Browse
Submit Data
Databases
API
Help

Dataset Information

22 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Towards deep learning with segregated dendrites.

ABSTRACT: Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the neocortex optimizes cost functions. Like neocortical pyramidal neurons, neurons in our model receive sensory information and higher-order feedback in electrotonically segregated compartments. Thanks to this segregation, neurons in different layers of the network can coordinate synaptic weight updates. As a result, the network learns to categorize images better than a single layer network. Furthermore, we show that our algorithm takes advantage of multilayer architectures to identify useful higher-order representations-the hallmark of deep learning. This work demonstrates that deep learning can be achieved using segregated dendritic compartments, which may help to explain the morphology of neocortical pyramidal neurons.

SUBMITTER: Guerguiev J

PROVIDER: S-EPMC5716677 | biostudies-literature | 2017 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Towards deep learning with segregated dendrites.

Guerguiev Jordan J Lillicrap Timothy P TP Richards Blake A BA

eLife 20171205

Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the neocortex optimizes cost functions. Like neocortical pyramidal neurons, neurons in our model receive sensory information and higher-order feedback in electrotonically ...[more]

PMID: 29205151

Similar Datasets

Towards calibration-invariant spectroscopy using deep learning.

Project description:The interaction between matter and electromagnetic radiation provides a rich understanding of what the matter is composed of and how it can be quantified using spectrometers. In many cases, however, the calibration of the spectrometer changes as a function of time (such as in electron spectrometers), or the absolute calibration may be different between different instruments. Calibration differences cause difficulties in comparing the absolute position of measured emission or absorption peaks between different instruments and even different measurements taken at different times on the same instrument. Present methods of avoiding this issue involve manual feature extraction of the original signal or qualitative analysis. Here we propose automated feature extraction using deep convolutional neural networks to determine the class of compound given only the shape of the spectrum. We classify three unique electronic environments of manganese (being relevant to many battery materials applications) in electron energy loss spectroscopy using 2001 spectra we collected in addition to testing on spectra from different instruments. We test a variety of commonly used neural network architectures found in the literature and propose a new fully convolutional architecture with improved translation-invariance which is immune to calibration differences.

| S-EPMC6376024 | biostudies-literature

Towards Interpretable Skin Lesion Classification with Deep Learning Models.

Project description:Skin disease is a prevalent condition all over the world. Computer vision-based technology for automatic skin lesion classification holds great promise as an effective screening tool for early diagnosis. In this paper, we propose an accurate and interpretable deep learning pipeline to achieve such a goal. Comparing with existing research, we would like to highlight the following aspects of our model. 1) Rather than a single model, our approach ensembles a set of deep learning architectures to achieve better classification accuracy; 2) Generative adversarial network (GAN) is involved in the model training to promote data scale and diversity; 3) Local interpretable model-agnostic explanation (LIME) strategy is applied to extract evidence from the skin images to support the classification results. Our experimental results on real-world skin image corpus demonstrate the effectiveness and robustness of our method. The explainability of our model further enhances its applicability in real clinical practice.

| S-EPMC7153112 | biostudies-literature

Deep learning of pharmacogenomics resources: moving towards precision oncology.

Project description:The recent accumulation of cancer genomic data provides an opportunity to understand how a tumor's genomic characteristics can affect its responses to drugs. This field, called pharmacogenomics, is a key area in the development of precision oncology. Deep learning (DL) methodology has emerged as a powerful technique to characterize and learn from rapidly accumulating pharmacogenomics data. We introduce the fundamentals and typical model architectures of DL. We review the use of DL in classification of cancers and cancer subtypes (diagnosis and treatment stratification of patients), prediction of drug response and drug synergy for individual tumors (treatment prioritization for a patient), drug repositioning and discovery and the study of mechanism/mode of action of treatments. For each topic, we summarize current genomics and pharmacogenomics data resources such as pan-cancer genomics data for cancer cell lines (CCLs) and tumors, and systematic pharmacologic screens of CCLs. By revisiting the published literature, including our in-house analyses, we demonstrate the unprecedented capability of DL enabled by rapid accumulation of data resources to decipher complex drug response patterns, thus potentially improving cancer medicine. Overall, this review provides an in-depth summary of state-of-the-art DL methods and up-to-date pharmacogenomics resources and future opportunities and challenges to realize the goal of precision oncology.

| S-EPMC7711267 | biostudies-literature

Towards perturbation prediction of biological networks using deep learning.

Project description:The mapping of the physical interactions between biochemical entities enables quantitative analysis of dynamic biological living systems. While developing a precise dynamical model on biological entity interaction is still challenging due to the limitation of kinetic parameter detection of the underlying biological system. This challenge promotes the needs of topology-based models to predict biochemical perturbation patterns. Pure topology-based model, however, is limited on the scale and heterogeneity of biological networks. Here we propose a learning based model that adopts graph convolutional networks to learn the implicit perturbation pattern factors and thus enhance the perturbation pattern prediction on the basic topology model. Our experimental studies on 87 biological models show an average of 73% accuracy on perturbation pattern prediction and outperforms the best topology-based model by 7%, indicating that the graph-driven neural network model is robust and beneficial for accurate prediction of the perturbation spread modeling and giving an inspiration of the implementation of the deep neural networks on biological network modeling.

| S-EPMC6697687 | biostudies-literature

Territories of heterologous inputs onto Purkinje cell dendrites are segregated by mGluR1-dependent parallel fiber synapse elimination.

Project description:In Purkinje cells (PCs) of the cerebellum, a single "winner" climbing fiber (CF) monopolizes proximal dendrites, whereas hundreds of thousands of parallel fibers (PFs) innervate distal dendrites, and both CF and PF inputs innervate a narrow intermediate domain. It is unclear how this segregated CF and PF innervation is established on PC dendrites. Through reconstruction of dendritic innervation by serial electron microscopy, we show that from postnatal day 9-15 in mice, both CF and PF innervation territories vigorously expand because of an enlargement of the region of overlapping innervation. From postnatal day 15 onwards, segregation of these territories occurs with robust shortening of the overlapping proximal region. Thus, innervation territories by the heterologous inputs are refined during the early postnatal period. Intriguingly, this transition is arrested in mutant mice lacking the type 1 metabotropic glutamate receptor (mGluR1) or protein kinase C? (PKC?), resulting in the persistence of an abnormally expanded overlapping region. This arrested territory refinement is rescued by lentivirus-mediated expression of mGluR1? into mGluR1-deficient PCs. At the proximal dendrite of rescued PCs, PF synapses are eliminated and free spines emerge instead, whereas the number and density of CF synapses are unchanged. Because the mGluR1-PKC? signaling pathway is also essential for the late-phase of CF synapse elimination, this signaling pathway promotes the two key features of excitatory synaptic wiring in PCs, namely CF monoinnervation by eliminating redundant CF synapses from the soma, and segregated territories of CF and PF innervation by eliminating competing PF synapses from proximal dendrites.

| S-EPMC4776453 | biostudies-literature

Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease.

Project description:Deep learning and computer vision algorithms can deliver highly accurate and automated interpretation of medical imaging to augment and assist clinicians. However, medical imaging presents uniquely pertinent obstacles such as a lack of accessible data or a high-cost of annotation. To address this, we developed data-efficient deep learning classifiers for prediction tasks in cardiology. Using pipeline supervised models to focus relevant structures, we achieve an accuracy of 94.4% for 15-view still-image echocardiographic view classification and 91.2% accuracy for binary left ventricular hypertrophy classification. We then develop semi-supervised generative adversarial network models that can learn from both labeled and unlabeled data in a generalizable fashion. We achieve greater than 80% accuracy in view classification with only 4% of labeled data used in solely supervised techniques and achieve 92.3% accuracy for left ventricular hypertrophy classification. In exploring trade-offs between model type, resolution, data resources, and performance, we present a comprehensive analysis and improvements of efficient deep learning solutions for medical imaging assessment especially in cardiology.

| S-EPMC6550282 | biostudies-literature

Towards automatic pulmonary nodule management in lung cancer screening with deep learning.

Project description:The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

| S-EPMC5395959 | biostudies-literature

Towards mechanistic models of mutational effects: Deep learning on Alzheimer's Aβ peptide.

Project description:Deep Mutational Scanning (DMS) has enabled multiplexed measurement of mutational effects on protein properties, including kinematics and self-organization, with unprecedented resolution. However, potential bottlenecks of DMS characterization include experimental design, data quality, and depth of mutational coverage. Here, we apply deep learning to comprehensively model the mutational effect of the Alzheimer's Disease associated peptide Aβ42 on aggregation-related biochemical traits from DMS measurements. Among tested neural network architectures, Convolutional Neural Networks and Recurrent Neural Networks are found to be the most cost-effective models with high performance even under insufficiently-sampled DMS studies. While sequence features are essential for satisfactory prediction from neural networks, geometric-structural features further enhance the prediction performance. Notably, we demonstrate how mechanistic insights into phenotype may be extracted from the neural networks themselves suitably designed. This methodological benefit is particularly relevant for biochemical systems displaying a strong coupling between structure and phenotype such as the conformation of Aβ42 aggregate and nucleation, as shown here using a Graph Convolutional Neural Network (GCN) developed from the protein atomic structure input. In addition to accurate imputation of missing values (which here ranged up to 55% of all phenotype values at key residues), the mutationally-defined nucleation phenotype generated from a GCN shows improved resolution for identifying known disease-causing mutations relative to the original DMS phenotype. Our study suggests that neural network derived sequence-phenotype mapping can be exploited not only to provide direct support for protein engineering or genome editing but also to facilitate therapeutic design with the gained perspectives from biological modeling.

| S-EPMC10114515 | biostudies-literature

Locally dynamic synaptic learning rules in pyramidal neuron dendrites.

Project description:Long-term potentiation (LTP) of synaptic transmission underlies aspects of learning and memory. LTP is input-specific at the level of individual synapses, but neural network models predict interactions between plasticity at nearby synapses. Here we show in mouse hippocampal pyramidal cells that LTP at individual synapses reduces the threshold for potentiation at neighbouring synapses. After input-specific LTP induction by two-photon glutamate uncaging or by synaptic stimulation, subthreshold stimuli, which by themselves were too weak to trigger LTP, caused robust LTP and spine enlargement at neighbouring spines. Furthermore, LTP induction broadened the presynaptic-postsynaptic spike interval for spike-timing-dependent LTP within a dendritic neighbourhood. The reduction in the threshold for LTP induction lasted approximately 10 min and spread over approximately 10 microm of dendrite. These local interactions between neighbouring synapses support clustered plasticity models of memory storage and could allow for the binding of behaviourally linked information on the same dendritic branch.

| S-EPMC3425382 | biostudies-other

Deep Learning for Reaction-Diffusion Glioma Growth Modeling: Towards a Fully Personalized Model?

Project description:Reaction-diffusion models have been proposed for decades to capture the growth of gliomas, the most common primary brain tumors. However, ill-posedness of the initialization at diagnosis time and parameter estimation of such models have restrained their clinical use as a personalized predictive tool. In this work, we investigate the ability of deep convolutional neural networks (DCNNs) to address commonly encountered pitfalls in the field. Based on 1200 synthetic tumors grown over real brain geometries derived from magnetic resonance (MR) data of six healthy subjects, we demonstrate the ability of DCNNs to reconstruct a whole tumor cell-density distribution from only two imaging contours at a single time point. With an additional imaging contour extracted at a prior time point, we also demonstrate the ability of DCNNs to accurately estimate the individual diffusivity and proliferation parameters of the model. From this knowledge, the spatio-temporal evolution of the tumor cell-density distribution at later time points can ultimately be precisely captured using the model. We finally show the applicability of our approach to MR data of a real glioblastoma patient. This approach may open the perspective of a clinical application of reaction-diffusion growth models for tumor prognosis and treatment planning.

| S-EPMC9139770 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data