The multilayer feed-forward ANN is an important modeling technique used in QSAR studying. The training of ANN is usually carried out only to optimize the weights of the neural network and without paying attention to the network topology. Some other strategies used to train ANN are, first, to discover an optimum structure of the network, and then to find weights for an already defined structure. These methods tend to converge to local optima, and may also lead to overfitting. In this article, a hybridized particle swarm optimization (PSO) approach was applied to the neural network structure training (HPSONN). The continuous version of PSO was used for the weight training of ANN, and the modified discrete PSO was applied to find appropriate the network architecture. The network structure and connectivity are trained simultaneously. The two versions of PSO can jointly search the global optimal ANN architecture and weights. A new objective function is formulated to determine the appropriate network architecture and optimum value of the weights. The proposed HPSONN algorithm was used to predict carcinogenic potency of aromatic amines and biological activity of a series of distamycin and distamycin-like derivatives. The results were compared to those obtained by PSO and GA training in which the network architecture was kept fixed. The comparison demonstrated that the HPSONN is a useful tool for training ANN, which converges quickly towards the optimal position, and can avoid overfitting in some extent.
In quantitative structure-activity relationship (QSAR) modeling, when compounds in a training set exhibit a significant structural distinction between each other, in particular when chemicals of biological interest interacting on the receptor involve a different mechanism, it might be difficult to construct a single linear model for the whole population of compounds of interest with desired residuals. Developing a piecewise linear local model can be effective to circumvent the aforementioned problem. In this paper, piecewise modeling by the particle swarm optimization (PMPSO) approach is applied to QSAR study. The minimum spanning tree is used for clustering all compounds in the training set to form a tree, and the modified discrete PSO is applied to divide the tree to find satisfactory piecewise linear models. A new objective function is formulated for searching the appropriate piecewise linear models. The proposed PMPSO algorithm was used to predict the antagonism of angiotensin II. The results demonstrated that PMPSO is useful for improvement of the performance of regression models.
Due to the excellent catalytic performance of Co-MOFs
and Ln-MOFs
on the chemical fixation of CO2, the self-assembly of microporous
heterometallic compounds with the aid of designed functional ligands
is carried out in our group. Herein, the solvothermal self-assembly
of Co2+, Yb3+, and 2,6-bis(2,4-dicarboxylphenyl)-4-(4-carboxylphenyl)pyridine
(H5BDCP) generated a rarely reported {CoYb}
n
-chain-based framework of {[CoYb(BDCP)(H2O)]·3DMF·3H2O}
n
(NUC-70) with quasi-nanoporous channels (aperture ca. 11.4 Å) shaped by six rows of {CoYb(CO2)5(H2O)}
n
nodes. To the best
of our knowledge, this is a rare 3d-4f heterometallic chain of {CoYb(CO2)5(H2O)}
n
with a staggered arrangement of Co2+ and Yb3+. After removing the associated water molecules, NUC-70a possesses the excellent characteristics of a large specific surface
area, unsaturated open metal sites of Co2+ and Yb3+ as Lewis acid sites, and high heat/water-resistant physicochemical
properties. Catalytic experiments showed that NUC-70a possessed a high catalytic activity on the cycloaddition reactions
of epoxides with CO2 under mild conditions. Furthermore,
the experiments performed confirmed that the Knoevenagel condensation
reactions of aldehydes and malononitrile could be efficiently catalyzed
by NUC-70a. This work illustrates that characteristic
ligand design plays a key role in the self-assembly of MOFs with specific
functions.
A coumarin derivative 4-methyl-8-methylacrylamide-2H, 5H-pyrano [3, 2-C] benzpyran 2, 5-dione (MMPBD) has been synthesized as a fluorescent carrier for preparing an optical chemical sensor. The carrier is immobilized on a quartz glass plate surface treated with a silanizing agent to prevent the leakage of the dye. This MMPBD sensor can be utilized for a nitrofurazone (NF) assay based on fluorescence quenching. The sensor shows good repeatability, a long lifetime and a fast response of less then 50 s. NF can be determined in the range between 1.0x10(-6)-1.0x10(-3 )mol L(-1) with a detection limit of 8.0x10(-7) mol L(-1 )at pH 7.0.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.