Biology subjects

Schuette, C.

Publications and source records attributed to Schuette, C..

4 recordsLinked to original sources

bioRxiv2026

Evolutionary exploration of drug-like chemical space utilizing generative AI and virtual screening

The identification of suitable lead molecules in the vast chemical space is a critical and challenging task in drug discovery campaigns. Recently, it has been demonstrated that large-scale virtual screening provides a powerful approach to accelerate the identification of novel drug candidates by screening ever increasing virtual ligand libraries, which have reached magnitudes of > 1020 compounds. However, this desirable increase in potentially bioactive molecules poses a new challenge as enumerating and virtually screening such huge compound libraries is computationally prohibitive. Consequently, advanced approaches to navigate ultra-large chemical spaces and to identify suitable candidate molecules therein are urgently needed. Here, we present an evolutionary algorithm framework using molecular generative AI, reaction-based substructure searching, and iterative model fine-tuning for a targeted and efficient exploration of chemical fragment spaces. Combining this approach with large-scale virtual screening we are able to identify target-specific candidate molecules within the commercially available Enamine REAL Space ([~]1015). We demonstrate the applicability of the approach by successfully identifying and biochemically validating pH-specific ligands of the {micro}-opioid receptor. Our results demonstrate that integrating generative AI with evolutionary algorithms provides a promising route to explore ultra-large chemical spaces for the discovery of novel, synthetically accessible lead molecules.

bioinformatics↗

bioRxiv2022

Chimeric U-Net - Modifying the standard U-Net towards Explainability

Healthcare guided by semantic segmentation has the potential to improve our quality of life through early and accurate disease detection. Convolutional Neural Networks, especially the U-Net-based architectures, are currently the state-of-the-art learningbased segmentation methods and have given unprecedented performances. However, their decision-making processes are still an active field of research. In order to reliably utilize such methods in healthcare, explainability of how the segmentation was performed is mandated. To date, explainability is studied and applied heavily in classification tasks. In this work, we propose the Chimeric U-Net, a U-Net architecture with an invertible decoder unit, that inherently brings explainability into semantic segmentation tasks. We find that having the restriction of an invertible decoder does not hinder the performance of the segmentation task. However, the invertible decoder helps to disentangle the class information in the latent space embedding and to construct meaningful saliency maps. Furthermore, we found that with a simple k-Nearest-Neighbours classifier, we could predict the Intersection over Union scores of unseen data, demonstrating that the latent space, constructed by the Chimeric U-Net, encodes an interpretable representation of the segmentation quality. Explainability is an emerging field, and in this work, we propose an alternative approach, that is, rather than building tools for explaining a generic architecture, we propose constraints on the architecture which induce explainability. With this approach, we could peer into the architecture to reveal its class correlations and local contextual dependencies, taking an insightful step towards trustworthy and reliable A.I. Code to build and utilize the Chimeric U-Net is made available under: https://github.com/kenrickschulze/Chimeric-UNet---Half-invertible-UNet-in-Pytorch

bioinformatics↗

bioRxiv2021

Inferring Gene Regulatory Networks from Single Cell RNA-seq Temporal Snapshot Data Requires Higher Order Moments

Single cell RNA-sequencing (scRNA-seq) has become ubiquitous in biology. Recently, there has been a push for using scRNA-seq snapshot data to infer the underlying gene regulatory networks (GRNs) steering cellular function. To date, this aspiration remains unrealised due to technical- and computational challenges. In this work, we focus on the latter, which is under-represented in the literature. We took a systemic approach by subdividing the GRN inference into three fundamental components: the data pre-processing, the feature extraction, and the inference. We saw that the regulatory signature is captured in the statistical moments of scRNA-seq data, and requires computationally intensive minimisation solvers to extract. Furthermore, current data pre-processing might not conserve these statistical moments. Though our moment-based approach is a didactic tool for understanding the different compartments of GRN inference, this line of thinking-finding computationally feasible multi-dimensional statistics of data-is imperative for designing GRN inference methods.

systems biology↗

bioRxiv2021

Rcompadre and Rage - two R packages to facilitate the use of the COMPADRE and COMADRE databases and calculation of life history traits from matrix population models

O_LIMatrix population models (MPMs) are an important tool for biologists seeking to understand the causes and consequences of variation in vital rates (e.g., survival, reproduction) across life cycles. Empirical MPMs describe the age- or stage-structured demography of organisms and usually represent the life history of a population during a particular time frame at a specific geographic location. C_LIO_LIThe COMPADRE Plant Matrix Database and COMADRE Animal Matrix Database are the most extensive resources for MPM data, collectively containing >12,000 individual projection matrices for >1,100 species globally. Although these databases represent an unparalleled resource for researchers, land managers, and educators, the current computational tools available to answer questions with MPMs impose significant barriers to potential COM(P)ADRE database users by requiring advanced knowledge to handle diverse data structures and program custom analysis functions. C_LIO_LITo close this knowledge gap, we present two interrelated R packages designed to (i) facilitate the use of these databases by providing functions to acquire, quality control, and manage both the MPM data contained in COMPADRE and COMADRE, and a users own MPM data (Rcompadre), and (ii) present a range of functions to calculate life history traits from MPMs in support of ecological and evolutionary analyses (Rage). We provide examples to illustrate the use of both. C_LIO_LIRcompadre and Rage will facilitate demographic analyses using MPM data and contribute to the improved replicability of studies using these data. We hope that this new functionality will allow researchers, land managers, and educators to unlock the potential behind the thousands of MPMs and ancillary metadata stored in the COMPADRE and COMADRE matrix databases, and in their own MPM data. C_LI

ecology↗