Building Attention and Edge Convolution Neural Networks for Bioactivity and Physical-Chemical Property Prediction

2019 ◽  
Author(s):  
Michael Withnall ◽  
Edvard Lindelöf ◽  
Ola Engkvist ◽  
Hongming Chen
Keyword(s):  
Message Passing ◽  
State Of The Art ◽  
A Priori ◽  
Model Performance ◽  
Learning Approaches ◽  
Physical Chemical ◽  
Chemical Descriptor ◽  
Derived Properties ◽  
Memory Schemes ◽  
Hyperparameter Selection

We introduce Attention and Edge Memory schemes to the existing Message Passing Neural Network framework for graph convolution, and benchmark our approaches against eight different physical-chemical and bioactivity datasets from the literature. We remove the need to introduce <i>a priori</i> knowledge of the task and chemical descriptor calculation by using only fundamental graph-derived properties. Our results consistently perform on-par with other state-of-the-art machine learning approaches, and set a new standard on sparse multi-task virtual screening targets. We also investigate model performance as a function of dataset preprocessing, and make some suggestions regarding hyperparameter selection.

Building Attention and Edge Convolution Neural Networks for Bioactivity and Physical-Chemical Property Prediction

2019 ◽  
Author(s):  
Michael Withnall ◽  
Edvard Lindelöf ◽  
Ola Engkvist ◽  
Hongming Chen
Keyword(s):  
Message Passing ◽  
State Of The Art ◽  
A Priori ◽  
Model Performance ◽  
Learning Approaches ◽  
Physical Chemical ◽  
Chemical Descriptor ◽  
Derived Properties ◽  
Memory Schemes ◽  
Hyperparameter Selection

We introduce Attention and Edge Memory schemes to the existing Message Passing Neural Network framework for graph convolution, and benchmark our approaches against eight different physical-chemical and bioactivity datasets from the literature. We remove the need to introduce <i>a priori</i> knowledge of the task and chemical descriptor calculation by using only fundamental graph-derived properties. Our results consistently perform on-par with other state-of-the-art machine learning approaches, and set a new standard on sparse multi-task virtual screening targets. We also investigate model performance as a function of dataset preprocessing, and make some suggestions regarding hyperparameter selection.

scholarly journals Building Attention and Edge Convolution Neural Networks for Bioactivity and Physical-Chemical Property Prediction

2019 ◽  
Author(s):  
Michael Withnall ◽  
Edvard Lindelöf ◽  
Ola Engkvist ◽  
Hongming Chen
Keyword(s):  
Message Passing ◽  
State Of The Art ◽  
A Priori ◽  
Model Performance ◽  
Learning Approaches ◽  
Physical Chemical ◽  
Chemical Descriptor ◽  
Derived Properties ◽  
Memory Schemes ◽  
Hyperparameter Selection

We introduce Attention and Edge Memory schemes to the existing Message Passing Neural Network framework for graph convolution, and benchmark our approaches against eight different physical-chemical and bioactivity datasets from the literature. We remove the need to introduce <i>a priori</i> knowledge of the task and chemical descriptor calculation by using only fundamental graph-derived properties. Our results consistently perform on-par with other state-of-the-art machine learning approaches, and set a new standard on sparse multi-task virtual screening targets. We also investigate model performance as a function of dataset preprocessing, and make some suggestions regarding hyperparameter selection.

scholarly journals Building attention and edge message passing neural networks for bioactivity and physical–chemical property prediction

2020 ◽  
Vol 12 (1) ◽  
Author(s):  
M. Withnall ◽  
E. Lindelöf ◽  
O. Engkvist ◽  
H. Chen
Keyword(s):  
Machine Learning ◽  
Message Passing ◽  
A Priori ◽  
Molecular Graph ◽  
Model Performance ◽  
Learning Approaches ◽  
Property Prediction ◽  
Physical Chemical ◽  
Chemical Descriptor ◽  
Hyperparameter Selection

AbstractNeural Message Passing for graphs is a promising and relatively recent approach for applying Machine Learning to networked data. As molecules can be described intrinsically as a molecular graph, it makes sense to apply these techniques to improve molecular property prediction in the field of cheminformatics. We introduce Attention and Edge Memory schemes to the existing message passing neural network framework, and benchmark our approaches against eight different physical–chemical and bioactivity datasets from the literature. We remove the need to introduce a priori knowledge of the task and chemical descriptor calculation by using only fundamental graph-derived properties. Our results consistently perform on-par with other state-of-the-art machine learning approaches, and set a new standard on sparse multi-task virtual screening targets. We also investigate model performance as a function of dataset preprocessing, and make some suggestions regarding hyperparameter selection.

scholarly journals BIOM-62 SENSITIVE DETECTION AND DISCRIMINATION OF INTRACRANIAL TUMORS BY BLOOD

2020 ◽  
Vol 22 (Supplement_2) ◽  
pp. ii15-ii15
Author(s):  
Farshad Nassiri ◽  
Ankur Chakravarthy ◽  
Shengrui Feng ◽  
Roxana Shen ◽  
Romina Nejad ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Brain Tumors ◽  
Model Performance ◽  
High Sensitivity ◽  
Circulating Tumor Dna ◽  
Low Grade ◽  
Learning Approaches ◽  
Intracranial Tumors ◽  
Cell Of Origin ◽  
Tumor Dna

Abstract BACKGROUND The diagnosis of intracranial tumors relies on tissue specimens obtained by invasive surgery. Non-invasive diagnostic approaches, particularly for patients with brain tumours, provide an opportunity to avoid surgery and mitigate unnecessary risk to patients. We reasoned that DNA methylation profiles of circulating tumor DNA in blood can be used as a clinically useful biomarker for patients with brain tumors, given the specificity of DNA methylation profiles for cell-of-origin. METHODS We generated methylation profiles on the plasma of 608 patients with cancer (219 intracranial, 388 extracranial) and 60 healthy controls using a cell-free methylated DNA immunoprecipitation combined with deep sequencing (cfMeDIP-seq) approach. Using machine-learning approaches we generated and evaluated models to distinguish brain tumors from extracranial cancers that may metastasize to the brain, as well as additional models to discriminate common brain tumors included in the differential diagnosis of solitary extra-axial and intra-axial tumors. RESULTS We observed high sensitivity and discriminative capacity for our models to distinguish gliomas from other cancerous and healthy patients (AUC=0.99, 95%CI 0.96–1), with similar performance in IDH mutant and wildtype gliomas as well as in lower- and high-grade gliomas. Excluding non-malignant contributors to plasma methylation did not change model performance (AUC=0.982, 95%CI 0.93–1). Models generated to discriminate intracranial tumors from each other also demonstrated high accuracy for common extra-axial tumors (AUCmeningioma=0.89, 95%CI 0.80–0.97; AUChemangiopericytoma=0.95, 95%CI 0.73–1) as well as intra-axial tumors ranging from low-grade indolent glial-neuronal tumors (AUC 0.93, 95%CI 0.80 – 1) to diffuse intra-axial gliomas with distinct molecular composition (AUCIDH-mutant glioma = 0.82, 95%CI 0.66 -0.98; AUCIDH-wildtype-glioma = 0.71, 95%CI 0.53 – 0.9). Plasma cfMeDIP-seq signals originated from corresponding tumor tissue DNA methylation signals (r=0.37, p&lt; 2.2e-16). CONCLUSIONS These results demonstrate the potential for cfMeDIP-seq profiles to not only detect circulating tumor DNA, but to accurately discriminate common intracranial tumors that share cell-of-origin lineages.

scholarly journals Efficient Rank-Based Diffusion Process with Assured Convergence

2021 ◽  
Vol 7 (3) ◽  
pp. 49
Author(s):  
Daniel Carlos Guimarães Pedronette ◽  
Lucas Pascotti Valem ◽  
Longin Jan Latecki
Keyword(s):  
Diffusion Process ◽  
Learning Strategies ◽  
State Of The Art ◽  
Representation Learning ◽  
Theoretical Background ◽  
High Dimensional ◽  
Visual Features ◽  
Learning Approaches ◽  
Previous Decade ◽  
Asymptotic Complexity

Visual features and representation learning strategies experienced huge advances in the previous decade, mainly supported by deep learning approaches. However, retrieval tasks are still performed mainly based on traditional pairwise dissimilarity measures, while the learned representations lie on high dimensional manifolds. With the aim of going beyond pairwise analysis, post-processing methods have been proposed to replace pairwise measures by globally defined measures, capable of analyzing collections in terms of the underlying data manifold. The most representative approaches are diffusion and ranked-based methods. While the diffusion approaches can be computationally expensive, the rank-based methods lack theoretical background. In this paper, we propose an efficient Rank-based Diffusion Process which combines both approaches and avoids the drawbacks of each one. The obtained method is capable of efficiently approximating a diffusion process by exploiting rank-based information, while assuring its convergence. The algorithm exhibits very low asymptotic complexity and can be computed regionally, being suitable to outside of dataset queries. An experimental evaluation conducted for image retrieval and person re-ID tasks on diverse datasets demonstrates the effectiveness of the proposed approach with results comparable to the state-of-the-art.

scholarly journals Excitonic effects in the optical spectra of Li2SiO3 compound

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Nguyen Thi Han ◽  
Vo Khuong Dien ◽  
Ming-Fa Lin
Keyword(s):  
Optical Properties ◽  
State Of The Art ◽  
Plasmon Mode ◽  
First Principle ◽  
Response Behavior ◽  
Electronic And Optical Properties ◽  
Physical Chemical ◽  
Excitonic Effects ◽  
Energy Loss Functions ◽  
Excitonic Effect

AbstractLi2SiO3 compound exhibits unique electronic and optical properties. The state-of-the-art analyses, which based on first-principle calculations, have successfully confirmed the concise physical/chemical picture and the orbital bonding in Li–O and Si–O bonds. Especially, the unusual optical response behavior includes a large red shift of the onset frequency due to the extremely strong excitonic effect, the polarization of optical properties along three-directions, various optical excitations structures and the most prominent plasmon mode in terms of the dielectric functions, energy loss functions, absorption coefficients and reflectance spectra. The close connections of electronic and optical properties can identify a specific orbital hybridization for each distinct excitation channel. The presented theoretical framework will be fully comprehending the diverse phenomena and widen the potential application of other emerging materials.

scholarly journals Supervised learning for the detection of negation and of its scope in French and Brazilian Portuguese biomedical corpora

2020 ◽  
pp. 1-21 ◽  
Author(s):  
Clément Dalloux ◽  
Vincent Claveau ◽  
Natalia Grabar ◽  
Lucas Emanuel Silva Oliveira ◽  
Claudia Maria Cabral Moro ◽  
...  
Keyword(s):  
Machine Learning ◽  
Information Extraction ◽  
State Of The Art ◽  
Automatic Detection ◽  
Brazilian Portuguese ◽  
Supervised Machine Learning ◽  
Biomedical Domain ◽  
Learning Approaches ◽  
Cross Domain ◽  
Automatic Methods

Abstract Automatic detection of negated content is often a prerequisite in information extraction systems in various domains. In the biomedical domain especially, this task is important because negation plays an important role. In this work, two main contributions are proposed. First, we work with languages which have been poorly addressed up to now: Brazilian Portuguese and French. Thus, we developed new corpora for these two languages which have been manually annotated for marking up the negation cues and their scope. Second, we propose automatic methods based on supervised machine learning approaches for the automatic detection of negation marks and of their scopes. The methods show to be robust in both languages (Brazilian Portuguese and French) and in cross-domain (general and biomedical languages) contexts. The approach is also validated on English data from the state of the art: it yields very good results and outperforms other existing approaches. Besides, the application is accessible and usable online. We assume that, through these issues (new annotated corpora, application accessible online, and cross-domain robustness), the reproducibility of the results and the robustness of the NLP applications will be augmented.

scholarly journals Hybrid Graph Neural Networks for Crowd Counting

2020 ◽  
Vol 34 (07) ◽  
pp. 11693-11700 ◽  
Author(s):  
Ao Luo ◽  
Fan Yang ◽  
Xin Li ◽  
Dong Nie ◽  
Zhicheng Jiao ◽  
...  
Keyword(s):  
Network Architecture ◽  
Message Passing ◽  
Large Scale ◽  
State Of The Art ◽  
Density Variation ◽  
Feature Maps ◽  
Crowd Counting ◽  
Multi Scale ◽  
Crowd Density ◽  
Graph Neural Networks

Crowd counting is an important yet challenging task due to the large scale and density variation. Recent investigations have shown that distilling rich relations among multi-scale features and exploiting useful information from the auxiliary task, i.e., localization, are vital for this task. Nevertheless, how to comprehensively leverage these relations within a unified network architecture is still a challenging problem. In this paper, we present a novel network structure called Hybrid Graph Neural Network (HyGnn) which targets to relieve the problem by interweaving the multi-scale features for crowd density as well as its auxiliary task (localization) together and performing joint reasoning over a graph. Specifically, HyGnn integrates a hybrid graph to jointly represent the task-specific feature maps of different scales as nodes, and two types of relations as edges: (i) multi-scale relations capturing the feature dependencies across scales and (ii) mutual beneficial relations building bridges for the cooperation between counting and localization. Thus, through message passing, HyGnn can capture and distill richer relations between nodes to obtain more powerful representations, providing robust and accurate results. Our HyGnn performs significantly well on four challenging datasets: ShanghaiTech Part A, ShanghaiTech Part B, UCF_CC_50 and UCF_QNRF, outperforming the state-of-the-art algorithms by a large margin.

scholarly journals Recovery of Zinc from Treatment of Spent Acid Solutions from the Pickling Stage of Galvanizing Plants

2021 ◽  
Vol 13 (1) ◽  
pp. 407
Author(s):  
Svetlana B. Zueva ◽  
Francesco Ferella ◽  
Valentina Innocenzi ◽  
Ida De Michelis ◽  
Valentina Corradini ◽  
...  
Keyword(s):  
Wastewater Treatment ◽  
Sodium Hydroxide ◽  
Calcium Hydroxide ◽  
State Of The Art ◽  
Zinc Content ◽  
Economic Viability ◽  
Acid Solutions ◽  
Physical Chemical ◽  
Galvanic Sludge ◽  
Valuable Metals

Typical methods for the treatment of waste pickling solutions include precipitation by alkaline reagents, most commonly calcium hydroxide. As a result, large volumes of galvanic sludge form, containing iron, calcium, sulphates, and a relatively small quantity of zinc (<20%), making Zn recovery not profitable. In summary, state-of-the-art Zn galvanization processes entail the loss of valuable metals and the irrational and expensive handling of spent pickling solutions (SPSs). The resulting conclusion is that there is room for a significant improvement in the way SPSs are treated, with the double goal of enhancing Zn galvanization methods’ economic viability and achieving a lesser impact on the environment’s processes. The experimental results show that it is possible to use SPS as a coagulant to treat the process wastewaters, kept separated, and added with sodium hydroxide. The results in obtaining precipitates with Zn contents higher than 40%, increasing the added advantage of making Zn recovery profitable. The results show the possibility of using SPS as a coagulant in the process of physical-chemical wastewater treatment and sodium hydroxide to obtain a precipitate with a zinc content of more than 40%.

Sign in / Sign up

Export Citation Format

Share Document