SEARCH · PubMed Health

Results for “representation learning”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5Linked to original sources

PubMed2026

Toward AI Virtual Cells for Hepatology: Representation, Generation, Dynamics, and Intervention in Single-Cell Models.

``Single-cell and spatial atlases describe the healthy and diseased liver at high resolution, including lobular hepatocyte zonation, fibrotic macrophage-stellate niches, cholangiocyte reactions, immune remodeling, and hepatocellular carcinoma ecosystems. These maps show where cell states occur but do not, by themselves, predict whether liver injury will progress or how the liver will respond to an untested drug, toxicant, or genetic perturbation. In this review, we organize current approaches toward an AI Virtual Cell (AIVC) for the liver into three complementary modeling routes. Generative models represent cell states, dynamics and transport models infer state transitions, and pretrained or foundation models test whether learned representations transfer across donors, etiologies, disease stages, and platforms. Perturbation-response prediction serves as a cross-cutting assessment of whether these layers can predict responses to untested genetic, chemical, inflammatory, or metabolic interventions. Available evidence can be categorized as direct liver validation, liver-included benchmarks, general single-cell evidence, and conceptual applications. Published models demonstrate individual components, including atlas integration, inferred trajectories, transferable representations, and retrospective response programs. However, these models do not constitute a prospectively validated liver simulator. At minimum, evaluation should include donor-, etiology-, stage-, platform-, and perturbation-level hold-outs. Model performance should be reported using response direction, recovery of differentially expressed genes and rare states, and calibrated uncertainty. Claims about tissue- or function-level prediction additionally require independent spatial, histologic, metabolic, and functional readouts. Near-term use should prioritize experiment selection and hypothesis generation, whereas clinical decision support remains a longer-term objective.

AI Virtual Cell↗

PubMed1995

What does the hippocampus really do?

Much of the evidence used to implicate the hippocampus in learning and memory has been obtained from clinical cases and/or experimental studies with animals where the damage is extensive and includes more than just the hippocampus. When the damage is limited to the cells that comprise the hippocampus (CA1-CA3 pyramidal cells, hilar and granule cells in the dentate gyrus) the effect on behavior in the rat is more limited than what is usually reported. Selective, axon-sparing ibotenic acid lesions of the hippocampus were used in the experiments that are reviewed to study the effects of removing the hippocampus on: (1) the acquisition of spatial and non-spatial information; (2) complex, non-spatial representational learning; and (3) acquisition and utilization of contextual information. The results indicated that rats with the hippocampus removed were impaired on those tasks that require the utilization of spatial and contextual information but performed like controls in learning about and handling (even complex) non-spatial information. Future research utilizing selective lesions of the hippocampus and sensitive behavioral testing techniques should help clarify the extent to which the impairments in the acquisition of spatial information and the ability to utilize contextual, background cues can be reduced to a single, underlying learning process.

Animals↗

PubMed2026

Biological Foundation Models for Complex Disease Research and Clinical Translation.

Complex diseases, including cancer, rare genetic disorders, neurodevelopmental and psychiatric conditions, and neurodegenerative diseases, arise from interactions among genetic variation, gene regulation, and cellular states that are difficult to capture using a single data type or biological scale. Biological foundation models address this challenge by treating nucleotides and genes as tokens and learning representations that can be transferred to downstream biomedical and clinical tasks. In this review, we examine two major model classes, genomic sequence foundation models and cell foundation models, and compare their tokenization strategies, model architectures, pretraining objectives, and adaptation methods. We summarize their emerging applications in regulatory variant interpretation, disease-associated cell-state analysis, drug-response prediction, and therapeutic target discovery across complex diseases. We distinguish applications supported by experimental or retrospective validation from those that remain primarily computational or conceptual. We further discuss key challenges to clinical translation, including multimodal data integration, model interpretability, benchmarking, patient-specific prediction, and privacy protection. We highlight future opportunities to integrate biological foundation models with emerging frameworks of medical digital twins, agentic AI, and federated learning. By linking model design to translational goals, this review provides a practical framework for evaluating biological foundation models and their readiness for complex disease research and clinical use.

biological foundation model↗

PubMed1988

Crossed buccofacial apraxia.

The cerebral hemisphere contralateral to the preferred hand is generally dominant for learned representational motor acts, including those involving buccofacial muscles. It is generally also language-dominant. This buccofacial apraxia has, with rare exceptions, been associated with left hemispheric lesions in right-handers. We describe two patients with severe buccofacial apraxia caused by large middle cerebral artery territory infarcts in the hemisphere ipsilateral to the preferred hand and nondominant for language. Neither patient had aphasia or major limb apraxia. Computed tomographic scans in the first patient and neuropathologic examination in the second failed to reveal an abnormality of the hemisphere contralateral to the preferred hand. Hence, in some individuals, the hemisphere controlling skilled representational buccofacial movements may not be the one that is dominant either for handedness or for language.

Aged↗

PubMed2026

Atlas-level single-cell integration and clustering-free differential expression analysis with GEDI 2.0.

MOTIVATION: GEDI is a generative framework for multi-sample, multi-condition single-cell analysis that performs batch correction, latent representation learning, and clustering-free differential expression within a unified model. However, the original implementation suffered from prohibitive memory use and runtime, preventing its application to modern atlas-scale datasets. RESULTS: We present GEDI 2.0, a complete high-performance reimplementation featuring a standalone C++ computational core with pre-allocated workspaces, strict sparse-matrix preservation, optimized BLAS routines, and multi-threaded block-coordinate descent. Across extensive benchmarks spanning up to 500 000 cells and 10 000 features, GEDI 2.0 achieves 40%-63.6% mean reduction in peak memory, 2.98× mean single-threaded speedups, and up to 11.5× acceleration with parallel execution, while maintaining full numerical equivalence to the original method. These improvements enable GEDI 2.0 to analyze million-cell datasets, a scale not achievable with the legacy implementation. GEDI 2.0 provides R and Python interfaces and seamless interoperability with common single-cell workflows. AVAILABILITY AND IMPLEMENTATION: Source code, documentation, reproducible codebase, and tutorials are available at https://github.com/csglab/gedi2.

Single-Cell Analysis↗

PubMed2026

ARISE: RNA-anchored shared-edge topology and hierarchical fusion for spatial multi-omics integration.

MOTIVATION: Spatial multi-omics technologies jointly profile transcriptomes, proteins and chromatin accessibility in situ, enabling integrative analysis of tissue organization across molecular layers. However, most existing graph-based integration methods rely on independently constructed modality-specific k-nearest-neighbor graphs. When auxiliary modalities are sparse or noisy, these graphs can become topologically discordant, propagate spurious edges, weaken cross-modal alignment, and reduce spatial domain resolution. RESULTS: We present Anchored RNA for Integrated Spatial Embedding (ARISE), an RNA expression anchored framework for spatial multi-omics integration. ARISE defines a shared-edge topology by intersecting RNA feature-similarity and spatial-proximity graphs, encodes auxiliary modalities on this common scaffold, and integrates them through inside-out hierarchical fusion. We further show theoretically that graph intersection minimizes false-positive edges within a broad class of k-of-r graph fusion rules, providing a principled basis for topology anchoring. Across various spatial multi-omics benchmarks spanning simulated and real datasets in bi-modal and tri-modal settings, ARISE improves spatial domain identification, cross-modal consistency, and preservation of tissue structure relative to existing methods. Furthermore, the learned representation supports biologically meaningful downstream analyses, including marker-based domain annotation, pathway enrichment, and cis-regulatory inference, indicating that ARISE yields a robust and interpretable framework for spatial multi-omics integration. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/XiangxiangWang-code/ARISE. The archived version used in this study is available at https://doi.org/10.6084/m9.figshare.32686137.v2.

Multiomics↗

PubMed1995

Learning a visuomotor transformation in a local area of work space produces directional biases in other areas.

1. The dependence of directional biases in reaching movements on the initial position of the hand was studied in normal human subjects moving their unseen hand on a horizontal digitizing tablet to visual targets displayed on a vertical computer screen. 2. When initial hand positions were to the right of midline, movements were systematically biased clockwise. Biases were counterclockwise for starting points to the left. Biases were unaffected by the screen location of the starting and target positions. 3. Vision of the hand in relation to the target before movement, as well as practice with vision of the cursor during the movement, temporarily eliminated these biases. The spatial organization of the biases suggests that, without vision of the limb, the nervous system underestimates the distance of the hand from an axis or plane that includes its most common operating location. 4. To test the hypothesis that such an underestimate might represent an adaptation to a local area of work space or range effect, subjects were trained to reach accurately from right or left positions. After training, movements initiated from other locations, including ones that were previously error free, showed new biases that again represented underestimates of the distance of the initial hand position from the new trained location. 5. We conclude that hand path planning is dependent on learned representations of the location of the hand in the work space.

Adult↗

PubMed2026

Large language models in bioinformatics: a comprehensive survey.

The emergence of foundation models with trillion-level parameters has redefined the landscape of artificial intelligence. Various fields are developing their own large-scale models, which can solve many problems within the field and improve work efficiency. Biological large-scale models are a cross-disciplinary research field that combines mathematics, computer science, and biology, aiming to simulate and understand the structure, function, and dynamic changes of biological systems through the establishment of complex computational models. This field covers multiple levels such as biological pathways, population dynamics, protein folding, etc., providing us with tools for deep exploration of the mysteries of life and applications in medicine, ecology, and other fields. This article reviews the background and research status of biological large-scale models, and discusses future directions. Large language models (LLMs) and other large-scale foundation models have rapidly advanced in recent years, enabling powerful representation learning and generation across text, sequences, and multimodal data. In bioinformatics and biomedicine, these models are increasingly used to analyze genomic sequences, infer protein properties and structures, support drug discovery, and integrate heterogeneous biomedical evidence. This survey reviews the basic principles of LLMs and summarizes representative applications in (i) gene and genome sequence analysis, (ii) protein structure and function prediction, and (iii) drug design, including virtual screening and personalized medicine. We also discuss emerging multi-model modeling approaches, as well as key challenges such as data quality and privacy, interpretability, generalization to new organisms and tasks, and responsible deployment in health-related settings. Finally, we outline future directions for developing reliable, scalable, and explainable bioinformatics foundation models.

bioinformatics↗

PubMed2003

Different roles for orbitofrontal cortex and basolateral amygdala in a reinforcer devaluation task.

The orbitofrontal cortex (OFC) and basolateral amygdala (BLA) are critical for using learned representations of outcomes to guide behavior. Neurophysiological findings suggest complementary roles in which the BLA acquires associations between cues and outcomes and the OFC subsequently uses them to guide behavior. Here, we have used a reinforcer devaluation paradigm to test this hypothesis. In this paradigm, rats are first trained to associate a light conditioned stimulus (CS) with a food outcome, and then the food is devalued by pairing it with illness. After this devaluation procedure, responding to the CS is assessed in a single probe session. Previously, we have shown that BLA and OFC lesions made before training do not affect the acquisition of conditioned responding but do impair the sensitivity of that responding to reinforcer devaluation. Rats with such lesions fail to exhibit the spontaneous decrease in conditioned responding to the light cue observed in controls in the probe test. Here, we have extended those findings by showing that performance in the probe test is impaired by OFC lesions made after light-food conditioning but not by BLA lesions made after that training. These findings indicate that the OFC and BLA play different roles in mediating normal goal-directed performance in this, and likely other, settings. The BLA seems critical to forming representations linking cues to the incentive properties of outcomes but not for maintaining these representations in memory, updating them with new information, or for expressing them in behavior. In contrast, the OFC seems essential for one or more of these latter processes.

Amygdala↗

PubMed2001

Are grammatical representations useful for learning from biological sequence data?--a case study.

This paper investigates whether Chomsky-like grammar representations are useful for learning cost-effective, comprehensible predictors of members of biological sequence families. The Inductive Logic Programming (ILP) Bayesian approach to learning from positive examples is used to generate a grammar for recognising a class of proteins known as human neuropeptide precursors (NPPs). Collectively, five of the co-authors of this paper, have extensive expertise on NPPs and general bioinformatics methods. Their motivation for generating a NPP grammar was that none of the existing bioinformatics methods could provide sufficient cost-savings during the search for new NPPs. Prior to this project experienced specialists at SmithKline Beecham had tried for many months to hand-code such a grammar but without success. Our best predictor makes the search for novel NPPs more than 100 times more efficient than randomly selecting proteins for synthesis and testing them for biological activity. As far as these authors are aware, this is both the first biological grammar learnt using ILP and the first real-world scientific application of the ILP Bayesian approach to learning from positive examples. A group of features is derived from this grammar. Other groups of features of NPPs are derived using other learning strategies. Amalgams of these groups are formed. A recognition model is generated for each amalgam using C4.5 and C4.5rules and its performance is measured using both predictive accuracy and a new cost function, Relative Advantage (RA). The highest RA was achieved by a model which includes grammar-derived features. This RA is significantly higher than the best RA achieved without the use of the grammar-derived features. Predictive accuracy is not a good measure of performance for this domain because it does not discriminate well between NPP recognition models: despite covering varying numbers of (the rare) positives, all the models are awarded a similar (high) score by predictive accuracy because they all exclude most of the abundant negatives.

Bayes Theorem↗

PubMed2006

Object recognition learning differentiates the representations of objects at the ERP component N1.

OBJECTIVE: Even if viewed from different angles, one can identify an object among similar distractors through learning. This study was designed to investigate the changes in neuronal activity related to learning. METHODS: Human subjects were asked to train themselves with novel objects by performing an object recognition task, in which the images of an object had to be discriminated from those of other objects regardless of the viewpoint. RESULTS: The ERP component-N1, the first negative peak at posterior electrodes, showed a significant increase in the amplitude variation across the objects during the learning process, while the variation across viewpoints decreased. CONCLUSIONS: These results suggest that object recognition learning differentiates between the representations of the objects, at least, at the N1 level. SIGNIFICANCE: The results may support the notion that object recognition differentiates among the functional representations of the trained objects in our brain.

Adolescent↗

PubMed2006

Proactive interference as a result of persisting neural representations of previously learned motor skills in primary motor cortex.

Learning to control movements in different dynamic environments is marked by proactive interference; learning a first skill interferes with the subsequent learning of a second one. The neural basis of this effect is poorly understood. We tested the idea that proactive interference results from persisting neural representations of previously learned skills in the primary motor cortex (M1). We used repetitive transcranial magnetic stimulation (rTMS) of M1 to disrupt retention of a recently learned motor skill. If interference results from the retention of this skill then its disruption should be associated with reduced interference. Subjects reached to targets while interacting with a robotic arm that applied force fields to the limb. Fifteen minutes of 1-Hz rTMS to M1 impaired the retention of a first force field, and more importantly, reduced proactive interference when subjects learned a second one. Our findings suggest that retention and interference are linked at the level of M1.

Algorithms↗

PubMed2006

The role of discourse context in developing word form representations: a paradoxical relation between reading and learning.

To acquire representations of printed words, children must attend to the written form of a word and link this form with the word's pronunciation. When words are read in context, they may be read with less attention to these features, and this can lead to poorer word form retention. Two experiments with young children (ages 5-8 years) confirmed this hypothesis. In our experiments, children attempted to read words they could not previously read, during a self-teaching period, either in context or in isolation. Later they were tested on how well they learned the words as a function of self-teaching condition (isolation or context). Consistent with previous research, children read more words accurately in context than in isolation during self-teaching; however, children had better retention for words learned in isolation. Furthermore, this benefit from learning in isolation was larger for less skilled readers. This effect of poorer word retention when words are learned in context is paradoxical because context has been shown to facilitate word identification. We discuss factors that may influence this effect of context, especially the role of children's skill level and the demands of learning new word representations at the beginning of reading instruction.

Child↗

PubMed1996

Image representations for visual learning.

Computer vision researchers are developing new approaches to object recognition and detection that are based almost directly on images and avoid the use of intermediate three-dimensional models. Many of these techniques depend on a representation of images that induce a linear vector space structure and in principle requires dense feature correspondence. This image representation allows the use of learning techniques for the analysis of images (for computer vision) as well as for the synthesis of images (for computer graphics).

Artificial Intelligence↗

PubMed2003

The effect of category learning on the representation of shape: dimensions can be biased but not differentiated.

Recent studies have suggested a profound influence of category learning on visual perception, resulting in independent processing of previously integral dimensions. The authors reinvestigate this issue for shape dimensions. They first extend previous findings that some shape dimensions (aspect ratio and curvature) are processed in a separable way, whereas others (radial frequency components) are not. They then show that a category-learning phase improved the discrimination of a relevant with respect to an irrelevant dimension, but only for separable dimensions. No similar effect was found on the relative sensitivity for integral shape dimensions. Thus, category learning is capable of biasing separable shape dimensions but does not alter the status of dimensions in the visual system as either separable or integral.

Discrimination, Psychological↗

PubMed2001

Linear constraints on weight representation for generalized learning of multilayer networks.

In this article, we present a technique to improve the generalization ability of multilayer neural networks. The proposed method introduces linear constraints on weight representation based on the invariance natures of training targets. We propose a learning method that introduces effective linear constraints into an error function as a penalty term. Furthermore, introduction of such constraints leads to reduction of the VC dimension of neural networks. We show bounds on the VC dimension of the neural networks with such constraints. Finally, we demonstrate the effectiveness of the proposed method by some experiments.

Algorithms↗

PubMed1994

[Experimental test of a model of memory-representation-generation in learning and recognition].

A highly structured set of stimuli was used in this study. Each stimulus had four binary attributes, whose values were determined so that any two stimuli could be transformed into each other by changing values of one or more attributes. In one experiment, 93 undergraduates rated similarity of paired stimuli. In another experiment, the same subjects learned three stimuli which were presented one after another for 10 seconds each. Later, in the recognition task, they made "old" or "new" judgment and rated the confidence of their judgment for each of the test stimuli. Two groups of subjects served the two experiments in different order. The results showed that (1) the rated similarity between the paired stimuli is a monotonically decreasing function of the number of transformations needed to get the pair equal, (2) the recognition confidence for new stimuli is significantly higher for stimuli generated by relevant transformations from the learned stimuli than for stimuli not so generated. The results support a model of memory-representation-generation (Suto, 1987, 1988), but not "prototype plus transformation model" nor "context model".

Adult↗

PubMed2005

Distinct neural systems underlie learning visuomotor and spatial representations of motor skills.

Motor skill learning depends upon acquiring knowledge about multiple features of sequential behaviors, including their visuomotor and spatial properties. To investigate the neural systems that distinguish these representations, we carried out functional magnetic resonance imaging (fMRI) as healthy adults learned to type sequences on a novel keyboard. On the initial training day, learning-related changes in brain activation were found in distributed cortical regions, only a subset of which correlated with improvements in movement time (MT), suggesting their preeminence in controlling movements online. Subjects received extended training on the sequences during the ensuing week, after which they returned to the scanner for another imaging session. Relative to performance at the end of the first training day, continued plasticity was most striking in the inferior parietal cortex and new areas of plasticity were uncovered in the caudate and cerebellum. Plasticity in these regions correlated with reaction time (RT), suggesting their role in planning sequences before movement onset. Two transfer conditions probed for "what" subjects learned. The probe for visuomotor learning produced increased activation in visual analysis (left inferior visual cortex) and advance planning (left caudate) systems. The probe for spatial learning produced increased activation in visuomotor-transformation (left dorsal visual pathway) and retrieval (left precuneus) systems. Increased activity in all of these regions correlated with increased RT, but not MT, indicating that both transfer conditions interfered with the neural representation of plans for the sequences, but not processes that controlled their implementation. These findings demonstrated that neuroanatomically dissociable systems support the acquisition of visuomotor and spatial representations of actions.

Adolescent↗