#iccs2025 — Public Fediverse posts

@scroeser hi, we're a academic conference, held once every three years (well, covid aside, when it was every 4 years).

Last year, our hashtag was #iccs2025 and there has been some activity (not a lot yet).

We also note that some people who were active went to different platforms, like LinkedIn

the third paper in the #iccs2025 collection is out: https://doi.org/10.1186/s13321-026-01203-8

"GRIPHIN: grids of pharmacophore interaction fields for affinity prediction"

"We investigate whether a purely pharmacophoric representation of the protein pocket is sufficient to train a deep learning model for affinity prediction. For this purpose, we devise a hybrid model architecture from simple building blocks for affinity prediction."

#cheminformatics #drugdiscovery

the second paper in the #iccs2025 collection is also out! https://doi.org/10.1186/s13321-026-01175-9

"ProQSAR: A modular and reproducible framework for small-data QSAR modeling with fit-and-use models"

"ProQSAR composes interchangeable modules for standardization, feature generation, splitting (including scaffold- and cluster-aware splits), preprocessing, outlier handling, scaling, feature selection, model training and tuning, statistical comparison, conformal calibration, and AD assessment."

the first paper in the #iccs2025 collection in the Journal of Cheminformatics is now out!

"ANNalog: generation of MedChem-similar molecules" https://doi.org/10.1186/s13321-026-01186-6

"ANNalog has the ability to produce structurally similar analogues involving minor modifications, such as substituent replacements, as well as the ability to perform scaffold hopping, generating structurally distinct yet chemically relevant analogues."

#cheminformatics

we're eagerly waiting for the first 3 papers in the #iccs2025 collection in the Journal of Cheminformatics to appear online!

#cheminformatics #openaccess

Two papers for the ICCS Collection in the Journal of Cheminformatics have been tagged as accepted now. With another 4 under review, and at least one more paper to be submitted. The deadline was extended one last time.

But we are looking forward to a nice collection of work presented at the ICCS 2025!

#cheminformatics #noordwijkerhout #ICCS2025

The submission deadline for the ICCS Collection in the Journal of Cheminformatics will be extended to March 1. We currently have four papers under review and expect at 2 more submissions.

https://link.springer.com/collections/jcfcedbfda

#cheminformatics #iccs2025

six #ICCS2025 posters can now be download from our website at https://iccs-nl.org/posters/

scientific discussion moved from "letters to the editor" to PubPeer. There is a lot to be said about that, but one thing that must be said is that PubPeer can disappear.

But Letters to the Editor are preserved, for better or worse. if not mistaken, it was @dalke that pointed me at #ICCS2025 to a 1977-1978 discussion via such letters. I looked them up, and annotated some of the citations with the Citation Typing Ontology, made @nanopub and put them in @wikidata

#openscience #cheminformatics

fediwalls are a thing! just 3 weeks too late for

https://egonw.github.io/ICCS2025/

#ICCS2025

I wanted to blog more, but there was too busy during the day. So, I have so far only this: https://chem-bla-ics.linkedchemistry.info/2025/06/08/iccs2025-1-back-in-noordwijkerhout.html

replies to this post become blog comments.

#iccs2025

if you missed the #ICCS2025, you can catch up with the slidedeck and poster PDFs that presenters have made available online, and counting:

- 1 presentation: https://iccs-nl.org/general-information/scientific-program/
- 4 posters: https://iccs-nl.org/posters/

the next International Conference on Chemical Structures, edition 14, will be held in the week of June 11-15 2028!

#ICCS2025 #ICCS2028

and there we are! the final #ICCS2025 talk!

Philipp Janssen (https://orcid.org/0000-0003-3223-9182) of University of Münster is answering in his talk "How unsociable is the fragment space, and can we do better?"

the third talk is by Niklas Piet Doering (https://orcid.org/0009-0004-8238-2985) from Freie Universität Berlin, with a talk about "MDPath: Unraveling Allosteric Communication Pathways through Molecular Dynamics Simulations"

#ICCS2025

we continue with Andreas Göller from Bayer AG, with the talk "Quantum Mechanics for Ligand Design, Binding Affinities, Toxicity Risk and Process Chemistry: Successes and Obstacles"

#ICCS2025

the last session has just started. First presentation is by Henriette Willems (https://orcid.org/0000-0001-7196-5975) from the University of Cambridge, with her talk "How useful are protein folding tools for drug design?"

#ICCS2025

now talking the floor is Domen Pregeljc (https://orcid.org/0009-0009-6310-904X) from ETH Zurich on "Advancing free-energy calculations by combining multiscale modeling and multistate enhanced sampling"

#ICCS2025

and this session was concluded by a talk by James Webster (https://orcid.org/0000-0002-7014-6350) of University of Dundee, on "Modernising the Reaction Vector Framework: From Legacy Code to Validated Synthesis"

#ICCS2025

the third talk was by Bernardo de Souza from FACCTs GmbH on "Validating the prediction of lowest-energy tautomers and conformers against experimental techniques"

#ICCS2025

the second talk in this session was Andrius Bernatavicius from Leiden University, with the talk title: "Docking-based geometric graph models for kinase-ligand affinity prediction"

#ICCS2025

yesterday, after the coffee break, we had four talks. The session was kicked of by John Wilkinson Mayfield (https://orcid.org/0000-0001-7730-2646) of NextMove Software showing even faster substructure search on billion-sized compound sets in "Honey, I shrunk the database: Making multi-billion compound libraries as small as possible"

#ICCS2025

next speaker is Leon Moritz Obendorf (https://orcid.org/0000-0002-5641-4961) from the Freie Universität Berlin. This talk has the title: "AI and MD-aided computational docking pipeline to elucidate TGF-beta type l receptor & signaling mediator interaction"

#ICCS2025

@intconfchemstr also happy to see the ETR1 signalling pathway is at least for one species (not fruit) in @wikipathways: https://www.wikipathways.org/pathways/WP2851.html

#ICCS2025

@intconfchemstr interesting aspect of this work was that the binding of agonists and antagonists of fruit ripening involves the binding with the copper ion in ETR1. The orientation of the HOMO/LUMO in the active site seems to correlate (determine) the biological action

#ICCS2025

and the final talk before the coffee break was by Luke Rossen (https://orcid.org/0009-0008-4942-0360) from the Eindhoven University of Technology on "Scaffold Hopping with Generative Reinforcement Learning"

#ICCS2025

the second talk yesterday was given by Rafał Adam Bachorz from Simulations Plus on :Navigating Synthon Space: Property-Driven Molecular Optimization for Pharmacokinetics"

#ICCS2025