Biology subjects

Zhu, O.

Publications and source records attributed to Zhu, O..

9 recordsLinked to original sources

bioRxiv2026

A structured study of cross-condition prediction of transcriptional responses to gene perturbations

Gene perturbation experiments coupled with transcriptomic profiling are crucial for uncovering causal gene-gene relationships, yet it remains cost-prohibitive to systematically explore perturbation responses across diverse biological conditions. As a result, in silico prediction of perturbation response has emerged as an important strategy for guiding cost-effective experimental design. Although recent methods have begun to address cross-condition perturbation prediction, it remains under-characterized across scenarios defined by whether the perturbation has been observed during training under other biological conditions. Here, we study cross-condition prediction under both seen- and unseen-perturbation scenarios. We introduce TranScouter, a lightweight encoderdecoder framework that represents perturbed genes using LLM-derived embeddings of their text summaries and represents biological conditions using transcriptomic profiles of control cells from the target condition. Across evaluated benchmarks, TranScouter performs competitively in both scenarios. We further use empirical analyses to characterize how condition-space coverage and perturbation-effect transferability shape crosscondition performance.

bioinformatics↗

bioRxiv2026

Beyond Expression Prediction: Benchmarking Differential Expression Classification in Single-Cell Perturbation Models

Accurate predictions of transcriptomic responses to genetic perturbations could unlock our understanding of gene functions and regulatory networks. While a growing number of methods and benchmarks target this task, existing evaluations focus on mean expression accuracy alone. This overlooks differential expression (DE), which captures both mean and variance and forms the basis for biological interpretation and experimental follow-up. Here, we systematically evaluate a diverse set of deep learning and non-deep-learning methods for their ability to predict DE outcomes under two generalization regimes: unseen perturbations within the same cell line, and unseen cellular contexts across cell lines. We find that simple baselines, such as embedding-based nearest neighbors, are competitive and often outperform specialized deep learning models for DE classification across datasets and evaluation metrics. We further show that sparsity calibration, motivated by the structure of single-cell data, substantially improves DE classification for deep learning models that do not explicitly account for sparsity. Together, our findings establish practical baselines and evaluation principles for benchmarking perturbation models on DE prediction.

genomics↗

bioRxiv2026

Frontal Eye Field Leads a Distributed Oculomotor Circuit for Abstract Categorical Decisions

Flexible decisions require the brain to transform sensory evidence into abstract, task-relevant variables and then into actions. Understanding this process requires identifying how distributed neural populations represent sensory, cognitive, and motor variables, and how interareal interactions mediate transformations between them. We simultaneously recorded population activity in frontal eye field (FEF), lateral intraparietal area (LIP) and superior colliculus (SC) while monkeys performed a flexible yet urgent visual motion-categorization task. Within this network, FEF first encoded abstract categories, followed by SC and then LIP. LIP showed the earliest encoding of visual stimulus features, but a later encoding of upcoming saccades. Single-trial analyses revealed directed information flow from FEF to LIP populations for category-and choice-related signals. Reversible FEF inactivation impaired categorization and saccadic choice, causally implicating FEF in category-guided action. These findings reveal a differentiated FEF-LIP-SC circuit for transforming sensory evidence into abstract categorical decisions and the actions used to report them.

neuroscience↗

bioRxiv2024

scPDA: Denoising Protein Expression in Droplet-Based Single-Cell Data

Droplet-based profiling techniques such as CITE-seq measure the surface protein abundance of single cells, providing crucial information for cell-type identification. How-ever, these measurements are often significantly contaminated by technical noise, which lowers the efficiency of using the gating strategy to identify cell types. Current computational denoising methods have serious limitations, including a strong reliance on often-unavailable empty droplets or null controls, insufficient efficiency due to the ignoring of protein-protein interactions, and a heavy computational load. Here, we introduce scPDA, a new probabilistic model that employs a variational autoencoder to achieve high computational efficiency. scPDA completely eliminates the use of empty droplets, and it shares information across proteins to increase denoising efficiency. Compared to currently available methods, scPDA has removed noise much more thoroughly while preserving biological signals, and it has substantially improved the efficiency of gating-strategy-based cell-type identification, marking a clear advancement in the computational denoising of the protein modality.

bioinformatics↗

bioRxiv2024

Scouter: Predicting Transcriptional Responses to Genetic Perturbations with LLM embeddings

This paper addresses the challenging problem of predicting transcriptional outcomes-- the expression levels of all genes--in gene perturbation experiments and introduces a novel method called Scouter. By leveraging the capabilities of large language models and employing a neural network that facilitates easy training, Scouter overcomes key limitations of current approaches and accurately predicts the outcomes of single-gene and two-gene perturbations, reducing the error of state-of-the-art methods by half or more.

bioinformatics↗

bioRxiv2024

Neuronal firing rate diversity lowers the dimension of population covariability

Neuronal responses are very diverse, with specific stimuli or behaviors eliciting a range of activity across a neuronal population. These responses also show large and correlated trial-to-trial fluctuations that occupy a low-dimensional region in activity space. We link these two aspects of neuronal response in both feedforward and recurrent circuit models and derive the following relation: the more diverse the firing rates of neurons in a population, the lower the effective dimension of their trial-to-trial covariability. We test our prediction using simultaneously recorded neuronal populations from numerous brain areas in mice, non-human primates, and in the motor cortex of human participants. Finally, we show how diverse neural codes lead to better stimulus discrimination, and that when the brain is in a heightened state of processing responses are more diverse and have lower-dimensional fluctuations. In sum, we present an organizing principle of population response that is widely observed across the nervous system and acts to synergistically improve population representation.

neuroscience↗

bioRxiv2023

Primate superior colliculus is engaged in abstract higher-order cognition

Categorization is a fundamental cognitive process by which the brain assigns stimuli to behaviorally meaningful groups. Investigations of visual categorization in primates have identified a hierarchy of cortical areas that are involved in the transformation of sensory information into abstract category representations. However, categorization behaviors are ubiquitous across diverse animal species, even those without a neocortex, motivating the possibility that subcortical regions may contribute to abstract cognition in primates. One candidate structure is the superior colliculus (SC), an evolutionarily conserved midbrain region that, although traditionally thought to mediate only reflexive spatial orienting, is involved in cognitive tasks that require spatial orienting. Here, we reveal a novel role of the primate SC in abstract, higher-order visual cognition. We compared neural activity in the SC and the posterior parietal cortex (PPC), a region previously shown to causally contribute to category decisions, while monkeys performed a visual categorization task in which they report their decisions with a hand movement. The SC exhibits stronger and shorter-latency category encoding than the PPC, and inactivation of the SC markedly impairs monkeys category decisions. These results extend SCs established role in spatial orienting to abstract, non-spatial cognition.

neuroscience↗

bioRxiv2020

Interaction between neuronal encoding and population dynamics during categorization task switching in parietal cortex

Primates excel at categorization, a cognitive process for assigning stimuli into behaviorally relevant groups. Categories are encoded in multiple brain areas and tasks, yet it remains unclear how neural encoding and dynamics support cognitive tasks with different demands. We recorded from parietal cortex during flexible switching between categorization tasks with distinct cognitive and motor demands, and also studied recurrent neural networks (RNNs) trained on the same tasks. In the one-interval categorization task (OIC), monkeys rapidly reported their decisions with a saccade. In the delayed match-to-category (DMC) task, monkeys decided whether sequentially presented stimuli were categorical matches. Neuronal category encoding generalized across tasks, but categorical encoding was more binary-like in the DMC task and more graded in the OIC task. Furthermore, analysis of the trained RNNs supports the hypothesis that binary-like encoding in the DMC task arises through compression of graded feature encoding by population attractor dynamics underlying short-term working memory.

neuroscience↗

bioRxiv2020

Distributed functions of prefrontal and parietal cortices during sequential categorical decisions

The ability to compare sequential sensory inputs is crucial for solving many behavioral tasks. To understand the neuronal mechanisms underlying sequential decisions, we compared neuronal responses in the prefrontal cortex (PFC) and the lateral and medial intra-parietal (LIP and MIP) areas in monkeys trained to decide whether sequentially presented stimuli were from matching (M) or nonmatching (NM) categories. We found that PFC leads the M/NM decision process relying on nonlinear neuronal integration of sensory and mnemonic information, whereas LIP and MIP are more involved in sensory evaluation and motor planning, respectively. Furthermore, multi-module recurrent neural networks trained on the same task exhibited the key features of PFC and LIP encoding, including nonlinear integrative encoding in the PFC-like module which was crucial for M/NM decisions. Together, our results illuminate the relative functions of LIP, PFC, and MIP in sensory, cognitive and motor functions, and suggest that nonlinear integration of task-related variables in PFC is important for mediating sequential decisions.

neuroscience↗