Skip to main content
Search

Leipzig University

3 related articles

Subscribe to updates
  1. Molecular generators learn to unlearn: SemlaFlow cuts motif-bearing molecules from 31.1% to 2.2%

    Molecular generators often emit reactive, metal-binding, charged or assay-interference motifs, while molecules lacking a given motif are scattered across chemical space and hard to learn as a positive class. Negative extrapolation (NE) instead fine-tunes on motif-containing molecules and reverses the resulting weight update to suppress the motif directly. On the 3D flow-matching generator SemlaFlow, standard NE lowered the fraction of valid molecules carrying any target motif from 31.1% to 5.3% but cut RDKit-valid graph yield from 93.9% to 65.9%; adding a correction direction learned from motif-free molecules brought the motif fraction to 2.2%, restored valid graph yield to 88.3%, and raised fixed-budget 3D usable yield from 60.0% to 80.8%.

  2. bioRxiv

    Latent generative search unlocks de novo design of untapped biomolecular interactions at scale

    This work introduces latent generative search for binder design, a framework that uses reward-guided search at inference time to steer the Proteina-Complexa generative model, which codesigns sequence and structure together in a continuous latent space and thereby removes the inverse-folding step; in a screen of more than one million designs by multiplexed phage display, it produced more validated binders than every other method tested, its codesigned sequences surpassed post hoc redesign, it delivered high-affinity binders across therapeutic receptors, a viral attachment protein and intracellular signalling targets, and it generated the first de novo proteins that bind a free carbohydrate, including one that discriminates between blood-group antigens.

  3. FEBS Letters

    Prospecting the Protein Design Landscape: From High-Affinity Binders to Functionally Switchable Proteins

    This review surveys the landscape of deep learning-driven protein design pipelines, discusses tailored applications in peptide, small molecule, binder, vaccine, and antibody design, argues that current confidence metrics for filtering and evaluating designs remain optimized for static protein interfaces and can fail on underrepresented or conformationally complex targets, proposes ensemble-based methods as a promising avenue for improving design success rates, and highlights emerging strategies such as fold-switching scaffolds and molecular glues realized through engineered cyclic peptides that expand the functional scope of designed proteins.

You’re all caught up