Zmiana języka

Projects search

Transformer-based methods for novel active chemical compounds

2019/35/N/ST6/02125

Keywords

Descriptors

  • ST6_011: Uczenie maszynowe, statystyczne przetwarzanie danych i zastosowania w przetwarzaniu sygnałów (np. mowy, obrazów, filmów)
  • ST6_007: Sztuczna inteligencja, systemy inteligentne i wieloagentowe

Panel

ST6 – Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems

Host institution

Uniwersytet Jagielloński, Wydział Matematyki i Informatyki

Voivodeship: małopolskie

Other projects carried out by the institution »

Principal investigator (from the host institution)

Łukasz Andrzej Maziarka

Number of co-investigators in the project: 3

Call

PRELUDIUM 18 – announced on 2019-09-16

Amount awarded
94 332 PLN
Project start date
2020-08-10
Project end date
2024-01-09
Project duration
41 months (the same as in the proposal)
Project status
Project settled

Project description

Download the project description in a pdf file

Note — project descriptions were prepared by the authors of the applications themselves and placed in the system in an unchanged form.

Information in the final report

Publication in academic press/journals (3)

  1. Extended study on atomic featurization in graph neural networks for molecular property prediction

    Authors:
    Agnieszka Wojtuch, Tomasz Danel, Sabina Podlewska, Łukasz Maziarka
    Academic press:
    Journal of Cheminformatics (year: 2023, volume: 15, pages: 81), Publisher: Springer
    Status:
    Published
    DOI:
    10.1186/s13321-023-00751-7 – link to the publication

  2. Relative molecule self-attention transformer

    Authors:
    Łukasz Maziarka, Dawid Majchrowski, Tomasz Danel, Piotr Gaiński, Jacek Tabor, Igor Podolak, Paweł Morkisz, Stanisław Jastrzębski
    Academic press:
    Journal of Cheminformatics (year: 2024, volume: 16, pages: 3), Publisher: Springer
    Status:
    Published
    DOI:
    10.1186/s13321-023-00789-7 – link to the publication

  3. Multi-Label Conditional Generation From Pre-Trained Models

    Authors:
    Magdalena Proszewska, Maciej Wołczyk, Maciej Zieba, Patryk Wielopolski, Łukasz Maziarka, Marek Śmieja
    Academic press:
    IEEE Transactions on Pattern Analysis and Machine Intelligence (year: 2024, volume: Early Access, pages: 46036), Publisher: IEEE
    Status:
    Published
    DOI:
    10.1109/TPAMI.2024.3382008 – link to the publication

Articles in post-conference publications (6)

  1. Multitask Learning Using BERT with Task-Embedded Attention

    Authors:
    Łukasz Maziarka; Tomasz Danel
    Conference:
    2021 International Joint Conference on Neural Networks (IJCNN) (year: 2021, volume: IJCNN 2021), Publisher: IEEE
    Date:
    conference 18-22.07.2021
    Status:
    Published
    DOI:
    10.1109/IJCNN52387.2021.9533990 – link to the publication

  2. Spatial Graph Convolutional Networks

    Authors:
    Tomasz Danel; Przemysław Spurek; Jacek Tabor; Marek Śmieja; Łukasz Struski; Agnieszka Słowik; Łukasz Maziarka
    Conference:
    International Conference on Neural Information Processing 2020 (year: 2020, volume: ICONIP 2020, pages: 668-675), Publisher: Springer, Cham
    Date:
    conference 18-22.11.2020
    Status:
    Published
    DOI:
    10.1007/978-3-030-63823-8_76 – link to the publication

  3. HuggingMolecules: An Open-Source Library for Transformer-Based Molecular Property Prediction

    Authors:
    Piotr Gaiński; Łukasz Maziarka; Tomasz Danel; Stanisław Jastrzębski
    Conference:
    The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-21) (Student Abstract) (year: 2022, volume: AAAI 2022, pages: 12949-12950), Publisher: Association for the Advancement of Artificial Intelligence
    Date:
    conference 22.02.2022 - 01.03.2022
    Status:
    Published
    DOI:
    10.1609/aaai.v36i11.21611 – link to the publication

  4. Comparison of Atom Representations in Graph Neural Networks for Molecular Property Prediction

    Authors:
    Agnieszka Pocha; Tomasz Danel; Sabina Podlewska; Jacek Tabor; Łukasz Maziarka
    Conference:
    2021 International Joint Conference on Neural Networks (IJCNN) (year: 2021, volume: IJCNN 2021), Publisher: IEEE
    Date:
    conference 18-22.07.2021
    Status:
    Published
    DOI:
    10.1109/IJCNN52387.2021.9533698 – link to the publication

  5. On the relationship between disentanglement and multi-task learning

    Authors:
    Łukasz Maziarka, Aleksandra Nowak, Maciej Wołczyk, Andrzej Bedychaj
    Conference:
    Machine Learning and Knowledge Discovery in Databases, European Conference, ECML PKDD 2022, Grenoble, France, September 19–23, 2022, Proceedings, Part I (year: 2023, volume: Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022., pages: 625–641), Publisher: Springer, Cham
    Date:
    conference 19-23.09.2022
    Status:
    Published
    DOI:
    10.1007/978-3-031-26387-3_38 – link to the publication

  6. PluGeN: Multi-Label Conditional Generation From Pre-Trained Models

    Authors:
    Maciej Wołczyk; Magdalena Proszewska; Łukasz Maziarka; Maciej Zieba; Patryk Wielopolski; Rafał Kurczab; Marek Śmieja
    Conference:
    The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-21) (year: 2022, volume: AAAI 2022, pages: 8647-8656), Publisher: Association for the Advancement of Artificial Intelligence
    Date:
    conference 22.02.2022 - 01.03.2022
    Status:
    Published
    DOI:
    10.1609/aaai.v36i8.20843 – link to the publication

« New search

Graphic design and implementation: Jakub Piotrowski