RESUMEN
Covid-19 has caused massive numbers of infections and fatalities globally. In response, there has been a large-scale experimental and computational research effort to study and develop drugs. Towards this, Deep learning techniques are used for the generation of potential novel drug candidates that are proven to be effective against exploring large molecular search spaces. Recent advances in reinforcement learning in conjunction with generative techniques has proven to be a promising field in the area of drug discovery. In this regard, we propose a generative drug discovery approach using reinforcement techniques for sampling novel molecules that bind to the main protease of SARS-COV2. The generative method reported significant validity scores for the generated novel molecules and captured the underlying features of the training molecules. Further, the model is fine-tuned on existing re-purposed molecules which are active towards specific target proteins based on similarity metrics. Upon fine tuning the model generated 92.71% valid, 93.55% unique, and 100% novel molecules. Unlike previous methods which are dependent on docking procedures, we proposed a deep learning based novel drug target interaction (DTI) model to find the binding affinity between candidate molecules and target protease sequence. Finally, the binding affinity of the generated molecules is predicted against the 3CLPro main protease by using the proposed DTI model. Most of the generated molecules have shown binding affinity scores <100 nM (lower the better), which are significantly better compared to the existing commercial drugs including Remdesevir.
Asunto(s)
COVID-19 , Humanos , ARN Viral , SARS-CoV-2 , Interacciones Farmacológicas , Péptido HidrolasasRESUMEN
Promoter is a small region of DNA where a protein called RNA polymerase binds thus resulting in initiation of transcription of a specific gene. In bacteria with prokaryotic cell type, the sigma subunit that combines with RNA polymerase helps in identifying promoters. In Escherichia coli (E.coli), the promoters are identified by different sigma factors consisting of different functionalities. There have been various methods used for prediction of different class of promoters. However, these methods need to be improved for better identification and classification of promoters. In this work, we propose a new multi-layer predictor named PPred-PCKSM that uses position-correlation based k-mer scoring matrix (PCKSM), a new feature extraction strategy and an artificial neural network (ANN) for predicting promoters and its six types, namely σ70, σ24, σ28, σ32, σ38 and σ54 in E.coli bacteria. We employ PCKSM technique to extract feature sets from different k-mers. The feature sets obtained from trimers and tetramers are concatenated and then passed through ANN for final prediction. The resultant feature set contained effective features that contributed towards achieving an accuracy of 98.02% and Matthews correlation coefficient (MCC) of 96.04% for promoter prediction task. Our model used 5-fold cross validation on the benchmark dataset and outperformed all the current state-of-art-methods used for prediction of promoters and its different types in E.coli bacteria.
Asunto(s)
ARN Polimerasas Dirigidas por ADN , Factor sigma , ARN Polimerasas Dirigidas por ADN/genética , ARN Polimerasas Dirigidas por ADN/metabolismo , Escherichia coli/genética , Escherichia coli/metabolismo , Regiones Promotoras Genéticas/genética , Factor sigma/genética , Factor sigma/metabolismo , Transcripción GenéticaRESUMEN
Neural network architectures are high-performing variable models that can solve many learning tasks. Designing architectures manually require substantial time and also prior knowledge and expertise to develop a high-accuracy model. Most of the architecture search methods are developed over the task of image classification resulting in the building of complex architectures intended for large data inputs such as images. Motivated by the applications of DNA computing in Neural Architecture Search (NAS), we propose NoAS-DS which is specifically built for the architecture search of sequence-based classification tasks. Furthermore, NoAS-DS is applied to the task of predicting binding sites. Unlike other methods that implement only Convolution layers, NoAS-DS, specifically combines Convolution and LSTM layers that helps in the process of automatic architecture building. This hybrid approach helped in achieving high accuracy results on TFBS and RBP datasets which outperformed other models in TF-DNA binding prediction tasks. The best architectures generated by the proposed model can be applied to other DNA datasets of similar nature using transfer learning technique that demonstrates its generalization capability. This greatly reduces the effort required to build new architectures for other prediction tasks.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Redes Neurales de la Computación , ADN/genética , Recolección de Datos , Generalización PsicológicaRESUMEN
Viral infection causes a wide variety of human diseases including cancer and COVID-19. Viruses invade host cells and associate with host molecules, potentially disrupting the normal function of hosts that leads to fatal diseases. Novel viral genome prediction is crucial for understanding the complex viral diseases like AIDS and Ebola. While most existing computational techniques classify viral genomes, the efficiency of the classification depends solely on the structural features extracted. The state-of-the-art DNN models achieved excellent performance by automatic extraction of classification features, but the degree of model explainability is relatively poor. During model training for viral prediction, proposed CNN, CNN-LSTM based methods (EdeepVPP, EdeepVPP-hybrid) automatically extracts features. EdeepVPP also performs model interpretability in order to extract the most important patterns that cause viral genomes through learned filters. It is an interpretable CNN model that extracts vital biologically relevant patterns (features) from feature maps of viral sequences. The EdeepVPP-hybrid predictor outperforms all the existing methods by achieving 0.992 mean AUC-ROC and 0.990 AUC-PR on 19 human metagenomic contig experiment datasets using 10-fold cross-validation. We evaluate the ability of CNN filters to detect patterns across high average activation values. To further asses the robustness of EdeepVPP model, we perform leave-one-experiment-out cross-validation. It can work as a recommendation system to further analyze the raw sequences labeled as 'unknown' by alignment-based methods. We show that our interpretable model can extract patterns that are considered to be the most important features for predicting virus sequences through learned filters.
RESUMEN
The genetic code contains information that impacts the efficiency and rate of translation. Translation elongation plays a crucial role in determining the composition of the proteome, errors within a protein contributes towards disease processes. It is important to analyze the novel coronavirus (2019-nCoV) at the codon level to find similarities and variations in hosts to compare with other human coronavirus (CoVs). This requires a comparative and comprehensive study of various human and zoonotic nature CoVs relating to codon usage bias, relative synonymous codon usage (RSCU), proportions of slow codons, and slow di-codons, the effective number of codons (ENC), mutation bias, codon adaptation index (CAI), and codon frequencies. In this work, seven different CoVs were analyzed to determine the protein synthesis rate and the adaptation of these viruses to the host cell. The result reveals that the proportions of slow codons and slow di-codons in human host of 2019-nCoV and SARS-CoV found to be similar and very less compared to the other five coronavirus types, which suggest that the 2019-nCoV and SARS-CoV have faster protein synthesis rate. Zoonotic CoVs have high RSCU and codon adaptation index than human CoVs which implies the high translation rate in zoonotic viruses. All CoVs have more AT% than GC% in genetic codon compositions. The average ENC values of seven CoVs ranged between 38.36 and 49.55, which implies the CoVs are highly conserved and are easily adapted to host cells. The mutation rate of 2019-nCoV is comparatively less than MERS-CoV and NL63 that shows an evidence for genetic diversity. Host-specific codon composition analysis portrays the relation between viral host sequences and the capability of novel virus replication in host cells. Moreover, the analysis provides useful measures for evaluating a virus-host adaptation, transmission potential of novel viruses, and thus contributes to the strategies of anti-viral drug design.