Genetic algorithm for the design of molecules with desired properties

Reverse Designing the Wavelength-Specific Thermally Activation Delayed Fluorescent Molecules Using a Genetic Algorithm Coupled with Cheap QM Methods

Genetic algorithm (GA) optimization coupled with the semiempirical intermediate neglect of differential overlap (INDO)/CIS method is presented to inversely design the red thermally activation delayed fluorescent (TADF) molecules. According to the predefined donor-acceptor (DA) library to build an AD_n-type TADF candidate, we utilized the chemical notation language SMILES code to generate a TADF molecule and apply the RDKit program to produce the initial 3D molecular structure. A combined fitness function is proposed to evaluate the performance of the functional-lead TADF molecule. The fitness function includes three key parameters, i.e., the emission wavelength, the energy gap (ΔE_ST) between the lowest singlet (S₁)- and triplet (T₁)-excited states, and the oscillator strengths for electron transition from S₀ and S₁. A cheap QM method, i.e., INDO/CIS, on the basis of an xTB-optimized molecular geometry is applied to quickly calculate the fitness function. Finally, the GA approach is utilized to globally search for the wavelength-specific TADF molecules under our predefined DA library, and the optimum 630 nm red and 660 nm deep red TADF molecules are inversely designed according to the evolution of molecular fitness functions.

A molecular evolution algorithm for ligand design in DOCK

As a complement to virtual screening, de novo design of small molecules is an alternative approach for identifying potential drug candidates. Here, we present a new 3D genetic algorithm to evolve molecules through breeding, mutation, fitness pressure, and selection. The method, termed DOCK_GA, builds upon and leverages powerful sampling, scoring, and searching routines previously implemented into DOCK6. Three primary experiments were used during development: Single-molecule evolution evaluated three selection methods (elitism, tournament, and roulette), in four clinically relevant systems, in terms of mutation type and crossover success, chemical properties, ensemble diversity, and fitness convergence, among others. Large scale benchmarking assessed performance across 651 different protein-ligand systems. Ensemble-based evolution demonstrated using multiple inhibitors simultaneously to seed growth in a SARS-CoV-2 target. Key takeaways include: (1) The algorithm is robust as demonstrated by the successful evolution of molecules across a large diverse dataset. (2) Users have flexibility with regards to parent input, selection method, fitness function, and molecular descriptors. (3) The program is straightforward to run and only requires a single executable and input file at run-time. (4) The elitism selection method yields more tightly clustered molecules in terms of 2D/3D similarity, with more favorable fitness, followed by tournament and roulette.

New Data Structure for Computational Molecular Design with Atomic or Fragment Resolution

A new molecular data structure and molecular structure operation algorithms are proposed for general purpose molecular design. The data structure allows for a variety of molecular operations for creating new molecules. Two types of molecular operations were developed, unimolecular and bimolecular operations. In unimolecular operations, a child molecule can be created from a parent via addition of a functional group, deletion of a fragment, mutation of an atom, etc. In bimolecular operations, children molecules are generated from two parent molecules through combination or crossover (hybridization). These molecular operations are essential for the creation and modification of molecules for the purpose of molecular design. The data structure is capable of representing linear, branched, multifunctional, and multivalent compounds. Algorithms are developed for deriving the molecular data structure of a molecule from its atomic coordinates and vice versa. We show that this new molecular data structure and the developed algorithms, referred to as Molecular Assembling and Representation Suite, allow one to generate a comprehensive library of new molecules via performing every possible molecular structure modification.

Development of a New De Novo Design Algorithm for Exploring Chemical Space

In the first stage of development of new drugs, various lead compounds with high activity are required. To design such compounds, we focus on chemical space defined by structural descriptors. New compounds close to areas where highly active compounds exist will show the same degree of activity. We have developed a new de novo design system to search a target area in chemical space. First, highly active compounds are manually selected as initial seeds. Then, the seeds are entered into our system, and structures slightly different from the seeds are generated and pooled. Next, seeds are selected from the new structure pool based on the distance from target coordinates on the map. To test the algorithm, we used two datasets of ligand binding affinity and showed that the proposed generator could produce diverse virtual compounds that had high activity in docking simulations.

Analysis of the relationship between end-to-end distance and activity of single-chain antibody against colorectal carcinoma

We investigated the relationship of End-to-end distance between VH and VL with different peptide linkers and the activity of single-chain antibodies by computer-aided simulation. First, we developed (G4S)n (where n = 1-9) as the linker to connect VH and VL, and estimated the 3D structure of single-chain Fv antibody (scFv) by homologous modeling. After molecular models were evaluated and optimized, the coordinate system of every protein was built and unified into one coordinate system, and End-to-end distances calculated using 3D space coordinates. After expression and purification of scFv-n with (G4S)n as n = 1, 3, 5, 7 or 9, the immunoreactivity of purified ND-1 scFv-n was determined by ELISA. A multi-factorial relationship model was employed to analyze the structural factors affecting scFv: rn=ABn-ABO2+CDn-CDO2+BCn-BCst2. The relationship between immunoreactivity and r-values revealed that fusion protein structure approached the desired state when the r-value = 3. The immunoreactivity declined as the r-value increased, but when the r-value exceeded a certain threshold, it stabilized. We used a linear relationship to analyze structural factors affecting scFv immunoreactivity.

Molecular evolution of a peptide GPCR ligand driven by artificial neural networks

Peptide ligands of G protein-coupled receptors constitute valuable natural lead structures for the development of highly selective drugs and high-affinity tools to probe ligand-receptor interaction. Currently, pharmacological and metabolic modification of natural peptides involves either an iterative trial-and-error process based on structure-activity relationships or screening of peptide libraries that contain many structural variants of the native molecule. Here, we present a novel neural network architecture for the improvement of metabolic stability without loss of bioactivity. In this approach the peptide sequence determines the topology of the neural network and each cell corresponds one-to-one to a single amino acid of the peptide chain. Using a training set, the learning algorithm calculated weights for each cell. The resulting network calculated the fitness function in a genetic algorithm to explore the virtual space of all possible peptides. The network training was based on gradient descent techniques which rely on the efficient calculation of the gradient by back-propagation. After three consecutive cycles of sequence design by the neural network, peptide synthesis and bioassay this new approach yielded a ligand with 70fold higher metabolic stability compared to the wild type peptide without loss of the subnanomolar activity in the biological assay. Combining specialized neural networks with an exploration of the combinatorial amino acid sequence space by genetic algorithms represents a novel rational strategy for peptide design and optimization.

ACTIVE SITE DRIVEN LIGAND DESIGN: AN EVOLUTIONARY APPROACH

An evolutionary approach for designing a ligand molecule that can bind to the active site of a target protein is described in this article. An earlier attempt in this regard assumed a fixed tree structure of the ligand on both sides of the pharmacophore, and used a genetic algorithm for optimizing the van der Waals energy. However, it is evident that knowledge about the size of the tree is difficult to obtain an a priori. Moreover, it will also change from one active site to another. This limitation is overcome in the present article by using variable string length genetic algorithm (VGA) for evolving an appropriate arrangement of the basic functional units of the molecule to be designed, whose size may now vary. The crossover and mutation operators are appropriately redesigned in order to tackle the concept of variable length chromosomes. Once the geometry of the molecule is obtained, the possible three-dimensional structure and its docking energy is determined. Results are demonstrated for five different target proteins both numerically and pictorially. It is found that not only does the molecule designed using variable length representation, in general, have lower energy values, the docking energies are also lower, as compared to the molecule evolved using fixed size representation.

Bioinformatics-led design of single-chain antibody molecules targeting DNA sequences for retinoblastoma

AIM

To analyze the relationship between the structure and function of single-chain Fv antibody (scFv) with bioinformatics methods, so as to provide theoretical basis for retinoblastoma targeted therapy.

METHODS

Single-chain antibodies are reconstructed for cancer-targeted therapy to provide good penetration into tumor tissue and to improve their pharmacokinetics in vivo, offering a clinically valuable application. The relationship needs to be analyzed that there may be some variations between the structure and function of the fusion proteins, and the relationship between the structure and function of protein molecules was obtained through analyzing relevant literature at home and abroad as well as modeling analysis.

RESULTS

Through our analysis of the interaction region between the antibody and the antigen, and of the binding sites for molecular conformation, it is clear that existing antibodies need to be modified at the DNA sequence level, enhancing the biological activity of the antibodies. Based on the view that bio-molecular computer models are closely integrated with biological experiments, a bio-molecular structure-activity relationship model can be established in terms of molecular conformation, physical and chemical properties and the biological activity of single-chain antibodies. Two enlightenments are obtained from our analysis. On the one hand, the structure-activity relationship is clear for new immune molecules at the gene expression level. On the other hand, a single-chain antibody molecule can be designed and optimized for the cancer-oriented treatment.

CONCLUSION

In this article, we provide the theoretical and experimental basis for the development of single-chain antibodies appropriate for retinoblastoma therapy.

Automated Lead Optimization of MMP-12 Inhibitors Using a Genetic Algorithm

Traditional lead optimization projects involve long synthesis and testing cycles, favoring extensive structure-activity relationship (SAR) analysis and molecular design steps, in an attempt to limit the number of cycles that a project must run to optimize a development candidate. Microfluidic-based chemistry and biology platforms, with cycle times of minutes rather than weeks, lend themselves to unattended autonomous operation. The bottleneck in the lead optimization process is therefore shifted from synthesis or test to SAR analysis and design. As such, the way is open to an algorithm-directed process, without the need for detailed user data analysis. Here, we present results of two synthesis and screening experiments, undertaken using traditional methodology, to validate a genetic algorithm optimization process for future application to a microfluidic system. The algorithm has several novel features that are important for the intended application. For example, it is robust to missing data and can suggest compounds for retest to ensure reliability of optimization. The algorithm is first validated on a retrospective analysis of an in-house library embedded in a larger virtual array of presumed inactive compounds. In a second, prospective experiment with MMP-12 as the target protein, 140 compounds are submitted for synthesis over 10 cycles of optimization. Comparison is made to the results from the full combinatorial library that was synthesized manually and tested independently. The results show that compounds selected by the algorithm are heavily biased toward the more active regions of the library, while the algorithm is robust to both missing data (compounds where synthesis failed) and inactive compounds. This publication places the full combinatorial library and biological data into the public domain with the intention of advancing research into algorithm-directed lead optimization methods.

De novo design: balancing novelty and confined chemical space

IMPORTANCE OF THE FIELD

De novo drug design serves as a tool for the discovery of new ligands for macromolecular targets as well as optimization of known ligands. Recently developed tools aim to address the multi-objective nature of drug design in an unprecedented manner.

AREAS COVERED IN THIS REVIEW

This article discusses recent advances in de novo drug design programs and accessory programs used to evaluate compounds post-generation.

WHAT THE READER WILL GAIN

The reader is introduced to the challenges inherent in de novo drug design and will become familiar with current trends in de novo design. Furthermore, the reader will be better prepared to assess the value of a tool, and be equipped to design more elegant tools in the future.

TAKE HOME MESSAGE

De novo drug design can assist in the efficient discovery of new compounds with a high affinity for a given target. The inclusion of existing chemoinformatic methods with current structure-based de novo design tools provides a means of enhancing the therapeutic value of these generated compounds.

VitAL: Viterbi algorithm for de novo peptide design

Background

Drug design against proteins to cure various diseases has been studied for several years. Numerous design techniques were discovered for small organic molecules for specific protein targets. The specificity, toxicity and selectivity of small molecules are hard problems to solve. The use of peptide drugs enables a partial solution to the toxicity problem. There has been a wide interest in peptide design, but the design techniques of a specific and selective peptide inhibitor against a protein target have not yet been established.

Methodology/Principal Findings

A novel de novo peptide design approach is developed to block activities of disease related protein targets. No prior training, based on known peptides, is necessary. The method sequentially generates the peptide by docking its residues pair by pair along a chosen path on a protein. The binding site on the protein is determined via the coarse grained Gaussian Network Model. A binding path is determined. The best fitting peptide is constructed by generating all possible peptide pairs at each point along the path and determining the binding energies between these pairs and the specific location on the protein using AutoDock. The Markov based partition function for all possible choices of the peptides along the path is generated by a matrix multiplication scheme. The best fitting peptide for the given surface is obtained by a Hidden Markov model using Viterbi decoding. The suitability of the conformations of the peptides that result upon binding on the surface are included in the algorithm by considering the intrinsic Ramachandran potentials.

Conclusions/Significance

The model is tested on known protein-peptide inhibitor complexes. The present algorithm predicts peptides that have better binding energies than those of the existing ones. Finally, a heptapeptide is designed for a protein that has excellent binding affinity according to AutoDock results.

Genetic algorithm optimization in drug design QSAR: Bayesian-regularized genetic neural networks (BRGNN) and genetic algorithm-optimized support vectors machines (GA-SVM)

Many articles in "in silico" drug design implemented genetic algorithm (GA) for feature selection, model optimization, conformational search, or docking studies. Some of these articles described GA applications to quantitative structure-activity relationships (QSAR) modeling in combination with regression and/or classification techniques. We reviewed the implementation of GA in drug design QSAR and specifically its performance in the optimization of robust mathematical models such as Bayesian-regularized artificial neural networks (BRANNs) and support vector machines (SVMs) on different drug design problems. Modeled data sets encompassed ADMET and solubility properties, cancer target inhibitors, acetylcholinesterase inhibitors, HIV-1 protease inhibitors, ion-channel and calcium entry blockers, and antiprotozoan compounds as well as protein classes, functional, and conformational stability data. The GA-optimized predictors were often more accurate and robust than previous published models on the same data sets and explained more than 65% of data variances in validation experiments. In addition, feature selection over large pools of molecular descriptors provided insights into the structural and atomic properties ruling ligand-target interactions.

Structure of a novel thrombin inhibitor with an uncharged D-amino acid as P1 residue

Thrombin, the ultimate proteinase of the coagulation cascade, is an attractive target for the treatment of a variety of cardiovascular diseases. Previously, a series of novel thrombin inhibitors, discovered by employing a powerful and new computer-assisted multiparameter optimization process (CADDIS), have been synthesized. We have now crystallized the complex of human alpha-thrombin with the most potent of these inhibitors, 8-5 (K(i)=3 nM), and have determined its 2.3A X-ray crystal structure. The Fourier map displayed clear electron density for the inhibitor. The central part of the inhibitor binds in an improved melagatran-like mode, while the structure identifies a d-tyrosine as P1 residue which forms a charged hydrogen bond with Asp 189 of thrombin. This is the first crystal structure of a thrombin-inhibitor complex, where an uncharged inhibitor residue makes hydrogen bonds within the thrombin S1 pocket. Additionally, novel favourable intermolecular hydrogen bonds of the inhibitor with the thrombin backbone become possible due to the d-configuration of the P1 residue. Two flanking voluminous side chains increase the strength of the subjacent hydrogen bonding system by shielding it from the bulk solvent.

Evolutionary computation and multimodal search: a good combination to tackle molecular diversity in the field of peptide design

The awesome degree of structural diversity accessible in peptide design has created a demand for computational resources that can evaluate a multitude of candidate structures. In our specific case, we translate the peptide design problem to an optimization problem, and use evolutionary computation (EC) in tandem with docking to carry out a combinatorial search. However, the use of EC in huge search spaces with different optima may pose certain drawbacks. For example, EC is prone to focus a search in the first good region found. This is a problem not only because of the undesirable and automatic rejection of potentially good search space regions, but also because the found solution may be extremely difficult to synthesize chemically or may even be a false docking positive. In order to avoid rejecting potentially good solutions and to maximize the molecular diversity of the search, we have implemented evolutionary multimodal search techniques, as well as the molecular diversity metric needed by the multimodal algorithms to measure differences between various regions of the search space.

A novel workflow for the inverse QSPR problem using multiobjective optimization

A workflow for the inverse quantitative structure-property relationship (QSPR) problem is reported in this paper for the de novo design of novel chemical entities (NCE) in silico through the application of existing QSPR models to calculate multiple objectives, including prediction confidence measures, to be optimized during the de novo design process. Two physical property datasets are applied as case studies of the inverse QSPR workflow (IQW): mean molecular polarizability and aqueous solubility. The case studies demonstrate the optimization of molecular structures to within a property range of interest; the optimized structures are then validated against QSPR models that are generated from sets of alternative descriptors to those used in the IQW. The paper concludes with a discussion of the results from the case studies.

Improving the efficiency of evolutionary de novo peptide design: strategies for probing configuration and parameter settings

Evolutionary molecular design based on genetic algorithms (GAs) has been demonstrated to be a flexible and efficient optimization approach with potential for locating global optima. Its efficacy and efficiency are largely dependent on the operations and control parameters of the GAs. Accordingly, we have explored new operations and probed good parameter setting through simulations. The findings have been evaluated in a helical peptide design according to "Parameter setting by analogy" strategy; highly helical peptides have been successfully obtained with a population of only 16 peptides and 5 iterative cycles. The results indicate that new operations such as multi-step crossover-mutation are able to improve the explorative efficiency and to reduce the sensitivity to crossover and mutation rates (CR-MR). The efficiency of the peptide design has been furthermore improved by setting the GAs at the good CR-MR setting determined through simulation. These results suggest that probing the operations and parameter settings through simulation in combination with "Parameter setting by analogy" strategy provides an effective framework for improving the efficiency of the approach. Consequently, we conclude that this framework will be useful for contributing to practical peptide design, and gaining a better understanding of evolutionary molecular design.

The Molecule Evoluator. An Interactive Evolutionary Algorithm for the Design of Drug-Like Molecules

We developed a software tool to design drug-like molecules, the "Molecule Evoluator", which we introduce and describe here. An atom-based evolutionary approach was used allowing both several types of mutation and crossover to occur. The novelty, we claim, is the unprecedented interactive evolution, in which the user acts as a fitness function. This brings a human being's creativity, implicit knowledge, and imagination into the design process, next to the more standard chemical rules. Proof-of-concept was demonstrated in a number of ways, both computationally and in the lab. Thus, we synthesized a number of compounds designed with the aid of the Molecule Evoluator. One of these is described here, a new chemical entity with activity on alpha-adrenergic receptors.

A combinatorial approach toward the generation of ambiphilic peptide-based inhibitors of protein:geranylgeranyl transferase-1

A combinatorial synthesis of oligopeptide analogues and their evaluation as protein:geranylgeranyl transferase inhibitors is presented. The combinatorial strategy is based on the random mutation, in each new generation, of one of any of the four amino acid building blocks of which the most effective compounds of the previous generation are assembled. In this way, a progressive improvement of the average inhibitory activity was observed until the fifth generation. The most active inhibitors were found to inhibit PGGT-1 in the low micromolar range (IC(50): 3.8-8.1 microM).

ENPDA: an evolutionary structure-based de novo peptide design algorithm

One of the goals of computational chemists is to automate the de novo design of bioactive molecules. Despite significant advances in computational approaches to ligand design and binding energy evaluation, novel procedures for ligand design are required. Evolutionary computation provides a new approach to this design endeavor. We propose an evolutionary tool for de novo peptide design, based on the evaluation of energies for peptide binding to a user-defined protein surface patch. Special emphasis has been placed on the evaluation of the proposed peptides, leading to two different evaluation heuristics. The software developed was successfully tested on the design of ligands for the proteins prolyl oligopeptidase, p53, and DNA gyrase.

Thrombin inhibitors identified by computer-assisted multiparameter design

Here, we present a series of thrombin inhibitors that were generated by using powerful computer-assisted multiparameter optimization process. The process was organized in design cycles, starting with a set of randomly chosen molecules. Each cycle combined combinatorial synthesis, multiparameter characterization of compounds in a variety of bioassays, and algorithmic processing of the data to devise a set of compounds to be synthesized in the next cycle. The identified lead compounds exhibited thrombin inhibitory constants in the lower nanomolar range. They are by far the most selective synthetic thrombin inhibitors, with selectivities of >100,000-fold toward other proteases such as Factor Xa, Factor XIIa, urokinase, plasmin, and Plasma kallikrein. Furthermore, these compounds exhibit a favorable profile, comprising nontoxicity, high metabolic stability, low serum protein binding, good solubility, high anticoagulant activity, and a slow and exclusively renal elimination from the circulation in a rat model. Finally, x-ray crystallographic analysis of a thrombin-inhibitor complex revealed a binding mode with a neutral moiety in the S1 pocket of thrombin.

A Graph-Based Genetic Algorithm and Its Application to the Multiobjective Evolution of Median Molecules

In this paper we propose a novel graph-based genetic algorithm for the evolution of novel molecular graphs from a predefined set of elements or molecular fragments with an external objective function. A brief overview of existing genetic algorithm approaches in molecular design is provided followed by a description of our approach. The paper continues to suggest a novel application of this program to the multiobjective evolution of median molecules that are structurally representative of a set of objective molecules. We conclude with a summary of our initial results along with a discussion of a variety of improvements and applications of our approach.