Explainable AI for Molecules - AiChemist

Información del proyecto

AiChemist

Identificador del acuerdo de subvención: 101120466

DOI

10.3030/101120466

Fecha de la firma de la CE 14 Julio 2023

Fecha de inicio 1 Septiembre 2023

Fecha de finalización 31 Agosto 2027

Financiado con arreglo a

• Marie Skłodowska-Curie Actions (MSCA)

Coste total

Sin datos

Aportación de la UE

€ 3 028 356,00

Coordinado por

HELMHOLTZ ZENTRUM MUENCHEN DEUTSCHES FORSCHUNGSZENTRUM FUER GESUNDHEIT UND UMWELT GMBH
Germany

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Resultado final

Documents, reports (6)

Minutes of the kick-off meeting

Kick-off meeting is organised

Communication and public engagement

Report summarises the communications and public engagement activities with a goal to identify potential gaps (if any)

WS2 school

School report

WS1 school

School report

Cardiotoxicity modelling

Development of explainable model for cardiotoxicity used as a common benchmark

XAI approaches for toxicity

Overview of XAI methods which are consistent with human interpretation of toxicity

Websites, patent fillings, videos etc. (5)

Advertisement of positions

Positions are advertised

First newsletter

Newsletter reviewing recruitment is published

Applications started

Positions are announced and web site contains information on how to apply for all PhDs

Website

Web site of the project is publicly available

SS1 school

School report

Publicaciones

Other (3)

Tox24 Challenge

Autores: Tetko, Igor V.
Publicado en: Chemical Research in Toxicology, 2024
DOI: 10.1021/ACS.CHEMRESTOX.4C00192

Advanced machine learning for innovative drug discovery

Autores: Igor V. Tetko; Djork-Arné Clevert
Publicado en: Journal of Cheminformatics, 2025
DOI: 10.1186/S13321-025-01061-W

Advancing Human and Environmental Safety Science Using <i>In Silico</i> Methods

Autores: Alessandra Roncaglioni, Simona Kovarich, Kamel Mansouri, Igor V. Tetko
Publicado en: Chemical Research in Toxicology, Edición 38, 2025, ISSN 0893-228X
Editor: American Chemical Society (ACS)
DOI: 10.1021/ACS.CHEMRESTOX.5C00293

Peer reviewed articles (9)

NanoToxRadar: A Multitarget Nano-QSAR Model for Predicting the Cytotoxicity Values of Multicomponent Nanoparticles

Autores: Jaehyeon Park, Shahzad Rashid, Helena Copsey, Lang Tran, Alex Zabeo, Danail Hristozov, Giorgos P. Gakis, Costas Charitidis, Seokjoo Yoon, Hyun Kil Shin
Publicado en: ACS Nanoscience Au, Edición 5, 2025, ISSN 2694-2496
Editor: American Chemical Society (ACS)
DOI: 10.1021/ACSNANOSCIENCEAU.5C00035

Benchmarking explainable AI methods for toxicophore detection and toxicity prediction

Autores: Dina Khasanova, Igor V. Tetko
Publicado en: Digital Discovery, Edición 5, 2026, ISSN 2635-098X
Editor: Royal Society of Chemistry (RSC)
DOI: 10.1039/D5DD00576K

Beyond Molecular Structures: Investigating Demographic Factors in Drug-Induced Cardiotoxicity Prediction Models

Autores: Mateusz Iwan, Alessandra Roncaglioni, Francesca Grisoni
Publicado en: Journal of Chemical Information and Modeling, Edición 66, 2026, ISSN 1549-9596
Editor: American Chemical Society (ACS)
DOI: 10.26434/CHEMRXIV.10001782/V1

Towards the explainability of protein language models

Autores: Andrea Hunklinger, Noelia Ferruz
Publicado en: Nature Machine Intelligence, Edición 8, 2026, ISSN 2522-5839
Editor: Springer Science and Business Media LLC
DOI: 10.48550/ARXIV.2506.19532

Predicting reaction conditions: a data-driven perspective

Autores: Matthew Ball, Dragos Horvath, Thierry Kogej, Mikhail Kabeshov, Alexandre Varnek
Publicado en: Chemical Science, Edición 16, 2025, ISSN 2041-6520
Editor: Royal Society of Chemistry (RSC)
DOI: 10.26434/CHEMRXIV-2025-VC6TV

Exploring reaction condition space with expert-informed representation learning

Autores: Matthew Ball, Felix Andreas Faber, Cassie Pratley, Thierry Kogej, Dragos Horvath, Alexandre Varnek, Giulia Bergonzini, Christof Martin Jäger, Mikhail Kabeshov
Publicado en: Digital Discovery, 2026, ISSN 2635-098X
Editor: Royal Society of Chemistry
DOI: 10.26434/CHEMRXIV.15001054/V2

BONAFIDE: a Python framework for the calculation of local features for atoms and bonds in molecules

Autores: Lukas M. Sigmund, Michele Assante, Matthew Ball, Mikhail Kabeshov
Publicado en: Journal of Cheminformatics, Edición 18, 2026, ISSN 1758-2946
Editor: Springer Science and Business Media LLC
DOI: 10.26434/CHEMRXIV.15001386/V1

MolEncoder: towards optimal masked language modeling for molecules

Autores: Fabian P. Krüger, Nicklas Österbacka, Mikhail Kabeshov, Ola Engkvist, Igor Tetko
Publicado en: Digital Discovery, 2025, ISSN 2635-098X
Editor: Royal Society of Chemistry (RSC)
DOI: 10.1039/D5DD00369E

25 Years of CardiacIon Channel QSAR: From hERG Dominanceto Multi-Channel Modeling

Autores: Mateusz Iwan, Francesca Grisoni, Anastasia Pentina, Marina Garcia de Lomana, Alessandra Roncaglioni
Publicado en: Journal of Chemical Information and Modeling, Edición 66, 2026, ISSN 1549-9596
Editor: American Chemical Society (ACS)
DOI: 10.26434/CHEMRXIV.15004509/V2

Conference proceedings (4)

Uni-Mol Docking V2: Towards Realistic and Accurate Binding Pose Prediction

Autores: Eric Alcaide, Zhifeng Gao, Guolin Ke, Yaqi Li, Linfeng Zhang, Hang Zheng, Gengmo Zhou
Publicado en: Lecture Notes in Computer Science, Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions, 2025
Editor: Springer Nature Switzerland
DOI: 10.48550/ARXIV.2405.11769

MolEncoder: Improved Masked Language Modeling for Molecules

Autores: Fabian P. Krüger, Nicklas Österbacka, Mikhail Kabeshov, Ola Engkvist, Igor Tetko
Publicado en: Lecture Notes in Computer Science, Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions, 2025
Editor: Springer Nature Switzerland
DOI: 10.26434/CHEMRXIV-2025-H4W9D

RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale

Autores: Daniel Goldstein, Eric Alcaide, Janna Lu, Eugene Cheah
Publicado en: arXiv
Editor: Cornell University
DOI: 10.48550/ARXIV.2505.03005

CP-BG-1M: A CONTROLLED MULTI-VIEW BENCH- MARK FOR DENSITY AND BACKGROUND SHORTCUTS IN MORPHOLOGY PROFILING

Autores: Tim Treis, Nikita Moshkov, Ghaith Mqawass, Fabian J. Theis
Publicado en: MLGenX Workshop, ICLR 2026, 2026
Editor: OpenReview.net
DOI: 10.5281/ZENODO.23564846