we establish a unique resource and new sequence modeling strategies to interpret functional non-coding variation in the human brain.

genomics↗

bioRxiv2025

CPP2Vec: a Representation Learning Approach for Cell-Penetrating Peptides Prediction

BackgroundCell-penetrating peptides (CPPs) facilitate the delivery of a variety of therapeutic molecules across the plasma membrane, from small chemical substances to nucleic acid-based macromolecules, such as antisense oligonucleotides (ASOs). Among neutral ASOs, peptide nucleic acids (PNAs) and phosphorodiamidate morpholino oligomers (PMOs) have been extensively studied as potential medical treatments for Duchenne Muscular Dystrophy (DMD), a severe genetic disease that causes muscle degeneration progressively. Over the last few decades, many in silico methods have emerged to detect novel CPPs, counterbalancing the cost of wet-lab experiments. ResultsIn this study, we propose CPP2Vec, a Word2Vec-based CPP prediction method, where the Word2Vec technique is used to represent amino acid sequences of peptides. We developed three task-specific supervised machine learning models for CPP-Classification, Uptake-Efficiency and PMO-Delivery. The first two models were designed to determine if an unseen peptide is a CPP and to pre-dict its uptake efficiency, respectively, while the PMO-Delivery model predicts if a peptide could enhance the cellular delivery of a PMO-complex compared to its naked version. Furthermore, we explored an alternative approach using pre-trained protein-based Large Language Models (LLMs) - T5, BERT, and ESM-2 - to generate the embeddings, resulting in three task-specific models, namely CPP2LLM. A comparison of CPP2Vec and CPP2LLM with state-of-the-art CPP prediction tools is included, proving their significant predictive performance. ConclusionIn this research, we present a Machine Learning (ML)-based tool that introduces the use of the Word2Vec technique in the field of CPPs pre-diction. Notably, it stands out for not requiring any manual a priori feature engineering and for its ability to generalize without any changes between studied tasks. CPP2Vec is available for use at: https://github.com/SSvolou/CPP2Vec.

bioinformatics↗

bioRxiv2025

CREsted: modeling genomic and synthetic cell type-specific enhancers across tissues and species

Sequence-based deep learning models have become the state of the art for the analysis of the genomic regulatory code. Particularly for transcriptional enhancers, deep learning models excel at deciphering sequence features and grammar that underlie their spatiotemporal activity. To enable end-to-end enhancer modeling and design, we developed a software and modeling package, called CREsted. It combines preprocessing starting from single-cell ATAC-seq data; modeling with a choice of several architectures for training classification and regression models on either topics or pseudobulk peak heights; sequence design using multiple strategies; and downstream analysis through a collection of tools to locate transcription factor (TF) binding sites, infer the effect of a TF (activating or repressing) on enhancer accessibility, decipher enhancer grammar, and score gene loci. We demonstrate CREsted using a mouse cortex model that we validate using the BICCN collection of in vivo validated mouse brain enhancers. Classical enhancers in immune cells, including the IFNB1 enhanceosome are revisited using a PBMC model, and we assess the accuracy of TF binding site predictions with ChIP-seq. Additionally, we use CREsted to compare mesenchymal-like cancer cell states between tumor types; and we investigate different fine-tuning strategies of Borzoi within CREsted, comparing their performance and explainability with CREsted models trained from scratch. Finally, we train a CREsted model on a scATAC-seq atlas of zebrafish development and use this to design and in vivo validate cell type-specific synthetic enhancers in three tissues. For varying datasets, we demonstrate that CREsted facilitates efficient training and analyses, enabling scrutinization of the enhancer logic and design of synthetic enhancers across tissues and species. CREsted is available at https://crested.readthedocs.io.

genomics↗

bioRxiv2024

Evaluating Methods for the Prediction of Cell Type-Specific Enhancers in the Mammalian Cortex

Identifying cell type-specific enhancers in the brain is critical to building genetic tools for investigating the mammalian brain. Computational methods for functional enhancer prediction have been proposed and validated in the fruit fly and not yet the mammalian brain. We organized the Brain Initiative Cell Census Network (BICCN) Challenge: Predicting Functional Cell Type-Specific Enhancers from Cross-Species Multi-Omics to assess machine learning and feature-based methods designed to nominate enhancer DNA sequences to target cell types in the mouse cortex. Methods were evaluated based on in vivo validation data from hundreds of cortical cell type-specific enhancers that were previously packaged into individual AAV vectors and retro-orbitally injected into mice. We find that open chromatin was a key predictor of functional enhancers, and sequence models improved prediction of non-functional enhancers that can be deprioritized as opposed to pursued for in vivo testing. Sequence models also identified cell type-specific transcription factor codes that can guide designs of in silico enhancers. This community challenge establishes a benchmark for enhancer prioritization algorithms and reveals computational approaches and molecular information that are crucial for identifying functional enhancers in mammalian cortical cell types. The results of this challenge bring us closer to understanding the complex gene regulatory landscape of the mammalian cortex and to designing more efficient genetic tools to target cortical cell types.

genomics↗

bioRxiv2022

CRISPRedict: The case for simple and interpretable efficiency prediction for CRISPR-Cas9 gene editing

The development of the CRISPR-Cas9 technology has provided a simple yet powerful system for targeted genome editing. Compared with previous gene-editing tools, the CRISPR-Cas9 system identifies target sites by the complementarity between the guide RNA (gRNA) and the DNA sequence, which is less expensive and time-consuming, as well as more precise and scalable. To effectively apply the CRISPR-Cas9 system, researchers need to identify target sites that can be cleaved efficiently and for which the candidate gRNAs have little or no cleavage at other genomic locations. For this reason, numerous computational approaches have been developed to predict cleavage efficiency and exclude undesirable targets. However, current design tools cannot robustly predict experimental success as prediction accuracy depends on the assumptions of the underlying model and how closely the experimental setup matches the training data. Moreover, the most successful tools implement complex machine learning and deep learning models, leading to predictions that are not easily interpretable. Here, we introduce CRISPRedict, a simple linear model that provides accurate and inter-pretable predictions for guide design. Comprehensive evaluation on twelve independent datasets demonstrated that CRISPRedict has an equivalent performance with the currently most accurate tools and outperforms the remaining ones. Moreover, it has the most robust performance for both U6 and T7 data, illustrating its applicability to tasks under different conditions. Therefore, our system can assist researchers in the gRNA design process by providing accurate and explainable predictions. These predictions can then be used to guide genome editing experiments and make plausible hypotheses for further investigation. The source code of CRISPRedict along with instructions for use is available at https://github.com/VKonstantakos/CRISPRedict.

bioinformatics↗