Lectures

On-line Lectures / paper club

Igor Tetko gave an invited lecture with an overview of AIDD results during Machine Learning for Molecules workshop [ML4Molecules] (06.12.2024)

Alan Kai Hassen gave a talk based on the article "Generate what you can make: achieving in-house synthesizability with readily available resources in de novo drug design" (23.10.2024).

Make Science Pop! - an online workshop on effective science communication co-organised by Chelonia Applied Science, the AiChemist, AIDD and AVITHRAPID projects took place, attracting 60 participants from Europe and the US, including the AIDD fellows. The workshop was hosted by Dr. James Beacham, physicist at the LHC at CERN, and featured talks by Dr. Andrea "Annie" Kritcher of the Lawrence Livermore National Laboratory, Ryan Mandelbaum of IBM Quantum and Dr. Michelle Roberts, Digital Health Editor at the BBC. (24.10.2024)

Igor Tetko gave a lecture "Advanced Machine Learning in Drug Discovery" at KU Leuven. (03.09.2024)

Dr. Iris Köhler and Dr. Sarah de Carvalho Hartmann of The Scientist Coach delivered workshops on "Competency Profiles" and "Job Applications" for the ESRs (18.06.24 and 24.06.24).

Vincenzo Palmacci gave a talk titled "Statistical approach enabling technology-specific assay interference prediction from large screening data sets". (30.04.2024)

Mikhail Andronov gave a talk based on his recently uploaded pre-print, titled "A reagent-driven visual method for analyzing chemical reaction data" (21.02.24)

Julian Cremer gave an online lecture titled "Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation" (12.12.23)

Arslan Masood gave an online lecture titled "Dissecting Drug-Induced-Liver-Injury" (28.11.23)

Rosa Friesacher gave an online lecture, titled "Understanding Model Uncertainty and Enhancing Probability Calibration in Neural Networks" (25.10.23)

Varvara Voinarovska gave an online lecture titled “When yield prediction does not yield prediction: an overview of the current challenges” (19.09.23)

Mariia Radaeva gave lecture "Targeting Androgen Receptor with CADD" (19.07.23)

On-line presentation "Science is fun but not only: career perspectives for young talented researchers in a modern society" with focus on opportunities in European Union and Germany by Igor Tetko (11.07.23)

"Success stories of structure-based drug discovery" by Ana Messias (22.06.23)

"FSL-CP: Few-shot Prediction of small molecule activity using cell microscopy images" by Son Ha (17.05 .23)

"Mind the Retrosynthesis Gap: Bridging the divide between Single-step and Multi-step Retrosynthesis Prediction" by Paula Torren (5.04.23)

"Extending 3D generative modeling of molecules with quantum-mechanical properties" by Alessio Fallani (8.03.23)

"Reagent prediction with a transformer and its benefits for reaction product prediction" by Mikhail Andronov (1.02.23)

"Equivariant Graph Neural Networks for Toxicity Prediction" by Julian Cremer (1.02.23)

A tour through molecular representations in AI-driven drug discovery by Laurianne David (13.07.22)

AIDD Codebase: a Framework for Model Integration, Collaboration and Sharing by Emma Svensson and Peter Hartog (22.06.22)

Contrastive Learning of Image and Structure-Based Representations in Drug Discovery by Ana Sanchez-Fernandez (08.06.22)

Development of a CCR5 antagonist for HIV therapy by Tiago Rodrigues (27.04.22)

Hands-on: Data preparation and interactive visualization of chemical structures in KNIME Analytics Platform by Daria Goldmann (21.04.2022), meeting recording password: fv+.$@3M

A Survey on Human-in-the-loop Machine Learning by Yasmine Hahal (16.03)

3D structure refinement by Filipe Miguel Cardoso Micu Menezes (23.02.2022) see also additional files (174MB)

Coarse graining molecular dynamics with graph neural networks (paper club) by Andrey Mossyayev (27.01.2022)

AiZynthFinder: how it works and why by Samuel Genheden (20.12.2021) - meeting recording

Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction by Mikhail Andronov (8.12.2021)

Closing Conference (ICANN2024, Lugano, September 17 - 20, 2024)

The Use of Active Learning for Effective Exploration of Chemical Universe, Artem Cherkasov

Temporal Evaluation of Probability Calibration with Experimental Errors, Rosa Friesacher

Atom-level Quantum Pretraining Enhances the Spectral Perception of Molecular Graphs in Graphormer, Alessio Fallani

Leveraging Quantum Mechanical Properties to Predict Solvent Effects on Large Drug-Like Molecules, Mathias Hilfiker

Balancing Imbalanced Toxicity Predictor: Using MolBERT with Focal Loss, Arslan Masood

Curating Reagents in Chemical Reaction Data with an Interactive Reagent Space Map, Mikhail Andronov

Improving Route Development Using Convergent Retrosynthesis Planning, Paula Torren-Peraire

Towards Interpretable Models of Chemist Preferences for Human-in-the-Loop Assisted Drug Discovery, Yasmine Nahal

Enhancing Interpretability in Molecular Property Prediction with Contextual Explanations of Molecular Graphical Depictions, Marco Bertolini

Scaffold Splits Overestimate Virtual Screening Performance, Pedro Ballester

Geometrically Guided Diffusion for Molecular Generation, Justin Diamond

Latent-Conditioned Equivariant Diffusion for Structure-Based De Novo Ligand Generation, Julian Cremer

Cross Multimodal Learning of Cell Painting and Transcriptomics Data, Son Ha

Target-Aware Drug Activity Model: A Deep Learning Approach to Virtual HTS, Fabrizio Ambrogi and Szymon Czaplak

Temporal Evaluation of Uncertainty Quantification under Distribution Shift, Emma Svensson

Artificial Intelligence Methods for Evaluating Mitochondrial Dysfunction: Exploring Various Chemical Notations Suitable for Neural Language Processing Models, Eduardo Viganò

Combinatorial Library Neural Network (CoLiNN) for Combinatorial Library Visual without Compound Enumertion, Regina Pikalyova

De novo Drug Design - Do We Really Want To Be "Original"? A Real-World Case Study on Colchicine-Site Tubulin Binders, Dragos Horvath

Final School (Berlin, March 4 - 12, 2024)

PI Intros (Tetko slides, Haese slides, Clevert).

PI Intros (Kabeshov slides, Varnek slides, Roncaglioni slides)

Lecture by John O'Donnell (Bayer) Integrated Structural Biology: everything but the kitchen sink

Lecture by Thomas Löhr (AstraZeneca) Navigating the Maize: Computational chemistry workflows with cycles and conditions

Lecture by Anna Montebaur (Bayer) Introduction to CRISPR.

Lecture by Verena Ziegler and Sandra Berndt (Bayer) Introduction to Tox.

Lecture by Felix Oden (Bayer) Intro to targeted radiotherapies.

Lecture by Hans Briem (Bayer) Introduction to Computer-Aided Drug Design.

Workshop by Gilles Marcou (UNISTRA) Intro to KNIME and Standardization of Molecules in KNIME. Materials and instructions https://filesender.renater.fr/?s=download&token=68637050-0446-4319-aef5-732b7f53a8f8 For Window and Linux use the latest version of KNIME (5.2). For Mac users, use the version 4.5 from the official KNIME web site

Lecture by Alex Tropsha (UNC Eshelman School of Pharmacy) Rigor and reproducibility of Chemoinformatics models: from data curation to experimental validation

Lecture by David Winkler (La Trobe University), Choosing an algorithm, descriptors and approach for diverse applications of AI and ML

Lecture by Alessandra Roncaglioni (IRFMN), Machine Learning Models to Address Cardiotoxicity within an AOP Framework

Lecture by Alexandre Tkatchenko (ULUX), Navigating Chemical Compound Space Directly and Inversely

Lecture by Aixia Yan (Beijing University of Chemical Technology), Application of Machine Learning Methods for Prediction of Compound Activities and SAR Analysis

Lecture by Robin Winter (Pfizer), Multi-Objective Optimization in Continuous Latent Spaces

GPU Programming Workshop by NVIDIA

Project Management Workshop by Alexander Egeling

Lecture by Geemi Wellawatte (EPFL), XAI for Chemistry

Lecture by Mike Preuss (ULEI) Monte Carlo tree search and multi-objective variants

AIDD Presentations, Peter Hartog slides, Son Ha slides, Ana Sanchez Fernandez slides, Yasmine Nahal slides, Vincenzo Palmacci slides

Fifth School (Gothenburg, July 3-7, 2023)

AI from a MedChem perspective, Werngard Czechtizky

Predicting reaction selectivity, Per-Ola Norrby

Overcoming safety liabilities with machine learning - An industry perspective, Vignesh Subramanian

Journey of Developing AI solutions for Digital Pathology Data, Feng Gu

The promise of graphs & graph-based learning in drug discovery, Ufuk Kirik

Data-driven enhanced sampling of conformational changes in membrane proteins, Lucie Delemotte

Knowledge graphs, Michaël Ughetto

The new journey on AI modelling after REINVENT, Hongming Chen

REINVENT+CAZP workshop (interactive)

Introduction to iLab, Tove Slagbrand

LLM, Chemistry, and the Future of AI, Mike Preuss

Introduction AI Sweden, Emma Ytterström

Privacy preserving ML at AI Sweden, Johan Östman

Fourth School (Aalto, March 20-23)

Collaborative modelling, design and decision making with AI, Samuel Kaski

Predicting drug combination responses in cancer, Juho Rousu

Deep latent variable models for longitudinal biomedical data, Harri Lähdesmäki

AI assistance for drug design tutorial, Elena Shaw, Sebastiaan de Peuter, Alex Hämäläinen

Efficient uncertainty estimation with node-based BNNs, Trung Trinh

Neural network potentials and beyond, Kristof Schutt

Qptuna: easy, automated QSAR model building, Lewis Mervin

Priors in Bayesian Deep Learning, Tianyu Cui

Treatment effect estimation with neural network-based models, Manuel Hausmann

Hybrid physics and AI methods for pKa predictions in proteins, Pedro Reis

Hamiltonian Monte Carlo, Aki Vehtari

Overview of the EUOS/SLAS Compound Solubility Kaggle Challenge, Wenyu Wang

OCHEM EUOS/SLAS Solubility Challenge solubility models, Igor Tetko

The Kaggle EUOS/SLAS Solubility Challenge : Visualizing and Understanding The Data Helps in Modelling, Bernhard Rohde

Third School (Leuven, October 17-26, 2022)

Use of Sampling Methods in Bayesian Inference, Christel Faes

Variational inference: from basics to modern applications, Ádám Arany

Time-to-event modelling: approaches and pitfalls, Jaak Simm

Causality-inspired ML: what can causality do for ML? The domain adaptation case, Sara Maglicane

Artificial intelligence and big data in synthetic chemistry, Timur Madzhidov (Reaxys)

Ethics of AI, Yves Moreau

Neural networks and kernel machines: the best of both worlds, Johan Suykens

Melloddy, Wouter Heyndrickx

High Content Imaging in drug discovery, Seong Joo Koo

JUMP-Cell Painting: A new public dataset to advance image-based drug discovery, Steffen Jaensch

Bidirectional Graphormer for Reactivity Understanding Neural Network Trained to Reaction Atom-to-Atom Mapping Task, Ramil Nugmanov

Multivalent interactions, Bence Bruncsics

Cell image, Srijit Seal

Bayesian Deep Learning, Günter Klambauer

Molecule property prediction, federated learning and uncertainty quantification, Lewis Mervin

Materials Informatics: The Marriage of Materials and Data Sciences, Hanoch Senderowitz

Unlocking new training data sources for Drug Discovery Machine Learning, Hugo Ceulemans

Responsible Conduct of Research, how to do it, Marcel van der Heyden

The intersection of Optical Chemical Structure Recognition (OCSR) and object detection, Martijn Oldenhof

Inferring missing data with auto-associators, Mark Embrechts

Improving the effectiveness of compound design - Lessons learned from a data driven predictive platform at UCB, Marie Ledecq

Second School (Lugano, May 8-18, 2022)

Sequential decision making, RL and MDPs by (lecture_1, lecture_2) Oleg Szehr

Synthesis planning strategies by Philippe Schwaller

SELFIES: self-referencing embedded strings by Florian Häse

HPC for drug discovery by Silvano Coletti and Carmine Talaric

Artificial curiosity by Jürgen Schmidhuber

Constructing accurate machine learning force fields for flexible molecules by Leonardo Medrano

Few and zero-shot learning in drug discovery by Günter Klambauer

Experimental computational work by Mike Preuss

Magic rings: navigation in the ring chemical space guided by the bioactive ring by Peter Ertl

Geometric Deep Learning by Silvio Giancola

Artificial intelligence and the chemical space by Jean-Louis Reymond

Comparing and clustering synthetic route prediction by Samuel Genheden

Explainable AIU: interpreting, explaining and visualising deep learning (lecture 1 - contact Alessandro Facchini, lecture 2) by Alessandro Antonucci and Alessandro Facchini

Graph neural networks at the service of molecular simulations by Vittorio Limongelli

Structure based drug discovery (contact Michael Sattler) by Michael Sattler

AI formula generator by Guillaume Godin

Conformal prediction for the design problem by Clara Wong-Fannjiang

Gaussian processes and sequential design of experiments by Dario Azzimonti

Bayesian inference by Adam Arany

Cell painting assay, data analysis and reporting, and its application for identifying biological activity in new chemical matter by Axel Pahl

Overview of toxicity prediction methods by Emilio Benfenati

Explainability for molecular neural networks by Floriane Montanari

Equivariant (G)NNs by Marco Bertolini

Presentation of the "VIRTUOUS" project (contact Dario Piga) by Dario Piga and Gianvito Grasso