Author name cluster

Erdem Varol

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

NeurIPS Conference 2025 Conference Paper

Predicting Functional Brain Connectivity with Context-Aware Deep Neural Networks

Alexander Ratzan
Sidharth Goel
Junhao Wen
Christos Davatzikos
Erdem Varol

Spatial location and molecular interactions have long been linked to the connectivity patterns of neural circuits. Yet, at the macroscale of human brain networks, the interplay between spatial position, gene expression, and connectivity remains incompletely understood. Recent efforts to map the human transcriptome and connectome have yielded spatially resolved brain atlases, however modeling the relationship between high-dimensional transcriptomic data and connectivity while accounting for inherent spatial confounds presents a significant challenge. In this paper, we present the first deep learning approaches for predicting whole-brain functional connectivity from gene expression and regional spatial coordinates, including our proposed Spatiomolecular Transformer (SMT). SMT explicitly models biological context by tokenizing genes based on their transcription start site (TSS) order to capture multi-scale genomic organization, and incorporating regional 3D spatial location via a dedicated context [CLS] token within its multi-head self-attention mechanism. We rigorously benchmark context-aware neural networks, including SMT and a single-gene resolution Multilayer-Perceptron (MLP), to established rules-based and bilinear methods. Crucially, to ensure that learned relationships in any model are not mere artifacts of spatial proximity, we introduce novel spatiomolecular null maps preserving key transcriptomic autocorrelation structure. Context-aware neural networks outperform linear methods, significantly exceed our stringent null map estimates, and generalize across diverse connectomic datasets and parcellation resolutions. Together, these findings demonstrate a strong, predictable link between the spatial distributions of gene expression and functional brain network architecture, and establish a rigorously validated deep learning framework for decoding this relationship. Code to reproduce our results is available at: github. com/neuroinfolab/GeneEx2Conn.

PDF Details

NeurIPS Conference 2025 Conference Paper

Self supervised learning for in vivo localization of microelectrode arrays using raw local field potential

Tianxiao He
Malhar Patel
Chenyi Li
Anna Maslarova
Mihály Vöröslakos
Nalini Ramanathan
Wei-Lun Hung
Gyorgy Buzsaki

Recent advances in large-scale neural recordings have enabled accurate decoding of behavior and cognitive states, yet decoding anatomical regions remains underexplored, despite being crucial for consistent targeting in multiday recordings and effective deep brain stimulation. Current approaches typically rely on external anatomical information, from atlas-based planning to post hoc histology, which are limited in precision, longitudinal applicability, and real-time feedback. In this work, we develop a self-supervised learning framework, Lfp2vec, to infer anatomical regions directly from the neural signal in vivo. We adapt an audio-pretrained transformer model by continuing self-supervised training on a large corpus of unlabeled local-field-potential (LFP) data, then fine-tuning for anatomical region decoding. Ablations show that combining out-of-domain initialization with in-domain self-supervision outperforms training from scratch. We demonstrate that our method achieves strong zero-shot generalization across different labs and probe geometries, and outperforming state-of-the-art self-supervised models on electrophysiology data. The learned embeddings form anatomically coherent clusters and transfer effectively to downstream tasks like disease classification with minimal fine-tuning. Altogether, our approach enables zero-shot prediction of brain regions in novel subjects, demonstrates that LFP signals encode rich anatomical information, and establishes self-supervised learning on raw LFP as a foundation to learn representations that can be tuned for diverse neural decoding tasks. Code to reproduce our results is found in the github repository at https: //github. com/tianxiao18/lfp2vec.

PDF Details

NeurIPS Conference 2023 Conference Paper

Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes

Yizi Zhang
Tianxiao He
Julien Boussard
Charles Windolf
Olivier Winter
Eric Trautmann
Noam Roth
Hailey Barrell

Neural decoding and its applications to brain computer interfaces (BCI) are essential for understanding the association between neural activity and behavior. A prerequisite for many decoding approaches is spike sorting, the assignment of action potentials (spikes) to individual neurons. Current spike sorting algorithms, however, can be inaccurate and do not properly model uncertainty of spike assignments, therefore discarding information that could potentially improve decoding performance. Recent advances in high-density probes (e. g. , Neuropixels) and computational methods now allow for extracting a rich set of spike features from unsorted data; these features can in turn be used to directly decode behavioral correlates. To this end, we propose a spike sorting-free decoding method that directly models the distribution of extracted spike features using a mixture of Gaussians (MoG) encoding the uncertainty of spike assignments, without aiming to solve the spike clustering problem explicitly. We allow the mixing proportion of the MoG to change over time in response to the behavior and develop variational inference methods to fit the resulting model and to perform decoding. We benchmark our method with an extensive suite of recordings from different animals and probe geometries, demonstrating that our proposed decoder can consistently outperform current methods based on thresholding (i. e. multi-unit activity) and spike sorting. Open source code is available at https: //github. com/yzhang511/density_decoding.

PDF Details

NeurIPS Conference 2021 Conference Paper

Three-dimensional spike localization and improved motion correction for Neuropixels recordings

Julien Boussard
Erdem Varol
Hyun Dong Lee
Nishchal Dethe
Liam Paninski

Neuropixels (NP) probes are dense linear multi-electrode arrays that have rapidly become essential tools for studying the electrophysiology of large neural populations. Unfortunately, a number of challenges remain in analyzing the large datasets output by these probes. Here we introduce several new methods for extracting useful spiking information from NP probes. First, we use a simple point neuron model, together with a neural-network denoiser, to efficiently map spikes detected on the probe into three-dimensional localizations. Previous methods localized spikes in two dimensions only; we show that the new localization approach is significantly more robust and provides an improved feature set for clustering spikes according to neural identity (``spike sorting"). Next, we apply a Poisson denoising method to the resulting three-dimensional point-cloud representation of the data, and show that the resulting 3D images can be accurately registered over time, leading to improved tracking of time-varying neural activity over the probe, and in turn, crisper estimates of neural clusters over time. The code to reproduce our results and an example neuropixels dataset is provided in the supplementary material.

PDF Details

YNIMG Journal 2018 Journal Article

MIDAS: Regionally linear multivariate discriminative statistical mapping

Erdem Varol
Aristeidis Sotiras
Christos Davatzikos

Statistical parametric maps formed via voxel-wise mass-univariate tests, such as the general linear model, are commonly used to test hypotheses about regionally specific effects in neuroimaging cross-sectional studies where each subject is represented by a single image. Despite being informative, these techniques remain limited as they ignore multivariate relationships in the data. Most importantly, the commonly employed local Gaussian smoothing, which is important for accounting for registration errors and making the data follow Gaussian distributions, is usually chosen in an ad hoc fashion. Thus, it is often suboptimal for the task of detecting group differences and correlations with non-imaging variables. Information mapping techniques, such as searchlight, which use pattern classifiers to exploit multivariate information and obtain more powerful statistical maps, have become increasingly popular in recent years. However, existing methods may lead to important interpretation errors in practice (i. e. , misidentifying a cluster as informative, or failing to detect truly informative voxels), while often being computationally expensive. To address these issues, we introduce a novel efficient multivariate statistical framework for cross-sectional studies, termed MIDAS, seeking highly sensitive and specific voxel-wise brain maps, while leveraging the power of regional discriminant analysis. In MIDAS, locally linear discriminative learning is applied to estimate the pattern that best discriminates between two groups, or predicts a variable of interest. This pattern is equivalent to local filtering by an optimal kernel whose coefficients are the weights of the linear discriminant. By composing information from all neighborhoods that contain a given voxel, MIDAS produces a statistic that collectively reflects the contribution of the voxel to the regional classifiers as well as the discriminative power of the classifiers. Critically, MIDAS efficiently assesses the statistical significance of the derived statistic by analytically approximating its null distribution without the need for computationally expensive permutation tests. The proposed framework was extensively validated using simulated atrophy in structural magnetic resonance imaging (MRI) and further tested using data from a task-based functional MRI study as well as a structural MRI study of cognitive performance. The performance of the proposed framework was evaluated against standard voxel-wise general linear models and other information mapping methods. The experimental results showed that MIDAS achieves relatively higher sensitivity and specificity in detecting group differences. Together, our results demonstrate the potential of the proposed approach to efficiently map effects of interest in both structural and functional data.

Details DOI

YNIMG Journal 2017 Journal Article

HYDRA: Revealing heterogeneity of imaging and genetic patterns through a multiple max-margin discriminative analysis framework

Erdem Varol
Aristeidis Sotiras
Christos Davatzikos

Multivariate pattern analysis techniques have been increasingly used over the past decade to derive highly sensitive and specific biomarkers of diseases on an individual basis. The driving assumption behind the vast majority of the existing methodologies is that a single imaging pattern can distinguish between healthy and diseased populations, or between two subgroups of patients (e. g. , progressors vs. non-progressors). This assumption effectively ignores the ample evidence for the heterogeneous nature of brain diseases. Neurodegenerative, neuropsychiatric and neurodevelopmental disorders are largely characterized by high clinical heterogeneity, which likely stems in part from underlying neuroanatomical heterogeneity of various pathologies. Detecting and characterizing heterogeneity may deepen our understanding of disease mechanisms and lead to patient-specific treatments. However, few approaches tackle disease subtype discovery in a principled machine learning framework. To address this challenge, we present a novel non-linear learning algorithm for simultaneous binary classification and subtype identification, termed HYDRA (Heterogeneity through Discriminative Analysis). Neuroanatomical subtypes are effectively captured by multiple linear hyperplanes, which form a convex polytope that separates two groups (e. g. , healthy controls from pathologic samples); each face of this polytope effectively defines a disease subtype. We validated HYDRA on simulated and clinical data. In the latter case, we applied the proposed method independently to the imaging and genetic datasets of the Alzheimer's Disease Neuroimaging Initiative (ADNI 1) study. The imaging dataset consisted of T1-weighted volumetric magnetic resonance images of 123 AD patients and 177 controls. The genetic dataset consisted of single nucleotide polymorphism information of 103 AD patients and 139 controls. We identified 3 reproducible subtypes of atrophy in AD relative to controls: (1) diffuse and extensive atrophy, (2) precuneus and extensive temporal lobe atrophy, as well some prefrontal atrophy, (3) atrophy pattern very much confined to the hippocampus and the medial temporal lobe. The genetics dataset yielded two subtypes of AD characterized mainly by the presence/absence of the apolipoprotein E (APOE) ε4 genotype, but also involving differential presence of risk alleles of CD2AP, SPON1 and LOC39095 SNPs that were associated with differences in the respective patterns of brain atrophy, especially in the precuneus. The results demonstrate the potential of the proposed approach to map disease heterogeneity in neuroimaging and genetic studies.

Details DOI