SMILES Strings Research Articles

DynaStI: A Dynamic Retention Time Database for Steroidomics.

Steroidomics studies face the challenge of separating analytical compounds with very similar structures (i.e., isomers). Liquid chromatography (LC) is commonly used to this end, but the shared core structure of this family of compounds compromises effective separations among the numerous chemical analytes with comparable physico-chemical properties. Careful tuning of the mobile phase gradient and an appropriate choice of the stationary phase can be used to overcome this problem, in turn modifying the retention times in different ways for each compound. In the usual workflow, this approach is suboptimal for the annotation of features based on retention times since it requires characterizing a library of known compounds for every fine-tuned configuration. We introduce a software solution, DynaStI, that is capable of annotating liquid chromatography-mass spectrometry (LC–MS) features by dynamically generating the retention times from a database containing intrinsic properties of a library of metabolites. DynaStI uses the well-established linear solvent strength (LSS) model for reversed-phase LC. Given a list of LC–MS features and some characteristics of the LC setup, this software computes the corresponding retention times for the internal database and then annotates the features using the exact masses with predicted retention times at the working conditions. DynaStI is able to automatically calibrate its predictions to compensate for deviations in the input parameters. The database also includes identification and structural information for each annotation, such as IUPAC name, CAS number, SMILES string, metabolic pathways, and links to external metabolomic or lipidomic databases.

Linking Molecular Structure via Functional Group to Chemical Literature for Establishing a Reaction Lineage for Application to Alternatives Assessment.

The evaluation of potential alternatives for chemicals of concern (CoC) requires an understanding of their potential human health and environmental impacts during the manufacture, use, recycle and disposal life stages. During the manufacturing phase, the processes used to produce a desired chemical are defined based on the sequence of chemical reactions and unit operations required to produce the molecule and separate it from other materials used or produced during its manufacture. This paper introduces and demonstrates a tool that links a chemical's structure to information about its synthesis route and the manufacturing process for that chemical. The structure of the chemical is entered using either a SMILES string or the molecule MOL file, and the molecule is searched to identify functional groups present. Based on those functional groups present, the respective named reactions that can be used in its synthesis routes are identified. This information can be used to identify input and output materials for each named reaction, along with reaction conditions, solvents, and catalysts that participate in the reaction. Additionally, the reaction database contains links to internet references and appropriate reaction-specific keywords, further increasing its comprehensiveness. The tool is designed to facilitate the cataloging and use of the chemical literature in a way that allows user to identify and evaluate information about the reactions, such as alternative solvents, catalysts, reaction conditions and other reaction products which enable the comparison of various reaction pathways for the manufacture of the subject chemical. The chemical manufacturing processing steps can be linked to a chemical process ontology to estimate releases and exposures occurring during the manufacturing phase of a chemical.

De Novo Molecular Design by Combining Deep Autoencoder Recurrent Neural Networks with Generative Topographic Mapping.

Here we show that Generative Topographic Mapping (GTM) can be used to explore the latent space of the SMILES-based autoencoders and generate focused molecular libraries of interest. We have built a sequence-to-sequence neural network with Bidirectional Long Short-Term Memory layers and trained it on the SMILES strings from ChEMBL23. Very high reconstruction rates of the test set molecules were achieved (>98%), which are comparable to the ones reported in related publications. Using GTM, we have visualized the autoencoder latent space on the two-dimensional topographic map. Targeted map zones can be used for generating novel molecular structures by sampling associated latent space points and decoding them to SMILES. The sampling method based on a genetic algorithm was introduced to optimize compound properties "on the fly". The generated focused molecular libraries were shown to contain original and a priori feasible compounds which, pending actual synthesis and testing, showed encouraging behavior in independent structure-based affinity estimation procedures (pharmacophore matching, docking).

Navigating around Patented Routes by Preserving Specific Motifs along Computer-Planned Retrosynthetic Pathways

Summary By keeping track of lists of specific bonds one wishes to preserve, a computer program is able to identify the key disconnections used in the patented syntheses and design synthetic routes that circumvent these approaches. Here, we provide examples of computer-designed syntheses relevant to medicinal chemistry, in which the machine avoids “strategic” disconnections common to industrial patents and is forced to use different starting materials. The ability of modern retrosynthetic planners to navigate around patented solutions may have significant implications for the ways in which intellectual property related to multistep syntheses is protected and/or challenged.

Application of Multivariate Adaptive Regression Splines (MARSplines) for Predicting Hansen Solubility Parameters Based on 1D and 2D Molecular Descriptors Computed from SMILES String

A new method of Hansen solubility parameters (HSPs) prediction was developed by combining the multivariate adaptive regression splines (MARSplines) methodology with a simple multivariable regression involving 1D and 2D PaDEL molecular descriptors. In order to adopt the MARSplines approach to QSPR/QSAR problems, several optimization procedures were proposed and tested. The effectiveness of the obtained models was checked via standard QSPR/QSAR internal validation procedures provided by the QSARINS software and by predicting the solubility classification of polymers and drug-like solid solutes in collections of solvents. By utilizing information derived only from SMILES strings, the obtained models allow for computing all of the three Hansen solubility parameters including dispersion, polarization, and hydrogen bonding. Although several descriptors are required for proper parameters estimation, the proposed procedure is simple and straightforward and does not require a molecular geometry optimization. The obtained HSP values are highly correlated with experimental data, and their application for solving solubility problems leads to essentially the same quality as for the original parameters. Based on provided models, it is possible to characterize any solvent and liquid solute for which HSP data are unavailable.

De Novo Molecule Design by Translating from Reduced Graphs to SMILES.

A key component of automated molecular design is the generation of compound ideas for subsequent filtering and assessment. Recently deep learning approaches have been explored as alternatives to traditional de novo molecular design techniques. Deep learning algorithms rely on learning from large pools of molecules represented as molecular graphs (generally SMILES), and several approaches can be used to tailor the generated molecules to defined regions of chemical space. Cheminformatics has developed alternative higher-level representations that capture the key properties of a set of molecules, and it would be of interest to understand whether such representations can be used to constrain the output of molecule generation algorithms. In this work we explore the use of one such representation, the Reduced Graph, as a definition of target chemical space for a deep learning molecule generator. The Reduced Graph replaces functional groups with superatoms representing the pharmacophoric features. Assigning these superatoms to specific nonorganic element types allows the Reduced Graph to be represented as a valid SMILES string. The mapping from standard SMILES to Reduced Graph SMILES is well-defined, however, the inverse is not true, and this presents a particular challenge. Here we present the results of a novel seq-to-seq approach to molecule generation, where the one to many mapping of Reduced Graph to SMILES is learned on a large training set. This training needs to be performed only once. In a subsequent step, this model can be used to generate arbitrary numbers of compounds that have the same Reduced Graph as any input molecule. Through analysis of data sets in ChEMBL we show that the approach generates valid molecules and can extrapolate to Reduced Graphs unseen in the training set. The method offers an alternative deep learning approach to molecule generation that does not rely on transfer learning, latent space generation, or adversarial networks and is applicable to scaffold hopping and other cheminformatics applications in drug discovery.

Multi-objective de novo drug design with conditional graph generative model

Recently, deep generative models have revealed itself as a promising way of performing de novo molecule design. However, previous research has focused mainly on generating SMILES strings instead of molecular graphs. Although available, current graph generative models are are often too general and computationally expensive. In this work, a new de novo molecular design framework is proposed based on a type of sequential graph generators that do not use atom level recurrent units. Compared with previous graph generative models, the proposed method is much more tuned for molecule generation and has been scaled up to cover significantly larger molecules in the ChEMBL database. It is shown that the graph-based model outperforms SMILES based models in a variety of metrics, especially in the rate of valid outputs. For the application of drug design tasks, conditional graph generative model is employed. This method offers highe flexibility and is suitable for generation based on multiple objectives. The results have demonstrated that this approach can be effectively applied to solve several drug design problems, including the generation of compounds containing a given scaffold, compounds with specific drug-likeness and synthetic accessibility requirements, as well as dual inhibitors against JNK3 and GSK-3β.

Using SMILES strings for the description of chemical connectivity in the Crystallography Open Database

Computer descriptions of chemical molecular connectivity are necessary for searching chemical databases and for predicting chemical properties from molecular structure. In this article, the ongoing work to describe the chemical connectivity of entries contained in the Crystallography Open Database (COD) in SMILES format is reported. This collection of SMILES is publicly available for chemical (substructure) search or for any other purpose on an open-access basis, as is the COD itself. The conventions that have been followed for the representation of compounds that do not fit into the valence bond theory are outlined for the most frequently found cases. The procedure for getting the SMILES out of the CIF files starts with checking whether the atoms in the asymmetric unit are a chemically acceptable image of the compound. When they are not (molecule in a symmetry element, disorder, polymeric species,etc.), the previously published cif_molecule program is used to get such image in many cases. The program package Open Babel is then applied to get SMILES strings from the CIF files (either those directly taken from the COD or those produced by cif_molecule when applicable). The results are then checked and/or fixed by a human editor, in a computer-aided task that at present still consumes a great deal of human time. Even if the procedure still needs to be improved to make it more automatic (and hence faster), it has already yielded more than 160,000 curated chemical structures and the purpose of this article is to announce the existence of this work to the chemical community as well as to spread the use of its results.

Reinforced Adversarial Neural Computer for de Novo Molecular Design.

In silico modeling is a crucial milestone in modern drug design and development. Although computer-aided approaches in this field are well-studied, the application of deep learning methods in this research area is at the beginning. In this work, we present an original deep neural network (DNN) architecture named RANC (Reinforced Adversarial Neural Computer) for the de novo design of novel small-molecule organic structures based on the generative adversarial network (GAN) paradigm and reinforcement learning (RL). As a generator RANC uses a differentiable neural computer (DNC), a category of neural networks, with increased generation capabilities due to the addition of an explicit memory bank, which can mitigate common problems found in adversarial settings. The comparative results have shown that RANC trained on the SMILES string representation of the molecules outperforms its first DNN-based counterpart ORGANIC by several metrics relevant to drug discovery: the number of unique structures, passing medicinal chemistry filters (MCFs), Muegge criteria, and high QED scores. RANC is able to generate structures that match the distributions of the key chemical features/descriptors (e.g., MW, logP, TPSA) and lengths of the SMILES strings in the training data set. Therefore, RANC can be reasonably regarded as a promising starting point to develop novel molecules with activity against different biological targets or pathways. In addition, this approach allows scientists to save time and covers a broad chemical space populated with novel and diverse compounds.

CypReact: A Software Tool for in Silico Reactant Prediction for Human Cytochrome P450 Enzymes.

In silico metabolism prediction requires first predicting whether a specific molecule will interact with one or more specific metabolizing enzymes, then predicting the result of each enzymatic reaction. Here, we provide a computational tool, CypReact, for performing this first task of reactant prediction. Specifically, CypReact takes as input an arbitrary molecule (specified as a SMILES string or a standard SDF file) and any one of the nine of the most important human cytochrome P450 (CYP450) enzymes-CYP1A2, CYP2A6, CYP2B6, CYP2C8, CYP2C9, CYP2C19, CYP2D6, CYP2E1, or CYP3A4-and accurately predicts whether the query molecule will react with that given CYP450 enzyme. Tests of CypReact, conducted over a data set of 1632 molecules (each considered a "plausible" reactant) show that it is very effective, with a (cross-validation) AUROC (area under the receiver operating characteristic curve) of 0.83-0.92. We also show that CypReact performs significantly better than other reactant prediction tools such as ADMET Predictor and (a reactant-predicting extension of) SMARTCyp, whose average AUROCs are 0.75 and 0.53, respectively. We then applied the learned CypReact models to a previously unseen set of molecules and found that our CypReact did even better and still significantly surpassed the performance of SMARTCyp and ADMET Predictor. These results suggest that CypReact could be an important component of a suite of in silico metabolism prediction tools for accurately predicting the products of Phase I, Phase II, and microbial metabolism in humans. CypReact is available at https://bitbucket.org/Leon_Ti/cypreact .

Constant size descriptors for accurate machine learning models of molecular properties.

Two different classes of molecular representations for use in machine learning of thermodynamic and electronic properties are studied. The representations are evaluated by monitoring the performance of linear and kernel ridge regression models on well-studied data sets of small organic molecules. One class of representations studied here counts the occurrence of bonding patterns in the molecule. These require only the connectivity of atoms in the molecule as may be obtained from a line diagram or a SMILES string. The second class utilizes the three-dimensional structure of the molecule. These include the Coulomb matrix and Bag of Bonds, which list the inter-atomic distances present in the molecule, and Encoded Bonds, which encode such lists into a feature vector whose length is independent of molecular size. Encoded Bonds' features introduced here have the advantage of leading to models that may be trained on smaller molecules and then used successfully on larger molecules. A wide range of feature sets are constructed by selecting, at each rank, either a graph or geometry-based feature. Here, rank refers to the number of atoms involved in the feature, e.g., atom counts are rank 1, while Encoded Bonds are rank 2. For atomization energies in the QM7 data set, the best graph-based feature set gives a mean absolute error of 3.4 kcal/mol. Inclusion of 3D geometry substantially enhances the performance, with Encoded Bonds giving 2.4 kcal/mol, when used alone, and 1.19 kcal/mol, when combined with graph features.

Adversarial Threshold Neural Computer for Molecular de Novo Design.

In this article, we propose the deep neural network Adversarial Threshold Neural Computer (ATNC). The ATNC model is intended for the de novo design of novel small-molecule organic structures. The model is based on generative adversarial network architecture and reinforcement learning. ATNC uses a Differentiable Neural Computer as a generator and has a new specific block, called adversarial threshold (AT). AT acts as a filter between the agent (generator) and the environment (discriminator + objective reward functions). Furthermore, to generate more diverse molecules we introduce a new objective reward function named Internal Diversity Clustering (IDC). In this work, ATNC is tested and compared with the ORGANIC model. Both models were trained on the SMILES string representation of the molecules, using four objective functions (internal similarity, Muegge druglikeness filter, presence or absence of sp3-rich fragments, and IDC). The SMILES representations of 15K druglike molecules from the ChemDiv collection were used as a training data set. For the different functions, ATNC outperforms ORGANIC. Combined with the IDC, ATNC generates 72% of valid and 77% of unique SMILES strings, while ORGANIC generates only 7% of valid and 86% of unique SMILES strings. For each set of molecules generated by ATNC and ORGANIC, we analyzed distributions of four molecular descriptors (number of atoms, molecular weight, logP, and tpsa) and calculated five chemical statistical features (internal diversity, number of unique heterocycles, number of clusters, number of singletons, and number of compounds that have not been passed through medicinal chemistry filters). Analysis of key molecular descriptors and chemical statistical features demonstrated that the molecules generated by ATNC elicited better druglikeness properties. We also performed in vitro validation of the molecules generated by ATNC; results indicated that ATNC is an effective method for producing hit compounds.

REStLESS: automated translation of glycan sequences from residue-based notation to SMILES and atomic coordinates

Glycans and glycoconjugates are usually recorded in dedicated databases in residue-based notations. Only a few of them can be converted into chemical (atom-based) formats highly demanded in conformational and biochemical studies. In this work, we present a tool for translation from a residue-based glycan notation to SMILES. The REStLESS algorithm for translation from the CSDB Linear notation to SMILES was developed. REStLESS stands for ResiduEs as Smiles and LinkagEs as SmartS, where SMARTS reaction expressions are used to merge pre-encoded residues into a molecule. The implementation supports virtually all structural features reported in natural carbohydrates and glycoconjugates. The translator is equipped with a mechanism for conversion of SMILES strings into optimized atomic coordinates which can be used as starting geometries for various computational tasks. REStLESS is integrated in the Carbohydrate Structure Database (CSDB) and is freely available on the web (http://csdb.glycoscience.ru/csdb2atoms.html). Supplementary data are available at Bioinformatics online.

De Novo Design of Bioactive Small Molecules by Artificial Intelligence.

Generative artificial intelligence offers a fresh view on molecular design. We present the first‐time prospective application of a deep learning model for designing new druglike compounds with desired activities. For this purpose, we trained a recurrent neural network to capture the constitution of a large set of known bioactive compounds represented as SMILES strings. By transfer learning, this general model was fine‐tuned on recognizing retinoid X and peroxisome proliferator‐activated receptor agonists. We synthesized five top‐ranking compounds designed by the generative model. Four of the compounds revealed nanomolar to low‐micromolar receptor modulatory activity in cell‐based assays. Apparently, the computational model intrinsically captured relevant chemical and biological knowledge without the need for explicit rules. The results of this study advocate generative artificial intelligence for prospective de novo molecular design, and demonstrate the potential of these methods for future medicinal chemistry.

A Substructure Search Method for Finding an Element of a Set of Chemical Structures Represented by a SMILES String with Regular Expression Extension

A Substructure Search Method for Finding an Element of a Set of Chemical Structures Represented by a SMILES String with Regular Expression Extension

Generative Recurrent Networks for De Novo Drug Design.

Generative artificial intelligence models present a fresh approach to chemogenomics and de novo drug design, as they provide researchers with the ability to narrow down their search of the chemical space and focus on regions of interest. We present a method for molecular de novo design that utilizes generative recurrent neural networks (RNN) containing long short‐term memory (LSTM) cells. This computational model captured the syntax of molecular representation in terms of SMILES strings with close to perfect accuracy. The learned pattern probabilities can be used for de novo SMILES generation. This molecular design concept eliminates the need for virtual compound library enumeration. By employing transfer learning, we fine‐tuned the RNN′s predictions for specific molecular targets. This approach enables virtual compound design without requiring secondary or external activity prediction, which could introduce error or unwanted bias. The results obtained advocate this generative RNN‐LSTM system for high‐impact use cases, such as low‐data drug discovery, fragment based molecular design, and hit‐to‐lead optimization for diverse drug targets.

ForceGen 3D structure and conformer generation: from small lead-like molecules to macrocyclic drugs

We introduce the ForceGen method for 3D structure generation and conformer elaboration of drug-like small molecules. ForceGen is novel, avoiding use of distance geometry, molecular templates, or simulation-oriented stochastic sampling. The method is primarily driven by the molecular force field, implemented using an extension of MMFF94s and a partial charge estimator based on electronegativity-equalization. The force field is coupled to algorithms for direct sampling of realistic physical movements made by small molecules. Results are presented on a standard benchmark from the Cambridge Crystallographic Database of 480 drug-like small molecules, including full structure generation from SMILES strings. Reproduction of protein-bound crystallographic ligand poses is demonstrated on four carefully curated data sets: the ConfGen Set (667 ligands), the PINC cross-docking benchmark (1062 ligands), a large set of macrocyclic ligands (182 total with typical ring sizes of 12–23 atoms), and a commonly used benchmark for evaluating macrocycle conformer generation (30 ligands total). Results compare favorably to alternative methods, and performance on macrocyclic compounds approaches that observed on non-macrocycles while yielding a roughly 100-fold speed improvement over alternative MD-based methods with comparable performance.

AceDRG: a stereochemical description generator for ligands.

The program AceDRG is designed for the derivation of stereochemical information about small molecules. It uses local chemical and topological environment-based atom typing to derive and organize bond lengths and angles from a small-molecule database: the Crystallography Open Database (COD). Information about the hybridization states of atoms, whether they belong to small rings (up to seven-membered rings), ring aromaticity and nearest-neighbour information is encoded in the atom types. All atoms from the COD have been classified according to the generated atom types. All bonds and angles have also been classified according to the atom types and, in a certain sense, bond types. Derived data are tabulated in a machine-readable form that is freely available from CCP4. AceDRG can also generate stereochemical information, provided that the basic bonding pattern of a ligand is known. The basic bonding pattern is perceived from one of the computational chemistry file formats, including SMILES, mmCIF, SDF MOL and SYBYL MOL2 files. Using the bonding chemistry, atom types, and bond and angle tables generated from the COD, AceDRG derives the `ideal' bond lengths, angles, plane groups, aromatic rings and chirality information, and writes them to an mmCIF file that can be used by the refinement program REFMAC5 and the model-building program Coot. Other refinement and model-building programs such as PHENIX and BUSTER can also use these files. AceDRG also generates one or more coordinate sets corresponding to the most favourable conformation(s) of a given ligand. AceDRG employs RDKit for chemistry perception and for initial conformation generation, as well as for the interpretation of SMILES strings, SDF MOL and SYBYL MOL2 files.

Jmol SMILES and Jmol SMARTS: specifications and applications.

BackgroundSMILES and SMARTS are two well-defined structure matching languages that have gained wide use in cheminformatics. Jmol is a widely used open-source molecular visualization and analysis tool written in Java and implemented in both Java and JavaScript. Over the past 10 years, from 2007 to 2016, work on Jmol has included the development of dialects of SMILES and SMARTS that incorporate novel aspects that allow new and powerful applications.ResultsThe specifications of “Jmol SMILES” and “Jmol SMARTS” are described. The dialects most closely resemble OpenSMILES and OpenSMARTS. Jmol SMILES is a superset of OpenSMILES, allowing a freer format, including whitespace and comments, the addition of “processing directives” that modify the meaning of certain aspects of SMILES processing such as aromaticity and stereochemistry, a more extensive treatment of stereochemistry, and several minor additions. Jmol SMARTS similarly adds these same modifications to OpenSMARTS, but also adds a number of additional “primitives” and elements of syntax tuned to matching 3D molecular structures and selecting their atoms. The result is an expansion of the capabilities of SMILES and SMARTS primarily for use in 3D molecular analysis, allowing a broader range of matching involving any combination of 3D molecular structures, SMILES strings, and SMARTS patterns. While developed specifically for Jmol, these dialects of SMILES and SMARTS are independent of the Jmol application itself.ConclusionsJmol SMILES and Jmol SMARTS add value to standard SMILES and SMARTS. Together they have proven exceptionally capable in extracting valuable information from 3D structural models, as demonstrated in Jmol. Capabilities in Jmol enabled by Jmol SMILES and Jmol SMARTS include efficient MMFF94 atom typing, conformational identification, SMILES comparisons without canonicalization, identification of stereochemical relationships, quantitative comparison of 3D structures from different sources (including differences in Kekulization), conformational flexible fitting, and atom mapping used to synchronize interactive displays of 2D structures, 3D structures, and spectral correlations, where data are being drawn from multiple sources.Electronic supplementary materialThe online version of this article (doi:10.1186/s13321-016-0160-4) contains supplementary material, which is available to authorized users.

CSAR 2014: A Benchmark Exercise Using Unpublished Data from Pharma.

The 2014 CSAR Benchmark Exercise was the last community-wide exercise that was conducted by the group at the University of Michigan, Ann Arbor. For this event, GlaxoSmithKline (GSK) donated unpublished crystal structures and affinity data from in-house projects. Three targets were used: tRNA (m1G37) methyltransferase (TrmD), Spleen Tyrosine Kinase (SYK), and Factor Xa (FXa). A particularly strong feature of the GSK data is its large size, which lends greater statistical significance to comparisons between different methods. In Phase 1 of the CSAR 2014 Exercise, participants were given several protein-ligand complexes and asked to identify the one near-native pose from among 200 decoys provided by CSAR. Though decoys were requested by the community, we found that they complicated our analysis. We could not discern whether poor predictions were failures of the chosen method or an incompatibility between the participant's method and the setup protocol we used. This problem is inherent to decoys, and we strongly advise against their use. In Phase 2, participants had to dock and rank/score a set of small molecules given only the SMILES strings of the ligands and a protein structure with a different ligand bound. Overall, docking was a success for most participants, much better in Phase 2 than in Phase 1. However, scoring was a greater challenge. No particular approach to docking and scoring had an edge, and successful methods included empirical, knowledge-based, machine-learning, shape-fitting, and even those with solvation and entropy terms. Several groups were successful in ranking TrmD and/or SYK, but ranking FXa ligands was intractable for all participants. Methods that were able to dock well across all submitted systems include MDock,1 Glide-XP,2 PLANTS,3 Wilma,4 Gold,5 SMINA,6 Glide-XP2/PELE,7 FlexX,8 and MedusaDock.9 In fact, the submission based on Glide-XP2/PELE7 cross-docked all ligands to many crystal structures, and it was particularly impressive to see success across an ensemble of protein structures for multiple targets. For scoring/ranking, submissions that showed statistically significant achievement include MDock1 using ITScore1,10 with a flexible-ligand term,11 SMINA6 using Autodock-Vina,12,13 FlexX8 using HYDE,14 and Glide-XP2 using XP DockScore2 with and without ROCS15 shape similarity.16 Of course, these results are for only three protein targets, and many more systems need to be investigated to truly identify which approaches are more successful than others. Furthermore, our exercise is not a competition.