Biology subjects

Pandarinath, C.

Publications and source records attributed to Pandarinath, C..

At least 19 recordsLinked to original sources

bioRxiv2026

A generalizable speech neuroprosthesis

Intracortical brain-computer interfaces (BCIs) can restore communication to people with vocal tract paralysis by decoding cortical activity during attempted speech into text. State-of-the-art systems pairing neural-to-phoneme decoders with phoneme-to-word language models have achieved word error rates (WERs) as low as 1%, but only after collecting thousands of sentences of training data. Shortening the data collection process would facilitate scaling this new technology by reducing the time from device implant to high-accuracy communication. Here we introduce a transformer-based decoder model trained jointly across six intracortical speech BCI participants. For every participant -- regardless of sex, disease etiology, or attempted speaking strategy -- a multi-user model decoded speech more accurately (over 50% lower relative WER on average) than models trained on individual users data. Notably, the multi-user model could be finetuned on fewer than 200 sentences from a held-out user to achieve a WER below 7%. These results reveal how to pool intracortical data across people to yield more accurate, generalizable, and rapidly-deployable decoding models.

bioengineering↗

bioRxiv2026

Neural decoding of speech using deep neural ensembles

Speech brain-computer interfaces (BCIs) can restore rapid communication to people with paralysis, but decoding errors still limit performance. In recent brain-to-text decoding competitions, deep ensemble methods, which combine predictions from multiple independently trained decoders, have delivered striking accuracy improvements and account for the largest gains over baseline approaches. However, these methods have not previously been tested in real-time, require substantial computational resources, and their performance under various clinically relevant constraints remains poorly understood. Here, we present the first closed-loop test of deep ensembles in a participant with bilateral intracortical microelectrode arrays, demonstrating a reduction in word error rate from 33.7% to 26.0% on a large-vocabulary task. Using additional data from three participants, we then assess how these gains depend on baseline error rate, training dataset size, and ensemble size, including the resource-accuracy tradeoffs most relevant for real-world deployment. Finally, we introduce a computationally efficient pseudoensembling approach based on test-time augmentation that improves decoding accuracy while requiring only a single base decoder, greatly reducing the computational burden of ensembling. Together, these results show that the benefits of deep ensembling can be realized in real time and under practical resource constraints, bringing speech BCIs closer to broader clinical adoption.

neuroscience↗

bioRxiv2026

Cross-brain transfer of high-performance intracortical speech and handwriting BCIs

Intracortical brain-computer interfaces (BCIs) that decode complex movements, such as handwriting and speech, can require substantial training data to achieve high performance. We investigated whether leveraging the neural activity recordings of previous users could reduce this initial data collection burden for new BCI users (an approach we call "cross-brain transfer"). Using intracortical recordings from five BrainGate2 clinical trial participants, we tested cross-brain transfer for both speech and handwriting neural decoders trained and evaluated on general, unconstrained corpora of spoken and written English. We found that cross-brain transfer improved decoding performance when training data from the target user was limited (< 200 sentences), and that dataset-specific input layers to the decoder were critical for combining data across users. Without trainable input layers, transfer failed and performed worse than training from scratch on target user data only. Finally, we measured the effectiveness of cross-brain transfer relative to training with (1) more data from the same user and (2) more electrode-permuted data from the same user, which simulates sampling from another brain with identical neural latent structure. In some cases (T16 speech, T12 handwriting), cross-brain transfer appeared as effective as additional permuted data from the same user, while in others (T12 speech, T15 speech) electrode-permuted data was more beneficial. Our results successfully demonstrate and characterize cross-brain transfer learning between multiple intracortical BCI users, for both speech and handwriting, using a general open-ended dataset not restricted to small sets of words or phrases. This work highlights a promising path towards addressing a key barrier to the clinical translation of BCIs, while clarifying when cross-brain transfer may be most beneficial and the decoder design choices needed to realize those gains.

neuroscience↗

bioRxiv2026

High performance sorting of motor unit action potentials with EMUsort

Understanding how neural signals control muscle activity during behavior is a key challenge in motor neuroscience. To this end, recent advances in intramuscular multielectrode arrays have enabled high-quality multichannel recordings of many motor unit action potentials (MUAPs) in freely moving subjects. However, identifying individual MUAP events within multichannel recordings is a significant challenge for existing spike sorting methods, which are typically optimized for identifying action potentials from neurons in the brain. To overcome this challenge, we developed the Enhanced Motor Unit sorter (EMUsort), an extension of Kilosort4 (KS4) that achieves high-performance MUAP spike sorting. We applied EMUsort to high-resolution intramuscular recordings from rat forelimb during locomotion and monkey forelimb during a reaching task. EMUsort improves upon prior methods by addressing key challenges encountered with MUAP datasets, including: 1) long time delays across electrodes due to propagation along muscle fibers, 2) more complex waveform shapes compared to neuronal action potentials, and 3) a high degree of MUAP overlap due to cumulative motor unit recruitment. We compared EMUsort to existing spike sorting methods quantitatively using simulated datasets that closely emulated the rat and monkey datasets we recorded. EMUsort provided median error rate reductions of 67.5% and 49.9% during periods of high motor unit activation for the rat and monkey datasets, respectively. In sum, EMUsort provides a substantial improvement to MUAP spike sorter accuracy, especially during regions of high MUAP overlap, in an easy-to-use software package.

neuroscience↗

bioRxiv2025

Preparatory encoding of diverse features of intended movement in the human motor cortex

Over the course of a voluntary movement, motor cortical activity exhibits a transition from preparation to execution, with markedly different activity across these phases. Preparatory activity in particular might be used to improve brain-computer interfaces (BCIs) that harness brain activity to control external assistive devices, for example by anticipating a users intended movement trajectory for quick and fluid performance. However, to leverage preparatory activity for clinical BCIs, we must first understand which features of upcoming movements are encoded by preparatory activity in humans. In this work, we collected intracortical recordings from 3 research participants in the BrainGate2 clinical trial to investigate whether diverse features of movement, such as direction, curvature, and distance, are encoded by preparatory activity in the human motor cortex. We first show that preparatory activity is tuned to the direction of upcoming movements, and this tuning is largely preserved across movements with different effectors. Further investigation demonstrated this preparatory activity is also informative of initial and endpoint directions of curved movement trajectories, and encodes movement distance and speed independently. Finally, we present an online control paradigm that leverages preparatory activity to predict movements towards intended directions in advance, yielding rapid, self-paced control of a computer cursor by human participants. Altogether, these results demonstrate that preparatory activity in the human motor cortex encodes rich features of upcoming movement, highlighting its potential use for high performance brain-computer interface applications.

neuroscience↗

bioRxiv2025

Behavioral Signature of Trihexyphenidyl in The Tor1a (DYT1) Knockin Mouse Model of Dystonia

Dystonia is a neurological disorder characterized by involuntary repetitive movements and abnormal postures. Animal models have played a pivotal role in studying the pathophysiology of dystonia. However, many genetic models, e.g. the Tor1a+/{Delta}E (DYT1) mouse, lack an overt motor phenotype, despite significant underlying neuronal abnormalities within the striatum and other motor control regions. Because the striatum is implicated in action sequencing, it is possible that the behavioral defect arises as a disruption in the frequency and temporal ordering of behaviors, rather than execution, which cannot be captured using traditional behavioral assays, thus limiting drug discovery efforts. To address this challenge, we used MoSeq, an unsupervised behavioral segmentation framework, to compare the continuous free behavior of control Tor1a+/+ mice and knockin Tor1a+/{Delta}E mutant mice in response to the anti-dystonia drug trihexyphenidyl. Although minimal baseline differences in behavioral organization were detected, both genotypes exhibited robust and consistent shifts in behavioral space structure after treatment with trihexyphenidyl. Further, we demonstrate differences in the behavioral space structure of male vs female mice after trihexyphenidyl challenge. The distinct behavioral signatures evoked by trihexyphenidyl and biological sex, a known risk factor for dystonia, suggest that the analysis of the temporal structure of continuous free behavior provides a sensitive and novel approach to the discovery of therapeutics for the treatment of dystonia.

neuroscience↗

bioRxiv2025

Encoding of speech modes and loudness in ventral precentral gyrus

The ability to vary the mode and loudness of speech is an important part of the expressive range of human vocal communication. However, the encoding of these behaviors in the ventral precentral gyrus (vPCG) has not been studied at the resolution of neuronal firing rates. We investigated this in two participants who had intracortical microelectrode arrays implanted in their vPCG as part of a speech neuroprosthesis clinical trial. Neuronal firing rates modulated strongly in vPCG as a function of attempted mimed, whispered, normal or loud speech. At the neural ensemble level, mode/loudness and phonemic content were encoded in distinct neural subspaces. Attempted mode/loudness could be decoded from vPCG with an accuracy of 94% and 89% for two participants respectively, and corresponding neural preparatory activity could be detected hundreds of milliseconds before speech onset. We then developed a closed-loop loudness decoder that achieved 94% online accuracy in modulating a brain-to-text speech neuroprosthesis output based on attempted loudness. These findings demonstrate the feasibility of decoding mode and loudness from vPCG, paving the way for speech neuroprostheses capable of synthesizing more expressive speech.

neuroscience↗

bioRxiv2025

Computation-through-Dynamics Benchmark: Simulated datasets and quality metrics for dynamical models of neural activity

A primary goal of systems neuroscience is to discover how ensembles of neurons transform inputs into goal-directed behavior, a process known as neural computation. A powerful framework for understanding neural computation uses neural dynamics - the rules that govern how neural activity evolves over time - to explain how goal-directed input-output transformations occur. As dynamical rules are not directly observable, we need computational models that can infer neural dynamics from recorded neural activity. We typically validate such models using synthetic datasets with known ground-truth dynamics, but unfortunately existing synthetic datasets dont reflect fundamental features of neural computation and may therefore be poor proxies for neural systems. Further, the field lacks validated metrics for quantifying the accuracy of the dynamics inferred by models. The Computation-through-Dynamics Toolkit (CtDToolkit) addresses these critical gaps by providing: 1) synthetic datasets that reflect computational properties of biological neural circuits, 2) interpretable metrics for quantifying model performance, and 3) a standardized pipeline for training and evaluating models with or without known external inputs. In this manuscript, we demonstrate how CtDToolkit can help guide the development, tuning, and troubleshooting of neural dynamics models. In summary, CtDToolkit provides a necessary framework for model developers to better understand and characterize neural computation through the lens of dynamics. Author SummaryUnderstanding how the brain works requires interpretable accounts of how populations of neurons process information to produce behavior. One powerful approach is to study "neural dynamics", the patterns of how neural activity evolves over time. Scientists develop computational models to infer these dynamics from neural recordings, but it has been challenging to know when the inferred dynamics are trustworthy. Existing datasets often lack key features of biological neural circuits, and current performance metrics can provide an incomplete picture of model quality. We developed the Computation-through-Dynamics Toolkit (CtDToolkit) to solve these problems. Our toolkit provides three key resources: biologically motivated synthetic datasets, improved metrics that provide more holistic accounts of model performance, and a standardized workflow for training and evaluating models. We hope that CtDToolkit enables researchers to rigorously test, improve, and troubleshoot their models before applying them to real brain data. This work establishes a crucial foundation for developing better methods to understand neural computation, ultimately advancing our ability to decode how the brain transforms sensory information into thought and action.

neuroscience↗

bioRxiv2024

Representation of Verbal Thought in Motor Cortex and Implications for Speech Neuroprostheses

Speech brain-computer interfaces show great promise in restoring communication for people who can no longer speak1-3, but have also raised privacy concerns regarding their potential to decode private verbal thought4-6. Using multi-unit recordings in three participants with dysarthria, we studied the representation of inner speech in the motor cortex. We found a robust neural encoding of inner speech, such that individual words and continuously imagined sentences could be decoded in real-time This neural representation was highly correlated with overt and perceived speech. We investigated the possibility of "eavesdropping" on private verbal thought, and demonstrated that verbal memory can be decoded during a non-speech task. Nevertheless, we found a neural "overtness" dimension that can help to avoid any unintentional decoding. Together, these results demonstrate the strong representation of verbal thought in the motor cortex, and highlight important design considerations and risks that must be addressed as speech neuroprostheses become more widespread.

neuroscience↗

bioRxiv2024

A mosaic of whole-body representations in human motor cortex

Understanding how the body is represented in motor cortex is key to understanding how the brain controls movement. The precentral gyrus (PCG) has long been thought to contain largely distinct regions for the arm, leg and face (represented by the "motor homunculus"). However, mounting evidence has begun to reveal a more intermixed, interrelated and broadly tuned motor map. Here, we revisit the motor homunculus using microelectrode array recordings from 20 arrays that broadly sample PCG across 8 individuals, creating a comprehensive map of human motor cortex at single neuron resolution. We found whole-body representations throughout all sampled points of PCG, contradicting traditional leg/arm/face boundaries. We also found two speech-preferential areas with a broadly tuned, orofacial-dominant area in between them, previously unaccounted for by the homunculus. Throughout PCG, movement representations of the four limbs were interlinked, with homologous movements of different limbs (e.g., toe curl and hand close) having correlated representations. Our findings indicate that, while the classic homunculus aligns with each areas preferred body region at a coarse level, at a finer scale, PCG may be better described as a mosaic of functional zones, each with its own whole-body representation.

neuroscience↗

bioRxiv2024

Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark

Intracortical brain-computer interfaces (iBCIs) can restore movement and communication abilities to individuals with paralysis by decoding their intended behavior from neural activity recorded with an implanted device. While this activity yields high-performance decoding over short timescales, neural data are often nonstationary, which can lead to decoder failure if not accounted for. To maintain performance, users must frequently recalibrate decoders, which requires the arduous collection of new neural and behavioral data. Aiming to reduce this burden, several approaches have been developed that either limit recalibration data requirements (few-shot approaches) or eliminate explicit recalibration entirely (zero-shot approaches). However, progress is limited by a lack of standardized datasets and comparison metrics, causing methods to be compared in an ad hoc manner. Here we introduce the FALCON benchmark suite (Few-shot Algorithms for COnsistent Neural decoding) to standardize evaluation of iBCI robustness. FALCON curates five datasets of neural and behavioral data that span movement and communication tasks to focus on behaviors of interest to modern-day iBCIs. Each dataset includes calibration data, optional few-shot recalibration data, and private evaluation data. We implement a flexible evaluation platform which only requires user-submitted code to return behavioral predictions on unseen data. We also seed the benchmark by applying baseline methods spanning several classes of possible approaches. FALCON aims to provide rigorous selection criteria for robust iBCI decoders, easing their translation to real-world devices. https://snel-repo.github.io/falcon/

neuroscience↗

bioRxiv2024

Spinal interneuron population dynamics underlying flexible pattern generation

The mammalian spinal locomotor network is composed of diverse populations of interneurons that collectively orchestrate and execute a range of locomotor behaviors. Despite the identification of many classes of spinal interneurons constituting the locomotor network, it remains unclear how the networks collective activity computes and modifies locomotor output on a step-by-step basis. To investigate this, we analyzed lumbar interneuron population recordings and multi-muscle electromyography from spinalized cats performing air stepping and used artificial intelligence methods to uncover state space trajectories of spinal interneuron population activity on single step cycles and at millisecond timescales. Our analyses of interneuron population trajectories revealed that traversal of specific state space regions held millisecond-timescale correspondence to the timing adjustments of extensor-flexor alternation. Similarly, we found that small variations in the path of state space trajectories were tightly linked to single-step, microvolt-scale adjustments in the magnitude of muscle output. One sentence summaryFeatures of spinal interneuron state space trajectories capture variations in the timing and magnitude of muscle activations across individual step cycles, with precision on the scales of milliseconds and microvolts respectively.

neuroscience↗

bioRxiv2023

Pseudo-linear Summation explains Neural Geometry of Multi-finger Movements in Human Premotor Cortex

How does the motor cortex combine simple movements (such as single finger flexion/extension) into complex movements (such hand gestures or playing piano)? Motor cortical activity was recorded using intracortical multi-electrode arrays in two people with tetraplegia as they attempted single, pairwise and higher order finger movements. Neural activity for simultaneous movements was largely aligned with linear summation of corresponding single finger movement activities, with two violations. First, the neural activity was normalized, preventing a large magnitude with an increasing number of moving fingers. Second, the neural tuning direction of weakly represented fingers (e.g. middle) changed significantly as a result of the movement of other fingers. These deviations from linearity resulted in non-linear methods outperforming linear methods for neural decoding. Overall, simultaneous finger movements are thus represented by the combination of individual finger movements by pseudo-linear summation.

neuroscience↗

bioRxiv2023

BRAND: A platform for closed-loop experiments with deep network models

Artificial neural networks (ANNs) are state-of-the-art tools for modeling and decoding neural activity, but deploying them in closed-loop experiments with tight timing constraints is challenging due to their limited support in existing real-time frameworks. Researchers need a platform that fully supports high-level languages for running ANNs (e.g., Python and Julia) while maintaining support for languages that are critical for low-latency data acquisition and processing (e.g., C and C++). To address these needs, we introduce the Backend for Realtime Asynchronous Neural Decoding (BRAND). BRAND comprises Linux processes, termed nodes, which communicate with each other in a graph via streams of data. Its asynchronous design allows for acquisition, control, and analysis to be executed in parallel on streams of data that may operate at different timescales. BRAND uses Redis to send data between nodes, which enables fast inter-process communication and supports 54 different programming languages. Thus, developers can easily deploy existing ANN models in BRAND with minimal implementation changes. In our tests, BRAND achieved <600 microsecond latency between processes when sending large quantities of data (1024 channels of 30 kHz neural data in 1-millisecond chunks). BRAND runs a brain-computer interface with a recurrent neural network (RNN) decoder with less than 8 milliseconds of latency from neural data input to decoder prediction. In a real-world demonstration of the system, participant T11 in the BrainGate2 clinical trial performed a standard cursor control task, in which 30 kHz signal processing, RNN decoding, task control, and graphics were all executed in BRAND. This system also supports real-time inference with complex latent variable models like Latent Factor Analysis via Dynamical Systems. By providing a framework that is fast, modular, and language-agnostic, BRAND lowers the barriers to integrating the latest tools in neuroscience and machine learning into closed-loop experiments.

neuroscience↗

bioRxiv2023

Identifying distinct neural features between the initial and corrective phases of precise reaching using AutoLFADS

Many initial movements require subsequent corrective movements, but how motor cortex transitions to make corrections and how similar the encoding is to initial movements is unclear. In our study, we explored how the brains motor cortex signals both initial and corrective movements during a precision reaching task. We recorded a large population of neurons from two male rhesus macaques across multiple sessions to examine the neural firing rates during not only initial movements but also subsequent corrective movements. AutoLFADS, an auto-encoder-based deep-learning model, was applied to provide a clearer picture of neurons activity on individual corrective movements across sessions. Decoding of reach velocity generalized poorly from initial to corrective submovements. Unlike initial movements, it was challenging to predict the velocity of corrective movements using traditional linear methods in a single, global neural space. We identified several locations in the neural space where corrective submovements originated after the initial reaches, signifying firing rates different than the baseline before initial movements. To improve corrective movement decoding, we demonstrate that a state-dependent decoder incorporating the population firing rates at the initiation of correction improved performance, highlighting the diverse neural features of corrective movements. In summary, we show neural differences between initial and corrective submovements and how the neural activity encodes specific combinations of velocity and position. These findings are inconsistent with assumptions that neural correlations with kinematic features are global and independent, emphasizing that traditional methods often fall short in describing these diverse neural processes for online corrective movements. Significance StatementWe analyzed submovement neural population dynamics during precision reaching. Using an auto- encoder-based deep-learning model, AutoLFADS, we examined neural activity on a single-trial basis. Our study shows distinct neural dynamics between initial and corrective submovements. We demonstrate the existence of unique neural features within each submovement class that encode complex combinations of position and reach direction. Our study also highlights the benefit of state-specific decoding strategies, which consider the neural firing rates at the onset of any given submovement, when decoding complex motor tasks such as corrective submovements.

bioengineering↗

bioRxiv2022

Stabilizing brain-computer interfaces through alignment of latent dynamics

Intracortical brain-computer interfaces (iBCIs) restore motor function to people with paralysis by translating brain activity into control signals for external devices. In current iBCIs, instabilities at the neural interface result in a degradation of decoding performance, which necessitates frequent supervised recalibration using new labeled data. One potential solution is to use the latent manifold structure that underlies neural population activity to facilitate a stable mapping between brain activity and behavior. Recent efforts using unsupervised approaches have improved iBCI stability using this principle; however, existing methods treat each time step as an independent sample and do not account for latent dynamics. Dynamics have been used to enable high performance prediction of movement intention, and may also help improve stabilization. Here, we present a platform for Nonlinear Manifold Alignment with Dynamics (NoMAD), which stabilizes iBCI decoding using recurrent neural network models of dynamics. NoMAD uses unsupervised distribution alignment to update the mapping of nonstationary neural data to a consistent set of neural dynamics, thereby providing stable input to the iBCI decoder. In applications to data from monkey motor cortex collected during motor tasks, NoMAD enables accurate behavioral decoding with unparalleled stability over weeks-to months-long timescales without any supervised recalibration.

neuroscience↗

bioRxiv2021

Estimating muscle activation from EMG using deep learning-based dynamical systems models

ObjectiveTo study the neural control of movement, it is often necessary to estimate how muscles are activated across a variety of behavioral conditions. However, estimating the latent command signal that underlies muscle activation is challenging due to its complex relation with recorded electromyographic (EMG) signals. Common approaches estimate muscle activation independently for each channel or require manual tuning of model hyperparameters to optimally preserve behaviorally-relevant features. ApproachHere, we adapted AutoLFADS, a large-scale, unsupervised deep learning approach originally designed to de-noise cortical spiking data, to estimate muscle activation from multi-muscle EMG signals. AutoLFADS uses recurrent neural networks (RNNs) to model the spatial and temporal regularities that underlie multi-muscle activation. Main ResultsWe first tested AutoLFADS on muscle activity from the rat hindlimb during locomotion, and found that it dynamically adjusts its frequency response characteristics across different phases of behavior. The model produced single-trial estimates of muscle activation that improved prediction of joint kinematics as compared to low-pass or Bayesian filtering. We also tested the generality of the approach by applying AutoLFADS to monkey forearm muscle activity from an isometric task. AutoLFADS uncovered previously uncharacterized high-frequency oscillations in the EMG that enhanced the correlation with measured force compared to low-pass or Bayesian filtering. The AutoLFADS-inferred estimates of muscle activation were also more closely correlated with simultaneously-recorded motor cortical activity than other tested approaches. SignificanceUltimately, this method leverages both dynamical systems modeling and artificial neural networks to provide estimates of muscle activation for multiple muscles that can be used for further studies of multi-muscle coordination and its control by upstream brain areas.

neuroscience↗

bioRxiv2021

A deep learning framework for inference of single-trial neural population activity from calcium imaging with sub-frame temporal resolution

In many brain areas, neural populations act as a coordinated network whose state is tied to behavior on a moment-by-moment basis and millisecond timescale. Two-photon (2p) calcium imaging is a powerful tool to probe network-scale computation, as it can measure the activity of many individual neurons, monitor multiple cortical layers simultaneously, and sample from identified cell types. However, estimating network state and dynamics from 2p measurements has proven challenging because of noise, inherent nonlinearities, and limitations on temporal resolution. Here we describe RADICaL, a deep learning method to overcome these limitations at the population level. RADICaL extends methods that exploit dynamics in spiking activity for application to deconvolved calcium signals, whose statistics and temporal dynamics are quite distinct from electrophysiologically-recorded spikes. It incorporates a novel network training strategy that capitalizes on the timing of 2p sampling to recover network dynamics with high temporal precision. In synthetic tests, RADICaL infers network state more accurately than previous methods, particularly for high-frequency components. In real 2p recordings from sensorimotor areas in mice performing a "water grab" task, RADICaL infers network state with close correspondence to single-trial variations in behavior, and maintains high-quality inference even when neuronal populations are substantially reduced.

neuroscience↗