Combating data incompetence in pollen images detection and classification for pollinosis prevention.

Automatic pollen images recognition is crucial for pollinosis symptoms prevention and treatment. The problem of pollen recognition can be efficiently solved using deep learning, however neural networks require tens of thousands of images to generalize. At the same time, the existing open pollen images datasets are very small. In this paper, we present a novel open pollen dataset annotated for both detection and classification tasks. Based on our dataset we study learning from a small data using different state-of-the-art approaches. For the detection task we propose to use our new Bayesian RetinaNet network, which models aleatoric uncertainty. We compare it with the baseline RetinaNet and demonstrate that our model allows for higher detection precision. For the classification task we compare the impact of pre-training on the synthetic images from generative adversarial networks (GANs) and metric-based few-shot learning. Namely, we pre-trained our small convolutional neural network and Siamese neural network classifiers on synthetic pollen images generated by two GANs: StyleGAN and Self-attention GAN. The best classifier is the convolutional neural network pre-trained on StyleGAN images. Our best models achieved 96.3% of mean average precision for the detection task and 97.7% of F1 measure for the classification task on 13 pollen plant species. We have implemented the best models in our pollen recognition web service, which is available for palynologists on request.

COVIDomic: A multi-modal cloud-based platform for identification of risk factors associated with COVID-19 severity.

Coronavirus disease 2019 (COVID-19) is an acute infection of the respiratory tract that emerged in December 2019 in Wuhan, China. It was quickly established that both the symptoms and the disease severity may vary from one case to another and several strains of SARS-CoV-2 have been identified. To gain a better understanding of the wide variety of SARS-CoV-2 strains and their associated symptoms, thousands of SARS-CoV-2 genomes have been sequenced in dozens of countries. In this article, we introduce COVIDomic, a multi-omics online platform designed to facilitate the analysis and interpretation of the large amount of health data collected from patients with COVID-19. The COVIDomic platform provides a comprehensive set of bioinformatic tools for the multi-modal metatranscriptomic data analysis of COVID-19 patients to determine the origin of the coronavirus strain and the expected severity of the disease. An integrative analytical workflow, which includes microbial pathogens community analysis, COVID-19 genetic epidemiology and patient stratification, allows to analyze the presence of the most common microbial organisms, their antibiotic resistance, the severity of the infection and the set of the most probable geographical locations from which the studied strain could have originated. The online platform integrates a user friendly interface which allows easy visualization of the results. We envision this tool will not only have immediate implications for management of the ongoing COVID-19 pandemic, but will also improve our readiness to respond to other infectious outbreaks.

Human Gut Microbiome Aging Clock Based on Taxonomic Profiling and Deep Learning.

The human gut microbiome is a complex ecosystem that both affects and is affected by its host status. Previous metagenomic analyses of gut microflora revealed associations between specific microbes and host age. Nonetheless there was no reliable way to tell a host's age based on the gut community composition. Here we developed a method of predicting hosts' age based on microflora taxonomic profiles using a cross-study dataset and deep learning. Our best model has an architecture of a deep neural network that achieves the mean absolute error of 5.91 years when tested on external data. We further advance a procedure for inferring the role of particular microbes during human aging and defining them as potential aging biomarkers. The described intestinal clock represents a unique quantitative model of gut microflora aging and provides a starting point for building host aging and gut community succession into a single narrative.

Identification of Novel Antibacterials Using Machine Learning Techniques.

Many pharmaceutical companies are avoiding the development of novel antibacterials due to a range of rational reasons and the high risk of failure. However, there is an urgent need for novel antibiotics especially against resistant bacterial strains. Available in silico models suffer from many drawbacks and, therefore, are not applicable for scoring novel molecules with high structural diversity by their antibacterial potency. Considering this, the overall aim of this study was to develop an efficient in silico model able to find compounds that have plenty of chances to exhibit antibacterial activity. Based on a proprietary screening campaign, we have accumulated a representative dataset of more than 140,000 molecules with antibacterial activity against Escherichia coli assessed in the same assay and under the same conditions. This intriguing set has no analogue in the scientific literature. We applied six in silico techniques to mine these data. For external validation, we used 5,000 compounds with low similarity towards training samples. The antibacterial activity of the selected molecules against E. coli was assessed using a comprehensive biological study. Kohonen-based nonlinear mapping was used for the first time and provided the best predictive power (av. 75.5%). Several compounds showed an outstanding antibacterial potency and were identified as translation machinery inhibitors in vitro and in vivo. For the best compounds, MIC and CC50 values were determined to allow us to estimate a selectivity index (SI). Many active compounds have a robust IP position.

Blood Biochemistry Analysis to Detect Smoking Status and Quantify Accelerated Aging in Smokers.

There is an association between smoking and cancer, cardiovascular disease and all-cause mortality. However, currently, there are no affordable and informative tests for assessing the effects of smoking on the rate of biological aging. In this study we demonstrate for the first time that smoking status can be predicted using blood biochemistry and cell count results andthe recent advances in artificial intelligence (AI). By employing age-prediction models developed using supervised deep learning techniques, we found that smokers exhibited higher aging rates than nonsmokers, regardless of their cholesterol ratios and fasting glucose levels. We further used those models to quantify the acceleration of biological aging due to tobacco use. Female smokers were predicted to be twice as old as their chronological age compared to nonsmokers, whereas male smokers were predicted to be one and a half times as old as their chronological age compared to nonsmokers. Our findings suggest that deep learning analysis of routine blood tests could complement or even replace the current error-prone method of self-reporting of smoking status and could be expanded to assess the effect of other lifestyle and environmental factors on aging.

Machine Learning on Human Muscle Transcriptomic Data for Biomarker Discovery and Tissue-Specific Drug Target Identification.

For the past several decades, research in understanding the molecular basis of human muscle aging has progressed significantly. However, the development of accessible tissue-specific biomarkers of human muscle aging that may be measured to evaluate the effectiveness of therapeutic interventions is still a major challenge. Here we present a method for tracking age-related changes of human skeletal muscle. We analyzed publicly available gene expression profiles of young and old tissue from healthy donors. Differential gene expression and pathway analysis were performed to compare signatures of young and old muscle tissue and to preprocess the resulting data for a set of machine learning algorithms. Our study confirms the established mechanisms of human skeletal muscle aging, including dysregulation of cytosolic Ca2+ homeostasis, PPAR signaling and neurotransmitter recycling along with IGFR and PI3K-Akt-mTOR signaling. Applying several supervised machine learning techniques, including neural networks, we built a panel of tissue-specific biomarkers of aging. Our predictive model achieved 0.91 Pearson correlation with respect to the actual age values of the muscle tissue samples, and a mean absolute error of 6.19 years on the test set. The performance of models was also evaluated on gene expression samples of the skeletal muscles from the Gene expression Genotype-Tissue Expression (GTEx) project. The best model achieved the accuracy of 0.80 with respect to the actual age bin prediction on the external validation set. Furthermore, we demonstrated that aging biomarkers can be used to identify new molecular targets for tissue-specific anti-aging therapies.

Reinforced Adversarial Neural Computer for de Novo Molecular Design.

In silico modeling is a crucial milestone in modern drug design and development. Although computer-aided approaches in this field are well-studied, the application of deep learning methods in this research area is at the beginning. In this work, we present an original deep neural network (DNN) architecture named RANC (Reinforced Adversarial Neural Computer) for the de novo design of novel small-molecule organic structures based on the generative adversarial network (GAN) paradigm and reinforcement learning (RL). As a generator RANC uses a differentiable neural computer (DNC), a category of neural networks, with increased generation capabilities due to the addition of an explicit memory bank, which can mitigate common problems found in adversarial settings. The comparative results have shown that RANC trained on the SMILES string representation of the molecules outperforms its first DNN-based counterpart ORGANIC by several metrics relevant to drug discovery: the number of unique structures, passing medicinal chemistry filters (MCFs), Muegge criteria, and high QED scores. RANC is able to generate structures that match the distributions of the key chemical features/descriptors (e.g., MW, logP, TPSA) and lengths of the SMILES strings in the training data set. Therefore, RANC can be reasonably regarded as a promising starting point to develop novel molecules with activity against different biological targets or pathways. In addition, this approach allows scientists to save time and covers a broad chemical space populated with novel and diverse compounds.

Use of deep neural network ensembles to identify embryonic-fetal transition markers: repression of COX7A1 in embryonic and cancer cells.

Here we present the application of deep neural network (DNN) ensembles trained on transcriptomic data to identify the novel markers associated with the mammalian embryonic-fetal transition (EFT). Molecular markers of this process could provide important insights into regulatory mechanisms of normal development, epimorphic tissue regeneration and cancer. Subsequent analysis of the most significant genes behind the DNNs classifier on an independent dataset of adult-derived and human embryonic stem cell (hESC)-derived progenitor cell lines led to the identification of COX7A1 gene as a potential EFT marker. COX7A1, encoding a cytochrome C oxidase subunit, was up-regulated in post-EFT murine and human cells including adult stem cells, but was not expressed in pre-EFT pluripotent embryonic stem cells or their in vitro-derived progeny. COX7A1 expression level was observed to be undetectable or low in multiple sarcoma and carcinoma cell lines as compared to normal controls. The knockout of the gene in mice led to a marked glycolytic shift reminiscent of the Warburg effect that occurs in cancer cells. The DNN approach facilitated the elucidation of a potentially new biomarker of cancer and pre-EFT cells, the embryo-onco phenotype, which may potentially be used as a target for controlling the embryonic-fetal transition.

Adversarial Threshold Neural Computer for Molecular de Novo Design.

In this article, we propose the deep neural network Adversarial Threshold Neural Computer (ATNC). The ATNC model is intended for the de novo design of novel small-molecule organic structures. The model is based on generative adversarial network architecture and reinforcement learning. ATNC uses a Differentiable Neural Computer as a generator and has a new specific block, called adversarial threshold (AT). AT acts as a filter between the agent (generator) and the environment (discriminator + objective reward functions). Furthermore, to generate more diverse molecules we introduce a new objective reward function named Internal Diversity Clustering (IDC). In this work, ATNC is tested and compared with the ORGANIC model. Both models were trained on the SMILES string representation of the molecules, using four objective functions (internal similarity, Muegge druglikeness filter, presence or absence of sp3-rich fragments, and IDC). The SMILES representations of 15K druglike molecules from the ChemDiv collection were used as a training data set. For the different functions, ATNC outperforms ORGANIC. Combined with the IDC, ATNC generates 72% of valid and 77% of unique SMILES strings, while ORGANIC generates only 7% of valid and 86% of unique SMILES strings. For each set of molecules generated by ATNC and ORGANIC, we analyzed distributions of four molecular descriptors (number of atoms, molecular weight, logP, and tpsa) and calculated five chemical statistical features (internal diversity, number of unique heterocycles, number of clusters, number of singletons, and number of compounds that have not been passed through medicinal chemistry filters). Analysis of key molecular descriptors and chemical statistical features demonstrated that the molecules generated by ATNC elicited better druglikeness properties. We also performed in vitro validation of the molecules generated by ATNC; results indicated that ATNC is an effective method for producing hit compounds.

Population Specific Biomarkers of Human Aging: A Big Data Study Using South Korean, Canadian, and Eastern European Patient Populations.

Accurate and physiologically meaningful biomarkers for human aging are key to assessing antiaging therapies. Given ethnic differences in health, diet, lifestyle, behavior, environmental exposures, and even average rate of biological aging, it stands to reason that aging clocks trained on datasets obtained from specific ethnic populations are more likely to account for these potential confounding factors, resulting in an enhanced capacity to predict chronological age and quantify biological age. Here, we present a deep learning-based hematological aging clock modeled using the large combined dataset of Canadian, South Korean, and Eastern European population blood samples that show increased predictive accuracy in individual populations compared to population specific hematologic aging clocks. The performance of models was also evaluated on publicly available samples of the American population from the National Health and Nutrition Examination Survey (NHANES). In addition, we explored the association between age predicted by both population specific and combined hematological clocks and all-cause mortality. Overall, this study suggests (a) the population specificity of aging patterns and (b) hematologic clocks predicts all-cause mortality. The proposed models were added to the freely-available Aging.AI system expanding the range of tools for analysis of human aging.

In search for geroprotectors: in silico screening and in vitro validation of signalome-level mimetics of young healthy state.

Populations in developed nations throughout the world are rapidly aging, and the search for geroprotectors, or anti-aging interventions, has never been more important. Yet while hundreds of geroprotectors have extended lifespan in animal models, none have yet been approved for widespread use in humans. GeroScope is a computational tool that can aid prediction of novel geroprotectors from existing human gene expression data. GeroScope maps expression differences between samples from young and old subjects to aging-related signaling pathways, then profiles pathway activation strength (PAS) for each condition. Known substances are then screened and ranked for those most likely to target differential pathways and mimic the young signalome. Here we used GeroScope and shortlisted ten substances, all of which have lifespan-extending effects in animal models, and tested 6 of them for geroprotective effects in senescent human fibroblast cultures. PD-98059, a highly selective MEK1 inhibitor, showed both life-prolonging and rejuvenating effects. Natural compounds like N-acetyl-L-cysteine, Myricetin and Epigallocatechin gallate also improved several senescence-associated properties and were further investigated with pathway analysis. This work not only highlights several potential geroprotectors for further study, but also serves as a proof-of-concept for GeroScope, Oncofinder and other PAS-based methods in streamlining drug prediction, repurposing and personalized medicine.

Deep biomarkers of human aging: Application of deep neural networks to biomarker development.

One of the major impediments in human aging research is the absence of a comprehensive and actionable set of biomarkers that may be targeted and measured to track the effectiveness of therapeutic interventions. In this study, we designed a modular ensemble of 21 deep neural networks (DNNs) of varying depth, structure and optimization to predict human chronological age using a basic blood test. To train the DNNs, we used over 60,000 samples from common blood biochemistry and cell count tests from routine health exams performed by a single laboratory and linked to chronological age and sex. The best performing DNN in the ensemble demonstrated 81.5 % epsilon-accuracy r = 0.90 with R(2) = 0.80 and MAE = 6.07 years in predicting chronological age within a 10 year frame, while the entire ensemble achieved 83.5% epsilon-accuracy r = 0.91 with R(2) = 0.82 and MAE = 5.55 years. The ensemble also identified the 5 most important markers for predicting human chronological age: albumin, glucose, alkaline phosphatase, urea and erythrocytes. To allow for public testing and evaluate real-life performance of the predictor, we developed an online system available at http://www.aging.ai. The ensemble approach may facilitate integration of multi-modal data linked to chronological age and sex that may lead to simple, minimally invasive, and affordable methods of tracking integrated biomarkers of aging in humans and performing cross-species feature importance analysis.

Applications of Deep Learning in Biomedicine.

Increases in throughput and installed base of biomedical research equipment led to a massive accumulation of -omics data known to be highly variable, high-dimensional, and sourced from multiple often incompatible data platforms. While this data may be useful for biomarker identification and drug discovery, the bulk of it remains underutilized. Deep neural networks (DNNs) are efficient algorithms based on the use of compositional layers of neurons, with advantages well matched to the challenges -omics data presents. While achieving state-of-the-art results and even surpassing human accuracy in many challenging tasks, the adoption of deep learning in biomedicine has been comparatively slow. Here, we discuss key features of deep learning that may give this approach an edge over other machine learning methods. We then consider limitations and review a number of applications of deep learning in biomedical studies demonstrating proof of concept and practical utility.