Using spectral moments of spiral networks based on PSA/mass spectra outcomes to derive quantitative proteome-disease relationships (QPDRs) and predicting prostate cancer

In prostate cancer (PCa), prognostic (predictive) factors are particularly important given the marked heterogeneity of this disease at clinical, morphologic, and biomolecular levels. Blood contains a treasure of previously unstudied biomarkers that could reflect the ongoing physiological state of all tissue. The serum prostate-specific antigen (PSA) measurement is a very good biomarker for PCa, but the percentage of bad classification is somewhat high. The blood proteome mass spectra (MS) represent a potential tool for detection of diseases; however the identification of a single biomarker from the complex output from MS is often difficult. In this paper, we propose a general strategy, based on computational chemistry techniques, which should improve the predictive power of PSA. Our group adapted the square-spiral graph to represent human serum-plasma-proteome MS for healthy and PCa patients. These graphs were previously applied to DNA and/or protein sequences. In this work, we calculated different classes of connectivity indices (CIs), and created various models based on the spectral moments. The best QPDRs model found showed accuracy values ranging from 71.7% to 97.2%, and 70.4% to 99.2% of specificity. This methodology might be useful for several applications in computational chemistry.     

Neural network‐derived Potts models for structure‐based protein design using backbone atomic coordinates and tertiary motifs

Designing novel proteins to perform desired functions, such as binding or catalysis, is a major goal in synthetic biology. A variety of computational approaches can aid in this task. An energy‐based framework rooted in the sequence‐structure statistics of tertiary motifs (TERMs) can be used for sequence design on predefined backbones. Neural network models that use backbone coordinate‐derived features provide another way to design new proteins. In this work, we combine the two methods to make neural structure‐based models more suitable for protein design. Specifically, we supplement backbone‐coordinate features with TERM‐derived data, as inputs, and we generate energy functions as outputs. We present two architectures that generate Potts models over the sequence space: TERMinator, which uses both TERM‐based and coordinate‐based information, and COORDinator, which uses only coordinate‐based information. Using these two models, we demonstrate that TERMs can be utilized to improve native sequence recovery performance of neural models. Furthermore, we demonstrate that sequences designed by TERMinator are predicted to fold to their target structures by AlphaFold. Finally, we show that both TERMinator and COORDinator learn notions of energetics, and these methods can be fine‐tuned on experimental data to improve predictions. Our results suggest that using TERM‐based and coordinate‐based features together may be beneficial for protein design and that structure‐based neural models that produce Potts energy tables have utility for flexible applications in protein science.