Biology subjects

Balci, A. T.

Publications and source records attributed to Balci, A. T..

5 recordsLinked to original sources

bioRxiv2025

Frustratingly easy domain adaptation for cross-speciestranscription factor binding prediction

MotivationUnderstanding how DNA sequence encodes gene regulation remains a central challenge in genomics. While deep learning models can predict regulatory activity from sequence with high accuracy, their generalizability across species--and thus their ability to capture fundamental biological principles--remains limited. Cross-species prediction provides a powerful test of model robustness and offers a window into conserved regulatory logic, but effectively bridging species-specific genomic differences remains a major barrier. ResultsWe present MORALE, a novel and scalable domain adaptation framework that significantly advances cross-species prediction of transcription factor (TF) binding. By aligning statistical moments of sequence embeddings across species, MORALE enables deep learning models to learn species-invariant regulatory features without requiring adversarial training or complex architectures. Applied to multi-species TF ChIP-seq datasets, MORALE achieves state-of-the-art performance--outperforming both baseline and adversarial approaches across all TFs--while preserving model interpretability and recovering canonical motifs with greater precision. In the five-species transfer setting, MORALE not only improves human prediction accuracy beyond human-only training but also reveals regulatory features conserved across mammals. These results highlight the potential of simple yet powerful domain adaptation techniques to drive generalization and discovery in regulatory genomics. Crucially, MORALE is architecture-agnostic and can be seamlessly integrated into any embedding-based sequence model. AvailabilityCode is available at https://github.com/loudrxiv/frustrating.

genomics↗

bioRxiv2024

Ultra-fast variant effect prediction using biophysical transcription factor binding models

Sequence variation within TF binding sites can significantly affect TF-DNA interactions, influencing gene expression and contributing to disease susceptibility or phenotypic traits. Despite recent progress in deep sequence-to-function models that predict functional output from sequence data, these methods perform inadequately on some variant effect prediction tasks, especially with common genetic variants. This limitation underscores the importance of leveraging biophysical models of TF binding to enhance interpretability of variant effect scores and facilitate mechanistic insights. We introduce motifDiff, a novel computational tool designed to quantify variant effects using mono and dinucleotide position weight matrices. motifDiff offers several key advantages, including scalability to score millions of variants within minutes, implementation of statistically rigorous normalization strategy critical for optimal performance, and support for both dinucleotide and mononucleotide models. We demonstrate motifDiff s efficacy by evaluating it across diverse ground truth datasets that quantify the effects of common variants in vivo, thereby establishing robust benchmarks for the predictive value of variant effect calculations. Finally, we show that our tool provides unique insights when interpreting human accelerated regions. motifDiff is available as a standalone Python application at https://github.com/rezwanhosseini/MotifDiff.

bioinformatics↗

bioRxiv2023

L0 segmentation enables data-driven concise representations of diverse epigenomic data

MotivationEpigenetic assays using next-generation sequencing (NGS) have furthered our understanding of the functional genomic regions and the mechanisms of gene regulation. However, a single assay produces billions of data represented by nucleotide resolution signal tracks. The signal strength at a given nucleotide is subject to numerous sources of technical and biological noise and thus conveys limited information about the underlying biological state. In order to draw biological conclusions, data is typically summarized into higher order patterns. Numerous specialized algorithms for summarizing epigenetic signal have been proposed and include methods for peak calling or finding differentially methylated regions. A key unifying principle underlying these approaches is that they all leverage the strong prior that signal must be locally consistent. ResultsWe propose L0 segmentation as a universal framework for extracting locally coherent signals for diverse epigenetic sources. L0 serves to both compress and smooth the input signal by approximating it as piece-wise constant. We implement a highly scalable L0 segmentation with additional loss functions designed for NGS epigenetic data types including Poisson loss for single tracks and binomial loss for methylation/coverage data. We show that the L0 segmentation approach retains the salient features of the data yet can identify subtle features, such as transcription end sites, missed by other analytic approaches. AvailabilityOur approach is implemented as an R package "l01segmentation" with a C++ backend. Available at https://github.com/boooooogey/l01segmentation.

bioinformatics↗

bioRxiv2023

An intrinsically interpretable neural network architecture for sequence to function learning

MotivationSequence-based deep learning approaches have been shown to predict a multitude of functional genomic readouts, including regions of open chromatin and RNA expression of genes. However, a major limitation of current methods is that model interpretation relies on computationally demanding post hoc analyses, and even then, one can often not explain the internal mechanics of highly parameterized models. Here, we introduce a deep learning architecture called tiSFM (totally interpretable sequence to function model). tiSFM improves upon the performance of standard multi-layer convolutional models while using fewer parameters. Additionally, while tiSFM is itself technically a multi-layer neural network, internal model parameters are intrinsically interpretable in terms of relevant sequence motifs. ResultsWe analyze published open chromatin measurements across hematopoietic lineage cell-types and demonstrate that tiSFM outperforms a state-of-the-art convolutional neural network model custom-tailored to this dataset. We also show that it correctly identifies context specific activities of transcription factors with known roles in hematopoietic differentiation, including Pax5 and Ebf1 for B-cells, and Rorc for innate lymphoid cells. tiSFMs model parameters have biologically meaningful interpretations, and we show the utility of our approach on a complex task of predicting the change in epigenetic state as a function of developmental transition. Availability and implementationThe source code, including scripts for the analysis of key findings, can be found at https://github.com/boooooogey/ATAConv, implemented in Python. Contactatb44@pitt.edu

bioinformatics↗

bioRxiv2019

DeepInterface: Protein-protein interface validation using 3D Convolutional Neural Networks

MotivationProtein-protein interactions are crucial in almost all biological processes. Proteins interact through their interfaces. It is important to determine how proteins interact through interfaces to understand protein binding mechanisms and to predict new protein-protein interactions.\n\nResultsWe present DeepInterface, a deep learning based method which predicts, for a given protein complex, if the interface between the proteins of a complex is a true interface or not. The model is a 3-dimensional convolutional neural networks model and the positive datasets are obtained from all complexes in the Protein Data Bank, the negative datasets are the incorrect solutions of the docking decoys. The model analyzes a given interface structure and outputs the probability of the given structure being an interface. The accuracy of the model for several interface data sets, including PIFACE, PPI4DOCK, DOCKGROUND is approximately 88% in the validation dataset and 75% in the test dataset. The method can be used to improve the accuracy of template based PPI predictions.

bioinformatics↗