Sökning: "Molecular descriptors"

Visar resultat 1 - 5 av 10 uppsatser innehållade orden Molecular descriptors.

  1. 1. Machine learning for molecular property prediction and drug safety

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Kinga Jenei; [2023-10-23]
    Nyckelord :Molecular property prediction; Acid dissociation constant; pKa; Machine learning; Graph Neural Networks; Molecular descriptors; Drug Discovery;

    Sammanfattning : Utilizing machine learning methods for the prediction of acid dissociation (pKa ) values of compounds holds great significance, as pKa is an important parameter, optimized frequently in drug discovery. Accurate prediction of pKa values could potentially provide valuable insights on other molecular properties and thereby support compound design. LÄS MER

  3. 2. Kvantkemisk förutsägelse av regioselektivitet och reaktivitet hos SNAr-reaktioner

    Kandidat-uppsats, KTH/Kemiteknik

    Författare :Elias Norstedt; Gunnar Åkerlind; Fredrik Robin; Olof De Verdier; [2023]
    Nyckelord :Kvantkemi; teoretisk kemi; SNAr reaktioner; aromatisk substitution; nukleofil; reaktivitet; regioselektivitet; modell; förutsägelse; lämnande grupp; klorid; bromid; fluorid;

    Sammanfattning : Multivariate regression of several different quantum chemical descriptors was used to build a model for the reactivity of nucleophilic aromatic substitution reactions, i.e. SNAr reactions, through predictingthe molecular reaction site’s Gibb’s free activation energy (ΔG‡). LÄS MER

  4. 3. Sublimation temperature prediction of OLED materials : using machine learning

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Analys och partiella differentialekvationer

    Författare :Niklas Norinder; [2023]
    Nyckelord :Semiconductors; OLED; machine learning; vapor deposition; sublimation; molecular property prediction; regression; ensemble learning; deep learning;

    Sammanfattning : Organic light-emitting diodes (OLED) are and have been the future of display technology for a minute. Looking back, display technology has moved from cathode-ray tube displays (CRTs) to liquid crystal displays (LCDs). Whereas CRT displays were clunky and had quite high powerconsumption, LCDs were thinner, lighter and consumed less energy. LÄS MER

  5. 4. Benchmarking Machine Learning Methods for Peptide Activity Predictions

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Boel Knutson; Lida Meskini Moudi; [2022-10-14]
    Nyckelord :Drug discovery; peptide; classification; molecular representation; Z-scales; pseudo amino acid composition; one-hot representation; random forests; support vector machines;

    Sammanfattning : One of the main challenges in the drug discovery process is to find a suitable compound for further analysis. The compound must affect the target relevant for the specific disease, while at the same time have desired properties to make it a safe and efficient drug candidate. LÄS MER

  7. 5. Comparison of Support Vector Machines and Deep Learning For QSAR with Conformal Prediction

    Master-uppsats, Uppsala universitet/Institutionen för farmaceutisk biovetenskap

    Författare :Maria Deligianni; [2022]
    Nyckelord :support vector machines; machine learning; qsar; conformal prediction; deep learning;

    Sammanfattning : Quantitative Structure Activity Relationship (QSAR) is a very useful computa-tional method which has facilitated great progress in drug development [1]. Thismethod can be used to predict a molecule’s activity against a certain target justby comparing its structural characteristics (i.e. LÄS MER