Artificial neural network, machine learning modelling of compressive strength of recycled coarse aggregate based self-compacting concrete.

This research study aims to understand the application of Artificial Neural Networks (ANNs) to forecast the Self-Compacting Recycled Coarse Aggregate Concrete (SCRCAC) compressive strength. From different literature, 602 available data sets from SCRCAC mix designs are collected, and the data are rearranged, reconstructed, trained and tested for the ANN model development. The models were established using seven input variables: the mass of cementitious content, water, natural coarse aggregate content, natural fine aggregate content, recycled coarse aggregate content, chemical admixture and mineral admixture used in the SCRCAC mix designs. Two normalization techniques are used for data normalization to visualize the data distribution. For each normalization technique, three transfer functions are used for modelling. In total, six different types of models were run in MATLAB and used to estimate the 28th day SCRCAC compressive strength. Normalization technique 2 performs better than 1 and TANSING is the best transfer function. The best k-fold cross-validation fold is k = 7. The coefficient of determination for predicted and actual compressive strength is 0.78 for training and 0.86 for testing. The impact of the number of neurons and layers on the model was performed. Inputs from standards are used to forecast the 28th day compressive strength. Apart from ANN, Machine Learning (ML) techniques like random forest, extra trees, extreme boosting and light gradient boosting techniques are adopted to predict the 28th day compressive strength of SCRCAC. Compared to ML, ANN prediction shows better results in terms of sensitive analysis. The study also extended to determine 28th day compressive strength from experimental work and compared it with 28th day compressive strength from ANN best model. Standard and ANN mix designs have similar fresh and hardened properties. The average compressive strength from ANN model and experimental results are 39.067 and 38.36 MPa, respectively with correlation coefficient is 1. It appears that ANN can validly predict the compressive strength of concrete.

Pharmacophore modeling, in silico screening, molecular docking and molecular dynamics approaches for potential alpha-delta bungarotoxin-4 inhibitors discovery.

BACKGROUND: The alpha-delta bungartoxin-4 (α-δ-Bgt-4) is a potent neurotoxin produced by highly venomous snake species, Bungarus caeruleus, mainly targeting neuronal acetylcholine receptors (nAchRs) and producing adverse biological malfunctions leading to respiratory paralysis and mortality. OBJECTIVE: In this study, we predicted the three-dimensional structure of α-δ-Bgt-4 using homology modeling and investigated the conformational changes and the key residues responsible for nAchRs inhibiting activity. MATERIALS AND METHODS: From the selected plants, which are traditionally used for snake bites, the active compounds are taken and performed molecular interaction studies and also used for modern techniques like pharmacophore modeling and mapping and absorption, distribution, metabolism, elimination and toxicity analysis which may increase the possibility of success. RESULTS: Moreover, 100's of drug-like compounds were retrieved and analyzed through computational virtual screening and allowed for pharmacokinetic profiling, molecular docking and dynamics simulation. CONCLUSION: Finally the top five drug-like compounds having competing level of inhibition toward α-δ-Bgt-4 toxin were suggested based on their interaction with α-δ-Bgt-4 toxin.

In silico analysis of potential inhibitors of Ca(2+) activated K(+) channel blocker, Charybdotoxin-C from Leiurus quinquestriatus hebraeus through molecular docking and dynamics studies.

OBJECTIVE: Charybdotoxin-C (ChTx-C), from the scorpion Leiurus, quinquestriatus hebraeus blocks the calcium-activated potassium channels and causes hyper excitability of the nervous system. Detailed understanding the structure of ChTx-C, conformational stability, and intermolecular interactions are required to select the potential inhibitors of the toxin. MATERIALS AND METHODS: The structure of ChTx-C was modeled using Modeller 9v7. The amino acid residues lining the binding site were predicted and used for toxin-ligand docking studies, further, selected toxin-inhibitor complexes were studied using molecular dynamics (MD) simulations. RESULTS: The predicted structure has 91.7% of amino acids in the core and allowed regions of Ramachandran plot. A total of 133 analog compounds of existing drugs for scorpion bites were used for docking. As a result of docking, a list of compounds was shown good inhibiting properties with target protein. By analyzing the interactions, Ser 15, Lys 32 had significant interactions with selected ligand molecules and Val5, which may have hydrophobic interaction with the cyclic group of the ligand. MD simulation studies revealed that the conformation and intermolecular interactions of all selected toxin-inhibitor complexes were stable. CONCLUSION: The interactions of the ligand and active site amino acids were found out for the best-docked poses in turn helpful in designing potential antitoxins which may further be exploited in toxin based therapies.