Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

2018 ◽  
Author(s):  
Roman Zubatyuk ◽  
Justin S. Smith ◽  
Jerzy Leszczynski ◽  
Olexandr Isayev
Keyword(s):  
Neural Network ◽  
Molecular System ◽  
Computational Cost ◽  
Chemical Properties ◽  
The State ◽  
Molecular Properties ◽  
Training Data ◽  
Dft Methods ◽  
Benchmark Datasets ◽  
Quantum Phenomena

<p>Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets the state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in computational cost. With AIMNet we show a new dimension of transferability: the ability to learn new targets utilizing multimodal information from previous training. The model can learn implicit solvation energy (like SMD) utilizing only a fraction of original training data, and archive MAD error of 1.1 kcal/mol compared to experimental solvation free energies in MNSol database.</p>

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

2018 ◽  
Author(s):  
Roman Zubatyuk ◽  
Justin S. Smith ◽  
Jerzy Leszczynski ◽  
Olexandr Isayev
Keyword(s):  
Neural Network ◽  
Molecular System ◽  
Computational Cost ◽  
Chemical Properties ◽  
The State ◽  
Molecular Properties ◽  
Training Data ◽  
Dft Methods ◽  
Benchmark Datasets ◽  
Quantum Phenomena

<p>Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets the state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in computational cost. With AIMNet we show a new dimension of transferability: the ability to learn new targets utilizing multimodal information from previous training. The model can learn implicit solvation energy (like SMD) utilizing only a fraction of original training data, and archive MAD error of 1.1 kcal/mol compared to experimental solvation free energies in MNSol database.</p>

Accurate and Transferable Multitask Prediction of Chemical Properties with an Atoms-in-Molecule Neural Network

2018 ◽  
Author(s):  
Roman Zubatyuk ◽  
Justin S. Smith ◽  
Jerzy Leszczynski ◽  
Olexandr Isayev
Keyword(s):  
Neural Network ◽  
Molecular System ◽  
Computational Cost ◽  
Chemical Properties ◽  
The State ◽  
Molecular Properties ◽  
Training Data ◽  
Dft Methods ◽  
Benchmark Datasets ◽  
Quantum Phenomena

<p>Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets the state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in computational cost. With AIMNet we show a new dimension of transferability: the ability to learn new targets utilizing multimodal information from previous training. The model can learn implicit solvation energy (like SMD) utilizing only a fraction of original training data, and archive MAD error of 1.1 kcal/mol compared to experimental solvation free energies in MNSol database.</p>

scholarly journals Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network

2019 ◽  
Vol 5 (8) ◽  
pp. eaav6490 ◽  
Author(s):  
Roman Zubatyuk ◽  
Justin S. Smith ◽  
Jerzy Leszczynski ◽  
Olexandr Isayev
Keyword(s):  
Neural Network ◽  
Molecular System ◽  
Computational Cost ◽  
Chemical Properties ◽  
Molecular Properties ◽  
Training Data ◽  
Dft Methods ◽  
Absolute Deviation ◽  
Benchmark Datasets ◽  
Quantum Phenomena

Atomic and molecular properties could be evaluated from the fundamental Schrodinger’s equation and therefore represent different modalities of the same quantum phenomena. Here, we present AIMNet, a modular and chemically inspired deep neural network potential. We used AIMNet with multitarget training to learn multiple modalities of the state of the atom in a molecular system. The resulting model shows on several benchmark datasets state-of-the-art accuracy, comparable to the results of orders of magnitude more expensive DFT methods. It can simultaneously predict several atomic and molecular properties without an increase in the computational cost. With AIMNet, we show a new dimension of transferability: the ability to learn new targets using multimodal information from previous training. The model can learn implicit solvation energy (SMD method) using only a fraction of the original training data and an archive median absolute deviation error of 1.1 kcal/mol compared to experimental solvation free energies in the MNSol database.

scholarly journals An efficient pruning scheme of deep neural networks for Internet of Things applications

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Chen Qi ◽  
Shibo Shen ◽  
Rongpeng Li ◽  
Zhifeng Zhao ◽  
Qing Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Internet Of Things ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Superior Performance ◽  
Compact Structure ◽  
Resource Limited ◽  
Benchmark Datasets ◽  
Iot Devices

AbstractNowadays, deep neural networks (DNNs) have been rapidly deployed to realize a number of functionalities like sensing, imaging, classification, recognition, etc. However, the computational-intensive requirement of DNNs makes it difficult to be applicable for resource-limited Internet of Things (IoT) devices. In this paper, we propose a novel pruning-based paradigm that aims to reduce the computational cost of DNNs, by uncovering a more compact structure and learning the effective weights therein, on the basis of not compromising the expressive capability of DNNs. In particular, our algorithm can achieve efficient end-to-end training that transfers a redundant neural network to a compact one with a specifically targeted compression rate directly. We comprehensively evaluate our approach on various representative benchmark datasets and compared with typical advanced convolutional neural network (CNN) architectures. The experimental results verify the superior performance and robust effectiveness of our scheme. For example, when pruning VGG on CIFAR-10, our proposed scheme is able to significantly reduce its FLOPs (floating-point operations) and number of parameters with a proportion of 76.2% and 94.1%, respectively, while still maintaining a satisfactory accuracy. To sum up, our scheme could facilitate the integration of DNNs into the common machine-learning-based IoT framework and establish distributed training of neural networks in both cloud and edge.

scholarly journals k-Nearest Neighbor Learning with Graph Neural Networks

Mathematics ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 830
Author(s):  
Seokho Kang
Keyword(s):  
Neural Network ◽  
Nearest Neighbor ◽  
Learning Algorithm ◽  
Weighting Function ◽  
High Sensitivity ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Main Challenge ◽  
Benchmark Datasets ◽  
Graph Neural Networks

k-nearest neighbor (kNN) is a widely used learning algorithm for supervised learning tasks. In practice, the main challenge when using kNN is its high sensitivity to its hyperparameter setting, including the number of nearest neighbors k, the distance function, and the weighting function. To improve the robustness to hyperparameters, this study presents a novel kNN learning method based on a graph neural network, named kNNGNN. Given training data, the method learns a task-specific kNN rule in an end-to-end fashion by means of a graph neural network that takes the kNN graph of an instance to predict the label of the instance. The distance and weighting functions are implicitly embedded within the graph neural network. For a query instance, the prediction is obtained by performing a kNN search from the training data to create a kNN graph and passing it through the graph neural network. The effectiveness of the proposed method is demonstrated using various benchmark datasets for classification and regression tasks.

scholarly journals Convolutional Neural Network-Based Discriminator for Outlier Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Fahad Alharbi ◽  
Khalil El Hindi ◽  
Saad Al Ahmadi ◽  
Hussien Alsalamn
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Systematic Approach ◽  
Data Augmentation ◽  
Random Noise ◽  
Training Data ◽  
Human Errors ◽  
Machine Learning Methods ◽  
Benchmark Datasets ◽  
Trusted Data

Noise in training data increases the tendency of many machine learning methods to overfit the training data, which undermines the performance. Outliers occur in big data as a result of various factors, including human errors. In this work, we present a novel discriminator model for the identification of outliers in the training data. We propose a systematic approach for creating training datasets to train the discriminator based on a small number of genuine instances (trusted data). The noise discriminator is a convolutional neural network (CNN). We evaluate the discriminator’s performance using several benchmark datasets and with different noise ratios. We inserted random noise in each dataset and trained discriminators to clean them. Different discriminators were trained using different numbers of genuine instances with and without data augmentation. We compare the performance of the proposed noise-discriminator method with seven other methods proposed in the literature using several benchmark datasets. Our empirical results indicate that the proposed method is very competitive to the other methods. It actually outperforms them for pair noise.

scholarly journals UVC: universality-based calling of small variants using pseudo-neural networks

2020 ◽  
Author(s):  
Xiaofei Zhao ◽  
Allison Hu ◽  
Sizhen Wang ◽  
Xiaoyue Wang
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Variant Calling ◽  
The State ◽  
Training Data ◽  
Normal Sample ◽  
Sequencing Data ◽  
Damage Repair ◽  
Biological Insight ◽  
Sensitivity Specificity

AbstractWe describe UVC (https://github.com/genetronhealth/uvc), an open-source method for calling small somatic variants. UVC is aware of both unique molecular identifiers (UMIs) and the tumor-matched normal sample. UVC utilizes the following power-law universality that we discovered: allele fraction is inversely proportional to the cubic root of variant-calling error rate. Moreover, UVC utilizes pseudo-neural network (PNN). PNN is similar to deep neural network but does not require any training data. UVC outperformed Mageri and smCounter2, the state-of-the-art UMI-aware variant callers, on the tumor-only datasets used for publishing these two variant callers. Also, UVC outperformed Mutect2 and Strelka2, the state-of-the-art variant callers for tumor-normal pairs, on the Genome-in-a-Bottle somatic truth sets. UVC outperformed Mutect2 and Strelka2 on 21 in silico mixtures simulating 21 combinations of tumor purity and normal purity. Performance is measured by using sensitivity-specificity trade off for all called variants. The improved variant calls generated by UVC from previously published UMI-based sequencing data are able to provide additional biological insight about DNA damage repair. The versatility and robustness of UVC makes it a useful tool for variant calling in clinical settings.

scholarly journals Automation of (Macro)molecular Properties Using a Bootstrapping Swarm Artificial Neural Network Method: Databases for Machine Learning

2019 ◽  
Author(s):  
Blerta Rahmani ◽  
Hiqmet Kamberaj
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Quantum Mechanics ◽  
Molecular Properties ◽  
Training Data ◽  
Neural Network Method ◽  
Network Method ◽  
Artificial Neural Network Method ◽  
Artificial Neural

AbstractIn this study, we employed a novel method for prediction of (macro)molecular properties using a swarm artificial neural network method as a machine learning approach. In this method, a (macro)molecular structure is represented by a so-called description vector, which then is the input in a so-called bootstrapping swarm artificial neural network (BSANN) for training the neural network. In this study, we aim to develop an efficient approach for performing the training of an artificial neural network using either experimental or quantum mechanics data. In particular, we aim to create different user-friendly online accessible databases of well-selected experimental (or quantum mechanics) results that can be used as proof of the concepts. Furthermore, with the optimized artificial neural network using the training data served as input for BSANN, we can predict properties and their statistical errors of new molecules using the plugins provided from that web-service. There are four databases accessible using the web-based service. That includes a database of 642 small organic molecules with known experimental hydration free energies, the database of 1475 experimental pKa values of ionizable groups in 192 proteins, the database of 2693 mutants in 14 proteins with given values of experimental values of changes in the Gibbs free energy, and a database of 7101 quantum mechanics heat of formation calculations.All the data are prepared and optimized in advance using the AMBER force field in CHARMM macromolecular computer simulation program. The BSANN is code for performing the optimization and prediction written in Python computer programming language. The descriptor vectors of the small molecules are based on the Coulomb matrix and sum over bonds properties, and for the macromolecular systems, they take into account the chemical-physical fingerprints of the region in the vicinity of each amino acid.Graphical TOC Entry

scholarly journals WEIGHTED POINT CLOUD AUGMENTATION FOR NEURAL NETWORK TRAINING DATA CLASS-IMBALANCE

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 981-987
Author(s):  
D. Griffiths ◽  
J. Boehm
Keyword(s):  
Neural Network ◽  
Class Imbalance ◽  
Point Clouds ◽  
Training Data ◽  
Natural Class ◽  
Validation Data ◽  
3D Data ◽  
Weighted Point ◽  
Recent Developments ◽  
Benchmark Datasets

<p><strong>Abstract.</strong> Recent developments in the field of deep learning for 3D data have demonstrated promising potential for end-to-end learning directly from point clouds. However, many real-world point clouds contain a large class im-balance due to the natural class im-balance observed in nature. For example, a 3D scan of an urban environment will consist mostly of road and façade, whereas other objects such as poles will be under-represented. In this paper we address this issue by employing a weighted augmentation to increase classes that contain fewer points. By mitigating the class im-balance present in the data we demonstrate that a standard PointNet++ deep neural network can achieve higher performance at inference on validation data. This was observed as an increase of F1 score of 19% and 25% on two test benchmark datasets; ScanNet and Semantic3D respectively where no class im-balance pre-processing had been performed. Our networks performed better on both highly-represented and under-represented classes, which indicates that the network is learning more robust and meaningful features when the loss function is not overly exposed to only a few classes.</p>

Strut Diameter Uncertainty Prediction by Deep Neural Network for Additively Manufactured Lattice Structures

2021 ◽  
Author(s):  
Recep M. Gorguluarslan ◽  
Gorkem Can Ates ◽  
O. Utku Gungor ◽  
Yusuf Yamaner
Keyword(s):  
Neural Network ◽  
Computer Aided Design ◽  
Deep Neural Network ◽  
Computational Cost ◽  
Training Data ◽  
Model Parameters ◽  
Effective Diameter ◽  
Lattice Structures ◽  
Validation Data ◽  
Geometric Uncertainties

Abstract Additive manufacturing introduces geometric uncertainties on the fabricated strut members of lattice structures. These uncertainties lead to deviations between the simulation result and the fabricated mechanical performance. Although these uncertainties can be characterized and quantified in the existing literature, the generation of a high number of samples for the quantified uncertainties to use in the computer-aided design of lattice structures for different strut diameters and angles requires high experimental effort and computational cost. The use of deep neural network models to accurately predict the samples of uncertainties is studied in this research to address this issue. For the training data, the geometric uncertainties on the fabricated struts introduced by the material extrusion process are characterized from microscope measurements using random field theory. These uncertainties are propagated to effective diameters of the strut members using a stochastic upscaling technique. The relationship between the deterministic strut model parameters, namely the model diameter and angle, and the effective diameter with propagated uncertainties is established through a deep neural network model. The validation data results show accurate predictions for the effective diameter when model parameters are given as inputs. Thus, the proposed model has the potential to use the fabricated results in the design optimization processes without requiring computationally expensive repetitive simulations.

Sign in / Sign up

Export Citation Format

Share Document