Biology subjects

Geiger, F.

Publications and source records attributed to Geiger, F..

5 recordsLinked to original sources

bioRxiv2026

What comes after de novo? Automated lead optimization of proteins with CRADLE-1

Lead optimization remains the longest and most expensive step in pre-clinical drug discovery, typically consuming 12-36 months whilst costing $5M-$15M per candidate. We introduce O_SCPLOWCRADLEC_SCPLOWO_SCPCAP-1C_SCPCAP, an automated framework for protein engineering. While O_SCPLOWCRADLEC_SCPLOWO_SCPCAP-1C_SCPCAP supports the full process of drug discovery and industrial protein engineering pipelines, including hit identification and de novo binder design, this work focuses on its application to multi-property lead optimization across protein modalities (VHHs, scFvs, IgGs, peptides, enzymes, CRISPR systems, vaccines). We show it is 4-7x faster than rational design, as measured by the number of wet lab rounds required. We provide in-vitro validation across all of the above modalities, typically optimizing multiple properties simultaneously (single and polyspecific binding down to picomolar, activity, thermostability,...). Technically, O_SCPLOWCRADLEC_SCPLOWO_SCPCAP-1C_SCPCAP starts with pre-trained foundation protein language models (PLMs), which are fine-tuned in unsupervised fashion on evolutionary neighborhoods, in supervised fashion using lab-in-the-loop data, and then deployed in a multi-model workflow. Of additional interest, we find that (a) the end-to-end system may be run in automated fashion; (b) wet lab data may be consumed in black box fashion without knowledge of the underlying biochemical mechanisms; (c) structural data may largely be superseded by sequence-function pairs.

bioengineering↗

bioRxiv2022

An Inhibitory Function of TRPA1 Channels in TGF-β1-driven Fibroblast to Myofibroblast Differentiation

Transient receptor potential ankyrin 1 (TRPA1) is a non-selective Ca2+ permeable cation channel, which was originally cloned from human lung fibroblasts (HLFs). TRPA1-mediated Ca2+ entry is evoked by exposure to several chemicals, including allyl isothiocyanate (AITC), and a protective effect of TRPA1 activation in the development of cardiac fibrosis has been proposed. Yet, the function of TRPA1 in transforming growth factor {beta}1 (TGF-{beta}1)-driven fibroblast to myofibroblast differentiation and the development of pulmonary fibrosis remains elusive. TRPA1 expression and function was analyzed in cultured primary HLFs, and mRNA levels were significantly reduced after adding TGF-{beta}1. Expression of genes encoding fibrosis markers, e.g. alpha smooth muscle actin (ACTA2), plasminogen activator inhibitor 1 (SERPINE1), fibronectin (FN1) and type I collagen (COL1A1) was increased after siRNA-mediated down-regulation of TRPA1-mRNA in HLFs. Moreover, AITC-induced Ca2+ entry in HLFs was decreased after TGF-{beta}1 treatment and by application of TRPA1 siRNAs, while AITC treatment alone did not reduce cell viability or enhanced apoptosis. Cell barrier function increased after addition of TRPA1 siRNAs or TGF-{beta}1 treatment. Most interestingly, AITC-induced TRPA1 activation augmented ERK1/2 phosphorylation, which might inhibit TGF-{beta}-receptor signaling. Our results suggest an inhibitory function of TRPA1 channels in TGF-{beta}1-driven fibroblast to myofibroblast differentiation. Therefore, activation of TRPA1 channels might be protective during the development of pulmonary fibrosis in patients.

cell biology↗

bioRxiv2020

Rotavirus Replication Factories Are Complex Ribonucleoprotein Condensates

RNA viruses induce formation of subcellular organelles that provide microenvironments conducive to their replication. Here we show that replication factories of rotaviruses represent protein-RNA condensates that are formed via liquid-liquid phase separation. We demonstrate that rotavirus proteins NSP5 and NSP2 undergo phase separation in vitro and form RNA-rich condensates in vivo that can be reversibly dissolved by aliphatic diols. During infection, these RNA-protein condensates became less dynamic and impervious to aliphatic diols, indicating a transition from a liquid to solid state. Some aspects of assembly of rotavirus replication factories mirror the formation of cytoplasmic ribonucleoprotein granules, while the selective enrichment of viral transcripts appears to be a unique feature of these condensates. Such complex RNA-protein condensates that underlie replication of RNA viruses represent an attractive target for developing novel therapeutic approaches.

biophysics↗

bioRxiv2020

Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations

Current state-of-the-art object recognition models are largely based on convolutional neural network (CNN) architectures, which are loosely inspired by the primate visual system. However, these CNNs can be fooled by imperceptibly small, explicitly crafted perturbations, and struggle to recognize objects in corrupted images that are easily recognized by humans. Here, by making comparisons with primate neural data, we first observed that CNN models with a neural hidden layer that better matches primate primary visual cortex (V1) are also more robust to adversarial attacks. Inspired by this observation, we developed VOneNets, a new class of hybrid CNN vision models. Each VOneNet contains a fixed weight neural network front-end that simulates primate V1, called the VOneBlock, followed by a neural network back-end adapted from current CNN vision models. The VOneBlock is based on a classical neuroscientific model of V1: the linear-nonlinear-Poisson model, consisting of a biologically-constrained Gabor filter bank, simple and complex cell nonlinearities, and a V1 neuronal stochasticity generator. After training, VOneNets retain high ImageNet performance, but each is substantially more robust, outperforming the base CNNs and state-of-the-art methods by 18% and 3%, respectively, on a conglomerate benchmark of perturbations comprised of white box adversarial attacks and common image corruptions. Finally, we show that all components of the VOneBlock work in synergy to improve robustness. While current CNN architectures are arguably brain-inspired, the results presented here demonstrate that more precisely mimicking just one stage of the primate visual system leads to new gains in ImageNet-level computer vision applications.

neuroscience↗

bioRxiv2020

Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream

After training on large datasets, certain deep neural networks are surprisingly good models of the neural mechanisms of adult primate visual object recognition. Nevertheless, these models are poor models of the development of the visual system because they posit millions of sequential, precisely coordinated synaptic updates, each based on a labeled image. While ongoing research is pursuing the use of unsupervised proxies for labels, we here explore a complementary strategy of reducing the required number of supervised synaptic updates to produce an adult-like ventral visual stream (as judged by the match to V1, V2, V4, IT, and behavior). Such models might require less precise machinery and energy expenditure to coordinate these updates and would thus move us closer to viable neuroscientific hypotheses about how the visual system wires itself up. Relative to the current leading model of the adult ventral stream, we here demonstrate that the total number of supervised weight updates can be substantially reduced using three complementary strategies: First, we find that only 2% of supervised updates (epochs and images) are needed to achieve ~80% of the match to adult ventral stream. Second, by improving the random distribution of synaptic connectivity, we find that 54% of the brain match can already be achieved "at birth" (i.e. no training at all). Third, we find that, by training only ~5% of model synapses, we can still achieve nearly 80% of the match to the ventral stream. When these three strategies are applied in combination, we find that these new models achieve ~80% of a fully trained models match to the brain, while using two orders of magnitude fewer supervised synaptic updates. These results reflect first steps in modeling not just primate adult visual processing during inference, but also how the ventral visual stream might be "wired up" by evolution (a models "birth" state) and by developmental learning (a models updates based on visual experience).

neuroscience↗