Refining Field Cancerization: An Institutional Cohort Analysis of Patient Characteristics in a Validation Cohort.

BACKGROUND: Field cancerization is poorly defined in dermatology. The author group previously proposed and applied a classification system in an original cohort to risk-stratify patients with field cancerization. OBJECTIVE: Apply the authors' classification system within a validation cohort. METHODS: Patients with keratinocyte carcinoma history completed a survey regarding demographic information, medical history, and chemoprevention use. Patients were assigned a field cancerization class, and differences between validation and original cohorts were assessed. RESULTS: A total of 363 patients were enrolled (mean age 67.4; 61.7% male). After comparing validation and original cohorts, there were differences in age between class II (p = .02) and class IVb (p = .047), and differences in chemoprevention use in class III (p = .04). Similar to the original cohort, the validation cohort was associated with increases in total number of skin cancers in the last year (p < .001), 5 years (p < .001), lifetime (p < .001), years since first skin cancer (p < .001), and chemoprevention use (p < .001). In the validation cohort, there were increases in age (p = .03) and immunocompromised status (p = .04) with increasing class, which were not observed in the original cohort. CONCLUSION: Differences among field cancerization classes were similar in a validation cohort, further highlighting the importance of class-specific treatment and management.

Predictive Models and Impact of Interfacial Contacts and Amino Acids on Protein-Protein Binding Affinity.

Protein-protein interactions (PPIs) play a central role in nearly all cellular processes. The strength of the binding in a PPI is characterized by the binding affinity (BA) and is a key factor in controlling protein-protein complex formation and defining the structure-function relationship. Despite advancements in understanding protein-protein binding, much remains unknown about the interfacial region and its association with BA. New models are needed to predict BA with improved accuracy for therapeutic design. Here, we use machine learning approaches to examine how well different types of interfacial contacts can be used to predict experimentally determined BA and to reveal the impact of the specific amino acids at the binding interface on BA. We create a series of multivariate linear regression models incorporating different contact features at both residue and atomic levels and examine how different methods of identifying and characterizing these properties impact the performance of these models. Particularly, we introduce a new and simple approach to predict BA based on the quantities of specific amino acids at the protein-protein interface. We found that the numbers of specific amino acids at the protein-protein interface were correlated with BA. We show that the interfacial numbers of amino acids can be used to produce models with consistently good performance across different data sets, indicating the importance of the identities of interfacial amino acids in underlying BA. When trained on a diverse set of complexes from two benchmark data sets, the best performing BA model was generated with an explicit linear equation involving six amino acids. Tyrosine, in particular, was identified as the key amino acid in controlling BA, as it had the strongest correlation with BA and was consistently identified as the most important amino acid in feature importance studies. Glycine and serine were identified as the next two most important amino acids in predicting BA. The results from this study further our understanding of PPIs and can be used to make improved predictions of BA, giving them implications for drug design and screening in the pharmaceutical industry.

Multiplexed Surface Protein Detection and Cancer Classification Using Gap-Enhanced Magnetic-Plasmonic Core-Shell Raman Nanotags and Machine Learning Algorithm.

Cancer is the second leading cause of death attributed to disease worldwide. Current standard detection methods often rely on a single cancer marker, which can lead to inaccurate results, including false negatives, and an inability to detect multiple cancers simultaneously. Here, we developed a multiplex method that can effectively detect and classify surface proteins associated with three distinct types of breast cancer by utilizing gap-enhanced Raman scattering nanotags and machine learning algorithm. We synthesized anisotropic magnetic core-gold shell gap-enhanced Raman nanotags incorporating three different Raman reporters. These multicolor Raman nanotags were employed to distinguish specific surface protein markers in breast cancer cells. The acquired signals were deconvoluted and analyzed using classical least-squares regression to generate a surface protein profile and characterize the breast cancer cells. Furthermore, computational data obtained via finite-difference time-domain and discrete dipole approximation showed the amplification of the electric fields within the gap region due to plasmonic coupling between the two gold layers. Finally, a random forest classifier achieved an impressive classification and profiling accuracy of 93.9%, enabling effective distinguishing between the three different types of breast cancer cell lines in a mixed solution. With the combination of immunomagnetic multiplex target specificity and separation, gap-enhancement Raman nanotags, and machine learning, our method provides an accurate and integrated platform to profile and classify different cancer cells, giving implications for identification of the origin of circulating tumor cells in the blood system.