scholarly journals Using Machine Learning for Robust Target Prediction in a Basic Oxygen Furnace System

2020 ◽  
Vol 51 (4) ◽  
pp. 1632-1645
Author(s):  
Juhee Bae ◽  
Yurong Li ◽  
Niclas Ståhl ◽  
Gunnar Mathiason ◽  
Niklas Kojola
Keyword(s):  
Machine Learning ◽  
Target Prediction ◽  
Basic Oxygen Furnace ◽  
Basic Oxygen

Epigenetic Target Prediction with Accurate Machine Learning Models

2021 ◽  
Author(s):  
Norberto Sánchez-Cruz ◽  
Jose L. Medina-Franco
Keyword(s):  
Machine Learning ◽  
Small Molecules ◽  
Predictive Models ◽  
Large Scale ◽  
Target Prediction ◽  
Quantitative Measure ◽  
Learning Models ◽  
Discovery Research ◽  
Drug Discovery Research ◽  
Machine Learning Models

<p>Epigenetic targets are a significant focus for drug discovery research, as demonstrated by the eight approved epigenetic drugs for treatment of cancer and the increasing availability of chemogenomic data related to epigenetics. This data represents a large amount of structure-activity relationships that has not been exploited thus far for the development of predictive models to support medicinal chemistry efforts. Herein, we report the first large-scale study of 26318 compounds with a quantitative measure of biological activity for 55 protein targets with epigenetic activity. Through a systematic comparison of machine learning models trained on molecular fingerprints of different design, we built predictive models with high accuracy for the epigenetic target profiling of small molecules. The models were thoroughly validated showing mean precisions up to 0.952 for the epigenetic target prediction task. Our results indicate that the herein reported models have considerable potential to identify small molecules with epigenetic activity. Therefore, our results were implemented as freely accessible and easy-to-use web application.</p>

Synthesis and characterisation of alites from reduced basic oxygen furnace slags

2021 ◽  
Vol 147 ◽  
pp. 106518
Author(s):  
Katharina Schraut ◽  
Burkart Adamczyk ◽  
Christian Adam ◽  
Dietmar Stephan ◽  
Birgit Meng ◽  
...  
Keyword(s):  
Basic Oxygen Furnace ◽  
Basic Oxygen

scholarly journals Time-Dependent Strength Behavior, Expansion, Microstructural Properties, and Environmental Impact of Basic Oxygen Furnace Slag-Treated Marine-Dredged Clay in South Korea

2021 ◽  
Vol 13 (9) ◽  
pp. 5026
Author(s):  
Gyeong-o Kang ◽  
Jung-goo Kang ◽  
Jin-young Kim ◽  
Young-sang Kim
Keyword(s):  
Particle Size ◽  
Environmental Impact ◽  
South Korea ◽  
Mechanical Characteristics ◽  
Basic Oxygen Furnace ◽  
Microstructural Properties ◽  
Compression Tests ◽  
Basic Oxygen ◽  
Strength Behavior ◽  
Bof Slag

The aim of this study was to investigate the mechanical characteristics, microstructural properties, and environmental impact of basic oxygen furnace (BOF) slag-treated clay in South Korea. Mechanical characteristics were determined via the expansion, vane shear, and unconfined compression tests according to various curing times. Scanning electron microscopy was conducted to analyze microstructural properties. Furthermore, environmental impacts were evaluated by the leaching test and pH measurements. According to the results, at the early curing stage (within 15 h), the free lime (F-CaO) content of the BOF slag is a significant factor for developing the strength of the adopted sample. However, the particle size of the BOF slag influences the increase in the strength at subsequent curing times. It was inferred that the strength behavior of the sample exhibits three phases depending on various incremental strength ratios. The expansion magnitude of the adopted samples is influenced by the F-CaO content and also the particle size of the BOF slag. Regarding the microstructural properties, the presence of reticulation structures in the amorphous gels with intergrowths of rod-like ettringite formation was verified inside the sample. Finally, the pH values and heavy metal leachates of the samples were determined within the compatible ranges of the threshold effect levels in the marine sediments of the marine environment standard of the Republic of Korea.

scholarly journals Component Modification of Basic Oxygen Furnace Slag with C4AF as Target Mineral and Application

2021 ◽  
Vol 13 (12) ◽  
pp. 6536
Author(s):  
Yanrong Zhao ◽  
Pengliang Sun ◽  
Ping Chen ◽  
Xiaomin Guan ◽  
Yuanhao Wang ◽  
...  
Keyword(s):  
Intermediate Phase ◽  
Raw Materials ◽  
Activity Index ◽  
Basic Oxygen Furnace ◽  
Hydration Products ◽  
Basic Oxygen ◽  
Bof Slag ◽  
Mineral Compositions ◽  
Slag Component ◽  
Basic Oxygen Furnace Slag

In this paper, a new method of basic oxygen furnace (BOF) slag component modification with a regulator was studied. The main mineral was designed as C4AF, C2S and C3S in modified BOF slag, and the batching method, mineral compositions, hydration rate, activation index and capability of resisting sulfate corrode also were studied. XRD, BEI and EDS were used to characterize the mineral formation, and SEM was used to study the morphology of hydration products. The results show that most inert phase in BOF slag can be converted into active minerals of C4AF and C2S through reasonable batching calculation and the amount of regulating agent. The formation of C4AF and C2S in modified BOF slag is better, and a small amount of MgO is embedded in the white intermediate phase, but C3S is not detected. With the increase in the CaO/SiO2 ratio in raw materials, the CaO/SiO2 ratio of calcium silicate minerals in modified BOF slag increases, the contents of f-CaO are less than 1.0%, and the activity index improves. Compared with the BOF slag, the activity index and exothermic rate of modified BOF slag improved obviously, and the activity index of 90 days is close to 100%. With the increase in modified BOF slag B cement, the flexural strength decrease; however, the capability of resisting sulfate corrode is improved due to the constant formation of a short rod-like shape ettringite in Na2SO4 solution and the improvement of the structure densification of the hydration products.

scholarly journals Accurate microRNA Target Prediction Using Detailed Binding Site Accessibility and Machine Learning on Proteomics Data

2012 ◽  
Vol 2 ◽  
Author(s):  
Martin Reczko ◽  
Manolis Maragkakis ◽  
Panagiotis Alexiou ◽  
Giorgio L. Papadopoulos ◽  
Artemis G. Hatzigeorgiou
Keyword(s):  
Machine Learning ◽  
Binding Site ◽  
Target Prediction ◽  
Proteomics Data ◽  
Microrna Target ◽  
Microrna Target Prediction

scholarly journals Simulated Experiment Study of Factors Influencing the Hydration Activity of f-CaO in Basic Oxygen Furnace Slag

2016 ◽  
Vol 2016 ◽  
pp. 1-15 ◽  
Author(s):  
Ruiquan Jia ◽  
Jiaxiang Liu
Keyword(s):  
Solid Solutions ◽  
Volume Expansion ◽  
Basic Oxygen Furnace ◽  
Hydration Reaction ◽  
Basic Oxygen ◽  
Activity Sequence ◽  
Bof Slag ◽  
Iron Phase ◽  
Calcium Iron ◽  
Iron Manganese

The compositions and formation process of f-CaO in BOF slag were revealed and simulated to understand its expansion rules and why its hydration activity is low. BSE showed the compositions of f-CaO, which included calcium iron phase and calcium iron manganese phase, were diverse. The hydration activity sequence was Ca2Fe2O5 and Ca3Fe1.5Mn1.5O8 in tricomponent f-CaO < CaO in tricomponent f-CaO < monocomponent f-CaO; only Ca2Fe2O5 and Ca3Fe1.5Mn1.5O8 were hard to hydrate, and the volume expansion rates of the tricomponent f-CaO varied with different compositions. Inductively, in BOF slag, the hydration activity sequence was solid solutions CaO-FeOx and CaO-FeOx-MnOy in tricomponent f-CaO < CaO in tricomponent f-CaO < monocomponent f-CaO; the volume expansion rates of tricomponent f-CaO changed with different compositions, and CaO-FeOx and CaO-FeOx-MnOy were difficult to hydrate. The reason why solid solutions CaO-FeOx and CaO-FeOx-MnOy were hard to hydrate was that their hydration reaction driving force, which is the absolute value of standard molar reaction Gibbs functions, decreased.

scholarly journals Drug Target Identification with Machine Learning: How to Choose Negative Examples

2021 ◽  
Vol 22 (10) ◽  
pp. 5118
Author(s):  
Matthieu Najm ◽  
Chloé-Agathe Azencott ◽  
Benoit Playe ◽  
Véronique Stoven
Keyword(s):  
Machine Learning ◽  
Drug Target ◽  
Target Identification ◽  
Target Prediction ◽  
False Positives ◽  
Machine Learning Algorithms ◽  
Statistical Bias ◽  
Protein Targets ◽  
Drug Target Identification ◽  
Approved Drugs

Identification of the protein targets of hit molecules is essential in the drug discovery process. Target prediction with machine learning algorithms can help accelerate this search, limiting the number of required experiments. However, Drug-Target Interactions databases used for training present high statistical bias, leading to a high number of false positives, thus increasing time and cost of experimental validation campaigns. To minimize the number of false positives among predicted targets, we propose a new scheme for choosing negative examples, so that each protein and each drug appears an equal number of times in positive and negative examples. We artificially reproduce the process of target identification for three specific drugs, and more globally for 200 approved drugs. For the detailed three drug examples, and for the larger set of 200 drugs, training with the proposed scheme for the choice of negative examples improved target prediction results: the average number of false positives among the top ranked predicted targets decreased, and overall, the rank of the true targets was improved.Our method corrects databases’ statistical bias and reduces the number of false positive predictions, and therefore the number of useless experiments potentially undertaken.

Sign in / Sign up

Export Citation Format

Share Document