Search

Motivation Developing new crop varieties with superior performance is highly important to ensure robust and sustainable global food security. The speed of variety development is limited by long field cycles and advanced generation selections in plant breeding programs. While methods to predict yield from genotype or phenotype data have been proposed, improved performance and integrated models are needed. Results We propose a machine learning model that leverages both genotype and phenotype measurements by fusing genetic variants with multiple data sources collected by unmanned aerial systems. We use a deep multiple instance learning framework with an attention mechanism that sheds light on the importance given to each input during prediction, enhancing interpretability. Our model reaches 0.754 ± 0.024 Pearson correlation coefficient when predicting yield in similar environmental conditions; a 34.8% improvement over the genotype-only linear baseline (0.559 ± 0.050). We further predict yield on new lines in an unseen environment using only genotypes, obtaining a prediction accuracy of 0.386 ± 0.010, a 13.5% improvement over the linear baseline. Our multi-modal deep learning architecture efficiently accounts for plant health and environment, distilling the genetic contribution and providing excellent predictions. Yield prediction algorithms leveraging phenotypic observations during training therefore promise to improve breeding programs, ultimately speeding up delivery of improved varieties., Bioinformatics, 39 (6), ISSN:1367-4803, ISSN:1460-2059

The proper regulation of muscle stem cell (MuSC) fate by cues from the niche is essential for regeneration of skeletal muscle. How pro-regenerative niche factors control the dynamics of MuSC fate decisions remains unknown due to limitations of population-level endpoint assays. To address this knowledge gap, we developed a novel binary dynamic fluorescence time lapse imaging analysis (BDFA) approach that leverages machine learning classification strategies to track single cell fate decisions with high temporal resolution. Using two fluorescent reporters that read out maintenance of stemness and myogenic commitment, we constructed detailed lineage trees for individual MuSCs and their progeny, classifying each division event as symmetric self-renewing, asymmetric, or symmetric committed. Our analysis reveals that treatment with the lipid metabolite, prostaglandin E2 (PGE2), accelerates the rate of MuSC proliferation over time, while biasing division events toward symmetric self-renewal. In contrast, the IL6 family member, Oncostatin M (OSM) decreases the proliferation rate after the first generation, while blocking myogenic commitment. These insights into the dynamics of MuSC regulation by niche cues were uniquely enabled by our BDFA approach. We anticipate that similar binary live cell readouts derived from BDFA will markedly expand our understanding of how niche factors control tissue regeneration in real time.

Motivation Protein design has become increasingly important for medical and biotechnological applications. Because of the complex mechanisms underlying protein formation, the creation of a novel protein requires tedious and time-consuming computational or experimental protocols. At the same time, machine learning has enabled the solving of complex problems by leveraging large amounts of available data, more recently with great improvements on the domain of generative modeling. Yet, generative models have mainly been applied to specific sub-problems of protein design. Results Here, we approach the problem of general-purpose protein design conditioned on functional labels of the hierarchical Gene Ontology. Since a canonical way to evaluate generative models in this domain is missing, we devise an evaluation scheme of several biologically and statistically inspired metrics. We then develop the conditional generative adversarial network ProteoGAN and show that it outperforms several classic and more recent deep-learning baselines for protein sequence generation. We further give insights into the model by analyzing hyperparameters and ablation baselines. Lastly, we hypothesize that a functionally conditional model could generate proteins with novel functions by combining labels and provide first steps into this direction of research., Bioinformatics, 38 (13), ISSN:1367-4803, ISSN:1460-2059

Bacterial processes necessary for adaption to stressful host environments are potential targets for new antimicrobials. Here, we report large-scale transcriptomic analyses of 32 human bacterial pathogens grown under 11 stress conditions mimicking human host environments. The potential relevance of the in vitro stress conditions and responses is supported by comparisons with available in vivo transcriptomes of clinically important pathogens. Calculation of a probability score enables comparative cross-microbial analyses of the stress responses, revealing common and unique regulatory responses to different stresses, as well as overlapping processes participating in different stress responses. We identify conserved and species-specific ‘universal stress responders’, that is, genes showing altered expression in multiple stress conditions. Non-coding RNAs are involved in a substantial proportion of the responses. The data are collected in a freely available, interactive online resource (PATHOgenex)., Nature Communications, 12 (1), ISSN:2041-1723

Background Patients on organ transplant waiting lists are evaluated for preexisting alloimmunity to minimize episodes of acute and chronic rejection by regularly monitoring for changes in alloimmune status. There are few studies on how alloimmunity changes over time in patients on kidney allograft waiting lists, and an apparent lack of research-based evidence supporting currently used monitoring intervals. Methods To investigate the dynamics of alloimmune responses directed at HLA antigens, we retrospectively evaluated data on anti-HLA antibodies measured by the single-antigen bead assay from 627 waitlisted patients who subsequently received a kidney transplant at University Hospital Zurich, Switzerland, between 2008 and 2017. Our analysis focused on a filtered dataset comprising 467 patients who had at least two assay measurements. Results Within the filtered dataset, we analyzed potential changes in mean fluorescence intensity values (reflecting bound anti-HLA antibodies) between consecutive measurements for individual patients in relation to the time interval between measurements. Using multiple approaches, we found no correlation between these two factors. However, when we stratified the dataset on the basis of documented previous immunizing events (transplant, pregnancy, or transfusion), we found significant differences in the magnitude of change in alloimmune status, especially among patients with a previous transplant versus patients without such a history. Further efforts to cluster patients according to statistical properties related to alloimmune status kinetics were unsuccessful, indicating considerable complexity in individual variability. Conclusions Alloimmune kinetics in patients on a kidney transplant waiting list do not appear to be related to the interval between measurements, but are instead associated with alloimmunization history. This suggests that an individualized strategy for alloimmune status monitoring may be preferable to currently used intervals.

Despite being genetically diverse, bacterial pathogens can adapt to similar stressful environments in human host, but how this diversity allows them to achive this is yet not fully understood. Knowledge gained through comparative genomics is insufficient as it lacks the level of gene expression reflecting gene usage. To fill this gap, we investigated the transcriptome of 32 diverse bacterial pathogens under 11 host related stress conditions. We revealed that diverse bacterial pathogens have common responses to similar stresses to a certain extent but mostly employ their unique repertoire with intersections between different stress responses. We also identified universal stress responders which shed light on the nature of antimicrobial targets. In addition, we found that known and unknown putative novel ncRNAs comprised a significant proportion of the responses. All the data is collected in PATHOgenex atlas, providing ample opportunities to discover novel players critical for virulence and maintenance of infection.

2019 IEEE International Conference on Data Mining (ICDM), ISBN:978-1-7281-4604-1, ISBN:978-1-7281-4605-8

Motivation Methods based on summary statistics obtained from genome-wide association studies have gained considerable interest in genetics due to the computational cost and privacy advantages they present. Imputing missing summary statistics has therefore become a key procedure in many bioinformatics pipelines, but available solutions may rely on additional knowledge about the populations used in the original study and, as a result, may not always ensure feasibility or high accuracy of the imputation procedure. Results We present ARDISS, a method to impute missing summary statistics in mixed-ethnicity cohorts through Gaussian Process Regression and automatic relevance determination. ARDISS is trained on an external reference panel and does not require information about allele frequencies of genotypes from the original study. Our method approximates the original GWAS population by a combination of samples from a reference panel relying exclusively on the summary statistics and without any external information. ARDISS successfully reconstructs the original composition of mixed-ethnicity cohorts and outperforms alternative solutions in terms of speed and imputation accuracy both for heterogeneous and homogeneous datasets., Bioinformatics, 34 (17), ISSN:1367-4803, ISSN:1460-2059

The ability to modulate intermolecular interactions in such a way as to impact nano-, micro- and even macroscale properties is an attractive aspect of self-assembling systems. We present an investigation of sequence-dependent rheological, photophysical and electrical properties of semiconducting peptide hydrogelators. Five different π-conjugated peptides containing a quaterthiophene core were studied, wherein the relative size and hydrophobicity of the amino acid residues adjacent to the π-electron core were varied in order to assess the impact of molecular variation on nanoscale and bulk material properties. Steady-state spectroscopic measurements of the peptides once assembled into 1D-nanostructures show distinct spectral characters as the relative size of the amino acid side chain adjacent to the π-electron core increases. Those peptides that formed hydrogels differed in network topography and rheological properties, with storage modulus (G′) values ranging from ∼3 to 20 kPa. The electrical properties of the peptide nanostructures were characterized by measuring the sheet resistance of dried peptide films on glass substrates. This study provides insights on the effects of amino acid sequence on the nanoscale to the macroscale electrical transport and mechanical properties of nanostructure-forming π-conjugated peptides.