Conformer Generation Research Articles

Assessing small molecule conformational sampling methods in molecular docking.

Small molecule conformational sampling plays a pivotal role in molecular docking. Recent advancements have led to the emergence of various conformational sampling methods, each employing distinct algorithms. This study investigates the impact of different small molecule conformational sampling methods in molecular docking using UCSF DOCK 3.7. Specifically, six traditional sampling methods (Omega, BCL::Conf, CCDC Conformer Generator, ConfGenX, Conformator, RDKit ETKDGv3) and a deep learning-based model (Torsional Diffusion) for generating conformational ensembles are evaluated. These ensembles are subsequently docked against the Platinum Diverse Dataset, the PoseBusters dataset and the DUDE-Z dataset to assess binding pose reproducibility and screening power. Notably, different sampling methods exhibit varying performance due to their unique preferences, such as dihedral angle sampling ranges on rotatable bonds. Combining complementary methods may lead to further improvements in docking performance.

Molli: A General Purpose Python Toolkit for Combinatorial Small Molecule Library Generation, Manipulation, and Feature Extraction.

The construction, management, and analysis of large in silico molecular libraries is critical in many areas of modern chemistry. Herein, we introduce the MOLecular LIibrary toolkit, "molli", which is a Python 3 cheminformatics module that provides a streamlined interface for manipulating large in silico libraries. Three-dimensional, combinatorial molecule libraries can be expanded directly from two-dimensional chemical structure fragments stored in CDXML files with high stereochemical fidelity. Geometry optimization, property calculation, and conformer generation are executed by interfacing with widely used computational chemistry programs such as OpenBabel, RDKit, ORCA, NWChem, and xTB/CREST. Conformer-dependent grid-based feature calculators provide numerical representation and interface to robust three-dimensional visualization tools that provide comprehensive images to enhance human understanding of libraries with thousands of members. The package includes a command-line interface in addition to Python classes to streamline frequently used workflows. Parallel performance is benchmarked on various hardware platforms, and common workflows are demonstrated for different tasks ranging from optimized grid-based descriptor calculation on catalyst libraries to an NMR chemical shift prediction workflow from CDXML files.

Understanding and Quantifying Molecular Flexibility: Torsion Angular Bin Strings.

Molecular flexibility is a commonly used, but not easily quantified term. It is at the core of understanding composition and size of a conformational ensemble and contributes to many molecular properties. For many computational workflows, it is necessary to reduce a conformational ensemble to meaningful representatives, however defining them and guaranteeing the ensemble's completeness is difficult. We introduce the concepts of torsion angular bin strings (TABS) as a discrete vector representation of a conformer's dihedral angles and the number of possible TABS (nTABS) as an estimation for the ensemble size of a molecule, respectively. Here, we show that nTABS corresponds to an upper limit for the size of the conformational space of small molecules and compare the classification of conformer ensembles by TABS with classifications by RMSD. Overcoming known drawbacks like the molecular size dependency and threshold picking of the RMSD measure, TABS is shown to meaningfully discretize the conformational space and hence allows e.g. for fast checks of the coverage of the conformational space. The current proof-of-concept implementation is based on the ETKDGv3 conformer generator as implemented in the RDKit and known torsion preferences extracted from small-molecule crystallographic data.

Exactly solvable floquet dynamics for conformal field theories in dimensions greater than two

We find classes of driven conformal field theories (CFT) in d + 1 dimensions with d > 1, whose quench and floquet dynamics can be computed exactly. The setup is suitable for studying periodic drives, consisting of square pulse protocols for which Hamiltonian evolution takes place with different deformations of the original CFT Hamiltonian in successive time intervals. These deformations are realized by specific combinations of conformal generators with a deformation parameter β; the β < 1 (β > 1) Hamiltonians can be unitarily related to the standard (Lüscher-Mack) CFT Hamiltonians. The resulting time evolution can be then calculated by performing appropriate conformal transformations. For d ≤ 3 we show that the transformations can be easily obtained in a quaternion formalism. Evolution with such a single Hamiltonian yields qualitatively different time dependences of observables depending on the value of β, with exponential decays characteristic of heating for β > 1, oscillations for β < 1 and power law decays for β = 1. This manifests itself in the behavior of the fidelity, unequal-time correlator, and the energy density at the end of a single cycle of a square pulse protocol with different hamiltonians in successive time intervals. When the Hamiltonians in a cycle involve generators of a single SU(1, 1) subalgebra we calculate the Floquet Hamiltonian. We show that one can get dynamical phase transitions for any β by varying the time period of a cycle, where the system can go from a non-heating phase which is oscillatory as a function of the time period to a heating phase with an exponentially damped behavior. Our methods can be generalized to other discrete and continuous protocols. We also point out that our results are expected to hold for a broader class of QFTs that possesses an SL(2, C) symmetry with fields that transform as quasi-primaries under this. As an example, we briefly comment on celestial CFTs in this context.

EC-Conf: A ultra-fast diffusion model for molecular conformation generation with equivariant consistency

Despite recent advancement in 3D molecule conformation generation driven by diffusion models, its high computational cost in iterative diffusion/denoising process limits its application. Here, an equivariant consistency model (EC-Conf) was proposed as a fast diffusion method for low-energy conformation generation. In EC-Conf, a modified SE (3)-equivariant transformer model was directly used to encode the Cartesian molecular conformations and a highly efficient consistency diffusion process was carried out to generate molecular conformations. It was demonstrated that, with only one sampling step, it can already achieve comparable quality to other diffusion-based models running with thousands denoising steps. Its performance can be further improved with a few more sampling iterations. The performance of EC-Conf is evaluated on both GEOM-QM9 and GEOM-Drugs sets. Our results demonstrate that the efficiency of EC-Conf for learning the distribution of low energy molecular conformation is at least two magnitudes higher than current SOTA diffusion models and could potentially become a useful tool for conformation generation and sampling.Scientific ContributionsIn this work, we proposed an equivariant consistency model that significantly improves the efficiency of conformation generation in diffusion-based models while maintaining high structural quality. This method serves as a general framework and can be further extended to more complex structure generation and prediction tasks, including those involving proteins, in future steps.

Conf-GEM: A geometric information-assisted direct conformation generation model

Molecular conformations generation (MCG) aims to efficiently obtain reasonable and stable three-dimensional (3D) atomic coordinates of the atoms in the molecule from scratch, providing a structural foundation for molecular representation learning models and advanced downstream molecular design tasks such as molecular property prediction, molecular generation, and molecular docking. Existing MCG methods mostly rely on indirect distance-based strategies, which which can result in geometrically unrealistic conformations, or direct coordinate-based methods, which have larger search spaces and are prone to overfitting. Therefore, this study introduces Conf-GEM, a novel geometric information-assisted direct conformation generation model based on E-GeoGNN, a geometrically augmented 3D graph neural network with multiple scales. Pre-training and divide-and-conquer strategies, are integrated into the proposed model. Conf-GEM outperforms RDKit and nine deep-learning-based MCG models on the GEOM-QM9 and GEOM-Drugs datasets, achieving conformational coverage of 96.69% and 96.07%, respectively, without force field optimization. It also excels on the X-ray diffraction crystal structure dataset with up to 97.04% conformational coverage. In conclusion, Conf-GEM provides a novel solution for stabilizing 3D conformations generation. We provide an online prediction service (https://confgem.cmdrg.com) with a user-friendly interface for researchers.

Refined Bonded Terms in Coarse-Grained Models for Intrinsically Disordered Proteins Improve Backbone Conformations.

Coarse-grained models designed for intrinsically disordered proteins and regions (IDP/Rs) usually omit some bonded potentials (e.g., angular and dihedral potentials) as a conventional strategy to enhance backbone flexibility. However, a notable drawback of this approach is the generation of inaccurate backbone conformations. Here, we addressed this problem by introducing residue-specific angular, refined dihedral, and correction map (CMAP) potentials, derived based on the statistics from a customized coil database. These bonded potentials were integrated into the existing Mpipi model, resulting in a new model, denoted as the "Mpipi+" model. Results show that the Mpipi+ model can improve backbone conformations. More importantly, it can markedly improve the secondary structure propensity (SSP) based on the experimental chemical shift and, consequently, succeed in capturing transient secondary structures. Moreover, the Mpipi+ model preserves the liquid-liquid phase separation (LLPS) propensities of IDPs.

A variant on the CREST iMTD algorithm for noncovalent clusters of flexible molecules.

Conformational ensemble generation and the search for the global minimum conformation are important problems in computational chemistry. In this work, a variant on the conformer-rotamer ensemble sampling tool (CREST) iterative metadynamics (iMTD) algorithm designed for determining structural ensembles and energetics of noncovalent clusters of flexible molecules is presented. We term this new algorithm a low-energy diversity-enhanced variant on CREST, or LEDE-CREST. As with CREST, the energies are evaluated using the semiempirical GFN2-xTB extended tight binding approach. The utility of the algorithm is highlighted by generating ensembles for a variety of noncovalent clusters of flexible or rigid monomers using both CREST and LEDE-CREST.

Efficient molecular conformation generation with quantum-inspired algorithm.

Conformation generation, also known as molecular unfolding (MU), is a crucial step in structure-based drug design, remaining a challenging combinatorial optimization problem. Quantum annealing (QA) has shown great potential for solving certain combinatorial optimization problems over traditional classical methods such as simulated annealing (SA). However, a recent study showed that a 2000-qubit QA hardware was still unable to outperform SA for the MU problem. Here, we propose the use of quantum-inspired algorithm to solve the MU problem, in order to go beyond traditional SA. We introduce a highly compact phase encoding method which can exponentially reduce the representation space, compared with the previous one-hot encoding method. For benchmarking, we tested this new approach on the public QM9 dataset generated by density functional theory (DFT). The root-mean-square deviation between the conformation determined by our approach and DFT is negligible (less than about 0.5Å), which underpins the validity of our approach. Furthermore, the median time-to-target metric can be reduced by a factor of five compared to SA. Additionally, we demonstrate a simulation experiment by MindQuantum using quantum approximate optimization algorithm (QAOA) to reach optimal results. These results indicate that quantum-inspired algorithms can be applied to solve practical problems even before quantum hardware becomes mature. The objective function of MU is defined as the sum of all internal distances between atoms in the molecule, which is a high-order unconstrained binary optimization (HUBO) problem. The degree of freedom of variables is discretized and encoded with binary variables by the phase encoding method. We employ the quantum-inspired simulated bifurcation algorithm for optimization. The public QM9 dataset is generated by DFT. The simulation experiment of quantum computation is implemented by MindQuantum using QAOA.

Knotted artifacts in predicted 3D RNA structures.

Unlike proteins, RNAs deposited in the Protein Data Bank do not contain topological knots. Recently, admittedly, the first trefoil knot and some lasso-type conformations have been found in experimental RNA structures, but these are still exceptional cases. Meanwhile, algorithms predicting 3D RNA models have happened to form knotted structures not so rarely. Interestingly, machine learning-based predictors seem to be more prone to generate knotted RNA folds than traditional methods. A similar situation is observed for the entanglements of structural elements. In this paper, we analyze all models submitted to the CASP15 competition in the 3D RNA structure prediction category. We show what types of topological knots and structure element entanglements appear in the submitted models and highlight what methods are behind the generation of such conformations. We also study the structural aspect of susceptibility to entanglement. We suggest that predictors take care of an evaluation of RNA models to avoid publishing structures with artifacts, such as unusual entanglements, that result from hallucinations of predictive algorithms.

Predicting binding events in very flexible, allosteric, multi-domain proteins.

Knowledge of the structures formed by proteins and small ligands is of fundamental importance for understanding molecular principles of chemotherapy and for designing new and more effective drugs. Due to the still high costs and to the several limitations of experimental techniques, it is most often desirable to predict these ligand-protein complexes in silico, particularly when screening for new putative drugs from databases of millions of compounds. While virtual screening based on molecular docking is widely used for this purpose, it generally fails in mimicking binding events associated with large conformational changes in the protein, particularly when the latter involve multiple domains. In this work, we describe a new methodology aimed at generating bound-like conformations of very flexible and allosteric proteins bearing multiple binding sites. Validation was performed on the enzyme adenylate kinase (ADK), a paradigmatic example of proteins that undergo very large conformational changes upon ligand binding. By only exploiting the unbound structure and the putative binding sites of the protein, we generated a significant fraction of bound-like structures, which employed in ensemble-docking calculations allowed to find native-like poses of substrates, inhibitors, and catalytically incompetent binders. Our protocol provides a general framework for the generation of bound-like conformations of flexible proteins that are suitable to host different ligands, demonstrating high sensitivity to the fine chemical details that regulate protein's activity. We foresee applications in virtual screening for difficult targets, prediction of the impact of amino acid mutations on structure and dynamics, and protein engineering.

Predicting equilibrium distributions for molecular systems with deep learning

Advances in deep learning have greatly improved structure prediction of molecules. However, many macroscopic observations that are important for real-world applications are not functions of a single molecular structure but rather determined from the equilibrium distribution of structures. Conventional methods for obtaining these distributions, such as molecular dynamics simulation, are computationally expensive and often intractable. Here we introduce a deep learning framework, called Distributional Graphormer (DiG), in an attempt to predict the equilibrium distribution of molecular systems. Inspired by the annealing process in thermodynamics, DiG uses deep neural networks to transform a simple distribution towards the equilibrium distribution, conditioned on a descriptor of a molecular system such as a chemical graph or a protein sequence. This framework enables the efficient generation of diverse conformations and provides estimations of state densities, orders of magnitude faster than conventional methods. We demonstrate applications of DiG on several molecular tasks, including protein conformation sampling, ligand structure sampling, catalyst–adsorbate sampling and property-guided structure generation. DiG presents a substantial advancement in methodology for statistically understanding molecular systems, opening up new research opportunities in the molecular sciences.

Development of Integrated Database for Experiments and Simulations

Researchers collect data and use various methods to organize it. Ensuring the reliability and reproducibility of data is crucial, and collaboration across different research fields is on the rise. However, when there is geographical distance, sharing data becomes a challenging task. Therefore, there is a need for the development of a mechanism for sharing data on the web. We have developed an integrated database to facilitate the sharing and management of research data, particularly focusing on small molecules. The integrated database serves as a platform for centralizing data related to small molecules, including their chemical structures, wet lab experimental data, simulation data, and more. It has been constructed as a web application, offering features such as library management for small molecules, registration and viewing of wet lab experiment results, generation of initial conformations for simulations, and data visualization. This enables researchers to efficiently share their research data and collaborate seamlessly, whether within their research group or via cloud-based access that allows project and team members to connect from anywhere. This integrated database plays a critical role in connecting wet lab experiments and simulations, enabling researchers to cross-reference and analyze experimental data comprehensively. It serves as an essential tool to advance research and foster idea generation.

COSMIC: Molecular Conformation Space Modeling in Internal Coordinates with an Adversarial Framework.

The fast and accurate conformation space modeling is an essential part of computational approaches for solving ligand and structure-based drug discovery problems. Recent state-of-the-art diffusion models for molecular conformation generation show promising distribution coverage and physical plausibility metrics but suffer from a slow sampling procedure. We propose a novel adversarial generative framework, COSMIC, that shows comparable generative performance but provides a time-efficient sampling and training procedure. Given a molecular graph and random noise, the generator produces a conformation in two stages. First, it constructs a conformation in a rotation and translation invariant representation─internal coordinates. In the second step, the model predicts the distances between neighboring atoms and performs a few fast optimization steps to refine the initial conformation. The proposed model considers conformation energy, achieving comparable space coverage, and diversity metrics results.

DiSCO: Diffusion Schrödinger Bridge for Molecular Conformer Optimization

The generation of energetically optimal 3D molecular conformers is crucial in cheminformatics and drug discovery. While deep generative models have been utilized for direct generation in Euclidean space, this approach encounters challenges, including the complexity of navigating a vast search space. Recent generative models that implement simplifications to circumvent these challenges have achieved state-of-the-art results, but this simplified approach unavoidably creates a gap between the generated conformers and the ground-truth conformational landscape. To bridge this gap, we introduce DiSCO: Diffusion Schrödinger Bridge for Molecular Conformer Optimization, a novel diffusion framework that enables direct learning of nonlinear diffusion processes in prior-constrained Euclidean space for the optimization of 3D molecular conformers. Through the incorporation of an SE(3)-equivariant Schrödinger bridge, we establish the roto-translational equivariance of the generated conformers. Our framework is model-agnostic and offers an easily implementable solution for the post hoc optimization of conformers produced by any generation method. Through comprehensive evaluations and analyses, we establish the strengths of our framework, substantiating the application of the Schrödinger bridge for molecular conformer optimization. First, our approach consistently outperforms four baseline approaches, producing conformers with higher diversity and improved quality. Then, we show that the intermediate conformers generated during our diffusion process exhibit valid and chemically meaningful characteristics. We also demonstrate the robustness of our method when starting from conformers of diverse quality, including those unseen during training. Lastly, we show that the precise generation of low-energy conformers via our framework helps in enhancing the downstream prediction of molecular properties. The code is available at https://github.com/Danyeong-Lee/DiSCO.

Physics-Informed Generative Model for Drug-like Molecule Conformers.

We present a diffusion-based generative model for conformer generation. Our model is focused on the reproduction of the bonded structure and is constructed from the associated terms traditionally found in classical force fields to ensure a physically relevant representation. Techniques in deep learning are used to infer atom typing and geometric parameters from a training set. Conformer sampling is achieved by taking advantage of recent advancements in diffusion-based generation. By training on large, synthetic data sets of diverse, drug-like molecules optimized with the semiempirical GFN2-xTB method, high accuracy is achieved for bonded parameters, exceeding that of conventional, knowledge-based methods. Results are also compared to experimental structures from the Protein Databank and the Cambridge Structural Database.

Leveraging 2D molecular graph pretraining for improved 3D conformer generation with graph neural networks

Predicting stable 3D molecular conformations from 2D molecular graphs is a challenging and resource-intensive task, yet it is critical for various applications, particularly drug design. Density functional theory (DFT) calculations set the standard for molecular conformation generation, yet they are computationally intensive. Deep learning offers more computationally efficient approaches, but struggles to match DFT accuracy, particularly on complex drug-like structures. Additionally, the steep computational demands of assembling 3D molecular datasets constrain the broader adoption of deep learning. This work aims to utilize the abundant 2D molecular graph datasets for pretraining a machine learning model, a step that involves initially training the model on a different task with a wealth of data before fine-tuning it for the target task of 3D conformation generation. We build on GeoMol, an end-to-end graph neural network (GNN) method for predicting atomic 3D structures and torsion angles. We examine the limitations of the GeoMol method and introduce new baselines to enhance molecular graph embeddings. Our computational results show that 2D molecular graph pretraining enhances the quality of generated 3D conformers, yielding a 7.7 % average improvement over state-of-the-art sequential methods. These advancements not only facilitate superior 3D conformation generation but also emphasize the potential of leveraging pretrained graph embeddings to boost performance in 3D chemical tasks with GNNs.

COVALENT-102: A phase 1/1b dose finding study of BMF-219, an oral covalent menin inhibitor, in adults with locally advanced, unresectable, or metastatic non-small cell lung cancer (NSCLC), pancreatic cancer (PDAC) and colorectal cancer (CRC) with activating KRAS mutations.

TPS716 Background: BMF-219 is a selective covalent inhibitor of menin, a transcriptional regulator of oncogenic signaling pathways in multiple cancers, that inhibits the menin/MYC interaction and downregulates the expression of MYC and MYC target genes, including KRAS. In addition, inhibition of the menin complex by BMF-219 alters function of the AP-1 transcription factor, JunD, a crucial factor for KRAS-driven tumorigenesis. Further, inhibition of the menin-MLL complex suppresses expression of Rasgrf1, a guanine nucleotide exchange factor essential for generation of the active RAS-GTP conformation of KRAS, activation of downstream pathways, and tumorigenesis. Preclinically, BMF-219 shows potent abrogation of menin-dependent oncogenic signaling and exerts pan-mutant KRAS anticancer activity independent of the specific KRAS-activating mutation. Methods: COVALENT-102 (NCT05631574) is a prospective, open-label, dose-finding study evaluating the safety, tolerability, and clinical activity of BMF-219 administered daily in adults with unresectable, locally advanced, or metastatic NSCLC (Cohort 1), PDAC (Cohort 2) and CRC (Cohort 3) with activating KRAS mutations who have received standard therapy. All indications as a group follow a 3+3 dose escalation design. BMF-219 is orally administered once or twice daily as continuous therapy in 28-day cycles until progression or intolerability/unacceptable toxicity. Following dose-escalation, each indication will enroll patients in expansion cohorts independently to obtain further safety and efficacy data. Eligible patients include those with any KRAS mutation and (Cohort 1) stage IIIB/IV NSCLC with 2-4 prior lines of therapy including immune checkpoint inhibitors (ICI) &amp;/or platinum-based chemo ± bevacizumab with ECOG 0-2; (Cohort 2) stage III/IV PDAC with ≥ 1 prior line of therapy including either FOLFIRINOX or gemcitabine/nab-paclitaxel, ECOG 0-1; or (Cohort 3) stage III/IV CRC with ≥ 1 prior line of therapy including FOLFOX or FOLFIRI ± bevacizumab (prior ICI if MSI-H/dMMR), ECOG 0-2. Patients must have documented progression and measurable disease as defined by RECIST 1.1. Patients with prior KRAS inhibitor exposure are eligible. Key exclusion criteria include untreated CNS metastasis, prior menin inhibitor therapy, and clinically significant cardiovascular disease. The primary objective is to determine the optimal biological dose/ recommended Phase 2 dose of BMF-219 monotherapy. Secondary objectives include further evaluation of safety and tolerability, characterization of the PK/PD of BMF-219, and efficacy based on duration of response and disease control rate. PFS, OS, and time to response are exploratory endpoints. Accrual began in January 2023 and is ongoing. Clinical trial information: NCT05631574 .

Molecular Gas-Phase Conformational Ensembles.

Accurately determining the global minima of a molecular structure is important in diverse scientific fields, including drug design, materials science, and chemical synthesis. Conformational search engines serve as valuable tools for exploring the extensive conformational space of molecules and for identifying energetically favorable conformations. In this study, we present a comparison of Auto3D, CREST, Balloon, and ETKDG (from RDKit), which are freely available conformational search engines, to evaluate their effectiveness in locating global minima. These engines employ distinct methodologies, including machine learning (ML) potential-based, semiempirical, and force field-based approaches. To validate these methods, we propose the use of collisional cross-section (CCS) values obtained from ion mobility-mass spectrometry studies. We hypothesize that experimental gas-phase CCS values can provide experimental evidence that we likely have the global minimum for a given molecule. To facilitate this effort, we used our gas-phase conformation library (GPCL) which currently consists of the full ensembles of 20 small molecules and can be used by the community to validate any conformational search engine. Further members of the GPCL can be readily created for any molecule of interest using our standard workflow used to compute CCS values, expanding the ability of the GPCL in validation exercises. These innovative validation techniques enhance our understanding of the conformational landscape and provide valuable insights into the performance of conformational generation engines. Our findings shed light on the strengths and limitations of each search engine, enabling informed decisions for their utilization in various scientific fields, where accurate molecular structure determination is crucial for understanding biological activity and designing targeted interventions. By facilitating the identification of reliable conformations, this study significantly contributes to enhancing the efficiency and accuracy of molecular structure determination, with particular focus on metabolite structure elucidation. The findings of this research also provide valuable insights for developing effective workflows for predicting the structures of unknown compounds with high precision.

Recent advances in protein conformation sampling by combining machine learning with molecular simulation

Abstract The rapid advancement and broad application of machine learning (ML) have driven a groundbreaking revolution in computational biology. One of the most cutting-edge and important applications of ML is its integration with molecular simulations to improving the sampling efficiency of the vast conformational space of large biomolecules. This review focuses on recent studies that utilize ML-based techniques in the exploration of protein conformational landscape. We first highlight the recent development of ML-aided enhanced sampling methods, including heuristic algorithms and neural networks that are designed to refine the selection of reaction coordinates for the construction of bias potential, or facilitate the exploration of the unsampled region of the energy landscape. Further, we review the development of autoencoder based methods which combine molecular simulations and deep learning to expand the search of protein conformations. Lastly, we discuss the cutting-edge methodologies for the one-shot generation of protein conformations with precise Boltzmann weights. Collectively, this review demonstrates the promising potential of machine learning in revolutionizing our insight into the complex conformational ensembles of proteins.