The Advantages of Flexibility: The Role of Entropy in Crystal Structures Containing C-H···F Interactions.

Molecular crystal structures are often interpreted in terms of strong, structure directing, intermolecular interactions, especially those with distinct geometric signatures such as H-bonds or π-stacking interactions. Other interactions can be overlooked, perhaps because they are weak or lack a characteristic geometry. We show that although the cumulative effect of weak interactions is significant, their deformability also leads to occupation of low energy vibrational energy levels, which provides an additional stabilizing entropic contribution. The entropies of five fluorobenzene derivatives have been calculated by periodic DFT calculations to assess the entropic influence of C-H···F interactions in stabilizing their crystal structures. Calculations reproduce inelastic neutron scattering data and experimental entropies from heat capacity measurements. C-H···F contacts are shown to have force constants which are around half of those of more familiar interactions such as hydrogen bonds, halogen bonds, and C-H···π interactions. This feature, in combination with the relatively high mass of F, means that the lowest energy vibrations in crystalline fluorobenzenes are dominated by C-H···F contributions. C-H···F contacts occur much more frequently than would be expected from their enthalpic contributions alone, but at 150 K, the stabilizing contribution of entropy provides, at -10 to -15 kJ mol-1, a similar level of stabilization to the N-H···N hydrogen bond in ammonia and O-H···O hydrogen bond in water.

Using deep learning-derived image features in radiologic time series to make personalised predictions: proof of concept in colonic transit data.

OBJECTIVES: Siamese neural networks (SNN) were used to classify the presence of radiopaque beads as part of a colonic transit time study (CTS). The SNN output was then used as a feature in a time series model to predict progression through a CTS. METHODS: This retrospective study included all patients undergoing a CTS in a single institution from 2010 to 2020. Data were partitioned in an 80/20 Train/Test split. Deep learning models based on a SNN architecture were trained and tested to classify images according to the presence, absence, and number of radiopaque beads and to output the Euclidean distance between the feature representations of the input images. Time series models were used to predict the total duration of the study. RESULTS: In total, 568 images of 229 patients (143, 62% female, mean age 57) patients were included. For the classification of the presence of beads, the best performing model (Siamese DenseNET trained with a contrastive loss with unfrozen weights) achieved an accuracy, precision, and recall of 0.988, 0.986, and 1. A Gaussian process regressor (GPR) trained on the outputs of the SNN outperformed both GPR using only the number of beads and basic statistical exponential curve fitting with MAE of 0.9 days compared to 2.3 and 6.3 days (p < 0.05) respectively. CONCLUSIONS: SNNs perform well at the identification of radiopaque beads in CTS. For time series prediction our methods were superior at identifying progression through the time series compared to statistical models, enabling more accurate personalised predictions. CLINICAL RELEVANCE STATEMENT: Our radiologic time series model has potential clinical application in use cases where change assessment is critical (e.g. nodule surveillance, cancer treatment response, and screening programmes) by quantifying change and using it to make more personalised predictions. KEY POINTS: • Time series methods have improved but application to radiology lags behind computer vision. Colonic transit studies are a simple radiologic time series measuring function through serial radiographs. • We successfully employed a Siamese neural network (SNN) to compare between radiographs at different points in time and then used the output of SNN as a feature in a Gaussian process regression model to predict progression through the time series. • This novel use of features derived from a neural network on medical imaging data to predict progression has potential clinical application in more complex use cases where change assessment is critical such as in oncologic imaging, monitoring for treatment response, and screening programmes.