RESUMO
Determining and modeling the possible behaviour and actions of molecules requires investigating the basic structural features and physicochemical properties that determine their behaviour during chemical, physical, biological, and environmental processes. Computational approaches such as machine learning methods are alternatives to predicting the physiochemical properties of molecules based on their structures. However, the limited accuracy and high error rates of such predictions restrict their use. In this paper, a novel technique based on a deep learning convolutional neural network (CNN) for the prediction of chemical compounds' bioactivity is proposed and developed. The molecules are represented in the new matrix format Mol2mat, a molecular matrix representation adapted from the well-known 2D-fingerprint descriptors. To evaluate the performance of the proposed methods, a series of experiments were conducted using two standard datasets, namely the MDL Drug Data Report (MDDR) and Sutherland, datasets comprising 10 homogeneous and 14 heterogeneous activity classes. After analysing the eight fingerprints, all the probable combinations were investigated using the five best descriptors. The results showed that a combination of three fingerprints, ECFP4, EPFP4, and ECFC4, along with a CNN activity prediction process, achieved the highest performance of 98% AUC when compared to the state-of-the-art ML algorithms NaiveB, LSVM, and RBFN.
Assuntos
Aprendizado de Máquina , Redes Neurais de Computação , AlgoritmosRESUMO
Molecular similarity is a pervasive concept in drug design. The basic idea underlying molecular similarity is the similar property principle, which states that structurally similar molecules will exhibit similar physicochemical and biological properties. In this paper, a new graph-based molecular descriptor (GBMD) is introduced. The GBMD is a new method of obtaining a rough description of 2D molecular structure in textual form based on the canonical representations of the molecule outline shape and it allows rigorous structure specification using small and natural grammars. Simulated virtual screening experiments with the MDDR database show clearly the superiority of the graph-based descriptor compared to many standard descriptors (ALOGP, MACCS, EPFP4, CDKFP, PCFP, and SMILE) using the Tanimoto coefficient (TAN) and the basic local alignment search tool (BLAST) when searches were carried.
Assuntos
Bases de Dados de Compostos Químicos , Modelos Moleculares , Algoritmos , Simulação por Computador , Desenho de Fármacos , Estrutura Molecular , SoftwareRESUMO
Consensus clustering methods have been successfully used for combining multiple classifiers in many areas such as machine learning, applied statistics, pattern recognition and bioinformatics. In this paper, consensus clustering is used for combining the clusterings of chemical structures to enhance the ability of separating biologically active molecules from inactive ones in each cluster. Two graph-based consensus clustering methods were examined. The Quality Partition Index method (QPI) was used to evaluate the clusterings and the results were compared to the Ward's clustering method. Two homogeneous and heterogeneous subsets DS1-DS2 of MDL Drug Data Report database (MDDR) were used for experiments and represented by two 2D fingerprints. The results, obtained by a combination of multiple runs of an individual clustering and a single run of multiple individual clusterings, showed that graph-based consensus clustering methods can improve the effectiveness of chemical structures clusterings.