Line Notation Research Articles

A positional statistic for 1324-avoiding permutations

We consider the class $S_n(1324)$ of permutations of size $n$ that avoid the pattern 1324 and examine the subset $S_n^{a\prec n}(1324)$ of elements for which $a\prec n\prec [a-1]$, $a\ge 1$. This notation means that, when written in one line notation, such a permutation must have $a$ to the left of $n$, and the elements of $\{1,\dots,a-1\}$ must all be to the right of $n$. For $n\ge 2$, we establish a connection between the subset of permutations in $S_n^{1\prec n}(1324)$ having the 1 adjacent to the $n$ (called primitives), and the set of 1324-avoiding dominoes with $n-2$ points. For $a\in\{1,2\}$, we introduce constructive algorithms and give formulas for the enumeration of $S_n^{a\prec n}(1324)$ by the position of $a$ relative to the position of $n$. For $a\ge 3$, we formulate some conjectures for the corresponding generating functions.

Zombie cheminformatics: extraction and conversion of Wiswesser Line Notation (WLN) from chemical documents

PurposeWiswesser Line Notation (WLN) is a old line notation for encoding chemical compounds for storage and processing by computers. Whilst the notation itself has long since been surpassed by SMILES and InChI, distribution of WLN during its active years was extensive. In the context of modernising chemical data, we present a comprehensive WLN parser developed using the OpenBabel toolkit, capable of translating WLN strings into various formats supported by the library. Furthermore, we have devised a specialised Finite State Machine l, constructed from the rules of WLN, enabling the recognition and extraction of chemical strings out of large bodies of text. Available open-access WLN data with corresponding SMILES or InChI notation is rare, however ChEMBL, ChemSpider and PubChem all contain WLN records which were used for conversion scoring. Our investigation revealed a notable proportion of inaccuracies within the database entries, and we have taken steps to rectify these errors whenever feasible.Scientific contributionTools for both the extraction and conversion of WLN from chemical documents have been successfully developed. Both the Deterministic Finite Automaton (DFA) and parser handle the majority of WLN rules officially endorsed in the three major WLN manuals, with the parser showing a clear jump in accuracy and chemical coverage over previous submissions. The GitHub repository can be found here: https://github.com/Mblakey/wiswesser.

Automated BigSMILES conversion workflow and dataset for homopolymeric macromolecules

The simplified molecular-input line-entry system (SMILES) has been utilized in a variety of artificial intelligence analyses owing to its capability of representing chemical structures using line notation. However, its ease of representation is limited, which has led to the proposal of BigSMILES as an alternative method suitable for the representation of macromolecules. Nevertheless, research on BigSMILES remains limited due to its preprocessing requirements. Thus, this study proposes a conversion workflow of BigSMILES, focusing on its automated generation from SMILES representations of homopolymers. BigSMILES representations for 4,927,181 records are provided, thereby enabling its immediate use for various research and development applications. Our study presents detailed descriptions on a validation process to ensure the accuracy, interchangeability, and robustness of the conversion. Additionally, a systematic overview of utilized codes and functions that emphasizes their relevance in the context of BigSMILES generation are produced. This advancement is anticipated to significantly aid researchers and facilitate further studies in BigSMILES representation, including potential applications in deep learning and further extension to complex structures such as copolymers.

RDCanon: A Python Package for Canonicalizing the Order of Tokens in SMARTS Queries.

SMARTS is a widely used language in cheminformatics for defining substructural queries for database lookups, reaction templates for chemical transformations, and other applications. As an extension to SMILES, many SMARTS patterns can represent the same query. Despite this, no canonicalization algorithm invariant of the line notation sequence or atomic numbering is publicly available. Here, we introduce RDCanon, an open-source Python package that can be used to standardize SMARTS queries. RDCanon is designed to ensure that the sequence of atomic queries remains consistent for all graphs representing the same substructure query and to ensure a canonical sequence of primitives within each individual atom query; furthermore, the algorithm can be applied to canonicalize the order of reactants, agents, and products and their atom map numbers in reaction SMARTS templates. As part of its canonicalization algorithm, RDCanon provides a mechanism in which the canonicalized SMARTS is optimized for speed against specific molecular databases. Several case studies are provided to showcase improved efficiency in substructure matching and retrosynthetic analysis.

Enhanced Structure-Based Prediction of Chiral Stationary Phases for Chromatographic Enantioseparation from 3D Molecular Conformations.

The accurate prediction of suitable chiral stationary phases (CSPs) for resolving the enantiomers of a given compound poses a significant challenge in chiral chromatography. Previous attempts at developing machine learning models for structure-based CSP prediction have primarily relied on 1D SMILES strings [the simplified molecular-input line-entry system (SMILES) is a specification in the form of a line notation for describing the structure of chemical species using short ASCII strings] or 2D graphical representations of molecular structures and have met with only limited success. In this study, we apply the recently developed 3D molecular conformation representation learning algorithm, which uses rapid conformational analysis and point clouds of atom positions in the 3D space, enabling efficient chemical structure-based machine learning. By harnessing the power of the rapid 3D molecular representation learning and a data set comprising over 300,000 chromatographic enantioseparation records sourced from the literature, our models afford notable improvements for the chemical structure-based choice of appropriate CSP for enantioseparation, paving the way for more efficient and informed decision-making in the field of chiral chromatography.

IUPAC International Chemical Identifier (InChI)-related education and training materials through InChI Open Education Resource (OER).

The IUPAC International Chemical Identifier (InChI) is a structure-based chemical identifier that encodes various aspects of a chemical structure into a hierarchically layered line notation. Because InChI is non-proprietary, open-source, and freely available to everyone, it is adopted in popular chemical information resources and software programs. This paper describes the InChI Open Education Resource (OER) (https://www.inchi-trust.org/oer/), designed to provide educators and other interested parties with resources, training material, and information related to InChI. Currently, the OER contains over 100 materials collected from various sources and provides users with search, filtering, and sorting functionalities to locate specific records. New relevant materials can be suggested by anyone, allowing the scientific community to share and find InChI-related resources. This paper will show how to use the InChI OER tag taxonomy to filter content and demonstrate two resources within the InChI OER; the ChemNames2LCSS Google Sheet and the InChILayersExplorer, an Excel spreadsheet that breaks an InChI into its layers. While the InChI OER is of value to a broader chemistry community, this paper seeks to reach out to chemical educators and provide them with an understanding of InChI and its role in the practice of science.

Gotta be SAFE: a new framework for molecular design

SAFE is a novel SMILES-compatible, fragment-based molecular line notation that streamlines molecule generation tasks. Unlike existing line notations, it enforces a sequential depiction of molecular substructures, thus simplifying molecule design.

Making the InChI FAIR and sustainable while moving to inorganics.

The InChI (International Chemical Identifier) standard stands as a cornerstone in chemical informatics, facilitating the structure-based identification and exchange chemical information about compounds across various platforms and databases. The InChI as a unique canonical line notation has made chemical structures searchable on the internet at a broad scale. The largest repositories working with InChIs contain more than 1 billion structures. Central to the functionality of the InChI is its codebase, which orchestrates a series of intricate steps to generate unique identifiers for chemical compounds. Up to now, these steps have been sparsely documented and the InChI algorithm had to be seen as a black box. For the new v1.07 release, the code has been analyzed and the major steps documented, more than 3000 bugs and security issues, as well as nearly 60 Google OSS-Fuzz issues have been fixed. New test systems have been implemented that allow users to directly test the code developments. The move to GitHub has not only made the development more transparent but will also enable external contributors to join the further development of the InChI code. Motivation for this modernisation was the urgency to treat molecular inorganic compounds by the InChI in a meaningful way. Until now, no classic string representation fulfills this need of molecular inorganic chemistry. Currently bonds to metal centers are by definition disconnected which makes most inorganic InChIs meaningless at the moment. Herein, we propose new routines to remedy this problem in the representation of molecular inorganic compounds by the InChI.

Generation of 3D molecules in pockets via a language model

Generative models for molecules based on sequential line notation (for example, the simplified molecular-input line-entry system) or graph representation have attracted an increasing interest in the field of structure-based drug design, but they struggle to capture important three-dimensional (3D) spatial interactions and often produce undesirable molecular structures. To address these challenges, we introduce Lingo3DMol, a pocket-based 3D molecule generation method that combines language models and geometric deep learning technology. A new molecular representation, the fragment-based simplified molecular-input line-entry system with local and global coordinates, was developed to assist the model in learning molecular topologies and atomic spatial positions. Additionally, we trained a separate non-covalent interaction predictor to provide essential binding pattern information for the generative model. Lingo3DMol can efficiently traverse drug-like chemical spaces, preventing the formation of unusual structures. The Directory of Useful Decoys-Enhanced dataset was used for evaluation. Lingo3DMol outperformed state-of-the-art methods in terms of drug likeness, synthetic accessibility, pocket binding mode and molecule generation speed.

Machine Translation between BigSMILES Line Notation and Chemical Structure Diagrams

Machine Translation between BigSMILES Line Notation and Chemical Structure Diagrams

Assessment of protein-ligand complexes in CASP15.

CASP15 introduced a new category, ligand prediction, where participants were provided with a protein or nucleic acid sequence, SMILES line notation, and stoichiometry for ligands and tasked with generating computational models for the three-dimensional structure of the corresponding protein-ligand complex. These models were subsequently compared with experimental structures determined by x-ray crystallography or cryoEM. To assess these predictions, two novel scores were developed. The Binding-Site Superposed, Symmetry-Corrected Pose Root Mean Square Deviation (BiSyRMSD) evaluated the absolute deviations of the models from the experimental structures. At the same time, the Local Distance Difference Test for Protein-Ligand Interactions (lDDT-PLI) assessed the ability of models to reproduce the protein-ligand interactions in the experimental structures. The ligands evaluated in this challenge range from single-atom ions to large flexible organic molecules. More than 1800 submissions were evaluated for their ability to predict 23 different protein-ligand complexes. Overall, the best models could faithfully reproduce the geometries of more than half of the prediction targets. The ligands' size and flexibility were the primary factors influencing the predictions' quality. Small ions and organic molecules with limited flexibility were predicted with high fidelity, while reproducing the binding poses of larger, flexible ligands proved more challenging.

PyPept: a python library to generate atomistic 2D and 3D representations of peptides

We present pyPept, a set of executables and underlying python-language classes to easily create, manipulate, and analyze peptide molecules using the FASTA, HELM, or recently-developed BILN notations. The framework enables the analysis of both pure proteinogenic peptides as well as those with non-natural amino acids, including support to assemble a customizable monomer library, without requiring programming. From line notations, a peptide is transformed into a molecular graph for 2D depiction tasks, the calculation of physicochemical properties, and other systematic analyses or processing pipelines. The package includes a module to rapidly generate approximate peptide conformers by incorporating secondary structure restraints either given by the user or predicted via pyPept, and a wrapper tool is also provided to automate the generation and output of 2D and 3D representations of a peptide directly from the line notation. HELM and BILN notations that include circular, branched, or stapled peptides are fully supported, eliminating errors in structure creation that are prone during manual drawing and connecting. The framework and common workflows followed in pyPept are described together with illustrative examples. pyPept has been released at: https://github.com/Boehringer-Ingelheim/pyPept.Graphical

Canonicalizing BigSMILES for Polymers with Defined Backbones.

BigSMILES, a line notation for encapsulating the molecular structure of stochastic molecules such as polymers, was recently proposed as a compact and readable solution for writing macromolecules. While BigSMILES strings serve as useful identifiers for reconstructing the molecular connectivity for polymers, in general, BigSMILES allows the same polymer to be codified into multiple equally valid representations. Having a canonicalization scheme that eliminates the multiplicity would be very useful in reducing time-intensive tasks like structural comparison and molecular search into simple string-matching tasks. Motivated by this, in this work, two strategies for deriving canonical representations for linear polymers are proposed. In the first approach, a canonicalization scheme is proposed to standardize the expression of BigSMILES stochastic objects, thereby standardizing the expression of overall BigSMILES strings. In the second approach, an analogy between formal language theory and the molecular ensemble of polymer molecules is drawn. Linear polymers can be converted into regular languages, and the minimal deterministic finite automaton uniquely associated with each prescribed language is used as the basis for constructing the unique text identifier associated with each distinct polymer. Overall, this work presents algorithms to convert linear polymers into unique structure-based text identifiers. The derived identifiers can be readily applied in chemical information systems for polymers and other polymer informatics applications.

Visualizing Generic Reaction Patterns.

Reaction schemes for organic molecules play a crucial role in modern in silico drug design processes. In contrast to the classical drawn reaction diagrams, computational chemists prefer SMARTS based line notations due to a substantially increased expressiveness and precision. They are used to search databases, calculate synthesizability, generate new molecules, or simulate novel reactions. Working with computer-readable representations of reaction schemes can be challenging due to the complexity of the features to be represented. Line representations of reaction schemes can often be cryptic, even to experienced users. To simplify the work with Reaction SMARTS for synthetic, computational, and medicinal chemists, we introduce a visualization technique for reaction schemes and provide a respective tool, called ReactionViewer. ReactionViewer is able to convert reaction schemes encoded as Reaction SMILES, Reaction SMARTS, or SMIRKS into a visual representation. The visualization technique is based on the concept of structure diagrams and follows IUPAC's "Compendium of Chemical Terminology" definition of chemical reaction equations for the reaction symbols. We demonstrate the applicability of the method using two data sets of organic synthesis reaction schemes taken from recent publications. We discuss various properties of the visualization and highlight its readability and interpretability.

Evaluating molecular representations in machine learning models for drug response prediction and interpretability.

Machine learning (ML) is increasingly being used to guide drug discovery processes. When applying ML approaches to chemical datasets, molecular descriptors and fingerprints are typically used to represent compounds as numerical vectors. However, in recent years, end-to-end deep learning (DL) methods that can learn feature representations directly from line notations or molecular graphs have been proposed as alternatives to using precomputed features. This study set out to investigate which compound representation methods are the most suitable for drug sensitivity prediction in cancer cell lines. Twelve different representations were benchmarked on 5 compound screening datasets, using DeepMol, a new chemoinformatics package developed by our research group, to perform these analyses. The results of this study show that the predictive performance of end-to-end DL models is comparable to, and at times surpasses, that of models trained on molecular fingerprints, even when less training data is available. This study also found that combining several compound representation methods into an ensemble can improve performance. Finally, we show that a post hoc feature attribution method can boost the explainability of the DL models.

BILN: A Human-Readable Line Notation for Complex Peptides.

We present an easy, human-readable line notation to describe even complex peptides.

Ambit-SLN: an Open Source Software Library for Processing of Chemical Objects via SLN Linear Notation.

SLN (SYBYL Line Notation) is the most comprehensive and rich linear notation for representation of chemical objects of various kinds facilitating a wide range of cheminformatics algorithms. Though, it is not the most popular linear notation nowadays, SLN has capabilities for supporting the most challenging tasks of the present day cheminformatics research. We present Ambit-SLN, a new software library for cheminformatics processing of chemical objects via linear notation SLN. Ambit-SLN is developed as a part of the cheminformatics platform AMBIT. It is an open-source tool, distributed under LGPL license, written in Java and based on the Chemistry Development Kit. Ambit-SLN includes a parser for the full SLN syntax of chemical structures and substructure search queries including support for macro and Markush atoms, global and local dictionaries and user defined properties which can be stored and used by the Ambit data model. The Ambit-SLN library includes functionalities for substructure matching based on SLN query strings and utilities for conversion of SLN objects to other chemical formats such as SMILES and SMARTS. The functionality for Markush atom expansion can be used for generation of combinatorial structure sets.

Exploring Chemical Information in PubChem.

PubChem (https://pubchem.ncbi.nlm.nih.gov) is a public chemical database that serves scientific communities as well as the general public. This database collects chemical information from hundreds of data sources and organizes them into multiple data collections, including Substance, Compound, BioAssay, Protein, Gene, Pathway, and Patent. These collections are interlinked with each other, allowing users to discover related records in the various collections (e.g., drugs targeting a protein or genes modulated by a chemical). PubChem can be searched by keyword (e.g., a chemical, protein, or gene name) as well as by chemical structure. The input structure can be provided using popular line notations or drawn with the PubChem Sketcher. PubChem supports various types of structure searches, including identity search, 2‐D and 3‐D similarity searches, and substructure and superstructure searches. Results from multiple searches can be combined using Boolean operators (i.e., AND, OR, and NOT) to formulate complex queries. PubChem allows the user to quickly retrieve a list of records annotated with a particular classification or ontological term. This paper provides step‐by‐step instructions on how to explore PubChem data with examples of commonly requested tasks. © 2021. This article is a U.S. Government work and is in the public domain in the USA. Current Protocols published by Wiley Periodicals LLC.Basic Protocol 1: Finding genes and proteins that interact with a given compoundBasic Protocol 2: Finding drug‐like compounds similar to a query compound through a two‐dimensional (2‐D) similarity searchBasic Protocol 3: Finding compounds similar to a query compound through a three‐dimensional (3‐D) similarity searchSupport Protocol: Computing similarity scores between compoundsBasic Protocol 4: Getting the bioactivity data for the hit compounds from substructure searchBasic Protocol 5: Finding drugs that target a particular geneBasic Protocol 6: Getting bioactivity data of all chemicals tested against a protein.Basic Protocol 7: Finding compounds annotated with classifications or ontological termsBasic Protocol 8: Finding stereoisomers and isotopomers of a compound through identity search

LINGO-DL: a text-based approach for molecular similarity searching.

The line notations of chemical structures are more compact than those of graphs and connection tables, so they can be useful for storing and transferring a large number of molecular structures. The simplified molecular input line system (SMILES) representation is the most extensively used, as it is much easier to utilise and comprehend than others, and it can be generated automatically from connection tables. A SMILES represents and encodes the molecule structure. It has been used by an existing method, LINGO, to calculate the molecular similarities and predict the structure-related properties. The LINGO method decomposes a canonical SMILES into a set of substrings of four characters referred to as LINGOs. The purpose of LINGO method is to measure the similarity between a pair of molecules by comparing the LINGOs that occur in each molecule. This paper aims to introduce an alternative version of the LINGO method using LINGOs of different lengths, called LINGO-DL. LINGO-DL is based on the fragmentation of canonical SMILES into substrings of three different lengths rather than one in LINGO method. Retrospective virtual screening experiments with MDDR, DUD, and MUV datasets show that the LINGO-DL outperforms the LINGO method, especially when the active molecules being sought have a high degree of structural heterogeneity.

Learning chemistry: exploring the suitability of machine learning for the task of structure-based chemical ontology classification

Chemical data is increasingly openly available in databases such as PubChem, which contains approximately 110 million compound entries as of February 2021. With the availability of data at such scale, the burden has shifted to organisation, analysis and interpretation. Chemical ontologies provide structured classifications of chemical entities that can be used for navigation and filtering of the large chemical space. ChEBI is a prominent example of a chemical ontology, widely used in life science contexts. However, ChEBI is manually maintained and as such cannot easily scale to the full scope of public chemical data. There is a need for tools that are able to automatically classify chemical data into chemical ontologies, which can be framed as a hierarchical multi-class classification problem. In this paper we evaluate machine learning approaches for this task, comparing different learning frameworks including logistic regression, decision trees and long short-term memory artificial neural networks, and different encoding approaches for the chemical structures, including cheminformatics fingerprints and character-based encoding from chemical line notation representations. We find that classical learning approaches such as logistic regression perform well with sets of relatively specific, disjoint chemical classes, while the neural network is able to handle larger sets of overlapping classes but needs more examples per class to learn from, and is not able to make a class prediction for every molecule. Future work will explore hybrid and ensemble approaches, as well as alternative network architectures including neuro-symbolic approaches.