Consejo Superior de Investigaciones Científicas

2 related articles

Subscribe to updates

bioRxiv Oct 14, 2026
INME, a circuit using only four cardinal-direction cells, reproduces eleven motion phenomena while million-parameter optical-flow networks miss most
Motion direction estimation has lacked a unified model spanning species and brain regions, since existing models tend to fit one animal class, one brain area or one phenomenon. INME uses only cells selective to the four cardinal directions, embedding dendritic nonlinearity and a back-propagating action potential in one circuit with a post-summation readout stage. Across eleven synthetic-stimulus experiments it qualitatively reproduces phenomena from contrast saturation and reverse-Phi to the breaking of time-reversal symmetry, while five deep optical-flow networks with millions of parameters reproduce only a few of them.
Motion direction estimation has lacked a unified model spanning species and brain regions, since existing models tend to fit one animal class, one brain area or one phenomenon. INME uses only cells selective to the four cardinal directions, embedding dendritic nonlinearity and a back-propagating action potential in one circuit with a post-summation readout stage. Across eleven synthetic-stimulus experiments it qualitatively reproduces phenomena from contrast saturation and reverse-Phi to the breaking of time-reversal symmetry, while five deep optical-flow networks with millions of parameters reproduce only a few of them.
Consejo Superior de Investigaciones Científicas Universidad Complutense de Madrid Universidad Politécnica de Madrid
María Berraquero（First author）Marcelo Bertalmı́o（Corresponding author）
INME Motion direction estimation
Journal of Chemical Information and Modeling Sep 14, 2026
PockLigGPT: Pocket-Sequence-Conditioned Molecular Generation with GPTs and RL
This work introduces PockLigGPT, a GPT-based framework for ligand generation conditioned on the amino acid sequence of a protein pocket, trained in four stages (large-scale ZINC20 chemical pretraining, ChEMBL bioactivity-oriented adaptation, pocket-sequence-conditioned fine-tuning, and pocket-specific docking-guided reinforcement learning with AutoDock Vina-based rewards), achieving competitive docking-oriented performance under a standardized evaluation protocol while maintaining chemical plausibility and Lipinski-based drug-likeness, with docking studies on Alzheimer's disease-associated targets and token-level analyses supporting its utility for de novo drug design.
This work introduces PockLigGPT, a GPT-based framework for ligand generation conditioned on the amino acid sequence of a protein pocket, trained in four stages (large-scale ZINC20 chemical pretraining, ChEMBL bioactivity-oriented adaptation, pocket-sequence-conditioned fine-tuning, and pocket-specific docking-guided reinforcement learning with AutoDock Vina-based rewards), achieving competitive docking-oriented performance under a standardized evaluation protocol while maintaining chemical plausibility and Lipinski-based drug-likeness, with docking studies on Alzheimer's disease-associated targets and token-level analyses supporting its utility for de novo drug design.
Universidad Autónoma de Madrid Consejo Superior de Investigaciones Científicas
Pablo Varas Pardo（First author）
PockLigGPT De novo drug design Reinforcement Learning

You’re all caught up

INME, a circuit using only four cardinal-direction cells, reproduces eleven motion phenomena while million-parameter optical-flow networks miss most

PockLigGPT: Pocket-Sequence-Conditioned Molecular Generation with GPTs and RL