RESUMO
Inspired by natural language processing techniques, we here introduce Mol2vec, which is an unsupervised machine learning approach to learn vector representations of molecular substructures. Like the Word2vec models, where vectors of closely related words are in close proximity in the vector space, Mol2vec learns vector representations of molecular substructures that point in similar directions for chemically related substructures. Compounds can finally be encoded as vectors by summing the vectors of the individual substructures and, for instance, be fed into supervised machine learning approaches to predict compound properties. The underlying substructure vector embeddings are obtained by training an unsupervised machine learning approach on a so-called corpus of compounds that consists of all available chemical matter. The resulting Mol2vec model is pretrained once, yields dense vector representations, and overcomes drawbacks of common compound feature representations such as sparseness and bit collisions. The prediction capabilities are demonstrated on several compound property and bioactivity data sets and compared with results obtained for Morgan fingerprints as a reference compound representation. Mol2vec can be easily combined with ProtVec, which employs the same Word2vec concept on protein sequences, resulting in a proteochemometric approach that is alignment-independent and thus can also be easily used for proteins with low sequence similarities.
Assuntos
Processamento de Linguagem Natural , Conformação Proteica , Aprendizado de Máquina não Supervisionado , Algoritmos , Conjuntos de Dados como Assunto , Modelos Químicos , Estrutura Molecular , Proteínas/química , Reprodutibilidade dos TestesRESUMO
Protein kinases are involved in a variety of diseases including cancer, inflammation, and autoimmune disorders. Although the development of new kinase inhibitors is a major focus in pharmaceutical research, a large number of kinases remained so far unexplored in drug discovery projects. The selection and assessment of targets is an essential but challenging area. Today, a few thousands of experimentally determined kinase structures are available, covering about half of the human kinome. This large structural source allows guiding the target selection via structure-based druggability prediction approaches such as DoGSiteScorer. Here, a thorough analysis of the ATP pockets of the entire human kinome in the DFG-in state is presented in order to prioritize novel kinase structures for drug discovery projects. For this, all human kinase X-ray structures available in the PDB were collected, and homology models were generated for the missing part of the kinome. DoGSiteScorer was used to calculate geometrical and physicochemical properties of the ATP pockets and to predict the potential of each kinase to be druggable. The results indicate that about 75% of the kinome are in principle druggable. Top ranking structures comprise kinases that are primary targets of known approved drugs but additionally point to so far less explored kinases. The presented analysis provides new insights into the druggability of ATP binding pockets of the entire kinome. We anticipate this comprehensive druggability assessment of protein kinases to be helpful for the community to prioritize so far untapped kinases for drug discovery efforts.
Assuntos
Trifosfato de Adenosina/metabolismo , Descoberta de Drogas/métodos , Proteínas Quinases/química , Proteínas Quinases/metabolismo , Homologia Estrutural de Proteína , Sítios de Ligação , Cristalografia por Raios X , Bases de Dados de Proteínas , Desenho de Fármacos , Humanos , Mesilato de Imatinib/química , Mesilato de Imatinib/farmacologia , Ligantes , Modelos Moleculares , Inibidores de Proteínas Quinases/química , Inibidores de Proteínas Quinases/farmacologiaRESUMO
In this manuscript, which appeared in ALTEX (2020), 37(1), 24-36, doi:10.14573/altex.1904031 , there were errors in Tables 1 and 3.
RESUMO
Microcystins (MC) represent a family of cyclic peptides with approx. 250 congeners presumed harmful to human health due to their ability to inhibit ser/thr-proteinphosphatases (PPP), albeit all hazard and risk assessments (RA) are based on data of one MC-congener (MC-LR) only. MC congener structural diversity is a challenge for the risk assessment of these toxins, especially as several different PPPs have to be included in the RA. Consequently, the inhibition of PPP1, PPP2A and PPP5 was determined with 18 structurally different MC and demonstrated MC congener dependent inhibition activity and a lower susceptibility of PPP5 to inhibition than PPP1 and PPP2A. The latter data were employed to train a machine learning algorithm that should allow prediction of PPP inhibition (toxicity) based on MCs 2D chemical structure. IC50 values were classified in toxicity classes and three machine learning models were used to predict the toxicity class, resulting in 80-90% correct predictions.