基于核范数正则化的抗癌药物组合协同作用预测

目的 抗癌药物联合疗法是一种很有前途的治疗策略。针对特定癌症类型，选择高度协同的药物组合，对提高癌症疗效至关重要。然而，确定具有协同作用的药物组合是一项复杂而困难的工作。本研究旨在完全以数据驱动、计算建模的方式优化抗癌药物组合高通量虚拟筛选，为“旧药重新定位新组合”提供理论参考。方法 借鉴矩阵填充思想，构建了基于核范数正则化的计算模型NNRM，用于预测抗癌药物组合的协同得分和协同状态。针对固定细胞系构造对称的协同得分观测矩阵；采用分折技巧将观测矩阵稀疏化；借助“交替方向乘子法”和“软阈值估计”求解模型。结果 将NNRM应用于O’Neil团队发布的数据集，预测的协同得分与观测值之间的均方根误差为14.78，预测的协同状态准确率为0.94，优于随机森林（RF）和支持向量机（SVM），完全可以与深度学习模型相媲美。此外，NNRM预测的部分缺失值结果与已有研究或临床实践相吻合。结论 NNRM可实现大规模、批量预测抗癌药物组合的协同作用，极大地降低了已有模型对数据的要求和计算成本，缩短了高通量虚拟筛选的测试时间，可以作为抗癌药物组合高通量虚拟筛选的可选择工具。     

Drug Repositioning by Integrating Known Disease-Gene and Drug-Target Associations in a Semi-supervised Learning Model

Computational drug repositioning has been proven as a promising and efficient strategy for discovering new uses from existing drugs. To achieve this goal, a number of computational methods have been proposed, which are based on different data sources of drugs and diseases. These methods approach the problem using either machine learning- or network-based models with an assumption that similar drugs can be used for similar diseases to identify new indications of drugs. Therefore, similarities between drugs and between diseases are usually used as inputs. In addition, known drug-disease associations are also needed for the methods as prior information. It should be noted that those associations are still not well established due to the fact that many of marketed drugs have been withdrawn and this could affect the outcome of the methods. In this study, we propose a novel method named RLSDR (Regularized Least Square for Drug Repositioning) to find new uses of drugs. More specifically, it relies on a semi-supervised learning model, Regularized Least Square, thus it does not require definition of non-drug-disease associations as previously proposed machine learning-based methods. In addition, the similarity between drugs measured by chemical structures of drug compounds and the similarity between diseases which share phenotypes can be represented in a form of either similarity network or similarity matrix as inputs of the method. Moreover, instead of using a gold-standard set of known drug-disease associations, we construct an artificial set of the associations based on known disease-gene and drug-target associations. Experiment results demonstrate that RLSDR achieves better prediction performance on the artificial set of drug-disease associations than that on the gold-standard ones in terms of area under the Receiver Operating Characteristic (ROC) curve (AUC). In addition, it outperforms two representative network-based methods irrespective of the prior information of drug-disease associations. Novel indications for a number of drugs are also identified and validated by evidences from a different data resource.     

ASDCD: Antifungal Synergistic Drug Combination Database

Finding effective drugs to treat fungal infections has important clinical significance based on high mortality rates, especially in an immunodeficient population. Traditional antifungal drugs with single targets have been reported to cause serious side effects and drug resistance. Nowadays, however, drug combinations, particularly with respect to synergistic interaction, have attracted the attention of researchers. In fact, synergistic drug combinations could simultaneously affect multiple subpopulations, targets, and diseases. Therefore, a strategy that employs synergistic antifungal drug combinations could eliminate the limitations noted above and offer the opportunity to explore this emerging bioactive chemical space. However, it is first necessary to build a powerful database in order to facilitate the analysis of drug combinations. To address this gap in our knowledge, we have built the first Antifungal Synergistic Drug Combination Database (ASDCD), including previously published synergistic antifungal drug combinations, chemical structures, targets, target-related signaling pathways, indications, and other pertinent data. Its current version includes 210 antifungal synergistic drug combinations and 1225 drug-target interactions, involving 105 individual drugs from more than 12,000 references. ASDCD is freely available at http://ASDCD.amss.ac.cn.     

基于机器学习的药物-靶标相互作用预测*

近年来,随着计算机硬件、软件工具和数据丰度的不断突破,以机器学习为代表的人工智能技术在生物、基础医学和药学等领域的应用不断拓展和融合,极大地推动了这些领域的发展,尤其是药物研发领域的变革。其中,药物-靶标相互作用(drug-target interactions, DTI)的识别是药物研发领域中的重要难题和人工智能技术交叉融合的热门方向,研究人员在DTI预测方面做了大量的工作,构建了许多重要的数据库,开发或拓展了各类机器学习算法和工具软件。对基于机器学习的DTI预测的基本流程进行了介绍,并对利用机器学习预测DTI的研究进行了回顾,同时对不同的机器学习方法运用于DTI预测的优缺点进行了简单总结,以期对开发更加有效的预测算法和DTI预测的发展提供帮助。     

Teamwork: Improved eQTL Mapping Using Combinations of Machine Learning Methods

Expression quantitative trait loci (eQTL) mapping is a widely used technique to uncover regulatory relationships between genes. A range of methodologies have been developed to map links between expression traits and genotypes. The DREAM (Dialogue on Reverse Engineering Assessments and Methods) initiative is a community project to objectively assess the relative performance of different computational approaches for solving specific systems biology problems. The goal of one of the DREAM5 challenges was to reverse-engineer genetic interaction networks from synthetic genetic variation and gene expression data, which simulates the problem of eQTL mapping. In this framework, we proposed an approach whose originality resides in the use of a combination of existing machine learning algorithms (committee). Although it was not the best performer, this method was by far the most precise on average. After the competition, we continued in this direction by evaluating other committees using the DREAM5 data and developed a method that relies on Random Forests and LASSO. It achieved a much higher average precision than the DREAM best performer at the cost of slightly lower average sensitivity.     

Determining Effects of Non-synonymous SNPs on Protein-Protein Interactions using Supervised and Semi-supervised Learning

Single nucleotide polymorphisms (SNPs) are among the most common types of genetic variation in complex genetic disorders. A growing number of studies link the functional role of SNPs with the networks and pathways mediated by the disease-associated genes. For example, many non-synonymous missense SNPs (nsSNPs) have been found near or inside the protein-protein interaction (PPI) interfaces. Determining whether such nsSNP will disrupt or preserve a PPI is a challenging task to address, both experimentally and computationally. Here, we present this task as three related classification problems, and develop a new computational method, called the SNP-IN tool (non-synonymous SNP INteraction effect predictor). Our method predicts the effects of nsSNPs on PPIs, given the interaction''s structure. It leverages supervised and semi-supervised feature-based classifiers, including our new Random Forest self-learning protocol. The classifiers are trained based on a dataset of comprehensive mutagenesis studies for 151 PPI complexes, with experimentally determined binding affinities of the mutant and wild-type interactions. Three classification problems were considered: (1) a 2-class problem (strengthening/weakening PPI mutations), (2) another 2-class problem (mutations that disrupt/preserve a PPI), and (3) a 3-class classification (detrimental/neutral/beneficial mutation effects). In total, 11 different supervised and semi-supervised classifiers were trained and assessed resulting in a promising performance, with the weighted f-measure ranging from 0.87 for Problem 1 to 0.70 for the most challenging Problem 3. By integrating prediction results of the 2-class classifiers into the 3-class classifier, we further improved its performance for Problem 3. To demonstrate the utility of SNP-IN tool, it was applied to study the nsSNP-induced rewiring of two disease-centered networks. The accurate and balanced performance of SNP-IN tool makes it readily available to study the rewiring of large-scale protein-protein interaction networks, and can be useful for functional annotation of disease-associated SNPs. SNIP-IN tool is freely accessible as a web-server at http://korkinlab.org/snpintool/.     

Fitness of Leishmania donovani Parasites Resistant to Drug Combinations

Drug resistance represents one of the main problems for the use of chemotherapy to treat leishmaniasis. Additionally, it could provide some advantages to Leishmania parasites, such as a higher capacity to survive in stress conditions. In this work, in mixed populations of Leishmania donovani parasites, we have analyzed whether experimentally resistant lines to one or two combined anti-leishmanial drugs better support the stress conditions than a susceptible line expressing luciferase (Luc line). In the absence of stress, none of the Leishmania lines showed growth advantage relative to the other when mixed at a 1:1 parasite ratio. However, when promastigotes from resistant lines and the Luc line were mixed and exposed to different stresses, we observed that the resistant lines are more tolerant of different stress conditions: nutrient starvation and heat shock-pH stress. Further to this, we observed that intracellular amastigotes from resistant lines present a higher capacity to survive inside the macrophages than those of the control line. These results suggest that resistant parasites acquire an overall fitness increase and that resistance to drug combinations presents significant differences in their fitness capacity versus single-drug resistant parasites, particularly in intracellular amastigotes. These results contribute to the assessment of the possible impact of drug resistance on leishmaniasis control programs.     

Optimal Combinations of Diagnostic Tests Based on AUC

Summary When several diagnostic tests are available, one can combine them to achieve better diagnostic accuracy. This article considers the optimal linear combination that maximizes the area under the receiver operating characteristic curve (AUC); the estimates of the combination's coefficients can be obtained via a nonparametric procedure. However, for estimating the AUC associated with the estimated coefficients, the apparent estimation by re‐substitution is too optimistic. To adjust for the upward bias, several methods are proposed. Among them the cross‐validation approach is especially advocated, and an approximated cross‐validation is developed to reduce the computational cost. Furthermore, these proposed methods can be applied for variable selection to select important diagnostic tests. The proposed methods are examined through simulation studies and applications to three real examples.     

Target Inhibition Networks: Predicting Selective Combinations of Druggable Targets to Block Cancer Survival Pathways

A recent trend in drug development is to identify drug combinations or multi-target agents that effectively modify multiple nodes of disease-associated networks. Such polypharmacological effects may reduce the risk of emerging drug resistance by means of attacking the disease networks through synergistic and synthetic lethal interactions. However, due to the exponentially increasing number of potential drug and target combinations, systematic approaches are needed for prioritizing the most potent multi-target alternatives on a global network level. We took a functional systems pharmacology approach toward the identification of selective target combinations for specific cancer cells by combining large-scale screening data on drug treatment efficacies and drug-target binding affinities. Our model-based prediction approach, named TIMMA, takes advantage of the polypharmacological effects of drugs and infers combinatorial drug efficacies through system-level target inhibition networks. Case studies in MCF-7 and MDA-MB-231 breast cancer and BxPC-3 pancreatic cancer cells demonstrated how the target inhibition modeling allows systematic exploration of functional interactions between drugs and their targets to maximally inhibit multiple survival pathways in a given cancer type. The TIMMA prediction results were experimentally validated by means of systematic siRNA-mediated silencing of the selected targets and their pairwise combinations, showing increased ability to identify not only such druggable kinase targets that are essential for cancer survival either individually or in combination, but also synergistic interactions indicative of non-additive drug efficacies. These system-level analyses were enabled by a novel model construction method utilizing maximization and minimization rules, as well as a model selection algorithm based on sequential forward floating search. Compared with an existing computational solution, TIMMA showed both enhanced prediction accuracies in cross validation as well as significant reduction in computation times. Such cost-effective computational-experimental design strategies have the potential to greatly speed-up the drug testing efforts by prioritizing those interventions and interactions warranting further study in individual cancer cases.     

Search Algorithms as a Framework for the Optimization of Drug Combinations

Combination therapies are often needed for effective clinical outcomes in the management of complex diseases, but presently they are generally based on empirical clinical experience. Here we suggest a novel application of search algorithms—originally developed for digital communication—modified to optimize combinations of therapeutic interventions. In biological experiments measuring the restoration of the decline with age in heart function and exercise capacity in Drosophila melanogaster, we found that search algorithms correctly identified optimal combinations of four drugs using only one-third of the tests performed in a fully factorial search. In experiments identifying combinations of three doses of up to six drugs for selective killing of human cancer cells, search algorithms resulted in a highly significant enrichment of selective combinations compared with random searches. In simulations using a network model of cell death, we found that the search algorithms identified the optimal combinations of 6–9 interventions in 80–90% of tests, compared with 15–30% for an equivalent random search. These findings suggest that modified search algorithms from information theory have the potential to enhance the discovery of novel therapeutic drug combinations. This report also helps to frame a biomedical problem that will benefit from an interdisciplinary effort and suggests a general strategy for its solution.     

AdaBoost Based Multi-Instance Transfer Learning for Predicting Proteome-Wide Interactions between Salmonella and Human Proteins

Pathogen-host protein-protein interaction (PPI) plays an important role in revealing the underlying pathogenesis of viruses and bacteria. The need of rapidly mapping proteome-wide pathogen-host interactome opens avenues for and imposes burdens on computational modeling. For Salmonella typhimurium, only 62 interactions with human proteins are reported to date, and the computational modeling based on such a small training data is prone to yield model overfitting. In this work, we propose a multi-instance transfer learning method to reconstruct the proteome-wide Salmonella-human PPI networks, wherein the training data is augmented by homolog knowledge transfer in the form of independent homolog instances. We use AdaBoost instance reweighting to counteract the noise from homolog instances, and deliberately design three experimental settings to validate the assumption that the homolog instances are effective to address the problems of data scarcity and data unavailability. The experimental results show that the proposed method outperforms the existing models and some predictions are validated by the findings from recent literature. Lastly, we conduct gene ontology based clustering analysis of the predicted networks to provide insights into the pathogenesis of Salmonella.     

Synergistic Inhibition of Microbial Sulfide Production by Combinations of the Metabolic Inhibitor Nitrite and Biocides

MICs of six broad-spectrum biocides and two specific metabolic inhibitors and fractional inhibitory concentration indexes (FICIs) for controlling a sulfide-producing consortium were determined. Nitrite was synergistic (FICI < 1) with all but one biocide due to its specific inhibition of dissimilatory sulfite reductase. Hence, combining nitrite with biocides allows more efficient and cost-effective control of sulfate-reducing bacteria.     

Identification of Drug Combinations Containing Imatinib for Treatment of BCR-ABL+ Leukemias

The BCR-ABL translocation is found in chronic myeloid leukemia (CML) and in Ph+ acute lymphoblastic leukemia (ALL) patients. Although imatinib and its analogues have been used as front-line therapy to target this mutation and control the disease for over a decade, resistance to the therapy is still observed and most patients are not cured but need to continue the therapy indefinitely. It is therefore of great importance to find new therapies, possibly as drug combinations, which can overcome drug resistance. In this study, we identified eleven candidate anti-leukemic drugs that might be combined with imatinib, using three approaches: a kinase inhibitor library screen, a gene expression correlation analysis, and literature analysis. We then used an experimental search algorithm to efficiently explore the large space of possible drug and dose combinations and identified drug combinations that selectively kill a BCR-ABL+ leukemic cell line (K562) over a normal fibroblast cell line (IMR-90). Only six iterations of the algorithm were needed to identify very selective drug combinations. The efficacy of the top forty-nine combinations was further confirmed using Ph+ and Ph- ALL patient cells, including imatinib-resistant cells. Collectively, the drug combinations and methods we describe might be a first step towards more effective interventions for leukemia patients, especially those with the BCR-ABL translocation.     

盐酸埃克替尼与多西他赛、培美曲塞不同联合方式对非小细胞肺癌PC-9细胞系作用的实验研究

目的:探讨盐酸埃克替尼以不同次序联合多西他赛、培美曲塞对非小细胞肺癌细胞系PC-9的作用。方法:运用xCELLigence系统检验多西他赛、培美曲塞、盐酸埃克替尼单药作用于PC-9细胞系的半数抑制浓度(Half maximal inhibitory concentration,IC50),用流式细胞仪检测埃克替尼与多西他赛/培美曲塞联合的不同组合方式对PC-9细胞系的细胞周期影响及凋亡。结果:1埃克替尼对PC-9细胞作用60 h后的IC50值为5.3μM;多西他赛对PC-9细胞作用36 h后的IC50为21.5 mg·m L-1;培美曲塞对PC-9细胞作用36 h后的IC50为30μM。2Annexin V-FITC凋亡实验观察到化疗药先于埃克替尼应用对靶细胞的体外杀伤作用均明显高于其他各组,先用多西他赛组细胞凋亡率为(23±0.2)%,高于先用埃克替尼组(10.2±0.1)%和两药同时用药组(15.8±0.4)%;先用培美曲塞组细胞凋亡率为(36.3±0.03)%,高于先用埃克替尼组(14.7±0.1)%和两药同时用药组(30.6±0.03)%,差异有统计学意义(P0.05)。3流式细胞仪周期检测结果显示埃克替尼先于多西他赛(或培美曲塞)用药或两药同时应用时PC-9细胞G0/G1期比例比多西他赛(或培美曲塞)先于埃克替尼用药组高。结论:多西他赛、培美曲塞先于埃克替尼应用方案对肿瘤细胞杀伤作用优于晚用埃克替尼或同时应用埃克替尼。     

Predicting Splicing from Primary Sequence with Deep Learning

1. Download high-res image (270KB)
2. Download full-size image