This Week In Cheminformatics: Issue #027

The 10th edition of cheminformatics summer school in Strasbourg came to an on the 26th of June. Below are some of the more appropriate images that I found on my phone over the last week. Apologies to everyone who’s not in them.

Once again, many thanks to the organizers of the event and the co-ordinators of the Erasmus Mundus Master Program in ChEMoinformaticsPlus for their support.

Clustering high-throughput screening hits into initial SAR series leaves medchemists with the tedious task of manually refining the groups to fix clustering / misclassifications. Fährrolfes et al. instead built a human-in-the-loop workflow to improve this. They start with a standard k-means++ assignment and present a flattened projection using a modified Stochastic Proximity Embedding algorithm. What makes this interesting is the feedback loop: when an expert manually drags a molecule to a different cluster to correct it, a modified Pegasos online Support Vector Machine instantly treats that reassignment as a hard constraint. It then incrementally updates the multi-class decision boundaries without retraining completely. The authors demonstrated that this interactive setup cuts the required manual refinement steps roughly in half across several benchmark datasets. Code can be found here. Good read !

Depenveiller et al. present a method, PP-MAPS, which extends dynophore analysis from small-molecule ligands to protein-peptide complexes. The practical obstacle is that peptides come encoded as part of the macromolecule in MD outputs, so most pharmacophore engines refuse to treat the peptide as a ligand. PP-MAPS solves this by enforcing the peptide at the end of each PDB frame and delegating feature detection to LigandScout or the open-source CDPKit. The output is a pharmacophore-type frequency matrix aggregated over the trajectory per residue, this makes comparisons across peptides and receptor variants possible. The CDPKit path runs end-to-end without a LigandScout license. Worth a read if you work on peptide therapeutics or need a compact way to summarize how a conformational ensemble fills a binding groove. Code can be found here.

• BEACON: a Bayesian optimization inspired strategy for efficient novelty search

• Benchmarking docking and ML re-scoring screening performance for KRAS G12D in pancreatic cancer

• Development of a double-pharmacophore workflow for screening subtype-selective M

• Enhancing molecular property prediction of transformer models with dual graph representation

• Semi‐Supervised Gaussian Mixture Regression With Gaussian Mixture Model Pretraining With Unlabeled Data

• Adaptive Interval Selection for Near‐Infrared Spectra via Fused Lasso and Backward Interval PLS

• Mechanism-Informed Rules Tunably Balance Novelty and Feasibility of Predicted Enzymatic Reactions

• Balancing Data Quantity and Quality: Evaluating Curation Strategies for Bioactivity Prediction in Lead Optimization

• Robustness of Protein–Ligand Binding Affinity Prediction Models to Docked and Predicted Structures

• Pathway-Aware Template-Based Retrosynthesis

• tmQM-RDF Data Set: A Knowledge Graph Representing Transition Metal Complexes

• Guided Adaptive Diffusion: An Evolutionary Framework for Multimodal Atomistic Structure Prediction

• Foldify: Web Application for Protein Structure Prediction

• Evaluating Molecular Representations for Predicting Cyclodextrin-PFAS Binding Energy with Machine Learning: Domain Transfer and Data Limitations

• ASO-RASAR: A Read-Across Framework for Predicting Antisense Oligonucleotide Gapmer Activity Across Target Genes

• Sampling out-of-distribution chemical spaces via Bayesian flow

• Hold on tight: the kinetic profiling of opioid receptor ligands using the CORAL-MD

• Universal graph-based identifiers of chemical structures for linking large material databases

• Towards selecting the virtual series of molecules using the central fragment via R-FBDD at the early stages of drug discovery

• Quantitative structure–activity relationship characterization and modeling of length-varying bioactive peptides

• Prot-ΔΔG: Prediction of protein–protein binding affinity changes upon mutations with pre-training strategies

• The deformation energy gap in computational drug design: why interaction energy alone cannot rank drug candidates and a thermodynamic correction protocol

• CycleVI: isolating cell cycle variation with an interpretable deep generative model

• The Intricate Mechanism of Nitric Oxide Synthase

• A Molecular “Thermometer” for Measuring Effective Non‐Local Exchange

• Insights to Orientation Dependence of Molecular Conduction Modeled by High‐Level Quantum Embedding

• Multimodal machine learning and deep graph neural networks for the prediction of molecular inhibitory activity and disease associations

• Goldilocks-Inspired Design of Mid-Size Macrocycles for Selective Targeting of Human Melanocortin Receptors

• Recent Advances in Targeting RNA Splicing Factors with Small Molecules

• Photocage Prodrug Coupled with Injectable Hydrogel for Self-Amplified Photochemotherapy

• Zero-shot design of drug-binding proteins via neural iterative selection−expansion

• Revealing the Hydrophobic Interactions between Annular Lipids and Transmembrane Peptides via Photo-Tagging and Mass Spectrometry

“paula”@paularambles

emozilla @theemozilla

I felt a great disturbance in the Force, as if millions of voices suddenly cried out in terror and were suddenly silenced. I fear something terrible has happened.

4:53 PM · Jun 26, 2026 · 1.03M Views

44 Replies · 1.03K Reposts · 30.1K Likes

David Sun@arcticinstincts

thank you for the math advice

Mathematica @mathemetica

"I don't have any magical ability. I look at a problem, play with it, work out a strategy." — Terence Tao

11:12 AM · Jun 26, 2026 · 176K Views

37 Replies · 129 Reposts · 3.51K Likes

Ash Jogalekar@curiouswavefn

Victor Weisskopf on why scientific style is important and why Pauli's lectures exemplified it.

4:14 AM · Jun 26, 2026 · 4.64K Views

3 Replies · 17 Reposts · 94 Likes

Ash Jogalekar@curiouswavefn

Very nice semi-quantitative estimation and justification of the Born-Oppenheimer approximation from Bethe and Jackiw, Intermediate Quantum Mechanics (Bethe said he learnt these kinds of orders-of-magnitude estimations from Fermi, the master of the art).

5:34 PM · Jun 22, 2026 · 2.58K Views

2 Reposts · 45 Likes

No Context Brits@NoContextBrits

2:48 PM · Jun 28, 2026 · 663K Views

169 Replies · 3.27K Reposts · 55.4K Likes

Best,
Manas

Guess who’s parking spot this is ?