Jérôme Waldispühl

The paper develops flowMagic, a machine learning tool for automated flow cytometry gating trained on expert data and citizen science gaming annotations, achieving high accuracy in cell population identification.

The paper tests if SMILES can be fragmented into ordered blocks for retrosynthetic analysis, finding that it improves physico-chemical property reproduction but degrades LLM performance.

Ribo-LENS detects RNA small-molecule binding sites using a geometric deep-learning framework, outperforming existing methods and enabling efficient virtual screening.

The paper introduces Dashing Turtle (DT), an algorithm for high-resolution detection of RNA structural modifications using direct RNA nanopore sequencing, showing improved accuracy over existing methods.

This study evaluates SMILES and SELFIES as molecular representations for generative chemistry, finding that neither ensures both viability and fidelity, and introduces ClearSMILES to improve both.

RNAmigos2 improves RNA virtual screening by combining semi-supervised graph learning and large-scale docking data, achieving high accuracy and speed.

The paper introduces an algorithm to find recurrent RNA structural modules spanning multiple secondary structure elements, identifying a module common to bacterial ribosomes.

OptiMol optimizes molecular binding affinities using a hybrid structure- and ligand-based approach, improving docking scores and compound generation efficiency.

RNAmigos predicts small molecule ligands for RNA binding sites using augmented base pairing networks, showing improved performance over baselines and highlighting the importance of non-canonical base pairs.

The paper models molecular interaction networks as computational optimization problems, showing that their mLmH topology arises as an adaptation to computational intractability.

The paper uses a nested cross-validation ensemble learning pipeline to analyze snoRNA-mRNA interactions in yeast, finding evidence of evolutionary pressure against crosstalk interactions.

The paper introduces BayesPairing 2, a sequence search algorithm for RNA 3D module identification, showing improved speed and accuracy over its predecessor.

This paper introduces 3DGV, a VR platform for exploring 3D genome structures, aiming to improve interpretation of complex genomic spatial data.

The paper introduces Science Game Lab, a platform to support the creation and enhancement of scientific games with a purpose.