RESUMEN
Predicting the protein-nucleic acid (PNA) binding affinity solely from their sequences is of paramount importance for the experimental design and analysis of PNA interactions (PNAIs). A large number of currently developed models for binding affinity prediction are limited to specific PNAIs while also relying on the sequence and structural information of the PNA complexes for both training and testing, and also as inputs. As the PNA complex structures available are scarce, this significantly limits the diversity and generalizability due to the small training data set. Additionally, a majority of the tools predict a single parameter, such as binding affinity or free energy changes upon mutations, rendering a model less versatile for usage. Hence, we propose DeePNAP, a machine learning-based model built from a vast and heterogeneous data set with 14,401 entries (from both eukaryotes and prokaryotes) from the ProNAB database, consisting of wild-type and mutant PNA complex binding parameters. Our model precisely predicts the binding affinity and free energy changes due to the mutation(s) of PNAIs exclusively from their sequences. While other similar tools extract features from both sequence and structure information, DeePNAP employs sequence-based features to yield high correlation coefficients between the predicted and experimental values with low root mean squared errors for PNA complexes in predicting KD and ΔΔG, implying the generalizability of DeePNAP. Additionally, we have also developed a web interface hosting DeePNAP that can serve as a powerful tool to rapidly predict binding affinities for a myriad of PNAIs with high precision toward developing a deeper understanding of their implications in various biological systems. Web interface: http://14.139.174.41:8080/.
Asunto(s)
Aprendizaje Profundo , Ácidos Nucleicos , Unión Proteica , Proteínas/química , MutaciónRESUMEN
Nephrotic syndrome (NS) is classified based on morphological changes of glomeruli in biopsied kidney tissues evaluated by time-consuming microscopy methods. In contrast, we employed desorption electrospray ionization mass spectrometry (DESI-MS) directly on renal biopsy specimens obtained from 37 NS patients to rapidly differentiate lipid profiles of three prevalent forms of NS: IgA nephropathy (n = 9), membranous glomerulonephritis (n = 7), and lupus nephritis (n = 8), along with other types of glomerular diseases (n = 13). As we noted molecular heterogeneity in regularly spaced renal tissue regions, multiple sections from each biopsy specimen were collected, providing a total of 973 samples for investigation. Using multivariate analysis, we report differential expressions of glycerophospholipids, sphingolipids, and glycerolipids among the above four classes of NS kidneys, which were otherwise overlooked in several past studies correlating lipid abnormalities with glomerular diseases. We developed machine learning (ML) models with the top 100 features using the support vector machine, which enabled us to discriminate the concerned glomerular diseases with 100% overall accuracy in the training, validation, and holdout test set. This DESI-MS/ML-based tissue analysis can be completed in a few minutes, in sharp contrast to a daylong procedure followed in the conventional histopathology of NS.