Smita Krishnaswamy

Epitope-based vaccines are promising therapeutic modalities for infectious diseases and cancer, but identifying immunogenic epitopes is chal… (voir plus)lenging. The vast majority of prediction methods are sequence-based, and do not incorporate wide-scale structure data and biochemical properties across each peptide-MHC (pMHC) complex. We present ImmunoStruct, a deep-learning model that integrates sequence, structural, and biochemical information to predict multi-allele class-I pMHC immunogenicity. By leveraging a multimodal dataset of ∼ 27,000 peptide-MHC complexes that we generated with AlphaFold, we demonstrate that ImmunoStruct improves immunogenicity prediction performance and interpretability beyond existing methods, across infectious disease epitopes and cancer neoepitopes. We further show strong alignment with in vitro assay results for a set of SARS-CoV-2 epitopes. This work also presents a new architecture that incorporates equivariant graph processing and multi-modal data integration for the long standing task in immunotherapy.

2024-11-03

bioRxiv (prépublication)

ImmunoStruct: Integration of protein sequence, structure, and biochemical properties for immunogenicity prediction and interpretation

Kevin Bijan Givechian

João Felipe Rocha

Edward Yang

Chen Liu

Kerrie Greene

Rex Ying

Etienne Caron

Akiko Iwasaki

2024-11-03

bioRxiv (prépublication)

ProtSCAPE: Mapping the landscape of protein conformations in molecular dynamics

Siddharth Viswanath

Dhananjay Bhaskar

David R. Johnson

João F. Rocha

Egbert Castro

Jackson Grady

Alex T. Grigas

Michael Perlmutter

Corey S. O'Hern

Understanding the dynamic nature of protein structures is essential for comprehending their biological functions. While significant progress… (voir plus) has been made in predicting static folded structures, modeling protein motions on microsecond to millisecond scales remains challenging. To address these challenges, we introduce a novel deep learning architecture, Protein Transformer with Scattering, Attention, and Positional Embedding (ProtSCAPE), which leverages the geometric scattering transform alongside transformer-based attention mechanisms to capture protein dynamics from molecular dynamics (MD) simulations. ProtSCAPE utilizes the multi-scale nature of the geometric scattering transform to extract features from protein structures conceptualized as graphs and integrates these features with dual attention structures that focus on residues and amino acid signals, generating latent representations of protein trajectories. Furthermore, ProtSCAPE incorporates a regression head to enforce temporally coherent latent representations.

2024-10-27

ArXiv (prépublication)

Convergence of Manifold Filter-Combine Networks

David R. Johnson

Joyce Chew

Siddharth Viswanath

Edward De Brouwer

Deanna Needell

Michael Perlmutter

In order to better understand manifold neural networks (MNNs), we introduce Manifold Filter-Combine Networks (MFCNs). The filter-combine fra… (voir plus)mework parallels the popular aggregate-combine paradigm for graph neural networks (GNNs) and naturally suggests many interesting families of MNNs which can be interpreted as the manifold analog of various popular GNNs. We then propose a method for implementing MFCNs on high-dimensional point clouds that relies on approximating the manifold by a sparse graph. We prove that our method is consistent in the sense that it converges to a continuum limit as the number of data points tends to infinity.

2024-10-18

ArXiv (prépublication)

Convergence of Manifold Filter-Combine Networks

David R. Johnson

Joyce A. Chew

Siddharth Viswanath

Edward De Brouwer

Deanna Needell

Michael Perlmutter

In order to better understand manifold neural networks (MNNs), we introduce Manifold Filter-Combine Networks (MFCNs). The filter-combine fra… (voir plus)mework parallels the popular aggregate-combine paradigm for graph neural networks (GNNs) and naturally suggests many interesting families of MNNs which can be interpreted as the manifold analog of various popular GNNs. We then propose a method for implementing MFCNs on high-dimensional point clouds that relies on approximating the manifold by a sparse graph. We prove that our method is consistent in the sense that it converges to a continuum limit as the number of data points tends to infinity.

2024-10-18

ArXiv (prépublication)

Neuro-GSTH: A Geometric Scattering and Persistent Homology Framework for Uncovering Spatiotemporal Signatures in Neural Activity

Dhananjay Bhaskar

Jessica Moore

Yanlei Zhang

Feng Gao

Bastian Rieck

Guy Wolf

Helen Pushkarskaya

Firas Khasawneh

Elizabeth Munch

Valentina Greco

Christopher Pittenger

2024-10-13

bioRxiv (prépublication)

Neuro-GSTH: A Geometric Scattering and Persistent Homology Framework for Uncovering Spatiotemporal Signatures in Neural Activity

Dhananjay Bhaskar

Jessica Moore

Feng Gao

Bastian Rieck

Firas A. Khasawneh

Elizabeth Munch

Valentina Greco

Understanding how neurons communicate and coordinate their activity is essential for unraveling the brain’s complex functionality. To anal… (voir plus)yze the intricate spatiotemporal dynamics of neural signaling, we developed Geometric Scattering Trajectory Homology (neuro-GSTH), a novel framework that captures time-evolving neural signals and encodes them into low-dimensional representations. GSTH integrates geometric scattering transforms, which extract multiscale features from brain signals modeled on anatomical graphs, with t-PHATE, a manifold learning method that maps the temporal evolution of neural activity. Topological descriptors from computational homology are then applied to characterize the global structure of these neural trajectories, enabling the quantification and differentiation of spatiotemporal brain dynamics. We demonstrate the power of neuro-GSTH in neuroscience by applying it to both simulated and biological neural datasets. First, we used neuro-GSTH to analyze neural oscillatory behavior in the Kuramoto model, revealing its capacity to track the synchronization of neural circuits as coupling strength increases. Next, we applied neuro-GSTH to neural recordings from the visual cortex of mice, where it accurately reconstructed visual stimulus patterns such as sinusoidal gratings. Neuro-GSTH-derived neural trajectories enabled precise classification of stimulus properties like spatial frequency and orientation, significantly outperforming traditional methods in capturing the underlying neural dynamics. These findings demonstrate that neuro-GSTH effectively identifies neural motifs—distinct patterns of spatiotemporal activity—providing a powerful tool for decoding brain activity across diverse tasks, sensory inputs, and neurological disorders. Neuro-GSTH thus offers new insights into neural communication and dynamics, advancing our ability to map and understand complex brain functions.

2024-10-13

bioRxiv (prépublication)

DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy Images

Chen Liu

Danqi Liao

Alejandro Parada-Mayorga

Alejandro Ribeiro

Marcello DiStasio

The proliferation of digital microscopy images, driven by advances in automated whole slide scanning, presents significant opportunities for… (voir plus) biomedical research and clinical diagnostics. However, accurately annotating densely packed information in these images remains a major challenge. To address this, we introduce DiffKillR, a novel framework that reframes cell annotation as the combination of archetype matching and image registration tasks. DiffKillR employs two complementary neural networks: one that learns a diffeomorphism-invariant feature space for robust cell matching and another that computes the precise warping field between cells for annotation mapping. Using a small set of annotated archetypes, DiffKillR efficiently propagates annotations across large microscopy images, reducing the need for extensive manual labeling. More importantly, it is suitable for any type of pixel-level annotation. We will discuss the theoretical properties of DiffKillR and validate it on three microscopy tasks, demonstrating its advantages over existing supervised, semi-supervised, and unsupervised methods.

2024-10-04

ArXiv (prépublication)

DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy Images

Chen Liu

Danqi Liao

Alejandro Parada-Mayorga

Alejandro Ribeiro

Marcello DiStasio

The proliferation of digital microscopy images, driven by advances in automated whole slide scanning, presents significant opportunities for… (voir plus) biomedical research and clinical diagnostics. However, accurately annotating densely packed information in these images remains a major challenge. To address this, we introduce DiffKillR, a novel framework that reframes cell annotation as the combination of archetype matching and image registration tasks. DiffKillR employs two complementary neural networks: one that learns a diffeomorphism-invariant feature space for robust cell matching and another that computes the precise warping field between cells for annotation mapping. Using a small set of annotated archetypes, DiffKillR efficiently propagates annotations across large microscopy images, reducing the need for extensive manual labeling. More importantly, it is suitable for any type of pixel-level annotation. We will discuss the theoretical properties of DiffKillR and validate it on three microscopy tasks, demonstrating its advantages over existing supervised, semi-supervised, and unsupervised methods.

2024-10-04

ArXiv (prépublication)

ProtSCAPE: Mapping the landscape of protein conformations in molecular dynamics

Siddharth Viswanath

Dhananjay Bhaskar

David R. Johnson

João Felipe Rocha

Egbert Castro

Jackson Grady

Alex T. Grigas

Michael Perlmutter

Corey S. O'Hern

Understanding the dynamic nature of protein structures is essential for comprehending their biological functions. While significant progress… (voir plus) has been made in predicting static folded structures, modeling protein motions on microsecond to millisecond scales remains challenging. To address these challenges, we introduce a novel deep learning architecture, Protein Transformer with Scattering, Attention, and Positional Embedding (ProtSCAPE), which leverages the geometric scattering transform alongside transformer-based attention mechanisms to capture protein dynamics from molecular dynamics (MD) simulations. ProtSCAPE utilizes the multi-scale nature of the geometric scattering transform to extract features from protein structures conceptualized as graphs and integrates these features with dual attention structures that focus on residues and amino acid signals, generating latent representations of protein trajectories. Furthermore, ProtSCAPE incorporates a regression head to enforce temporally coherent latent representations.

2024-10-01

arXiv (publié)

Latent Representation Learning for Multimodal Brain Activity Translation

Arman Afrasiyabi

Dhananjay Bhaskar

Erica L. Busch

Laurent Caplette

Rahul Singh

Guillaume Lajoie

Nicholas B. Turk-Browne

Neuroscience employs diverse neuroimaging techniques, each offering distinct insights into brain activity, from electrophysiological recordi… (voir plus)ngs such as EEG, which have high temporal resolution, to hemodynamic modalities such as fMRI, which have increased spatial precision. However, integrating these heterogeneous data sources remains a challenge, which limits a comprehensive understanding of brain function. We present the Spatiotemporal Alignment of Multimodal Brain Activity (SAMBA) framework, which bridges the spatial and temporal resolution gaps across modalities by learning a unified latent space free of modality-specific biases. SAMBA introduces a novel attention-based wavelet decomposition for spectral filtering of electrophysiological recordings, graph attention networks to model functional connectivity between functional brain units, and recurrent layers to capture temporal autocorrelations in brain signal. We show that the training of SAMBA, aside from achieving translation, also learns a rich representation of brain information processing. We showcase this classify external stimuli driving brain activity from the representation learned in hidden layers of SAMBA, paving the way for broad downstream applications in neuroscience research and clinical contexts.

2024-09-27

ArXiv (prépublication)

Latent Representation Learning for Multimodal Brain Activity Translation

Arman Afrasiyabi

Dhananjay Bhaskar

Erica Lindsey Busch

Laurent Caplette

Rahul Singh

Guillaume Lajoie

Nicholas B Turk-Browne

Neuroscience employs diverse neuroimaging techniques, each offering distinct insights into brain activity, from electrophysiological recordi… (voir plus)ngs such as EEG, which have high temporal resolution, to hemodynamic modalities such as fMRI, which have increased spatial precision. However, integrating these heterogeneous data sources remains a challenge, which limits a comprehensive understanding of brain function. We present the Spatiotemporal Alignment of Multimodal Brain Activity (SAMBA) framework, which bridges the spatial and temporal resolution gaps across modalities by learning a unified latent space free of modality-specific biases. SAMBA introduces a novel attention-based wavelet decomposition for spectral filtering of electrophysiological recordings, graph attention networks to model functional connectivity between functional brain units, and recurrent layers to capture temporal autocorrelations in brain signal. We show that the training of SAMBA, aside from achieving translation, also learns a rich representation of brain information processing. We showcase this classify external stimuli driving brain activity from the representation learned in hidden layers of SAMBA, paving the way for broad downstream applications in neuroscience research and clinical contexts.

2024-09-27

ArXiv (prépublication)