Predicting synergism of cancer drug combinations using NCI-ALMANAC data

AbstractBackgroundDrug combinations are of great interest for cancer treatment. Unfortunately, the discovery of synergistic combinations by purely experimental means is only feasible on small sets of drugs.In silicomodeling methods can substantially widen this search by providing tools able to predict which of all possible combinations in a large compound library are synergistic. Here we investigate to which extent drug combination synergy can be predicted by exploiting the largest available dataset to date (NCI-ALMANAC, with over 290,000 synergy determinations).MethodsEach cell line is modeled using primarily two machine learning techniques, Random Forest (RF) and Extreme Gradient Boosting (XGBoost), on the datasets provided by NCI-ALMANAC. This large-scale predictive modeling study comprises more than 5000 pair-wise drug combinations, 60 cell lines, 4 types of models and 5 types of chemical features. The application of a powerful, yet uncommonly used, RF-specific technique for reliability prediction is also investigated.ResultsThe evaluation of these models shows that it is possible to predict the synergy of unseen drug combinations with high accuracy (Pearson correlations between 0.43 and 0.86 depending on the considered cell line, with XGBoost providing slightly better predictions than RF). We have also found that restricting to the most reliable synergy predictions results in at least two-fold error decrease with respect to employing the best learning algorithm without any reliability estimation. Alkylating agents, tyrosine kinase inhibitors and topoisomerase inhibitors are the drugs whose synergy with other partner drugs are better predicted by the models.ConclusionsDespite its leading size, NCI-ALMANAC comprises an extremely small part of all conceivable combinations. Given their accuracy and reliability estimation, the developed models should drastically reduce the number of requiredin vitrotests by predictingin silicowhich of the considered combinations are likely to be synergistic.

Download Full-text

HyP-ABC: A Novel Automated Hyper-Parameter Tuning Algorithm Using Evolutionary Optimization

10.36227/techrxiv.14714508.v3 ◽

2021 ◽

Author(s):

Leila Zahedi ◽

Farid Ghareh Mohammadi ◽

M. Hadi Amini

Keyword(s):

Real World ◽

Large Scale ◽

Convergence Rates ◽

Parameter Tuning ◽

Population Based ◽

Machine Learning Techniques ◽

Gradient Boosting ◽

Support Vector ◽

Wide Range ◽

Extreme Gradient Boosting

<p>Machine learning techniques lend themselves as promising decision-making and analytic tools in a wide range of applications. Different ML algorithms have various hyper-parameters. In order to tailor an ML model towards a specific application working at its best, its hyper-parameters should be tuned. Tuning the hyper-parameters directly affects the performance. However, for large-scale search spaces, efficiently exploring the ample number of combinations of hyper-parameters is computationally expensive. Many of the automated hyper-parameter tuning techniques suffer from low convergence rates and high experimental time complexities. In this paper, we propose HyP-ABC, an automatic innovative hybrid hyper-parameter optimization algorithm using the modified artificial bee colony approach, to measure the classification accuracy of three ML algorithms: random forest, extreme gradient boosting, and support vector machine. In order to ensure the robustness of the proposed method, the algorithm takes a wide range of feasible hyper-parameter values and is tested using a real-world educational dataset. Experimental results show that HyP-ABC is competitive with state-of-the-art techniques. Also, it has fewer hyper-parameters to be tuned than other population-based algorithms, making it worthwhile for real-world HPO problems.</p>

Download Full-text

Intercomparing the robustness of machine learning models in simulation and forecasting of streamflow

Journal of Water and Climate Change ◽

10.2166/wcc.2020.365 ◽

2020 ◽

Author(s):

Parthiban Loganathan ◽

Amit Baburao Mahindrakar

Keyword(s):

Machine Learning ◽

Large Scale ◽

Resource Planning ◽

Machine Learning Techniques ◽

Low Flow ◽

Gradient Boosting ◽

Daily Streamflow ◽

Learning Techniques ◽

Extreme Gradient Boosting ◽

Hydrological Indices

Abstract The intercomparison of streamflow simulation and the prediction of discharge using various renowned machine learning techniques were performed. The daily streamflow discharge model was developed for 35 observation stations located in a large-scale river basin named Cauvery. Various hydrological indices were calculated for observed and predicted discharges for comparing and evaluating the replicability of local hydrological conditions. The model variance and bias observed from the proposed extreme gradient boosting decision tree model were less than 15%, which is compared with other machine learning techniques considered in this study. The model Nash–Sutcliffe efficiency and coefficient of determination values are above 0.7 for both the training and testing phases which demonstrate the effectiveness of model performance. The comparison of monthly observed and model-predicted discharges during the validation period illustrates the model's ability in representing the peaks and fall in high-, medium-, and low-flow zones. The assessment and comparison of hydrological indices between observed and predicted discharges illustrate the model's ability in representing the baseflow, high-spell, and low-spell statistics. Simulating streamflow and predicting discharge are essential for water resource planning and management, especially in large-scale river basins. The proposed machine learning technique demonstrates significant improvement in model efficiency by dropping variance and bias which, in turn, improves the replicability of local-scale hydrology.

Download Full-text

Machine learning models to identify low adherence to influenza vaccination among Korean adults with cardiovascular disease

BMC Cardiovascular Disorders ◽

10.1186/s12872-021-01925-7 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Moojung Kim ◽

Young Jae Kim ◽

Sung Jin Park ◽

Kwang Gi Kim ◽

Pyung Chun Oh ◽

...

Keyword(s):

Machine Learning ◽

Cardiovascular Disease ◽

Influenza Vaccination ◽

Machine Learning Techniques ◽

Gradient Boosting ◽

Support Vector ◽

Age Group ◽

Learning Models ◽

Extreme Gradient Boosting ◽

Machine Learning Models

Abstract Background Annual influenza vaccination is an important public health measure to prevent influenza infections and is strongly recommended for cardiovascular disease (CVD) patients, especially in the current coronavirus disease 2019 (COVID-19) pandemic. The aim of this study is to develop a machine learning model to identify Korean adult CVD patients with low adherence to influenza vaccination Methods Adults with CVD (n = 815) from a nationally representative dataset of the Fifth Korea National Health and Nutrition Examination Survey (KNHANES V) were analyzed. Among these adults, 500 (61.4%) had answered "yes" to whether they had received seasonal influenza vaccinations in the past 12 months. The classification process was performed using the logistic regression (LR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGB) machine learning techniques. Because the Ministry of Health and Welfare in Korea offers free influenza immunization for the elderly, separate models were developed for the < 65 and ≥ 65 age groups. Results The accuracy of machine learning models using 16 variables as predictors of low influenza vaccination adherence was compared; for the ≥ 65 age group, XGB (84.7%) and RF (84.7%) have the best accuracies, followed by LR (82.7%) and SVM (77.6%). For the < 65 age group, SVM has the best accuracy (68.4%), followed by RF (64.9%), LR (63.2%), and XGB (61.4%). Conclusions The machine leaning models show comparable performance in classifying adult CVD patients with low adherence to influenza vaccination.

Download Full-text

High-Resolution Vegetation Mapping Using eXtreme Gradient Boosting Based on Extensive Features

Remote Sensing ◽

10.3390/rs11121505 ◽

2019 ◽

Vol 11 (12) ◽

pp. 1505 ◽

Cited By ~ 7

Author(s):

Heng Zhang ◽

Anwar Eziz ◽

Jian Xiao ◽

Shengli Tao ◽

Shaopeng Wang ◽

...

Keyword(s):

New Zealand ◽

High Resolution ◽

Large Scale ◽

Field Survey ◽

Terrestrial Ecosystems ◽

Google Earth ◽

Gradient Boosting ◽

Global Changes ◽

Vegetation Map ◽

Extreme Gradient Boosting

Accurate mapping of vegetation is a premise for conserving, managing, and sustainably using vegetation resources, especially in conditions of intensive human activities and accelerating global changes. However, it is still challenging to produce high-resolution multiclass vegetation map in high accuracy, due to the incapacity of traditional mapping techniques in distinguishing mosaic vegetation classes with subtle differences and the paucity of fieldwork data. This study created a workflow by adopting a promising classifier, extreme gradient boosting (XGBoost), to produce accurate vegetation maps of two strikingly different cases (the Dzungarian Basin in China and New Zealand) based on extensive features and abundant vegetation data. For the Dzungarian Basin, a vegetation map with seven vegetation types, 17 subtypes, and 43 associations was produced with an overall accuracy of 0.907, 0.801, and 0.748, respectively. For New Zealand, a map of 10 habitats and a map of 41 vegetation classes were produced with 0.946, and 0.703 overall accuracy, respectively. The workflow incorporating simplified field survey procedures outperformed conventional field survey and remote sensing based methods in terms of accuracy and efficiency. In addition, it opens a possibility of building large-scale, high-resolution, and timely vegetation monitoring platforms for most terrestrial ecosystems worldwide with the aid of Google Earth Engine and citizen science programs.

Download Full-text

Prediction of hot spots in protein–DNA binding interfaces based on supervised isometric feature mapping and extreme gradient boosting

BMC Bioinformatics ◽

10.1186/s12859-020-03683-3 ◽

2020 ◽

Vol 21 (S13) ◽

Cited By ~ 2

Author(s):

Ke Li ◽

Sijia Zhang ◽

Di Yan ◽

Yannan Bin ◽

Junfeng Xia

Keyword(s):

Feature Selection ◽

Manifold Learning ◽

Hot Spots ◽

Large Scale ◽

Computational Method ◽

Gradient Boosting ◽

Feature Mapping ◽

Accessible Information ◽

Extreme Gradient Boosting ◽

Isometric Feature Mapping

Abstract Background Identification of hot spots in protein-DNA interfaces provides crucial information for the research on protein-DNA interaction and drug design. As experimental methods for determining hot spots are time-consuming, labor-intensive and expensive, there is a need for developing reliable computational method to predict hot spots on a large scale. Results Here, we proposed a new method named sxPDH based on supervised isometric feature mapping (S-ISOMAP) and extreme gradient boosting (XGBoost) to predict hot spots in protein-DNA complexes. We obtained 114 features from a combination of the protein sequence, structure, network and solvent accessible information, and systematically assessed various feature selection methods and feature dimensionality reduction methods based on manifold learning. The results show that the S-ISOMAP method is superior to other feature selection or manifold learning methods. XGBoost was then used to develop hot spots prediction model sxPDH based on the three dimensionality-reduced features obtained from S-ISOMAP. Conclusion Our method sxPDH boosts prediction performance using S-ISOMAP and XGBoost. The AUC of the model is 0.773, and the F1 score is 0.713. Experimental results on benchmark dataset indicate that sxPDH can achieve generally better performance in predicting hot spots compared to the state-of-the-art methods.

Download Full-text

Identification of Potential Type II Diabetes in a Large-Scale Chinese Population Using a Systematic Machine Learning Framework

Journal of Diabetes Research ◽

10.1155/2020/6873891 ◽

2020 ◽

Vol 2020 ◽

pp. 1-12

Author(s):

Mingyue Xue ◽

Yinxia Su ◽

Chen Li ◽

Shuxia Wang ◽

Hua Yao

Keyword(s):

Machine Learning ◽

Risk Factors ◽

Decision Tree ◽

Type Ii Diabetes ◽

Large Scale ◽

Systolic Pressure ◽

Gradient Boosting ◽

Significant Feature ◽

Type Ii ◽

Extreme Gradient Boosting

Background. An estimated 425 million people globally have diabetes, accounting for 12% of the world’s health expenditures, and the number continues to grow, placing a huge burden on the healthcare system, especially in those remote, underserved areas. Methods. A total of 584,168 adult subjects who have participated in the national physical examination were enrolled in this study. The risk factors for type II diabetes mellitus (T2DM) were identified by p values and odds ratio, using logistic regression (LR) based on variables of physical measurement and a questionnaire. Combined with the risk factors selected by LR, we used a decision tree, a random forest, AdaBoost with a decision tree (AdaBoost), and an extreme gradient boosting decision tree (XGBoost) to identify individuals with T2DM, compared the performance of the four machine learning classifiers, and used the best-performing classifier to output the degree of variables’ importance scores of T2DM. Results. The results indicated that XGBoost had the best performance (accuracy=0.906, precision=0.910, recall=0.902, F‐1=0.906, and AUC=0.968). The degree of variables’ importance scores in XGBoost showed that BMI was the most significant feature, followed by age, waist circumference, systolic pressure, ethnicity, smoking amount, fatty liver, hypertension, physical activity, drinking status, dietary ratio (meat to vegetables), drink amount, smoking status, and diet habit (oil loving). Conclusions. We proposed a classifier based on LR-XGBoost which used fourteen variables of patients which are easily obtained and noninvasive as predictor variables to identify potential incidents of T2DM. The classifier can accurately screen the risk of diabetes in the early phrase, and the degree of variables’ importance scores gives a clue to prevent diabetes occurrence.

Download Full-text

Understanding Multi-Vehicle Collision Patterns on Freeways—A Machine Learning Approach

Infrastructures ◽

10.3390/infrastructures5080062 ◽

2020 ◽

Vol 5 (8) ◽

pp. 62

Author(s):

Clint Morris ◽

Jidong J. Yang

Keyword(s):

Machine Learning ◽

Statistical Methods ◽

Machine Learning Techniques ◽

Gradient Boosting ◽

Learning Approaches ◽

Crash Analysis ◽

Suitable Alternative ◽

Crash Data ◽

Extreme Gradient Boosting ◽

Modern Machine

Generating meaningful inferences from crash data is vital to improving highway safety. Classic statistical methods are fundamental to crash data analysis and often regarded for their interpretability. However, given the complexity of crash mechanisms and associated heterogeneity, classic statistical methods, which lack versatility, might not be sufficient for granular crash analysis because of the high dimensional features involved in crash-related data. In contrast, machine learning approaches, which are more flexible in structure and capable of harnessing richer data sources available today, emerges as a suitable alternative. With the aid of new methods for model interpretation, the complex machine learning models, previously considered enigmatic, can be properly interpreted. In this study, two modern machine learning techniques, Linear Discriminate Analysis and eXtreme Gradient Boosting, were explored to classify three major types of multi-vehicle crashes (i.e., rear-end, same-direction sideswipe, and angle) occurred on Interstate 285 in Georgia. The study demonstrated the utility and versatility of modern machine learning methods in the context of crash analysis, particularly in understanding the potential features underlying different crash patterns on freeways.

Download Full-text

Forecasting sub-resolution temporal variability of irradiance

10.5194/egusphere-egu2020-10152 ◽

2020 ◽

Author(s):

Frank Kreuwel ◽

Chiel van Heerwaarden

Keyword(s):

Large Scale ◽

Point Of View ◽

Surface Radiation ◽

Gradient Boosting ◽

Distribution Grid ◽

Electricity Grid ◽

Pv Systems ◽

Extreme Gradient Boosting ◽

Scale Integration ◽

Meso Scale

<p>Variability of solar irradiance is an important factor concerning large-scale integration of solar photovoltaics (PV) systems onto the electricity grid. Calculations of irradiance are computationally expensive, leaving operational meso-scale forecasting models struggling to achieve accurate results. Moreover, such models deliver outputs at a temporal resolution in the order of hours, whereas from a grid-integration point of view, minute-to-minute variability is a major concern. In previous work, we found that absolute power peaks in the order of seconds are up to 18% higher compared to 15-minute resolution for irradiance and even upwards of 22% higher for household PV systems. Moreover, these maximum peaks in output power are solely observed under mixed-cloud conditions, for which alse the greatest variability is found. In this work we present a machine-learning model which can forecast sub-resolution variability of irradiance, based on standard meso-scale outputs of the HARMONIE model of the The Royal Netherlands Meteorological Institute (KNMI). For training and validation, irradiance measurements obtained at a 1-second interval are used of the Baseline Surface Radiation Network (BSRN) site of Cabauw. A tree-based model was employed, for which the optimum members were constructed using extreme gradient boosting. In this work, we explore the dominant features of the model and link the machine-learned-relations to meteorological processes and dynamics. This research was executed in collaboration with the Distribution Grid Operator Alliander.</p>

Download Full-text

Cell line-specific network models of ER+ breast cancer identify PI3Kα inhibitor sensitivity factors and drug combinations

10.1101/2020.08.25.261370 ◽

2020 ◽

Author(s):

Jorge Gómez Tejeda Zañudo ◽

Pingping Mao ◽

Clara Alcon ◽

Kailey J. Kowalski ◽

Gabriela N. Johnson ◽

...

Keyword(s):

Breast Cancer ◽

Drug Resistance ◽

Mathematical Models ◽

Cell Line ◽

Network Models ◽

Drug Combinations ◽

Cancer Drug ◽

Bh3 Mimetics ◽

Cancer Drug Resistance ◽

Sensitivity Factors

Durable control of invasive solid tumors necessitates identifying therapeutic resistance mechanisms and effective drug combinations. A promising approach to tackle the cancer drug resistance problem is to build mechanistic mathematical models of the signaling network of cancer cells, and explicitly model the dynamics of information flow through this network under distinct genetic conditions and in response to perturbations. In this work, we used a network-based mathematical model to identify sensitivity factors and drug combinations for the PI3K&alpha inhibitor alpelisib, which was recently approved for ER+ PIK3CA mutant breast cancer. We experimentally validated the model-predicted efficacious combination of alpelisib and BH3 mimetics (e.g. MCL1 inhibitors) in ER+ breast cancer cell lines. We also experimentally validated the reduced sensitivity to alpelisib caused by FOXO3 knockdown, which is a novel potential resistance mechanism. Our experimental results showed cell line-specific sensitivity to the combination of alpelisib and BH3 mimetics, which was driven by the choice of BH3 mimetics. We find that cell lines were sensitive to the addition of either MCL1 inhibitor s63845 alone or in combination with BCL-XL/BCL-2 inhibitor navitoclax, and that the need for the combination of both BH3 mimetics was predicted by the expression of BCL-XL. Based on these results, we developed cell line-specific network models that are able to recapitulate the observed differential response to alpelisib and BH3 mimetics, and also incorporate the most recent knowledge on resistance and response to PI3K&alpha inhibitors. Overall, we present an approach for the development, experimental testing, and refining of mathematical models, which we apply to the context of PI3K&alpha inhibitor drug resistance in breast cancer. Our approach predicted and validated PI3K&alpha inhibitor sensitivity factors (FOXO3 knockdown) and drug combinations (BH3 mimetics), and illustrates that network-based mathematical models can contribute to overcoming the challenge of cancer drug resistance.

Download Full-text

Gully Erosion Susceptibility Mapping in Highly Complex Terrain Using Machine Learning Models

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10100680 ◽

2021 ◽

Vol 10 (10) ◽

pp. 680

Author(s):

Annan Yang ◽

Chunmei Wang ◽

Guowei Pang ◽

Yongqing Long ◽

Lei Wang ◽

...

Keyword(s):

Machine Learning ◽

Complex Terrain ◽

Large Scale ◽

Area Under The Curve ◽

Gully Erosion ◽

Susceptibility Mapping ◽

Weight Of Evidence ◽

Gradient Boosting ◽

Machine Learning Classification ◽

Extreme Gradient Boosting

Gully erosion is the most severe type of water erosion and is a major land degradation process. Gully erosion susceptibility mapping (GESM)’s efficiency and interpretability remains a challenge, especially in complex terrain areas. In this study, a WoE-MLC model was used to solve the above problem, which combines machine learning classification algorithms and the statistical weight of evidence (WoE) model in the Loess Plateau. The three machine learning (ML) algorithms utilized in this research were random forest (RF), gradient boosted decision trees (GBDT), and extreme gradient boosting (XGBoost). The results showed that: (1) GESM were well predicted by combining both machine learning regression models and WoE-MLC models, with the area under the curve (AUC) values both greater than 0.92, and the latter was more computationally efficient and interpretable; (2) The XGBoost algorithm was more efficient in GESM than the other two algorithms, with the strongest generalization ability and best performance in avoiding overfitting (averaged AUC = 0.947), followed by the RF algorithm (averaged AUC = 0.944), and GBDT algorithm (averaged AUC = 0.938); and (3) slope gradient, land use, and altitude were the main factors for GESM. This study may provide a possible method for gully erosion susceptibility mapping at large scale.

Download Full-text