Artificial intelligence in the life sciences最新文献

Designing magic shotgun compounds, i.e., compounds hitting multiple targets using artificial intelligence (AI) systems based on machine learning (ML) and deep learning (DL) approaches, has a huge potential to revolutionize drug discovery. Such intelligent systems enable computers to create new chemical structures and predict their multi-target properties at a low cost and in a time-efficient manner. Most examples of AI applied to drug discovery are single-target oriented and there is still a lack of concise information regarding the application of this technology for the discovery of multi-target drugs or drugs with broad-spectrum action. In this review, we focus on current developments in AI systems for the next generation of automated design of multi-target drugs. We discuss how classical ML methods, cutting-edge generative models, and multi-task deep neural networks can help de novo design and hit-to-lead optimization of multi-target drugs. Moreover, we present state-of-the-art workflows and highlight some studies demonstrating encouraging experimental results, which pave the way for de novo drug design and multi-target drug discovery.

Current application of machine learning in the process of antimicrobial peptide discovery call for the reduction of the false positive predictions that are produced by the classification models. Considering that the positive predictions of high confidence drive modern experimental design, the model’s sensitivity is crucial to reduce the number of unnecessary in vitro tests. Furthermore, taking into account the expert-based design approaches that employ random mutations on confirmed sequences, the machine learning models are required to distinguish between subtle differences among shuffled sequences. With the goal of reducing the false positive rate and improving sensitivity, we propose a hybrid approach to antimicrobial peptide prediction that utilizes combined encoding models. To this end, we implement models that employ both the physico-chemical features and sequence ordering information to stress the importance of using both representations. We also investigate the usage of binary encoding for peptide representation purposes, a method that is insufficiently represented in related research, which proved to act as a viable low dimensional alternative to the one-hot encoding. Our results, supported by Cochran and McNemar statistical tests and Spearman correlation analysis, indicate that the sequence-based encodings complement the physico-chemical features and their synergic effect yields improvement in terms of every evaluation metric. Finally, the proposed hybrid approach that combines physico-chemical features and binary encoding using logical conjunction was shown to be superior to other single models by a factor of 2.96 in terms of fall-out and up to 6.1% in terms of precision.

Janus kinase 1 (JAK1) is a key regulator of gene transcription, inhibition of JAK1 is an intervention for many diseases including rheumatoid arthritis and Crohn's disease. In this study, we collected a dataset containing 2982 JAK1 inhibitors, characterized molecules by MACCS fingerprints and Morgan fingerprints. We used support vector machine (SVM), decision tree (DT), random forest (RF) and extreme gradient boosting tree (XGBoost) algorithms to build 16 traditional machine learning classification models. Additionally, we utilized deep neural networks (DNN) to develop four deep learning models. The best model (Model 3B) built by RF and Morgan fingerprints achieved the accuracy (ACC) of 93.6% and Mathews correlation coefficient (MCC) of 0.87 on the test set. Furthermore, we made structure–activity relationship (SAR) analyses for JAK1 inhibitors, based on the output from the random forest models. After analyzing the important keys of two types of fingerprints, it was observed that some substructures such as pyrazole, pyrrolotriazolopyrimidine and pyrazolopyrimidine appeared frequently in highly active JAK1 inhibitors.

Target specific drug design has attracted much attention in drug discovery. But, it is a great challenge to efficiently explore the target-focused chemical space. Fragment-based drug design (FBDD) has shown its potential to do this thing. In this study, we introduced a deep learning-based fragment linking method, namely SyntaLinker-Hybrid, for target specific molecular generation. By carrying out transfer learning and fragment hybridization, this method allows to generate a great number of linker fragments to assemble given terminal fragments into the molecules with target specificity. This work demonstrates that the method has the capacity to generate target specific structures for various targets. We believe that its application could be extended to a broader target scope.

Drug repurposing consists in identifying additional uses for known drugs and, since these new findings are built on previous knowledge, it reduces both the length and the costs of the drug development. In this work, we assembled an automated computational pipeline for drug repurposing, integrating also a network-based analysis for screening the possible drug combinations. The selection of drugs relies both on their proximity to the disease on the protein-protein interactome and on their influence on the expression of disease-related genes. Combined therapies are then prioritized on the basis of the drugs’ separation on the human interactome and the known drug-drug interactions. We eventually collected a number of molecules, and their plausible combinations, that could be proposed for the treatment of Huntington's disease and multiple sclerosis. Finally, this pipeline could potentially provide new suggestions also for other complex disorders.

Cheminformatics is the chemical field that deals with the storage, retrieval, analysis and manipulation of an increasing volume of available chemical data, and it plays a fundamental role in the fields of drug discovery, biology, chemistry, and biochemistry. Open source and freely available cheminformatics tools not only contribute to the generation of public knowledge, but also to reduce the technological gap between high- and low- to middle-income countries. Here, we describe a series of in-house cheminformatics applications developed by our academic drug discovery team, which are freely available on our website (https://lideb.biol.unlp.edu.ar/) as Web Apps and stand-alone versions. These apps include tools for clustering small molecules, decoy generation, druggability assessment, classificatory model evaluation, and data standardization and visualization.