Kronborganderson1096

space acquired from the generative model. Features of the enzymatic reaction are embedded into the fixed-dimensional vector, and it is possible to express structural changes of enzymatic reactions comprehensively. The technique also involves differential-evolution-based reaction selection to design feasible candidate pathways and pathway scoring using neural-network-based reaction-possibility prediction. The proposed technique was applied to the non-registered pathways relevant to the production of 2-butanone, and successfully explored feasible pathways that include such reactions.

Human microbes get closely involved in an extensive variety of complex human diseases and become new drug targets. In silico methods for identifying potential microbe-drug associations provide an effective complement to conventional experimental methods, which can not only benefit screening candidate compounds for drug development but also facilitate novel knowledge discovery for understanding microbe-drug interaction mechanisms. On the other hand, the recent increased availability of accumulated biomedical data for microbes and drugs provides a great opportunity for a machine learning approach to predict microbe-drug associations. We are thus highly motivated to integrate these data sources to improve prediction accuracy. In addition, it is extremely challenging to predict interactions for new drugs or new microbes, which have no existing microbe-drug associations.

In this work, we leverage various sources of biomedical information and construct multiple networks (graphs) for microbes and drugs. Then, wery data are available at Bioinformatics online.

In de novo sequence assembly, a standard pre-processing step is k-mer counting, which computes the number of occurrences of every length-k sub-sequence in the sequencing reads. Sequencing errors can produce many k-mers that do not appear in the genome, leading to the need for an excessive amount of memory during counting. NU7026 in vivo This issue is particularly serious when the genome to be assembled is large, the sequencing depth is high, or when the memory available is limited.

Here, we propose a fast near-exact k-mer counting method, CQF-deNoise, which has a module for dynamically removing noisy false k-mers. It automatically determines the suitable time and number of rounds of noise removal according to a user-specified wrong removal rate. We tested CQF-deNoise comprehensively using data generated from a diverse set of genomes with various data properties, and found that the memory consumed was almost constant regardless of the sequencing errors while the noise removal procedurehad minimal effects on counting accuracy. Compared with four state-of-the-art k-mer counting methods, CQF-deNoise consistently performed the best in terms of memory usage, consuming 49-76% less memory than thesecond best method. When counting the k-mers from a human dataset with around 60× coverage, the peakmemory usage of CQF-deNoise was only 10.9GB (gigabytes) for k = 28 and 21.5GB for k = 55. De novo assembly of 106× human sequencing data using CQF-deNoise for k-mer counting required only 2.7 h and 90GB peak memory.

The source codes of CQF-deNoise and SH-assembly are available at https//github.com/Christina-hshi/CQF-deNoise.git and https//github.com/Christina-hshi/SH-assembly.git, respectively, both under the BSD 3-Clause license.

The source codes of CQF-deNoise and SH-assembly are available at https//github.com/Christina-hshi/CQF-deNoise.git and https//github.com/Christina-hshi/SH-assembly.git, respectively, both under the BSD 3-Clause license.

Increasing number of gene expression profiles has enabled the use of complex models, such as deep unsupervised neural networks, to extract a latent space from these profiles. However, expression profiles, especially when collected in large numbers, inherently contain variations introduced by technical artifacts (e.g. batch effects) and uninteresting biological variables (e.g. age) in addition to the true signals of interest. These sources of variations, called confounders, produce embeddings that fail to transfer to different domains, i.e. an embedding learned from one dataset with a specific confounder distribution does not generalize to different distributions. To remedy this problem, we attempt to disentangle confounders from true signals to generate biologically informative embeddings.

In this article, we introduce the Adversarial Deconfounding AutoEncoder (AD-AE) approach to deconfounding gene expression latent spaces. The AD-AE model consists of two neural networks (i) an autoencoder to generate an embedding that can reconstruct original measurements, and (ii) an adversary trained to predict the confounder from that embedding. We jointly train the networks to generate embeddings that can encode as much information as possible without encoding any confounding signal. By applying AD-AE to two distinct gene expression datasets, we show that our model can (i) generate embeddings that do not encode confounder information, (ii) conserve the biological signals present in the original space and (iii) generalize successfully across different confounder domains. We demonstrate that AD-AE outperforms standard autoencoder and other deconfounding approaches.

Our code and data are available at https//gitlab.cs.washington.edu/abdincer/ad-ae.

Supplementary data are available at Bioinformatics online.

Supplementary data are available at Bioinformatics online.

Accurate prediction of cancer drug response (CDR) is challenging due to the uncertainty of drug efficacy and heterogeneity of cancer patients. Strong evidences have implicated the high dependence of CDR on tumor genomic and transcriptomic profiles of individual patients. Precise identification of CDR is crucial in both guiding anti-cancer drug design and understanding cancer biology.

In this study, we present DeepCDR which integrates multi-omics profiles of cancer cells and explores intrinsic chemical structures of drugs for predicting CDR. Specifically, DeepCDR is a hybrid graph convolutional network consisting of a uniform graph convolutional network and multiple subnetworks. Unlike prior studies modeling hand-crafted features of drugs, DeepCDR automatically learns the latent representation of topological structures among atoms and bonds of drugs. Extensive experiments showed that DeepCDR outperformed state-of-the-art methods in both classification and regression settings under various data settings. We also evaluated the contribution of different types of omics profiles for assessing drug response.