scholarly journals DeepNeurite TM : identification of neurites from non‐specific binding of fluorescence probes through deep learning

2021 ◽  
Author(s):  
Kai‐Chih Huang ◽  
Shan Lou ◽  
Chih‐Chieh Wang ◽  
Monica S. Thanawala ◽  
Jesse Turner ◽  
...  
Keyword(s):  
Deep Learning ◽  
Specific Binding ◽  
Fluorescence Probes

scholarly journals Uncovering tissue-specific binding features from differential deep learning

2019 ◽  
Author(s):  
Mike Phuycharoen ◽  
Peyman Zarrineh ◽  
Laure Bridoux ◽  
Shilu Amin ◽  
Marta Losa ◽  
...  
Keyword(s):  
Deep Learning ◽  
Binding Sites ◽  
Specific Binding ◽  
Specific Expression ◽  
Tissue Specific ◽  
Dimensional Classification ◽  
Branchial Arches ◽  
Gradient Based ◽  
Differential Binding

ABSTRACTMotivationTranscription factors (TFs) can bind DNA in a cooperative manner, enabling a mutual increase in occupancy. Through this type of interaction, alternative binding sites can be preferentially bound in different tissues to regulate tissue-specific expression programmes. Recently, deep learning models have become state-of-the-art in various pattern analysis tasks, including applications in the field of genomics. We therefore investigate the application of convolutional neural network (CNN) models to the discovery of sequence features determining cooperative and differential TF binding across tissues.ResultsWe analyse ChIP-seq data from MEIS, TFs which are broadly expressed across mouse branchial arches, and HOXA2, which is expressed in the second and more posterior branchial arches. By developing models predictive of MEIS differential binding in all three tissues we are able to accurately predict HOXA2 co-binding sites. We evaluate transfer-like and multitask approaches to regularising the high-dimensional classification task with a larger regression dataset, allowing for creation of deeper and more accurate models. We test the performance of perturbation and gradient-based attribution methods in identifying the HOXA2 sites from differential MEIS data. Our results show that deep regularised models significantly outperform shallow CNNs as well as k-mer methods in the discovery of tissue-specific sites bound in vivo.AvailabilityFor implementation and models please visit https://doi.org/10.5281/zenodo.2635463.

scholarly journals An automated framework for efficiently designing deep convolutional neural networks in genomics

2020 ◽  
Author(s):  
Zijun Zhang ◽  
Christopher Y. Park ◽  
Chandra L. Theesfeld ◽  
Olga G. Troyanskaya
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Specific Binding ◽  
Genomic Sequences ◽  
Network Architectures ◽  
Deep Convolutional Neural Networks ◽  
Major Barrier ◽  
Automated Method ◽  
Allele Specific

AbstractConvolutional neural networks (CNNs) have become a standard for analysis of biological sequences. Tuning of network architectures is essential for CNN’s performance, yet it requires substantial knowledge of machine learning and commitment of time and effort. This process thus imposes a major barrier to broad and effective application of modern deep learning in genomics. Here, we present AMBER, a fully automated framework to efficiently design and apply CNNs for genomic sequences. AMBER designs optimal models for user-specified biological questions through the state-of-the-art Neural Architecture Search (NAS). We applied AMBER to the task of modelling genomic regulatory features and demonstrated that the predictions of the AMBER-designed model are significantly more accurate than the equivalent baseline non-NAS models and match or even exceed published expert-designed models. Interpretation of AMBER architecture search revealed its design principles of utilizing the full space of computational operations for accurately modelling genomic sequences. Furthermore, we illustrated the use of AMBER to accurately discover functional genomic variants in allele-specific binding and disease heritability enrichment. AMBER provides an efficient automated method for designing accurate deep learning models in genomics.

scholarly journals Uncovering tissue-specific binding features from differential deep learning

2020 ◽  
Vol 48 (5) ◽  
pp. e27-e27 ◽  
Author(s):  
Mike Phuycharoen ◽  
Peyman Zarrineh ◽  
Laure Bridoux ◽  
Shilu Amin ◽  
Marta Losa ◽  
...  
Keyword(s):  
Deep Learning ◽  
Binding Sites ◽  
Specific Binding ◽  
Specific Expression ◽  
Tissue Specific ◽  
Dimensional Classification ◽  
Branchial Arches ◽  
Gradient Based ◽  
Differential Binding

Abstract Transcription factors (TFs) can bind DNA in a cooperative manner, enabling a mutual increase in occupancy. Through this type of interaction, alternative binding sites can be preferentially bound in different tissues to regulate tissue-specific expression programmes. Recently, deep learning models have become state-of-the-art in various pattern analysis tasks, including applications in the field of genomics. We therefore investigate the application of convolutional neural network (CNN) models to the discovery of sequence features determining cooperative and differential TF binding across tissues. We analyse ChIP-seq data from MEIS, TFs which are broadly expressed across mouse branchial arches, and HOXA2, which is expressed in the second and more posterior branchial arches. By developing models predictive of MEIS differential binding in all three tissues, we are able to accurately predict HOXA2 co-binding sites. We evaluate transfer-like and multitask approaches to regularizing the high-dimensional classification task with a larger regression dataset, allowing for the creation of deeper and more accurate models. We test the performance of perturbation and gradient-based attribution methods in identifying the HOXA2 sites from differential MEIS data. Our results show that deep regularized models significantly outperform shallow CNNs as well as k-mer methods in the discovery of tissue-specific sites bound in vivo.

scholarly journals GPS-PBS: A Deep Learning Framework to Predict Phosphorylation Sites that Specifically Interact with Phosphoprotein-Binding Domains

Cells ◽  
2020 ◽  
Vol 9 (5) ◽  
pp. 1266 ◽  
Author(s):  
Yaping Guo ◽  
Wanshan Ning ◽  
Peiran Jiang ◽  
Shaofeng Lin ◽  
Chenwei Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Strategy ◽  
Specific Binding ◽  
Signaling Networks ◽  
Phosphorylation Sites ◽  
Akt Signaling Pathway ◽  
Online Service ◽  
Learning Framework ◽  
Binding Domains ◽  
Model Training

Protein phosphorylation is essential for regulating cellular activities by modifying substrates at specific residues, which frequently interact with proteins containing phosphoprotein-binding domains (PPBDs) to propagate the phosphorylation signaling into downstream pathways. Although massive phosphorylation sites (p-sites) have been reported, most of their interacting PPBDs are unknown. Here, we collected 4458 known PPBD-specific binding p-sites (PBSs), considerably improved our previously developed group-based prediction system (GPS) algorithm, and implemented a deep learning plus transfer learning strategy for model training. Then, we developed a new online service named GPS-PBS, which can hierarchically predict PBSs of 122 single PPBD clusters belonging to two groups and 16 families. By comparison, GPS-PBS achieved a highly competitive accuracy against other existing tools. Using GPS-PBS, we predicted 371,018 mammalian p-sites that potentially interact with at least one PPBD, and revealed that various PPBD-containing proteins (PPCPs) and protein kinases (PKs) can simultaneously regulate the same p-sites to orchestrate important pathways, such as the PI3K-Akt signaling pathway. Taken together, we anticipate GPS-PBS can be a great help for further dissecting phosphorylation signaling networks.

Ultrastructural Localization of Antigens by Capillary Action Immunocytochemistry

1996 ◽  
Vol 54 ◽  
pp. 40-41
Author(s):  
László G. Kömüves
Keyword(s):  
San Francisco ◽  
Colloidal Gold ◽  
Specific Binding ◽  
Ultrastructural Localization ◽  
Ultrastructural Level ◽  
Uranyl Acetate ◽  
Adhesive Tape ◽  
Distilled Water ◽  
Capillary Action ◽  
Rabbit Igg

Light microscopic immunohistochemistry based on the principle of capillary action staining is a widely used method to localize antigens. Capillary action immunostaining, however, has not been tested or applied to detect antigens at the ultrastructural level. The aim of this work was to establish a capillary action staining method for localization of intracellular antigens, using colloidal gold probes.Post-embedding capillary action immunocytochemistry was used to detect maternal IgG in the small intestine of newborn suckling piglets. Pieces of the jejunum of newborn piglets suckled for 12 h were fixed and embedded into LR White resin. Sections on nickel grids were secured on a capillary action glass slide (100 μm wide capillary gap, Bio-Tek Solutions, Santa Barbara CA, distributed by CMS, Houston, TX) by double sided adhesive tape. Immunolabeling was performed by applying reagents over the grids using capillary action and removing reagents by blotting on filter paper. Reagents for capillary action staining were from Biomeda (Foster City, CA). The following steps were performed: 1) wet the surface of the sections with automation buffer twice, 5 min each; 2) block non-specific binding sites with tissue conditioner, 10 min; 3) apply first antibody (affinity-purified rabbit anti-porcine IgG, Sigma Chem. Co., St. Louis, MO), diluted in probe diluent, 1 hour; 4) wash with automation buffer three times, 5 min each; 5) apply gold probe (goat anti-rabbit IgG conjugated to 10 nm colloidal gold, Zymed Laboratories, South San Francisco, CA) diluted in probe diluent, 30 min; 6) wash with automation buffer three times, 5 min each; 7) post-fix with 5% glutaraldehyde in PBS for 10 min; 8) wash with PBS twice, 5 min each; 9) contrast with 1% OSO4 in PBS for 15 min; 10) wash with PBS followed by distilled water for5 min each; 11) stain with 2% uranyl acetate for 10 min; 12) stain with lead citrate for 2 min; 13) wash with distilled water three times, 1 min each. The glass slides were separated, and the grids were air-dried, then removed from the adhesive tape. The following controls were used to ensure the specificity of labeling: i) omission of the first antibody; ii) normal rabbit IgG in lieu of first antibody; iii) rabbit anti-porcine IgG absorbed with porcine IgG.

Deep Learning

2009 ◽  
Author(s):  
Stellan Ohlsson
Keyword(s):  
Deep Learning

Intelligence artificielle : le futur de l’Orthodontie ?

2019 ◽  
Vol 53 (3) ◽  
pp. 281-294
Author(s):  
Jean-Michel Foucart ◽  
Augustin Chavanne ◽  
Jérôme Bourriau
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Intelligence Artificielle ◽  
Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

On the Role of Transferrin in 67Ga Uptake by Tumor Cells

1988 ◽  
Vol 27 (04) ◽  
pp. 151-153
Author(s):  
P. Thouvenot ◽  
F. Brunotte ◽  
J. Robert ◽  
L. J. Anghileri
Keyword(s):  
Specific Binding ◽  
Subcellular Fractionation ◽  
Animal Blood ◽  
Tumor Bearing ◽  
Cell Structures ◽  
The Difference ◽  
Sarcoma Cells ◽  
In Vitro Uptake

In vitro uptake of 67Ga-citrate and 59Fe-citrate by DS sarcoma cells in the presence of tumor-bearing animal blood plasma showed a dramatic inhibition of both 67Ga and 59Fe uptakes: about ii/io of 67Ga and 1/5o of the 59Fe are taken up by the cells. Subcellular fractionation appears to indicate no specific binding to cell structures, and the difference of binding seems to be related to the transferrin chelation and transmembrane transport differences

Plasminogen-Plasmin System IX. Specific Binding of Tranexamic Acid to Plasmin

1975 ◽  
Vol 33 (03) ◽  
pp. 573-585 ◽  
Author(s):  
Masahiro Iwamoto
Keyword(s):  
Tranexamic Acid ◽  
Affinity Chromatography ◽  
Dissociation Constant ◽  
Factor Xiii ◽  
Specific Binding ◽  
The Other ◽  
Inhibitory Mechanism ◽  
Binding Studies ◽  
Similar Affinity ◽  
Fibrin Structure

SummaryInteractions between tranexamic acid and protein were studied in respect of the antifibrinolytic actions of tranexamic acid. Tranexamic acid did neither show any interaction with fibrinogen or fibrin, nor was incorporated into cross-linked fibrin structure by the action of factor XIII. On the other hand, tranexamic acid bound to human plasmin with a dissociation constant of 3.5 × 10−5 M, which was very close to the inhibition constant (3.6 × 10−5 M) for this compound in inhibiting plasmin-induced fibrinolysis. The binding site of tranexamic acid on plasmin was not the catalytic site of plasmin, because TLCK-blocked plasmin also showed a similar affinity to tranexamic acid (the dissociation constant, 2.9–4.8 × 10−5 M).In the binding studies with the highly purified plasminogen and TLCK-plasmin preparations which were obtained by affinity chromatography on lysine-substituted Sepharose, the molar binding ratio was shown to be 1.5–1.6 moles tranexamic acid per one mole protein.On the basis of these and other findings, a model for the inhibitory mechanism of tranexamic acid is presented.

Sign in / Sign up

Export Citation Format

Share Document