Search

Background: Early diagnosis is the most effective intervention to improve the prognosis of cutaneous melanoma. Even though the introduction of dermoscopy has improved the diagnostic accuracy, it can still be difficult to distinguish some melanomas from benign melanocytic lesions. Digital dermoscopy monitoring can identify dynamic changes of melanocytic lesions: To date, some algorithms were proposed, but a universally accepted one is still lacking. Objectives: To identify independent predictive variables associated with the diagnosis of cutaneous melanoma and develop a multivariable dermoscopic prediction model able to discriminate benign from malignant melanocytic lesions undergoing digital dermoscopy monitoring. Methods: We collected dermoscopic images of melanocytic lesions excised after dermoscopy monitoring and carried out static and dynamic evaluations of dermoscopic features. We built two multivariable predictive models based on logistic regression and random forest. Results: We evaluated 173 lesions (65 cutaneous melanomas and 108 nevi). Forty‐two melanomas were in situ, and the median thickness of invasive melanomas was 0.35 mm. The median follow‐up time was 9.8 months for melanomas and 9.1 for nevi. The logistic regression and random forest models performed with AUC values of 0.87 and 0.89, respectively, were substantially higher than those of the static evaluation models (ABCD TDS score, 0.57; 7‐point checklist, 0.59). Finally, we built two risk calculators, which translate the proposed models into user‐friendly applications, to assist clinicians in the decision‐making process. Conclusions: The present study demonstrates that the integration of dynamic and static evaluations of melanocytic lesions is a safe approach that can significantly boost the diagnostic accuracy for cutaneous melanoma. We propose two diagnostic tools that significantly increase the accuracy in discriminating melanoma from nevi during digital dermoscopy monitoring. [ABSTRACT FROM AUTHOR]

The prediction of free energy changes upon protein residue variations is an important application in biophysics and biomedicine. Several methods have been developed to address this problem so far, including physical-based and machine learning models. However, most of the current computational tools, especially data-driven approaches, fail to incorporate the antisymmetric basic thermodynamic principle: a variation from wild-type to a mutated form of the protein structure () and its reverse process () must have opposite values of the free energy difference:. Here, we build a deep neural network system that, by construction, satisfies the antisymmetric properties. We show that the new method (ACDC-NN) achieved comparable or better performance with respect to other state-of-the-art approaches on both direct and reverse variations, making this method suitable for scoring new protein variants preserving the antisymmetry. The code is available at: https://github.com/compbiomed-unito/acdc-nn. [ABSTRACT FROM AUTHOR]

The prediction of the protein tertiary structure from solely its residue sequence (the so called Protein Folding Problem) is one of the most challenging problems in Structural Bioinformatics. We focus on the protein residue contact map. When this map is assigned it is possible to reconstruct the 3D structure of the protein backbone. The general problem of recovering a set of 3D coordinates consistent with some given contact map is known as a unit-disk-graph realization problem and it has been recently proven to be NP-Hard. In this paper we describe a heuristic method (COMAR) that is able to reconstruct with an unprecedented rate (3-15 seconds) a 3D model that exactly matches the target contact map of a protein. Working with a non-redundant set of 1760 proteins, we find that the scoring efficiency of finding a 3D model very close to the protein native structure depends on the threshold value adopted to compute the protein residue contact map. Contact maps whose threshold values range from 10 to 18 Aringngstroms allow reconstructing 3D models that are very similar to the proteins native structure. [ABSTRACT FROM PUBLISHER]

A Cascade Correlation Learning Architecture (CCLA) of neural networks is tested on the task of predicting the secondary structure of proteins. The results are compared with those obtained with Neural Networks (NN) trained with the back-propagation algorithm (BPNN) and generated with genetic algorithms. CCLA proceeds towards the global minimum of the error function more efficiently than BPNN. However, only a slight improvement in the average efficiency value is noticeable (61.82% as compared with 61.61% obtained with BPNN). The values of the three correlation coefficients for the discriminated secondary structures are also rather similar (Ct8, C α, C β and Ccoil are 0.36, 0.29 and 0.36 with CCLA, and 0.36, 0.31 and 0.35 with BPNN). This indicates that the efficiency of the prediction does not depend upon the training algorithm, and confirms our previous observation that when single sequences are used as input code to the network system, different NN architectures can perform similarly. [ABSTRACT FROM AUTHOR]