Quantitative Biology

Originally a speculative pattern in ecological networks, the hybrid or compound nested-modular pattern has been confirmed, during the last decade, as a relevant structural arrangement that emerges in a variety of contexts --in ecological mutualistic system and beyond. This implies shifting the focus from the measurement of nestedness as a global property (macro level), to the detection of blocks (meso level) that internally exhibit a high degree of nestedness. Unfortunately, the availability and understanding of the methods to properly detect in-block nested partitions lie behind the empirical findings: while a precise quality function of in-block nestedness has been proposed, we lack an understanding of its possible inherent constraints. Specifically, while it is well known that Newman-Girvan's modularity, and related quality functions, notoriously suffer from a resolution limit that impairs their ability to detect small blocks, the potential existence of resolution limits for in-block nestedness is unexplored. Here, we provide empirical, numerical and analytical evidence that the in-block nestedness function lacks a resolution limit, and thus our capacity to detect correct partitions in networks via its maximization depends solely on the accuracy of the optimization algorithms.

Factors that mediate ethanol preference in Drosophila melanogaster are not well understood. A major confound has been the use of diverse methods to estimate ethanol consumption. We measured fly consumptive ethanol preference on base diets varying in nutrients, taste, and ethanol concentration. Both sexes showed ethanol preference that was abolished on high nutrient concentration diets. Additionally, manipulating total food intake without altering the nutritive value of the base diet or the ethanol concentration was sufficient to evoke or eliminate ethanol preference. Absolute ethanol intake and food volume consumed were stronger predictors of ethanol preference than caloric intake or the dietary caloric content. Our findings suggest that the effect of the base diet on ethanol preference is largely mediated by total consumption associated with the delivery medium, which ultimately determines the level of ethanol intake. We speculate that a physiologically relevant threshold for ethanol intake is essential for preferential ethanol consumption.

The novel coronavirus disease, named COVID-19, emerged in China in December 2019, and has rapidly spread around the world. It is clearly urgent to fight COVID-19 at global scale. The development of methods for identifying drug uses based on phenotypic data can improve the efficiency of drug development. However, there are still many difficulties in identifying drug applications based on cell picture data. This work reported one state-of-the-art machine learning method to identify drug uses based on the cell image features of 1024 drugs generated in the LINCS program. Because the multi-dimensional features of the image are affected by non-experimental factors, the characteristics of similar drugs vary greatly, and the current sample number is not enough to use deep learning and other methods are used for learning optimization. As a consequence, this study is based on the supervised ITML algorithm to convert the characteristics of drugs. The results show that the characteristics of ITML conversion are more conducive to the recognition of drug functions. The analysis of feature conversion shows that different features play important roles in identifying different drug functions. For the current COVID-19, Chloroquine and Hydroxychloroquine achieve antiviral effects by inhibiting endocytosis, etc., and were classified to the same community. And Clomiphene in the same community inibited the entry of Ebola Virus, indicated a similar MoAs that could be reflected by cell image.

Structure-based virtual screening is an important tool in early stage drug discovery that scores the interactions between a target protein and candidate ligands. As virtual libraries continue to grow (in excess of 10 8 molecules), so too do the resources necessary to conduct exhaustive virtual screening campaigns on these libraries. However, Bayesian optimization techniques can aid in their exploration: a surrogate structure-property relationship model trained on the predicted affinities of a subset of the library can be applied to the remaining library members, allowing the least promising compounds to be excluded from evaluation. In this study, we assess various surrogate model architectures, acquisition functions, and acquisition batch sizes as applied to several protein-ligand docking datasets and observe significant reductions in computational costs, even when using a greedy acquisition strategy; for example, 87.9% of the top-50000 ligands can be found after testing only 2.4% of a 100M member library. Such model-guided searches mitigate the increasing computational costs of screening increasingly large virtual libraries and can accelerate high-throughput virtual screening campaigns with applications beyond docking.

BACKGROUND:Automated volumetry software (AVS) has recently become widely available to neuroradiologists. MRI volumetry with AVS may support the diagnosis of dementias by identifying regional atrophy. Moreover, automatic classifiers using machine learning techniques have recently emerged as promising approaches to assist diagnosis. However, the performance of both AVS and automatic classifiers has been evaluated mostly in the artificial setting of research datasets.OBJECTIVE:Our aim was to evaluate the performance of two AVS and an automatic classifier in the clinical routine condition of a memory clinic.METHODS:We studied 239 patients with cognitive troubles from a single memory center cohort. Using clinical routine T1-weighted MRI, we evaluated the classification performance of: 1) univariate volumetry using two AVS (volBrain and Neuroreader TM ); 2) Support Vector Machine (SVM) automatic classifier, using either the AVS volumes (SVM-AVS), or whole gray matter (SVM-WGM); 3) reading by two neuroradiologists. The performance measure was the balanced diagnostic accuracy. The reference standard was consensus diagnosis by three neurologists using clinical, biological (cerebrospinal fluid) and imaging data and following international criteria.RESULTS:Univariate AVS volumetry provided only moderate accuracies (46% to 71% with hippocampal volume). The accuracy improved when using SVM-AVS classifier (52% to 85%), becoming close to that of SVM-WGM (52 to 90%). Visual classification by neuroradiologists ranged between SVM-AVS and SVM-WGM.CONCLUSION:In the routine practice of a memory clinic, the use of volumetric measures provided by AVS yields only moderate accuracy. Automatic classifiers can improve accuracy and could be a useful tool to assist diagnosis.

Motivation: Cryo-Electron Tomography (cryo-ET) is a 3D bioimaging tool that visualizes the structural and spatial organization of macromolecules at a near-native state in single cells, which has broad applications in life science. However, the systematic structural recognition and recovery of macromolecules captured by cryo-ET are difficult due to high structural complexity and imaging limits. Deep learning based subtomogram classification have played critical roles for such tasks. As supervised approaches, however, their performance relies on sufficient and laborious annotation on a large training dataset. Results: To alleviate this major labeling burden, we proposed a Hybrid Active Learning (HAL) framework for querying subtomograms for labelling from a large unlabeled subtomogram pool. Firstly, HAL adopts uncertainty sampling to select the subtomograms that have the most uncertain predictions. Moreover, to mitigate the sampling bias caused by such strategy, a discriminator is introduced to judge if a certain subtomogram is labeled or unlabeled and subsequently the model queries the subtomogram that have higher probabilities to be unlabeled. Additionally, HAL introduces a subset sampling strategy to improve the diversity of the query set, so that the information overlap is decreased between the queried batches and the algorithmic efficiency is improved. Our experiments on subtomogram classification tasks using both simulated and real data demonstrate that we can achieve comparable testing performance (on average only 3% accuracy drop) by using less than 30% of the labeled subtomograms, which shows a very promising result for subtomogram classification task with limited labeling resources.

Effective property prediction methods can help accelerate the search for COVID-19 antivirals either through accurate in-silico screens or by effectively guiding on-going at-scale experimental efforts. However, existing prediction tools have limited ability to accommodate scarce or fragmented training data currently available. In this paper, we introduce a novel approach to learn predictors that can generalize or extrapolate beyond the heterogeneous data. Our method builds on and extends recently proposed invariant risk minimization, adaptively forcing the predictor to avoid nuisance variation. We achieve this by continually exercising and manipulating latent representations of molecules to highlight undesirable variation to the predictor. To test the method we use a combination of three data sources: SARS-CoV-2 antiviral screening data, molecular fragments that bind to SARS-CoV-2 main protease and large screening data for SARS-CoV-1. Our predictor outperforms state-of-the-art transfer learning methods by significant margin. We also report the top 20 predictions of our model on Broad drug repurposing hub.

Properties of molecules are indicative of their functions and thus are useful in many applications. As a cost-effective alternative to experimental approaches, computational methods for predicting molecular properties are gaining increasing momentum and success. However, there lacks a comprehensive collection of tools and methods for this task currently. Here we develop the MoleculeKit, a suite of comprehensive machine learning tools spanning different computational models and molecular representations for molecular property prediction and drug discovery. Specifically, MoleculeKit represents molecules as both graphs and sequences. Built on these representations, MoleculeKit includes both deep learning and traditional machine learning methods for graph and sequence data. Noticeably, we propose and develop novel deep models for learning from molecular graphs and sequences. Therefore, MoleculeKit not only serves as a comprehensive tool, but also contributes towards developing novel and advanced graph and sequence learning methodologies. Results on both online and offline antibiotics discovery and molecular property prediction tasks show that MoleculeKit achieves consistent improvements over prior methods.

Antimicrobial resistance is an emerging global health crisis that is undermining advances in modern medicine and, if unmitigated, threatens to kill 10 million people per year worldwide by 2050. Research over the last decade has demonstrated that the differences between genetically identical cells in the same environment can lead to drug resistance. Fluctuations in gene expression, modulated by gene regulatory networks, can lead to non-genetic heterogeneity that results in the fractional killing of microbial populations causing drug therapies to fail; this non-genetic drug resistance can enhance the probability of acquiring genetic drug resistance mutations. Mathematical models of gene networks can elucidate general principles underlying drug resistance, predict the evolution of resistance, and guide drug resistance experiments in the laboratory. Cells genetically engineered to carry synthetic gene networks regulating drug resistance genes allow for controlled, quantitative experiments on the role of non-genetic heterogeneity in the development of drug resistance. In this perspective article, we emphasize the contributions that mathematical, computational, and synthetic gene network models play in advancing our understanding of antimicrobial resistance to discover effective therapies against drug-resistant infections.

The aim of this study was to investigate the age dependence of the fitness and body mass index (BMI) in Korean adults and to find an effective exercise to restore the degradation of fitness due to aging. The age dependence of the fitness and BMI were calculated using their lump mean values (LMVs) and a linear regression method. The fitness sensitivity percentage to age (FSPA) and fitness sensitivity percentage to BMI (FSPB) were introduced as indicators for the effective improvement of the fitness. The results showed that the degradation of fitness due to aging, especially the degradation of cardiorespiratory endurance and muscular endurance, could be improved effectively by controlling the 20-m multi-stage shuttle run and sit-up scores for both males and females. The results also showed that the BMIs could be effectively controlled with enhancing the 10-m shuttle run and standing long jump scores for both males and females. It is expected that the LMV, FSPA, and FSPB could be used to improve fitness effectively and to establish personal exercise aims.