OWOlaf Wiest

Olaf Wiest

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Olaf Wiest has a total of 438 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • C-MAGE: Automated Extraction and Organization Engine for Molecular Representations in Chemical Documents

    by Alexander Taylor, Jeehyun Hwang, Mihir Surve, Wei Wang, Olaf Wiest

    To exploit the data present in chemical literature for AI applications in chemistry, an expanded and reliable extraction pipeline is needed. AI-ready chemical databases broaden chemical space coverage and provide benchmarking and training sets for machine learning model development to drive innovation within the field. To curate data from chemical documents, a multimodal approach is needed. C-MAGE is an open-source molecule extraction engine that processes figures and tables in PDF files to provide machine-readable molecule data sets of the structures as CXSMILES strings, an encompassing representation that evades heuristic translation of superatoms to SMILES subunits. This led to a 7.1% increase in accurate molecular representations generated. All data extracted undergo confidence-based sorting to ensure high precision (77.6%) in data set collection and remove the need for manually sorting data point validity. Both the CXSMILES and their confidence values are reproducible and are generated efficiently (1.7 s per molecule). C-MAGE’s use is demonstrated by the generation of an annotated data set containing 1454 CXSMILES strings from 38 chemical documents. C-MAGE thus enables large-scale information extraction of chemical structures in a consistent and reproducible pipeline, complementing the more common text extractions.

  • Open Access

    C-MAGE: Automated Extraction and Organization Engine for Molecular Representations in Chemical Documents

    by Alexander Taylor, Jeehyun Hwang, Mihir Surve, Wei Wang, Olaf Wiest

    To exploit the data present in chemical literature for AI applications in chemistry, an expanded and reliable extraction pipeline is needed. AI-ready chemical databases broaden chemical space coverage and provide benchmarking and training sets for machine learning model development to drive innovation within the field. To curate data from chemical documents a multimodal approach is needed. C-MAGE is an open-source molecule extraction engine that processes figures and tables in PDF files to provide machine-readable molecule datasets of the structures as CXS-MILES strings, an encompassing representation which evades heuristic translation of superatoms to SMILES subunits. This led to a 7.1% increase in accurate molecular representations generated. All data extracted undergo confidence-based sorting to ensure high precision (77.6%) in dataset collection, and removes the need for manually sorting datapoint validity. Both the CXSMILES and their confidence values are reproducible and are generated efficiently (1.7 seconds per molecule). C-MAGE’s use is demonstrated by the generation of an annotated dataset containing 1454 CXSMILES strings from 38 chemical documents. C-MAGE thus enables large-scale information extraction of chemical structures in a consistent and reproducible pipeline, complementing the more common text extractions.

  • Open Access

    Strategic ligand design for modulating axial sites in dirhodium catalysts: towards enhanced asymmetric cyclopropanation

    by Ernest Bennin, Ryan J. O'COnnell, Cristian Zavala, Gisela A. González-Montiel, Olaf Wiest, Ampofo Darko

    Dirhodium paddlewheel complexes with tethered chiral ligands improve enantioselectivity in the cyclopropanation of styrene with methyl phenyldiazoacetate.

  • Open Access

    From VAEs to Diffusion and LLMs: Modern Generative Models for Molecular Discovery

    by Kehan Guo, Yili Shen, Jeeyhun Hwang, Yue Huang, Chujie Gao, Olexandr Isayev, Olaf Wiest, Wei Wang, Xiangliang Zhang

  • Open Access

    Organic Chemistry as a Catalyst for AI Innovation: Challenges, Methods, and Emerging Paradigms

    by Nitesh V. Chawla, Gisela A. González-Montiel, Kehan Guo, Taicheng Guo, Ting Hua, Xiaobao Huang, Eric Inae, Meng Jiang, Khiem Le, Gang Liu, et al.

    Artificial intelligence and organic chemistry are redefining each other in a fundamentally bidirectional relationship. This Review highlights how the intrinsic challenges of organic chemistry have acted as a catalyst for conceptual and methodological innovation in AI itself. Sparse and heterogeneous reaction data sets spurred the development of self-supervised and few-shot learning paradigms; the combinatorial complexity of multireactant chemistry motivated the transition from graph neural networks to hypergraph architectures; the need to bridge symbolic chemical reasoning with statistical prediction inspired chemical language models grounded in large language model frameworks; and the iterative, decision-intensive nature of synthesis planning catalyzed the rise of autonomous agentic systems. We survey the multimodal landscape of chemical data, tracing the evolution of molecular representations from classical fingerprints to geometric encodings and examining how each representation class shapes downstream model capabilities. We analyze how data scarcity and uneven property distributions have driven advances in transfer learning, self-supervised pretraining, and meta-learning frameworks tailored to molecules and reactions. Reaction prediction, mechanistic inference, and retrosynthesis planning are examined as core areas where chemistry has shaped modern AI techniques. We further explore chemical reasoning through multimodal fusion, generative molecular design, and self-driving laboratories. We conclude by identifying persistent challenges, including data sparsity, selection bias, benchmark-to-lab gaps, and reproducibility.


  • Open Access

    Revisiting the Mechanism and Origin of Selectivity in Pd(II) Catalyzed Conjugate Additions of Arylboronic Acids

    by Laura R. Andreola, Olaf Wiest, Steven E. Wheeler

    Pd(II) catalyzed conjugate additions of arylboronic acids to α,β-unsaturated carbonyls using PyDHIQ or PyOx ligands are widely used for the enantioselective synthesis of quaternary centers. Building on previous computational studies of this reaction, the transmetalation step was revisited to locate several previously unknown but energetically competitive transition structures, specifically an alternative favorable pathway for the transmetalation through a 4-membered transition state with the PyOx ligand. Extensive conformational sampling of the transition structures provides into the effect of the conformation of the PyDHIQ ligand on the selectivity in the synthesis of β-aryl, β-quaternary δ-lactams. The ligand adopts the ‘closed’ conformation in the selectivity-determining transition state. Detailed analysis of noncovalent and electrostatic interactions in the different conformations provides physical insights into the origin of the experimentally observed stereoselectivity.

  • A Lactone-Enabled Approach to Metronidazole-Based Scaffolds

    by Xiaotan Yu, Gisela A. González-Montiel, Pradip Shit, Mayland Chang, Olaf Wiest, Shahriar Mobashery

    A scaffold-divergent approach to metronidazole-based compounds was described. Attempts to prepare N1-hydroxyethyl nitroimidazole-2-carboxylic acid resulted in rapid decarboxylation. A lactone (compound 8) serves as a stable and practical surrogate, enabling access to both oxadiazole and amide derivatives. Density functional theory calculations revealed that the instability of N1-hydroxyethyl nitroimidazole-2-carboxylic acid arises from a low-barrier decarboxylation pathway.


  • Open Access

    Dynamic Kinetic Resolution of Spirocyclopropyl Allenes in a (4+3)-Cycloaddition Approach Toward Cyclohepta[cd]indolones

    by Jiyoon Kim, Laura R. Andreola, Reinhard C. L. Bartsch, Kuang Gu, Allen G. Oliver, Olaf Wiest, Brandon L. Ashfeld

    An expedient approach toward the ubiquitous cyclohepta[cd]indolone scaffold employing a RhII/AgI-catalyzed (4+3)cycloaddition between a 1,3-enyne bearing an instrumental propargyl acetate and a diazooxindole is presented herein. The union of 3- and 4-atom components proceeds through a RhII-catalyzed cyclopropanation followed by a AgI-catalyzed 1,3-acetoxy rearrangement to set the stage for a [3,3]-rearrangement that engages the arene of the oxindole component resulting in a streamlined assembly of the core molecular framework. The stereoconvergence of cyclopropane and allene stereoisomers through a dynamic kinetic resolution is instrumental in achieving complete E-selective formation of the exocyclic olefin and high yields of the cycloadducts observed across a diverse array of 1,3-enynes and diazooxindole substrates.

  • Open Access

    Watching Pseudomonas mevalonii HMG-CoA Reductase in Action

    by Vatsal Purohit, Himani Patel, Calvin Steussy, Timothy Schmidt, Walker A. Hoisington, Mikaela Farrugia, Phillip S Rushton, Paul Helquist, Cynthia Stauffacher, Olaf Wiest

  • Rapid FF Generation via Hessian-Informed Initial Parameters and Automated Refinement

    by Mikaela Farrugia, Paul Helquist, Per-Ola Norrby, Olaf Wiest

    The FUERZA method and its modifications have greatly improved the generation of force field parameters from electronic structure calculations. The QFUERZA method presented here addresses some of the shortcomings of the original method and places it in a comprehensive workflow for the further optimization of the derived force constants within the Q2MM workflow. QFUERZA demonstrated improved accuracy when applied to the generation and full optimization of a ground-state force field for cis-platinum and a transition-state force field for the stereoselecting step of the rhodium-catalyzed hydrogenation of enamides, which combines literature MM3* values with new atom types for the reactive center. QFUERZA outperforms three similarly simple approaches to the derivation of force constants from the literature. Application of the gradient optimizer in the Q2MM workflow on the four different preliminary force fields also demonstrates faster convergence to parameters with excellent agreement with reference data when QFUERZA is used as the starting point. Comparison of QFUERZA-derived parameters for transition-state force fields can identify parameters closely associated with the chemical transition, automating parameter selection for the final stage of transition-state parameter refinement.