Search

We present Propulate, an evolutionary optimization algorithm and software package for global optimization and in particular hyperparameter search. For efficient use of HPC resources, Propulate omits the synchronization after each generation as done in conventional genetic algorithms. Instead, it steers the search with the complete population present at time of breeding new individuals. We provide an MPI-based implementation of our algorithm, which features variants of selection, mutation, crossover, and migration and is easy to extend with custom functionality. We compare Propulate to the established optimization tool Optuna. We find that Propulate is up to three orders of magnitude faster without sacrificing solution accuracy, demonstrating the efficiency and efficacy of our lazy synchronization approach. Code and documentation are available at https://github.com/Helmholtz-AI-Energy/propulate, Comment: 18 pages, 5 figures submitted to ISC High Performance 2023

In this article, we present JUWELS Booster, a recently commissioned high-performance computing system at the J\"ulich Supercomputing Center. With its system architecture, most importantly its large number of powerful Graphics Processing Units (GPUs) and its fast interconnect via InfiniBand, it is an ideal machine for large-scale Artificial Intelligence (AI) research and applications. We detail its system architecture, parallel, distributed model training, and benchmarks indicating its outstanding performance. We exemplify its potential for research application by presenting large-scale AI research highlights from various scientific fields that require such a facility., Comment: 12 pages, 5 figures. Accepted at ISC 2021, Workshop Deep Learning on Supercomputers. This is a duplicate submission as my previous submission is on hold for several weeks now and my attempts to contact the moderators failed

Structured RNA plays many functionally relevant roles in molecular life. Structural information, while required to understand the functional cycles in detail, is challenging to gather. Computational methods promise to complement experimental efforts by predicting three-dimensional RNA models. Here, we provide a concise view of the state of the art methodologies with a focus on the strengths and the weaknesses of the different approaches. Furthermore, we analyzed the recent developments regarding the use of coevolutionary information and how it can boost the prediction performances. We finally discuss some open perspectives and challenges for the near future in the RNA structural stability field., Comment: 14 pages, 4 figures

Knowing a biomolecule's structure is inherently linked to and a prerequisite for any detailed understanding of its function. Significant effort has gone into developing technologies for structural characterization. These technologies do not directly provide 3D structures; instead they typically yield noisy and erroneous distance information between specific entities such as atoms or residues, which have to be translated into consistent 3D models. Here we present an approach for this translation process based on maxent-stress optimization. Our new approach extends the original graph drawing method for the new application's specifics by introducing additional constraints and confidence values as well as algorithmic components. Extensive experiments demonstrate that our approach infers structural models (i. e., sensible 3D coordinates for the molecule's atoms) that correspond well to the distance information, can handle noisy and error-prone data, and is considerably faster than established tools. Our results promise to allow domain scientists nearly-interactive structural modeling based on distance constraints., Comment: Accepted by 25th Annual European Symposium on Algorithms (ESA 2017)

Proteins have evolved to perform diverse cellular functions, from serving as reaction catalysts to coordinating cellular propagation and development. Frequently, proteins do not exert their full potential as monomers but rather undergo concerted interactions as either homo-oligomers or with other proteins as hetero-oligomers. The experimental study of such protein complexes and interactions has been arduous. Theoretical structure prediction methods are an attractive alternative. Here, we investigate homo-oligomeric interfaces by tracing residue coevolution via the global statistical Direct Coupling Analysis (DCA). DCA can accurately infer spatial adjacencies between residues. These adjacencies can be included as constraints in structure-prediction techniques to predict high-resolution models. By taking advantage of the on-going exponential growth of sequence databases, we go significantly beyond anecdotal cases of a few protein families and apply DCA to a systematic large-scale study of nearly 2000 PFAM protein families with sufficient sequence information and structurally resolved homo-oligomeric interfaces. We find that large interfaces are commonly identified by DCA. We further demonstrate that DCA can differentiate between subfamilies of different binding modes within one large PFAM family. Sequence derived contact information for the subfamilies proves sufficient to assemble accurate structural models of the diverse protein-oligomers. Thus, we provide an approach to investigate oligomerization for arbitrary protein families leading to structural models complementary to often difficult experimental methods. Combined with ever more abundant sequential data, we anticipate that this study will be instrumental to allow the structural description of many hetero-protein complexes in the future., Comment: 18 pages, 6 figures, to appears in PNAS

Despite the biological importance of non-coding RNA, their structural characterization remains challenging. Making use of the rapidly growing sequence databases, we analyze nucleotide coevolution across homologous sequences via Direct-Coupling Analysis to detect nucleotide-nucleotide contacts. For a representative set of riboswitches, we show that the results of Direct-Coupling Analysis in combination with a generalized Nussinov algorithm systematically improve the results of RNA secondary structure prediction beyond traditional covariance approaches based on mutual information. Even more importantly, we show that the results of Direct-Coupling Analysis are enriched in tertiary structure contacts. By integrating these predictions into molecular modeling tools, systematically improved tertiary structure predictions can be obtained, as compared to using secondary structure information alone., Comment: 22 pages, 8 figures, supplemental information available on the publisher's webpage (http://nar.oxfordjournals.org/content/early/2015/09/29/nar.gkv932.abstract)

The quantitative characterization of mutational landscapes is a task of outstanding importance in evolutionary and medical biology: It is, e.g., of central importance for our understanding of the phenotypic effect of mutations related to disease and antibiotic drug resistance. Here we develop a novel inference scheme for mutational landscapes, which is based on the statistical analysis of large alignments of homologs of the protein of interest. Our method is able to capture epistatic couplings between residues, and therefore to assess the dependence of mutational effects on the sequence context where they appear. Compared to recent large-scale mutagenesis data of the beta-lactamase TEM-1, a protein providing resistance against beta-lactam antibiotics, our method leads to an increase of about 40% in explicative power as compared to approaches neglecting epistasis. We find that the informative sequence context extends to residues at native distances of about 20{\AA} from the mutated site, reaching thus far beyond residues in direct physical contact., Comment: 14 pages, 5 figures. Supplementary files on the publisher's website: http://mbe.oxfordjournals.org/content/early/2015/10/06/molbev.msv211.short?rss=1