lightweight deep convolution neural network model Search Results


convolutional neural network model  (Accelrys)
90
Accelrys convolutional neural network model
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Convolutional Neural Network Model, supplied by Accelrys, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/convolutional neural network model/product/Accelrys
Average 90 stars, based on 1 article reviews
convolutional neural network model - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
convolutional neural network models  (Cleerly Inc)
90
Cleerly Inc convolutional neural network models
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Convolutional Neural Network Models, supplied by Cleerly Inc, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/convolutional neural network models/product/Cleerly Inc
Average 90 stars, based on 1 article reviews
convolutional neural network models - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
custom convolutional neural network models  (Hamad Medical Corporation)
90
Hamad Medical Corporation custom convolutional neural network models
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Custom Convolutional Neural Network Models, supplied by Hamad Medical Corporation, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/custom convolutional neural network models/product/Hamad Medical Corporation
Average 90 stars, based on 1 article reviews
custom convolutional neural network models - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
deep convolutional neural network (cnn)-based encoding model  (Murty Pharmaceuticals)
90
Murty Pharmaceuticals deep convolutional neural network (cnn)-based encoding model
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Deep Convolutional Neural Network (Cnn) Based Encoding Model, supplied by Murty Pharmaceuticals, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/deep convolutional neural network (cnn)-based encoding model/product/Murty Pharmaceuticals
Average 90 stars, based on 1 article reviews
deep convolutional neural network (cnn)-based encoding model - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
breast cancer diagnosis using lightweight deep convolution neural network model  (IEEE Access)
90
IEEE Access breast cancer diagnosis using lightweight deep convolution neural network model
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Breast Cancer Diagnosis Using Lightweight Deep Convolution Neural Network Model, supplied by IEEE Access, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/breast cancer diagnosis using lightweight deep convolution neural network model/product/IEEE Access
Average 90 stars, based on 1 article reviews
breast cancer diagnosis using lightweight deep convolution neural network model - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
word-level convolutional neural network (cnn) model  (Actavis Inc)
90
Actavis Inc word-level convolutional neural network (cnn) model
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Word Level Convolutional Neural Network (Cnn) Model, supplied by Actavis Inc, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/word-level convolutional neural network (cnn) model/product/Actavis Inc
Average 90 stars, based on 1 article reviews
word-level convolutional neural network (cnn) model - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
convolutional neural network (cnn) model  (Lenovo Inc)
90
Lenovo Inc convolutional neural network (cnn) model
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Convolutional Neural Network (Cnn) Model, supplied by Lenovo Inc, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/convolutional neural network (cnn) model/product/Lenovo Inc
Average 90 stars, based on 1 article reviews
convolutional neural network (cnn) model - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
deep convolutional neural network algorithm models for ihc analyses  (Aiforia Technologies)
90
Aiforia Technologies deep convolutional neural network algorithm models for ihc analyses
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Deep Convolutional Neural Network Algorithm Models For Ihc Analyses, supplied by Aiforia Technologies, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/deep convolutional neural network algorithm models for ihc analyses/product/Aiforia Technologies
Average 90 stars, based on 1 article reviews
deep convolutional neural network algorithm models for ihc analyses - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
vision-based convolutional neural network model  (Deepak Inc)
90
Deepak Inc vision-based convolutional neural network model
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Vision Based Convolutional Neural Network Model, supplied by Deepak Inc, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/vision-based convolutional neural network model/product/Deepak Inc
Average 90 stars, based on 1 article reviews
vision-based convolutional neural network model - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
convolutional neural network (cnn) models  (NeuroPace)
90
NeuroPace convolutional neural network (cnn) models
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Convolutional Neural Network (Cnn) Models, supplied by NeuroPace, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/convolutional neural network (cnn) models/product/NeuroPace
Average 90 stars, based on 1 article reviews
convolutional neural network (cnn) models - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
convolutional neural network (cnn) model  (Peschl Ultraviolet)
90
Peschl Ultraviolet convolutional neural network (cnn) model
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Convolutional Neural Network (Cnn) Model, supplied by Peschl Ultraviolet, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/convolutional neural network (cnn) model/product/Peschl Ultraviolet
Average 90 stars, based on 1 article reviews
convolutional neural network (cnn) model - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier
model development for convolutional neural networks (cnns)  (PathAI Inc)
90
PathAI Inc model development for convolutional neural networks (cnns)
Schematic of deep <t>convolutional</t> neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.
Model Development For Convolutional Neural Networks (Cnns), supplied by PathAI Inc, used in various techniques. Bioz Stars score: 90/100, based on 1 PubMed citations. ZERO BIAS - scores, article reviews, protocol conditions and more
https://www.bioz.com/result/model development for convolutional neural networks (cnns)/product/PathAI Inc
Average 90 stars, based on 1 article reviews
model development for convolutional neural networks (cnns) - by Bioz Stars, 2026-03
90/100 stars
  Buy from Supplier

Image Search Results


Schematic of deep convolutional neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.

Journal: Journal of chemical information and modeling

Article Title: Modeling Small-Molecule Reactivity Identifies Promiscuous Bioactive Compounds

doi: 10.1021/acs.jcim.8b00104

Figure Lengend Snippet: Schematic of deep convolutional neural network models for predicting small-molecule reactivity and bioassay promiscuity. (A) Atoms in a test compound are represented as rows of numerical descriptors in a data matrix. These data are input to a neural network with one hidden layer of ten units. This neural network calculates four atom reactivity scores, each score predicts nucleophilic attack at that atom by GSH, cyanide, DNA, or protein. The top five atom reactivity scores in each category are then combined with molecule descriptors and are then used to calculate four molecule reactivity scores. Each molecule level reactivity score is then trained to predict conjugation of the input molecule to either GSH, cyanide, DNA, or protein.34,35 (B) Molecule-level reactivity scores are further combined with another neural network to produce a single integrated reactive promiscuity score. This network can then be trained to predict promiscuous bioactivity in HTS data sets. (C) A hybrid model combines molecule-level reactivity scores with binary indicators for PAINS substructure filter matches. A single hidden layer neural network is then trained to predict promiscuous behavior in HTS data sets.

Article Snippet: 34 , 35 Briefly, a convolutional neural network model was trained using literature-derived data extracted from the Accelrys Metabolite Database and other sources.

Techniques: Bioassay, Conjugation Assay