The Hitchhiker's Guide to Deep Learning Driven Generative Chemistry.
Ontology highlight
ABSTRACT:
SUBMITTER: Ivanenkov Y
PROVIDER: S-EPMC10351082 | biostudies-literature | 2023 Jul
REPOSITORIES: biostudies-literature
Publications
The Hitchhiker's Guide to Deep Learning Driven Generative Chemistry.
Ivanenkov Yan Y Zagribelnyy Bogdan B Malyshev Alex A Evteev Sergei S Terentiev Victor V Kamya Petrina P Bezrukov Dmitry D Aliper Alex A Ren Feng F Zhavoronkov Alex A
ACS medicinal chemistry letters 20230630 7
This microperspective covers the most recent research outcomes of artificial intelligence (AI) generated molecular structures from the point of view of the medicinal chemist. The main focus is on studies that include synthesis and experimental <i>in vitro</i> validation in biochemical assays of the generated molecular structures, where we analyze the reported structures' relevance in modern medicinal chemistry and their novelty. The authors believe that this review would be appreciated by medici ...[more]
Similar Datasets
Project description:Deep learning has significantly accelerated drug discovery, with 'chemical language' processing (CLP) emerging as a prominent approach. CLP approaches learn from molecular string representations (e.g., Simplified Molecular Input Line Entry Systems [SMILES] and Self-Referencing Embedded Strings [SELFIES]) with methods akin to natural language processing. Despite their growing importance, training predictive CLP models is far from trivial, as it involves many 'bells and whistles'. Here, we analyze the key elements of CLP and provide guidelines for newcomers and experts. Our study spans three neural network architectures, two string representations, three embedding strategies, across ten bioactivity datasets, for both classification and regression purposes. This 'hitchhiker's guide' not only underscores the importance of certain methodological decisions, but it also equips researchers with practical recommendations on ideal choices, e.g., in terms of neural network architectures, molecular representations, and hyperparameter optimization.
| S-EPMC11667676 | biostudies-literature
Project description:A generative model is a statistical model capable of generating new data instances from previously observed ones. In the context of business processes, a generative model creates new execution traces from a set of historical traces, also known as an event log. Two types of generative business process models have been developed in previous work: data-driven simulation models and deep learning models. Until now, these two approaches have evolved independently, and their relative performance has not been studied. This paper fills this gap by empirically comparing a data-driven simulation approach with multiple deep learning approaches for building generative business process models. The study sheds light on the relative strengths of these two approaches and raises the prospect of developing hybrid approaches that combine these strengths.
| S-EPMC8293933 | biostudies-literature
Project description:Intelligent decisions in response to external informative input can allow organisms to achieve their biological goals while spending very little of their own resources. In this paper, we develop and study a minimal model for a navigational task, performed by an otherwise completely motorless particle that possesses the ability of hitchhiking in a bath of active Brownian particles (ABPs). Hitchhiking refers to identifying and attaching to suitable surrounding bath particles. Using a reinforcement learning algorithm, such an agent, which we refer to as intelligent hitchhiking particle (IHP), is enabled to persistently navigate in the desired direction. This relatively simple IHP can also anticipate and react to characteristic motion patterns of their hosts, which we exemplify for a bath of chiral ABPs (cABPs). To demonstrate that the persistent motion of the IHP will outperform that of the bath particles in view of long-time ballistic motion, we calculate the mean-squared displacement and discuss its dependence on the density and persistence time of the bath ABPs by means of an analytic model.
| S-EPMC11698853 | biostudies-literature
Project description: Not available
| S-EPMC11560434 | biostudies-literature
Project description:Nanomedicine plays an essential role in developing new therapies through novel drug delivery systems, diagnostic and imaging systems, vaccine development, antibacterial tools, and high-throughput screening. One of the most promising drug delivery systems are nanoparticles, which can be designed with various compositions, sizes, shapes, and surface modifications. These nanosystems have improved therapeutic profiles, increased bioavailability, and reduced the toxicity of the product they carry. However, the clinical translation of nanomedicines requires a thorough understanding of their properties to avoid problems with the most questioned aspect of nanosystems: safety. The particular physicochemical properties of nano-drugs lead to the need for additional safety, quality, and efficacy testing. Consequently, challenges arise during the physicochemical characterization, the production process, in vitro characterization, in vivo characterization, and the clinical stages of development of these biopharmaceuticals. The lack of a specific regulatory framework for nanoformulations has caused significant gaps in the requirements needed to be successful during their approval, especially with tests that demonstrate their safety and efficacy. Researchers face many difficulties in establishing evidence to extrapolate results from one level of development to another, for example, from an in vitro demonstration phase to an in vivo demonstration phase. Additional guidance is required to cover the particularities of this type of product, as some challenges in the regulatory framework do not allow for an accurate assessment of NPs with sufficient evidence of clinical success. This work aims to identify current regulatory issues during the implementation of nanoparticle assays and describe the major challenges that researchers have faced when exposing a new formulation. We further reflect on the current regulatory standards required for the approval of these biopharmaceuticals and the requirements demanded by the regulatory agencies. Our work will provide helpful information to improve the success of nanomedicines by compiling the challenges described in the literature that support the development of this novel encapsulation system. We propose a step-by-step approach through the different stages of the development of nanoformulations, from their design to the clinical stage, exemplifying the different challenges and the measures taken by the regulatory agencies to respond to these challenges.
| S-EPMC8879439 | biostudies-literature
Project description:Numerous reviews have summarized the epidemiology, pathophysiology and the various therapeutic aspects of Coronavirus disease 2019 (COVID-19), but a practical guide on "how to treat whom with what and when" based on an understanding of the immunological background of the disease stages remains missing. This review attempts to combine the current knowledge about the immunopathology of COVID-19 with published evidence of available and emerging treatment options. We recognize that the information about COVID-19 and its treatment is rapidly changing, but hope that this guide offers those on the frontline of this pandemic an understanding of the host response in COVID-19 patients and supports their ongoing efforts to select the best treatments tailored to their patient's clinical status.
| S-EPMC8461017 | biostudies-literature
Project description:Lipidomics is a newly emerged discipline involving the identification and quantification of thousands of lipids. As a part of the omics field, lipidomics has shown rapid growth both in the number of studies and in the size of lipidome datasets, thus, requiring specific and efficient data analysis approaches. This paper aims to provide guidelines for analyzing and interpreting lipidome data obtained using untargeted methods that rely on liquid chromatography coupled with mass spectrometry (LC-MS) to detect and measure the intensities of lipid compounds. We present a state-of-the-art untargeted LC-MS workflow for lipidomics, from study design to annotation of lipid features, focusing on practical, rather than theoretical, approaches for data analysis, and we outline possible applications of untargeted lipidomics for biological studies. We provide a detailed R notebook designed specifically for untargeted lipidome LC-MS data analysis, which is based on xcms software.
| S-EPMC8624948 | biostudies-literature
Project description:Plant life critically depends on the function of MADS-box genes encoding MADS-domain transcription factors, which are present to a limited extent in nearly all major eukaryotic groups, but constitute a large gene family in land plants. There are two types of MADS-box genes, termed type I and type II, and in plants these groups are distinguished by exon-intron and domain structure, rates of evolution, developmental function and degree of functional redundancy. The type I genes are further subdivided into three groups - M alpha, M beta and M gamma - while the type II genes are subdivided into the MIKCC and MIKC* groups. The functional diversification of MIKCC genes is closely linked to the origin of developmental and morphological novelties in the sporophytic (usually diploid) generation of seed plants, most spectacularly the floral organs and fruits of angiosperms. Functional studies suggest different specializations for the different classes of genes; whereas type I genes may preferentially contribute to female gametophyte, embryo and seed development and MIKC*-group genes to male gametophyte development, the MIKCC-group genes became essential for diverse aspects of sporophyte development. Beyond the usual transcriptional regulation, including feedback and feed-forward loops, various specialized mechanisms have evolved to control the expression of MADS-box genes, such as epigenetic control and regulation by small RNAs. In future, more data from genome projects and reverse genetic studies will allow us to understand the birth, functional diversification and death of members of this dynamic and important family of transcription factors in much more detail.
| S-EPMC2911102 | biostudies-literature
Project description:Key messageTwo novel major effect loci (Sen4 and Sen5) and several minor effect QTLs for potato wart disease resistance have been mapped. The importance of minor effect loci to bring full resistance to wart disease was investigated. Using the newly identified and known wart disease resistances, a panel of potato breeding germplasm and Solanum wild species was screened. This provided a state-of-the-art "hitch-hikers-guide" of complementary wart disease resistance sources. Potato wart disease, caused by the obligate biotrophic soil-born fungus Synchytrium endobioticum, is the most important quarantine disease of potato. Because of its huge impact on yield, the lack of chemical control and the formation of resting spores with long viability, breeding for resistant varieties combined with strict quarantine measures are the only way to efficiently and durably manage the disease. In this study, we set out to make an inventory of the different resistance sources. Using a Genome-Wide Association Study (GWAS) in the potato breeding genepool, we identified Sen4, associated with pathotypes 2, 6 and 18 resistance. Associated SNPs mapped to the south arm of chromosome 12 and were validated to be linked to resistance in one full-sib population. Also, a bulked segregant analysis combined with a Comparative Subsequence Sets Analysis (CoSSA) resulted in the identification of Sen5, associated with pathotypes 2, 6 and 18 resistance, on the south arm of chromosome 5. In addition to these two major effect loci, the GWAS and CoSSA allowed the identification of several quantitative trait loci necessary to bring full resistance to certain pathotypes. Panels of varieties and Solanum accessions were screened for the presence of Sen1, Sen2, Sen3, Sen4 and Sen5. Combined with pedigree analysis, we could trace back some of these genes to the ancestral resistance donors. This analysis revealed complementary resistance sources and allows elimination of redundancy in wart resistance breeding programs.
| S-EPMC7567731 | biostudies-literature
Project description:Eukaryotic voltage-gated sodium (Nav) channels contribute to the rising phase of action potentials and served as an early muse for biophysicists laying the foundation for our current understanding of electrical signaling. Given their central role in electrical excitability, it is not surprising that (a) inherited mutations in genes encoding for Nav channels and their accessory subunits have been linked to excitability disorders in brain, muscle, and heart; and (b) Nav channels are targeted by various drugs and naturally occurring toxins. Although the overall architecture and behavior of these channels are likely to be similar to the more well-studied voltage-gated potassium channels, eukaryotic Nav channels lack structural and functional symmetry, a notable difference that has implications for gating and selectivity. Activation of voltage-sensing modules of the first three domains in Nav channels is sufficient to open the channel pore, whereas movement of the domain IV voltage sensor is correlated with inactivation. Also, structure-function studies of eukaryotic Nav channels show that a set of amino acids in the selectivity filter, referred to as DEKA locus, is essential for Na(+) selectivity. Structures of prokaryotic Nav channels have also shed new light on mechanisms of drug block. These structures exhibit lateral fenestrations that are large enough to allow drugs or lipophilic molecules to gain access into the inner vestibule, suggesting that this might be the passage for drug entry into a closed channel. In this Review, we will synthesize our current understanding of Nav channel gating mechanisms, ion selectivity and permeation, and modulation by therapeutics and toxins in light of the new structures of the prokaryotic Nav channels that, for the time being, serve as structural models of their eukaryotic counterparts.
| S-EPMC4692491 | biostudies-literature