Biology subjects

Cicek, A. E.

Publications and source records attributed to Cicek, A. E..

At least 19 recordsLinked to original sources

bioRxiv2026

REFCON: Reference-free and robust copy number inference in single-cell tumor transcriptomes

Single-cell RNA sequencing (scRNA-seq) is widely used to infer copy number profiles from tumor cells. Existing methods build on a reference-based normalization paradigm: normalizing each tumor cell against a reference of normal cells, whether supplied, in-sample, or synthesized. This makes them reference-dependent and as a result, sensitive to cohort composition, and prone to false positives. To address these limitations, we introduce REFCON, a deep-learning model that enables reference-free copy number profiling from scRNA-seq data. REFCON estimates local copy-number deviations and jointly optimizes them into a genome-wide per-cell profile. It profiles pure tumors, generalizes to unseen tissues and platforms, and stays robust to cohort composition. Predicted copy number profiles distinguish malignant cells with high specificity, producing far fewer false-positive calls, and improve clonal reconstruction. The model can also benefit from reference cells when available, turning a field requirement into an optional refinement. Hence, REFCON extends reliable per-cell copy number profiling to the scRNA-seq data collected without matched normals.

bioinformatics↗

bioRxiv2025

CHALLENGER: Detecting Copy Number Variants in Challenging Regions Using Whole Genome Sequencing Data

Copy number variation (CNV) detection remains a major challenge in whole-genome sequencing (WGS) data, particularly within repetitive, duplicated, and camouflaged genomic regions where short-read sequencing (srWGS) often fails to produce confident alignments. Although long-read WGS (lrWGS) substantially improves structural variant resolution, its high cost limits widespread adoption, especially in clinical settings. To address these limitations, we introduce CHALLENGER, a masked language modeling-based approach for clinical CNV detection using short-read depth signals over coding regions. While the model uses only short-read data as input, it can make calls typically accessible only with long reads, providing a cost-effective way to obtain information characteristic of both technologies. The model is pre-trained on semi-ground truth calls made on srWGS data and then fine-tuned using (i) lrWGS-derived, (ii) human expert-labeled, and (iii) experimentally validated CNV call sets, enabling it to learn technology- and labeling strategy-specific variant signatures hidden within srWGS profiles and to operate in challenging genomic regions. We show that our short-read-only approach improves the state-of-the-art CNV detection F1-score by 40.8%, while, for the first time, capturing 80.3% of CNVs that can only be detected using long reads in challenging genomic regions. The improvement in F1-score in the set of human experts calls is 70.5% for duplications, and 24.6% for deletions in challenging genes. We also specialize CHALLENGER on paralog genes SMN1/2, AMY1/2, and NPY4R, and show that it can improve the performance on experimentally validated call sets while being able to make paralog-specific calls in addition to aggregate calls. The CHALLENGER code and model are available at GitHub.

bioinformatics↗

bioRxiv2025

ExactCN: Predicting Exact Copy Numbers on Whole Exome Sequencing Data

The quantification of the precise copy number variations (CNVs) is crucial to understanding the effects of gene dosage, disease severity, and therapeutic response. Although whole-exome sequencing (WES) offers a cost-effective solution for CNV detection in a clinical setting, it introduces several biases, including those related to sequence length, GC content, and the use of targeting probes. Consequently, estimating exact copy numbers remains challenging, especially for WES data. Here, we present ExactCN, a deep learning-based method for estimation of exact copy numbers from WES data per exon. The architecture integrates convolutional layers that extract local read-depth patterns with transformer encoder blocks that capture genomic context and handle sequencing noise. ExactCN is trained on WES samples from the 1000 Genomes Project, using matching WGS-based calls as semi-ground truth. In benchmarks, ExactCN improves the state-of-the-art integer CNV calling performance by reducing the macro-averaged mean absolute error (MAE) from 0.91 to 0.62 and the macro-averaged root mean squared error (RMSE) from 1.31 to 0.78. It also achieves an overall Pearson correlation of 0.669 and Spearman correlation of 0.550, improving the second-best method by 0.641 and 0.482, respectively. Furthermore, a fine-tuned and specialized version of ExactCN for aggregate CNV detection in clinically important duplicated genes SMN1/2 achieved a macro averaged F1-score of 0.657, and mean absolute error of 0.3. These results substantially improves the state-of-the-art performance and demonstrates the models applicability to both research and clinical genomic analyses. ExactCN is available at https://github.com/ciceklab/ExactCN.

bioinformatics↗

bioRxiv2025

RNA-X: Modeling RNA interactions to design binder RNA and simultaneously target multiple molecules of different types

RNA interactions with proteins, other RNA molecules, and DNA play essential roles in numerous cellular processes and underpin a wide range of therapeutic mechanisms. Consequently, modeling these interactions is critical for understanding biological systems and designing novel RNA-based therapeutics. However, designing RNA sequences that selectively and strongly bind to a specific target remains a major challenge due to the vast sequence space and the current limitations of experimental and computational methods. In this study, we introduce RNA-X, the first RNA interaction foundation model which is based on masked language modeling for representation learning, conditional RNA design, and optimization. For the first time, RNA-X enables (i) RNA design targeting not only proteins but also other RNA and DNA molecules, and (ii) simultaneous design against multiple targets. Our extensive experiments demonstrate that RNA-X generates RNA sequences with natural structural characteristics and surpasses state-of-the-art methods in protein targeting. Using affinity predictors and molecular dynamics simulations, we further show that the model can design RNA molecules that (i) target therapeutically relevant molecules such as p53 and thrombin proteins, and (ii) bind to targets with no prior interaction data, such as SDAD1 protein. As a proof of concept, we designed a novel guide RNA from scratch that simultaneously binds (i) to the DNA of a bacterium and (ii) to the Cas9 protein. The resulting design achieves a predicted binding energy comparable to that of the wild-type guide RNA reported in the Protein Data Bank. Despite having orders of magnitude fewer parameters than existing RNA foundation models, RNA-X produces representations that outperform them across diverse RNA interaction-related downstream tasks. The code and pretrained model are publicly available on GitHub.

bioinformatics↗

bioRxiv2025

One-Hot News: Drug Synergy Models Take a Shortcut

Combinatorial drug therapy holds great promise for tackling complex diseases, but the vast number of possible drug combinations makes exhaustive experimental testing infeasible. Computational models have been developed to guide experimental screens by assigning synergy scores to drug pair-cell line combinations, where they take input structural and chemical information on drugs and molecular features of cell lines. The premise of these models is that they leverage this biological and chemical information to predict synergy measurements. In this study, we demonstrate that replacing drug and cell line representations with simple one-hot encodings results in comparable or even slightly improved performance across diverse published drug combination models. This unexpected finding suggests that current models use these representations primarily as identifiers and exploit covariation in the synergy labels. Our synthetic data experiments show that models can learn from the true features; however, when drugs and cell lines recur across drug-drug-cell triplets, this repeating structure impairs feature-based learning. While the current synergy prediction models can still aid in prioritizing drug pairs within a panel of tested drugs and cell lines, our results highlight the need for better strategies to learn from intended features and generalize to unseen drugs and cell lines.

bioinformatics↗

bioRxiv2025

RNAtranslator: Modeling protein-conditional RNA design as sequence-to-sequence natural language translation

Protein-RNA interactions are essential in gene regulation, splicing, RNA stability, and translation, making RNA a promising therapeutic agent for targeting proteins, including those considered undruggable. However, designing RNA sequences that selectively bind to proteins remains a significant challenge due to the vast sequence space and limitations of current experimental and computational methods. Traditional approaches rely on in vitro selection techniques or computational models that require post-generation optimization, restricting their applicability to well-characterized proteins. We introduce RNAtranslator, a generative language model that formulates protein-conditional RNA design as a sequence-to-sequence natural language translation problem for the first time. By learning a joint representation of RNA and protein interactions from large-scale datasets, RNAtranslator directly generates binding RNA sequences for any given protein target without the need for additional optimization. Our results demonstrate that RNAtranslator produces RNA sequences with natural-like properties, high novelty, and enhanced binding affinity compared to existing methods. This approach enables efficient RNA design for a wide range of proteins, paving the way for new RNA-based therapeutics and synthetic biology applications. The model and the code is released at github.com/ciceklab/RNAtranslator.

bioinformatics↗

bioRxiv2025

OT-Fusion: Cortex-conditioned Fusion of Matched PET and MRI Images Using Optimal Transport

Positron Emission Tomography (PET) and Magnetic Resonance Imaging (MRI) are crucial in diagnosing various medical conditions related to brain. FDG-PET provides essential functional information by capturing synaptic transmission activity, while MRI offers anatomical details. The integration of these modalities has become increasingly valuable, especially with the advent of hybrid PET/MRI systems that enable acquisition of both images in a single session. However, a notable challenge arises due to the inherent differences in spatial resolution between PET and MRI. PET images often have lower spatial resolution, leading to metabolic signals from active regions, such as the cerebral cortex and basal ganglia, appearing diffused and extended into adjacent areas like the white matter. This diffusion can complicate the accurate localization of metabolic activity, posing difficulties in clinical assessments, particularly in neurological pathologies such as epilepsy where precise mapping is crucial. To address this issue, we propose a novel approach that effectively maps the metabolic activity observed in PET onto the cortical structures delineated in MRI. We formulate this mapping as an optimal transport problem that corresponds to finding the optimum way to transform one probability distribution into another. Our method aims to enhance the structural quality of PET images, making them more detailed and informative for clinical decisions related to neurological disorders. The experiments using paired PET and MRI images indicate that our method performs better than the state-of-the-art image fusion methods on quantitative metrics and improves image quality based on visual qualitative evaluation by an expert physician.

bioinformatics↗

bioRxiv2025

DeepSynBa: Actionable Drug Combination Prediction with Complete Dose-Response Profiles

Many cancer monotherapies demonstrate limited clinical efficacy, making combination therapies a relevant treatment strategy. The extensive number of potential drug combinations and context-specific response profiles complicates the prediction of drug combination responses. Existing computational models are typically trained to predict a single aggregated synergy score, which summarises drug responses across different dosage combinations, such as Bliss or Loewe scores. This oversimplification of the drug-response surface leads to high prediction uncertainty and limited actionability, as these models fail to distinguish between potency and efficacy. We introduce DeepSynBa, an actionable model that predicts the complete dose-response matrix of drug pairs instead of relying on an aggregated synergy score. This is achieved by predicting parameters describing the response surface as an intermediate layer in the model. Evaluated on the NCI-ALMANAC and the ONeil datasets, DeepSynBa outperforms the state-of-the-art methods in the dose-response matrix prediction task across most evaluation scenarios, including testing on novel drug combinations, cell lines, and drugs, across nine different tissue types. We also show that DeepSynBa yields reliable synergy score predictions. More importantly, DeepSynBa can predict drug combination responses across different dosages for untested combinations. The intermediate dose-response parameter layer enables the separation of efficacy from potency, informing the selection of dosage ranges that optimise efficacy while limiting off-target toxicity in experimental screens. The predictive capability and the downstream actionability make DeepSynBa a powerful tool for advancing drug combination research beyond the limitations of the current approaches. The code and the dataset for DeepSynBa are available at https://github.com/hikuru/DeepSynBa.

bioinformatics↗

bioRxiv2024

Beacon Reconstruction Attack: Reconstruction of genomes in genomic data-sharing beacons using summary statistics

Genomic data sharing beacon protocol, developed by the Global Alliance for Genomics and Health (GA4GH), offers a privacy-preserving mechanism for querying genomic datasets while restricting direct data access. Despite their design, beacons remain vulnerable to privacy attacks. This study introduces a novel privacy vulnerability of the protocol: One can reconstruct large portions of the genomes of all beacon participants by only using the summary statistics reported by the protocol. We introduce a novel optimization-based algorithm that leverages beacon responses and single nucleotide polymorphism (SNP) correlations for reconstruction. By optimizing for the SNP correlations and allele frequencies, the proposed approach achieves genome reconstruction with a substantially higher F1-score (70%) compared to baseline methods (45%) on beacons generated using individuals from the HapMap and OpenSNP datasets. Our findings reveal critical vulnerabilities in beacon protocol, underscoring the need for enhanced privacy-preserving mechanisms to protect genomic data. Our implementation is available at https://github.com/ASAP-Bilkent/Beacon-Reconstruction-Attack.

bioinformatics↗

bioRxiv2024

A Reinforcement Learning-based Approach for Dynamic Privacy Protection in Genomic Data Sharing Beacons

The rise of genomic sequencing has led to significant privacy concerns due to the sensitive and identifiable nature of genomic data. The Beacon Project, initiated by the Global Alliance for Genomics and Health (GA4GH), was designed to enable privacy-preserving sharing of genomic information via an online querying system. However, studies have revealed that the protocol is vulnerable to membership inference attacks, which can expose the presence of individuals in sensitive datasets. Various countermeasures, such as noise addition and query restrictions, have been proposed but are limited by static implementation, leaving them prone to attackers that can adapt and change strategies. In this study, we present the first reinforcement learning (RL)-based approach for dynamic privacy protection of the beacon protocol. We employ a multi-player RL setting where we train (i) a "Generic-Beacon-Defender" agent who can adjust the honesty rate of its responses, against (ii) a "Generic-Beacon-Attacker" agent who can choose the order of the queries and ask random queries to make the beacon think it is a regular user. This is the first defense mechanism capable of adapting its strategy in real time based on user queries, distinguishing between legitimate users and potential attackers, and applying tailored policies accordingly. By doing so, this method enhances both privacy and utility, effectively countering sophisticated and evolving threats. The code and the models are available at github.com/ciceklab/beacon-defense-strategies.

bioinformatics↗

bioRxiv2024

LYCEUM: Learning to call copy number variants on low coverage ancient genomes

Copy number variants (CNVs) are pivotal in driving phenotypic variation that facilitates species adaptation. They are significant contributors to various disorders, making ancient genomes crucial for uncovering the genetic origins of disease susceptibility across populations. However, detecting CNVs in ancient DNA (aDNA) samples poses substantial challenges due to several factors: (i) aDNA is often highly degraded; (ii) contamination from microbial DNA and DNA from closely related species introduce additional noise into sequencing data; and finally, (iii) the typically low coverage of aDNA renders accurate CNV detection particularly difficult. Conventional CNV calling algorithms, which are optimized for high coverage read-depth signals, underperform under such conditions. To address these limitations, we introduce LYCEUM, the first machine learning-based CNV caller for aDNA. To overcome challenges related to data quality and scarcity, we employ a two-step training strategy. First, the model is pre-trained on whole genome sequencing data from the 1000 Genomes Project, teaching it CNV-calling capabilities similar to conventional methods. Next, the model is fine-tuned using high-confidence CNV calls derived from only a few existing high-coverage aDNA samples. During this stage, the model adapts to making CNV calls based on the downsampled read depth signals of the same aDNA samples. LYCEUM achieves accurate detection of CNVs even in typically low-coverage ancient genomes. We also observe that the segmental deletion calls made by LYCEUM show correlation with the demographic history of the samples and exhibit patterns of negative selection inline with natural selection. LYCEUM is available at https://github.com/ciceklab/LYCEUM.

bioinformatics↗

bioRxiv2023

RNAGEN: A generative adversarial network-based model to generate synthetic RNA sequences to target proteins

RNA - protein binding plays an important role in regulating protein activity by affecting localization and stability. While proteins are usually targeted via small molecules or other proteins, easy-to-design and synthesize small RNAs are a rather unexplored and promising venue. The problem is the lack of methods to generate RNA molecules that have the potential to bind to certain proteins. Here, we propose a method based on generative adversarial networks (GAN) that learn to generate short RNA sequences with natural RNA-like properties such as secondary structure and free energy. Using an optimization technique, we fine-tune these sequences to have them bind to a target protein. We use RNA-protein binding prediction models from the literature to guide the model. We show that even if there is no available guide model trained specifically for the target protein, we can use models trained for similar proteins, such as proteins from the same family, to successfully generate a binding RNA molecule to the target protein. Using this approach, we generated piRNAs that are tailored to bind to SOX2 protein using models trained for its relative (SOX10, SOX14, and SOX8) and experimentally validated in vitro that the top-2 molecules we generated specifically bind to SOX2.

bioinformatics↗

bioRxiv2023

From Cell-Lines to Cancer Patients: Personalized Drug Synergy Prediction

Combination drug therapies are effective treatments for cancer. However, the genetic heterogeneity of the patients and exponentially large space of drug pairings pose significant challenges for finding the right combination for a specific patient. Current in silico prediction methods can be instrumental in reducing the vast number of candidate drug combinations. However, existing powerful methods are trained with cancer cell line gene expression data, which limits their applicability in clinical settings. While synergy measurements on cell lines models are available at large scale, patient-derived samples are too few to train a complex model. On the other hand, patient-specific single-drug response data are relatively more available. In this work, we propose a deep learning framework, Personalized Deep Synergy Predictor (PDSP), that enables us to use the patient-specific single drug response data for customizing patient drug synergy predictions. PDSP is first trained to learn synergy scores of drug pairs and their single drug presonses for a given cell line using drug structures and large scale cell line gene expression data. Then, the model is fine-tuned for patients with their patient gene expression data and associated single drug response measured on the patient ex vivo samples. In this study, we evaluate PDSP on data from three leukemia patients and observe that it improves the prediction accuracy by 27% compared to models trained on cancer cell line data. PDSP is built and available at https://github.com/hikuru/PDSP

bioinformatics↗

bioRxiv2023

Learning to Generate 5' UTR Sequences for Optimized Ribosome Load and Gene Expression

The 5 untranslated region (5 UTR) of mRNA is crucial for the molecules translatability and stability, making it essential for designing synthetic biological circuits for high and stable protein expression. Several UTR sequences are patented and widely used in laboratories. This paper presents UTRGAN, a Generative Adversarial Network (GAN)-based model for generating 5 UTR sequences, coupled with an optimization procedure to ensure high expression for target gene sequences or high ribosome load and translation efficiency. The model generates sequences mimicking various properties of natural UTR sequences and optimizes them to achieve (i) up to 5-fold higher average expression on target genes, (ii) up to 2-fold higher mean ribosome load, and (iii) a 34-fold higher average translation efficiency compared to initial UTR sequences. UTRGAN-generated sequences also exhibit higher similarity to known regulatory motifs in regions such as internal ribosome entry sites, upstream open reading frames, G-quadruplexes, and Kozak and initiation start codon regions. In-vitro experiments show that the UTR sequences designed by UTRGAN result in a higher translation rate for the human TNF- protein compared to the human Beta Globin 5 UTR, a UTR with high production capacity.

bioinformatics↗

bioRxiv2022

ECOLE: Learning to call copy number variants on whole exome sequencing data

Copy number variants (CNV) are shown to contribute to the etiology of several genetic disor{-}ders. Accurate detection of CNVs on whole exome sequencing (WES) data has been a long sought-after goal for use in clinics. This was not possible despite recent improvements in performance because algo{-}rithms mostly suffer from low precision and even lower recall on expert-curated gold standard call sets. Here, we present a deep learning-based somatic and germline CNV caller for WES data, named ECOLE. Based on a variant of the transformer architecture, the model learns to call CNVs per exon, using high-confidence calls made on matched WGS samples. We further train and fine-tune the model with a small set of expert calls via transfer learning. We show that ECOLE achieves high performance on human ex{-}pert labeled data for the first time with 68.7% precision and 49.6% recall. This corresponds to precision and recall improvements of 18.7% and 30.8% over the next best-performing methods, respectively. We also show that the same fine-tuning strategy using tumor samples enables ECOLE to detect RT-qPCR validated variations in bladder cancer samples without the need for a control sample. ECOLE is available at https://github.com/ciceklab/ECOLE.

bioinformatics↗

bioRxiv2022

Pathway-informed deep learning model for survivalanalysis and pathological classification of gliomas

Online assessment of tumor characteristics during surgery is important and has the potential to establish an intraoperative surgeon feedback mechanism. With the availability of such feedback, surgeons could decide to be more liberal or conservative regarding the resection of the tumor. While there are methods to perform metabolomics-based online tumor pathology prediction, their model complexity and, in turn, the predictive performance is limited by the small dataset sizes. Furthermore, the information conveyed by the feedback provided on the tumor tissue could be improved both in terms of content and accuracy. In this study, we propose a metabolic pathway-informed deep learning model, PiDeeL, to perform survival analysis and pathology assessment based on metabolite concentrations. We show that incorporating pathway information into the model architecture substantially reduces parameter complexity and achieves better survival analysis and pathological classification performance. With these design decisions, we show that PiDeeL improves tumor pathology prediction performance of the state-of-the-art in terms of the Area Under the ROC Curve (AUC-ROC) by 3.38% and the Area Under the Precision-Recall Curve (AUC-PR) by 4.06%. Similarly, with respect to the time-dependent concordance index (c-index), we observe that PiDeeL achieves better survival analysis performance (improvement up to 4.3%) when compared to the state-of-the-art. Moreover, we show that importance analyses performed on input metabolite features as well as pathway-specific hidden-layer neurons of PiDeeL provide insights into tumor metabolism. We foresee that the use of this model in the surgery room will help surgeons adjust the surgery plan on the fly and will result in better prognosis estimates tailored to surgical procedures. AvailabilityThe code is released at https://github.com/ciceklab/PiDeeL. The data used in this study is released at https://zenodo.org/record/7228791. Contactcicek@cs.bilkent.edu.tr Supplementary informationSupplementary data are available at Briefings in Bioinformatics online.

bioinformatics↗

bioRxiv2021

A read count-based method to detect multiplets and their cellular origins from snATAC-seq data

Similar to other droplet-based single cell assays, single nucleus ATAC-seq (snATAC-seq) data harbor multiplets that confound downstream analyses. Detecting multiplets in snATAC-seq data is particularly challenging due to its sparsity and trinary nature (0 reads: closed chromatin, 1: open in one allele, 2: open in both alleles), yet offers a unique opportunity to infer multiplets when >2 uniquely aligned reads are observed at multiple loci. Here, we implemented the first read count-based multiplet detection method, ATAC-DoubletDetector, that detects multiplets independently of cell-type. Using PBMC and pancreatic islet datasets, ATAC-DoubletDetector captured simulated heterotypic multiplets (different cell-types) with [~]0.60 recall, showing [~]24% improvement over state of the art. ATAC-DoubletDetector detected homotypic multiplets with [~]0.61 recall, representing the first method to detect multiplets originating from the same cell type. Using our novel clustering-based algorithm, multiplets were annotated to their cellular origins with [~]85% accuracy. Application of ATAC-DoubletDetector will improve downstream analysis of snATAC-seq.

bioinformatics↗

bioRxiv2020

Uncovering complementary sets of variants for the prediction of quantitative phenotypes

MotivationGenome-wide association studies show that variants in individual genomic loci alone are not sufficient to explain the heritability of complex, quantitative phenotypes. Many computational methods have been developed to address this issue by considering subsets of loci that can collectively predict the phenotype. This problem can be considered a challenging instance of feature selection in which the number of dimensions (loci that are screened) is much larger than the number of samples. While currently available methods can achieve decent phenotype prediction performance, they either do not scale to large datasets or have parameters that require extensive tuning. ResultsWe propose a fast and simple algorithm, Macarons, to select a small, complementary subset of variants by avoiding redundant pairs that are in linkage disequilibrium. Our method features two interpretable parameters that control the time/performance trade-off without requiring parameter tuning. In our computational experiments, we show that Macarons consistently achieves similar or better prediction performance than state-of-the-art selection methods while having a simpler premise and being at least 2 orders of magnitude faster. Overall, Macarons can seamlessly scale to the human genome with ~107 variants in a matter of minutes while taking the dependencies between the variants into account. ConclusionMacarons can offer a reasonable trade-off between phenotype predictivity, runtime and the complementarity of the selected subsets. The framework we present can be generalized to other high-dimensional feature selection problems within and beyond biomedical applications. AvailabilityMacarons is implemented in Matlab and the source code is available at: https://github.com/serhan-yilmaz/macarons

bioinformatics↗