RESUMEN
The most direct approach to determining if two aqueous solutions will phase-separate upon mixing is to exhaustively screen them in a pair-wise fashion. This is a time-consuming process that involves preparation of numerous stock solutions, precise transfer of highly concentrated and often viscous solutions, exhaustive agitation to ensure thorough mixing, and time-sensitive monitoring to observe the presence of emulsion characteristics indicative of phase separation. Here, we examined the pair-wise mixing behavior of 68 water-soluble compounds by observing the formation of microscopic phase boundaries and droplets of 2278 unique 2-component solutions. A series of machine learning classifiers (artificial neural network, random forest, k-nearest neighbors, and support vector classifier) were then trained on physicochemical property data associated with the 68 compounds and used to predict their miscibility upon mixing. Miscibility predictions were then compared to the experimental observations. The random forest classifier was the most successful classifier of those tested, displaying an average receiver operator characteristic area under the curve of 0.74. The random forest classifier was validated by removing either one or two compounds from the input data, training the classifier on the remaining data and then predicting the miscibility of solutions involving the removed compound(s) using the classifier. The accuracy, specificity, and sensitivity of the random forest classifier were 0.74, 0.80, and 0.51, respectively, when one of the two compounds to be examined was not represented in the training data. When asked to predict the miscibility of two compounds, neither of which were represented in the training data, the accuracy, specificity, and sensitivity values for the random forest classifier were 0.70, 0.82 and 0.29, respectively. Thus, there is potential for this machine learning approach to improve the design of screening experiments to accelerate the discovery of aqueous two-phase systems for numerous scientific and industrial applications.
RESUMEN
At the most fundamental level, collagen fibrils are rope-like structures assembled from triple-helical collagen molecules. One key structural characteristic of the fibril is the 67 nm D-band pattern arising from the quarter-stagger packing of the molecules. Our current understanding of the structural changes induced by tensile loading of collagen fibrils comes mostly from atomistic molecular dynamics simulations and tissue level experiments. Tensile testing of individual fibrils is an upcoming field of investigation, and thus far structural analysis has always taken place after the fibrils have been ruptured or strained and subsequently dried. There is therefore a gap in understanding how the structure of collagen fibrils transforms under tension, and how this reorganization affects the functionality of collagen fibrils within tissues. In this study, atomic force microscopy based nanomechanical mapping is introduced to image hydrated collagen fibrils absorbed to an elastic substrate. Upon stretching the substrate between 5 and 30%, we observe a radial stiffening consistent with the fibrils being under tension. This is associated with an increase in D-band length. In addition the indentation modulus contrast associated with the D-band pattern increases linearly with D-band strain. These results provide direct confirmation of, and new information on the axially inhomogeneous structural response of collagen fibrils to applied tension as previously proposed on the basis of X-ray scattering experiments on stretched tissues. Furthermore our approach opens the road for studying the structural impacts of tension on cell-matrix interactions at the molecular level.