Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 28 for “"molecular representation"”.

  1. Contrastive Learning For Molecular Representation

    … AstraZeneca’s in-house generative model for molecular design, with the aim of improving the model’s understanding of chemical equivalence between different SMILES representations of the same compound. To this end, a contrastive learning framework was developed, incorporating SMILES-based data …

    chalmers Repository record for Contrastive Learning For Molecular Representation (opens in a new tab)

  2. Molecular representation modeling with graph neural networks for antibiotic discovery

    … into computer-interpretable features with rich molecular information is a core problem of data-driven machine learning applications in chemical and drug-related tasks. As small molecules can be considered as non-structural data, graph convolutional neural networks (GCNs), which can learn and …

    manitoba Repository record for Molecular representation modeling with graph neural networks for antibiotic discovery (opens in a new tab)

  3. Molecular representation learning for extreme low data in vivo toxicity modeling

    … While deep learning has revolutionized molecular modeling, its application to toxicology is severely limited by the "data scarcity bottleneck." Unlike the abundant bioactivity data available for target screening, high-quality toxicity labels from animal models and clinical trials are …

    aalto Repository record for Molecular representation learning for extreme low data in vivo toxicity modeling (opens in a new tab)

  4. RBN-World: Sub-Symbolic Artificial Chemistry for Artificial Life

    … are identified. This leads to a novel form of molecular representation -- sub-symbolic. A group of novel Artificial Chemistries called RBN-World is developed using Random Boolean Networks as a sub-symbolic molecular representation. It is shown that RBN-World has several properties of interest, …

    whiterose Download PDF for RBN-World: Sub-Symbolic Artificial Chemistry for Artificial Life (opens in a new tab)

  5. Geometric deep learning in drug discovery

    … discovery by enabling efficient, data-driven molecular modeling and prediction. In this thesis, we present a series of interpretable and task-specific methods grounded in Geometric Deep Learning (GDL) to advance molecular representation learning across key domains such as molecular property …

    manitoba Repository record for Geometric deep learning in drug discovery (opens in a new tab)

  6. Graph representation learning: algorithm development and its application to early drug discovery

    … machine learning, especially the graph representation learning (GRL)-based approaches have drawn wide-range attention. This is due to their powerful capability to flexibly handle various molecular and biological interaction information at different data scales, enabling effective …

    birmingham Download PDF for Graph representation learning: algorithm development and its application to early drug discovery (opens in a new tab)

  7. Algorithms for Self-driving Labs

    … were predicted using language models and a molecular representation called SMILES.

    toronto-retro Repository record for Algorithms for Self-driving Labs (opens in a new tab)

  8. KNOWLEDGE DISTILLATION FOR MOLECULAR PROPERTY PREDICTION

    … This study investigated KD's efficacy in molecular property prediction across domain-specific and cross-domain tasks, leveraging state-of-the-art graph neural networks (SchNet, DimeNet++, and TensorNet). In the domain-specific setting, KD improved regression performance across diverse …

    cornell Repository record for KNOWLEDGE DISTILLATION FOR MOLECULAR PROPERTY PREDICTION (opens in a new tab)

  9. Advanced Deep Learning Methods for Chemistry and Material Science

    … advances research on deep learning methods for molecular and material property predictions from three key perspectives: 1) Molecular Representation Learning: We propose an expressive neural network (HMGNN) that can learn better molecule representations and achieves state-of-the-art performance …

    umn Repository record for Advanced Deep Learning Methods for Chemistry and Material Science (opens in a new tab)

  10. Integration of topological fingerprints and machine learning for the prediction of chemical mutagenicity

    … reliance on animal tests. The quality of a good molecular representation is usually the key to building an accurate and robust in silico model, in that each representation provides a different way for the machine to look at the molecular structure. While most molecular descriptors were introduced …

    msu Repository record for Integration of topological fingerprints and machine learning for the prediction of chemical mutagenicity (opens in a new tab)

  11. Motif-based Graph Neural Networks: Representation, interpretation, and extraction

    … (GNNs) have emerged as powerful tools for molecular representation learning, but they often struggle to capture higher-order structural properties and suffer from a lack of transparency. This thesis addresses these limitations by leveraging motifs—recurring and statistically significant …

    iastate Repository record for Motif-based Graph Neural Networks: Representation, interpretation, and extraction (opens in a new tab)

  12. Impact of Virtual Models on Students’ Multilevel Understanding of an Organic Reaction

    … how students engage with the content and virtual representation to develop their understanding of a chemical reaction. This convergent mixed methods study looked at the effect of dynamic virtual molecular representation on students' ability to understand a reaction mechanism at the symbolic and …

    south-carolina Repository record for Impact of Virtual Models on Students’ Multilevel Understanding of an Organic Reaction (opens in a new tab)

  13. Molecular Study of Capsaicin in Aqueous and Hydrophobic Environments

    … to the structure and dynamics of membranes. Molecular dynamics simulations are used to study the molecular interactions. The first part of this study evaluates different molecular representations for capsaicin in an 1-octanol/water system. This inhomogeneous system is commonly used to …

    vt Repository record for Molecular Study of Capsaicin in Aqueous and Hydrophobic Environments (opens in a new tab)

  14. An Alignment-Free, Property-Dependent, Spectral Descriptor of Molecular Surfaces

    … properties is a fundamental challenge of molecular representation for cheminformatics and chemical machine learning. Existing molecular descriptors either require molecular alignment which is computationally expensive or fail to combine molecular shape and property into a unified …

    queens Repository record for An Alignment-Free, Property-Dependent, Spectral Descriptor of Molecular Surfaces (opens in a new tab)

  15. Machine Learning in Discrete Molecular Spaces

    … Whether it is in property prediction, synthesis, molecular design, or any other subdivision, machine learning seems poised to become an integral, if not a dominant, component of future research efforts. This extraordinary capacity rests on the interac- tion between machine learning models and the …

    anu Repository record for Machine Learning in Discrete Molecular Spaces (opens in a new tab)

  16. Modeling the self-assembly of functionalized fullerenes on solid surfaces using Monte Carlo simulations

    … fullerenes with the aim of tailoring their intermolecular interactions and controlling interactions with the solid substrate.The success of these rational design approaches hinges on the subtle interplay of intermolecular forces and molecule-substrate interactions. Molecular modeling is …

    unh-thes Repository record for Modeling the self-assembly of functionalized fullerenes on solid surfaces using Monte Carlo simulations (opens in a new tab)

  17. Uncertainty-Aware and Data-Efficient Fine-Tuning and Application of Foundation Models

    … novel techniques to enhance model calibration. Molecular Uncertainty Benchmark (MUBen) establishes a best-practice benchmark for UQ in molecular representation models, thoroughly evaluating uncertainty calibration and predictive accuracy in large-scale discriminative tasks. Expanding uncertainty …

    gatech Repository record for Uncertainty-Aware and Data-Efficient Fine-Tuning and Application of Foundation Models (opens in a new tab)

  18. Geometric Deep Learning for Molecular Discoveries

    … In this dissertation, we focus on AI for molecular science, such as small molecules and proteins, aiming to build efficient and effective methods to accelerate molecular discovery. we particularly focus on two fundamental tasks, molecular representation learning and molecule generation. …

    tamu Repository record for Geometric Deep Learning for Molecular Discoveries (opens in a new tab)

  19. Deep Inverse Design, Discovery, and Optimization of Molecular Structure through 3D Invariant and Multimodal Machine Learning

    … Learning this mapping would vastly expedite molecular discovery and is at the heart of the field of de novo molecular design. In this work, we explore a variety of generative statistical machine learning methods for approximating the joint probability manifold of molecular structure and …

    washington Repository record for Deep Inverse Design, Discovery, and Optimization of Molecular Structure through 3D Invariant and Multimodal Machine Learning (opens in a new tab)

  20. A Tree Representation Approach for Machine Learning Antimicrobial Drug Repurposing

    … and antibacterial activity using structure-based molecular representations. Compounds from the DrugBank database were encoded using a tree framework derived from the Junction Tree method, decomposing molecules into fixed-size substructures. Multiple models, including Logistic Regression, Random …

    guelph Repository record for A Tree Representation Approach for Machine Learning Antimicrobial Drug Repurposing (opens in a new tab)

Page 1 of 2