Symbolic, neural, and Bayesian machine learning models for predicting carcinogenicity of chemical compounds

Experimental programs have been underway for several years to determine the environmental effects of chemical compounds, mixtures, and the like. Among these programs is the National Toxicology Program (NTP) on rodent carcinogenicity. Because these experiments are costly and time-consuming, the rate at which test articles (i.e., chemicals) can be tested is limited. The ability to predict the outcome of the analysis at various points in the process would facilitate informed decisions about the allocation of testing resources. To assist human experts in organizing an empirical testing regime, and to try to shed light on mechanisms of toxicity, we constructed toxicity models using various machine learning and data mining methods, both existing and those of our own devising. These models took the form of decision trees, rule sets, neural networks, rules extracted from trained neural networks, and Bayesian classifiers. As a training set, we used recent results from rodent carcinogenicity bioassays conducted by the NTP on 226 test articles. We performed 10-way cross-validation on each of our models to approximate their expected error rates on unseen data. The data set consists of physical-chemical parameters of test articles, alerting chemical substructures, salmonella mutagenicity assay results, subchronic histopathology data, and information on route, strain, and sex/species for 744 individual experiments. These results contribute to the ongoing process of evaluating and interpreting the data collected from chemical toxicity studies.     

The synthesis and characterization of some cyclic N-cyanoguanidines

The sodium hydroxide catalyzed synthesis of several cyclic N-cyanoguanidines ( 8,10 ) from dimethyl cyanoimidodithioearbonate ( 2 ) and the appropriate aniline derivative ( 4,5 ) is described. Base-induced di-N-alkylation to afford 9 and 11 occurs readily.     

Novel polycyclic heterocycles. XIV. 1,2-Dihydro-4-(trifluoromethyl)-3H-8H-quino[1,8-ab][4,1]benzoxazepin-3-one and its derivatives

Procedures for the isolation of 1,2-dihydro-4-(trifluoromethyl)-3H,8H-quino[1,8-ab][4,1]-benzoxazepine, 3 , from reaction mixtures containing 3 as the minor component, and the isomer, 1,2-dihydro-11-(trifluoromethyl)-3H,7H-quino[8,1-cd][1,5]benzoxazepin-3-one, 2 , as the major component, are described. The reactivity of 3 toward hydroxylamine and aromatic aldehydes has been investigated and the preparation of derivatives with those reactants is described.     

Aqueous RAFT Synthesis of Low Molecular Weight Anionic Polymers for Determination of Structure/Binding Interactions with Gliadin

Gliadin, a component of gluten and a known epitope, is implicated in celiac disease (CeD) and results in an inflammatory response in CeD patients when consumed. Acrylamide‐based polyelectrolytes are employed as models to determine the effect of molecular weight and pendent group on non‐covalent interaction modes with gliadin in vitro. Poly(sodium 2‐acrylamido‐2‐methylpropane sulfonate) and poly(sodium 3‐methylpropyl‐3‐butanoate) are synthesized via aqueous reversible addition fragmentation chain transfer (aRAFT) polymerization and characterized by gel permeation chromatography‐multiangle laser light scattering. The polymer/gliadin blends are examined via circular dichroism, zeta potential measurements, 8‐anilinonaphthalene‐1‐sulfonic acid fluorescence spectroscopy, and dynamic light scattering. Acrylamide polymers containing strong anionic pendent groups have a profound effect on gliadin secondary structure and solution behavior below the isoelectric point, while polymers containing hydrophobic character only have a minor impact. The polymers have little effect on gliadin secondary structure and solution behavior at the isoelectric point.     

Sorption of inorganic nanoparticles in woven cellulose fabrics

Titanium dioxide was deposited from aqueous suspension onto cellulosic surfaces.Titania was sourced from Degussa (P25TM,70:30 anatase:rutile).Dry uptake of particles was shown to be rapid and dominant with one-third of the deposition occurring in less than 30 s and over one-half in the first minute.Isotherms were recorded to compare the rate of titanium deposition on dry and pre-wetted cotton.In the dry case uptake reached a maximum in 30 min whereas in the pre-wetted case the uptake was seen to continue beyond 180 min.A broad trend of higher deposition occurring at lower pH was seen,corresponding to the region where surface charges were opposite and thus attractive.Dry pickup was less significant at high pH.The response to varying ionic strength was complex and was attributed to the combined effect of charge screening,particle aggregation and consequent particle entrapment or occlusion.Titania deposition into the interstices of woven cotton sheets resulted in the formation of inorganic,nanoparticulate skeletons which could be isolated by controlled combustion of the cellulose and thus cotton was suggested to have potential for the templated synthesis of high surface area semiconductor materials.     

Quaternary derivatives from 2-aminobenzimidazole and 2-phenylethyl- and phenyloxymethyl halides

2-Aminobenzimidazole has been reacted with phenylethyl bromides and phenyloxymethyl chlorides to prepare a number of novel 1,3-bis-substituted quaternary derivatives.