Matching anticancer compounds and tumor cell lines by neural networks with ranking loss

ABSTRACT Computational drug sensitivity models have the potential to improve therapeutic outcomes by identifying targeted drug components that are likely to achieve the highest efficacy for a cancer cell line at hand at a therapeutic dose. State of the art drug sensitivity models use regression techniques to predict the inhibitory concentration of a drug for a tumor cell line. This regression objective is not directly aligned with either of these principal goals of drug sensitivity models: We argue that drug sensitivity modeling should be seen as a ranking problem with an optimization criterion that quantifies a drug’s inhibitory capacity for the cancer cell line at hand relative to its toxicity for healthy cells. We derive an extension to the well-established drug sensitivity regression model PaccMann that employs a ranking loss and focuses on the ratio of inhibitory concentration and therapeutic dosage range. We find that the ranking extension significantly enhances the model’s capability to identify the most effective anticancer drugs for unseen tumor cell profiles based in on in-vitro data.

Identifying Multiple Influential Spreaders in Complex Networks by Considering the Dispersion of Nodes

Identifying multiple influential spreaders, which relates to finding k (k > 1) nodes with the most significant influence, is of great importance both in theoretical and practical applications. It is usually formulated as a node-ranking problem and addressed by sorting spreaders’ influence as measured based on the topological structure of interactions or propagation process of spreaders. However, ranking-based algorithms may not guarantee that the selected spreaders have the maximum influence, as these nodes may be adjacent, and thus play redundant roles in the propagation process. We propose three new algorithms to select multiple spreaders by taking into account the dispersion of nodes in the following ways: (1) improving a well-performed local index rank (LIR) algorithm by extending its key concept of the local index (an index measures how many of a node’s neighbors have a higher degree) from first-to second-order neighbors; (2) combining the LIR and independent set (IS) methods, which is a generalization of the coloring problem for complex networks and can ensure the selected nodes are non-adjacent if they have the same color; (3) combining the improved second-order LIR method and IS method so as to make the selected spreaders more disperse. We evaluate the proposed methods against six baseline methods on 10 synthetic networks and five real networks based on the classic susceptible-infected-recovered (SIR) model. The experimental results show that our proposed methods can identify nodes that are more influential. This suggests that taking into account the distances between nodes may aid in the identification of multiple influential spreaders.

Preference Neural Network

Equality and incomparability multi-label ranking have not been introduced to learning before. This paper proposes new native ranker neural network to address the problem of multi-label ranking including incomparable preference orders using a new activation and error functions and new architecture. Preference Neural Network PNN solves the multi-label ranking problem, where labels may have indifference preference orders or subgroups which are equally ranked. PNN is a nondeep, multiple-value neuron, single middle layer and one or more output layers network. PNN uses a novel positive smooth staircase (PSS) or smooth staircase (SS) activation function and represents preference orders and Spearman ranking correlation as objective functions. It is introduced in two types, Type A is traditional NN architecture and Type B uses expanding architecture by introducing new type of hidden neuron has multiple activation function in middle layer and duplicated output layers to reinforce the ranking by increasing the number of weights. PNN accepts single data instance as inputs and output neurons represent the number of labels and output value represents the preference value. PNN is evaluated using a new preference mining data set that contains repeated label values which have not experimented on before. SS and PS speed-up the learning and PNN outperforms five previously proposed methods for strict label ranking in terms of accurate results with high computational efficiency.

Comparative Multicriteria Analysis Methods for Ranking Sites for Solar Farm Deployment: A Case Study in Greece

This study investigated the prioritization and ranking problem of the appropriate locations at which to deploy solar photovoltaic (PV) farms. Although different Multicriteria Decision Making (MCDM) methods can be found in the literature to address this problem, a comparative analysis of those methods is missing. The aim of this study is to compare four different MCDM approaches to evaluate and rank suitable areas for the deployment of solar PV farms, with the island of Rhodes (Greece) being used as an example. Feasible areas for the location of such facilities were identified with the use of Geographical Information Systems (GIS), by applying certain exclusion criteria found either in the national legislative framework or in the international literature. Data were obtained from Greek open geospatial data. The feasible sites were evaluated and ranked using four different MCDM methods: the Analytical Hierarchy Process (AHP), the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), the VIKOR (VIseKriterijumska Optimizacija I Kompromisno Resenje), and the PROMETHEE II (Preference Ranking Organization METHod for Enrichment of Evaluations) method. The best alternative rated according to three TOPSIS, VIKOR and PROMETHEE is site (S2). The second-best alternative in the above three methods is site (S1), while the worst is site (S3). The best alternative rated according to AHP (S4) is in sixth position according to TOPSIS and in fifth position VIKOR and PROMETHEE. The comparison demonstrated that different MCDM techniques may generate different ranks. The simultaneous use of several MCDM methods in energy siting problems is considered advantageous as it can help decision makers to select the most sustainable sites, avoiding the disadvantages and availing the advantages of each method.

NeuRank: learning to rank with neural networks for drug–target interaction prediction

Background Experimental verification of a drug discovery process is expensive and time-consuming. Therefore, recently, the demand to more efficiently and effectively identify drug–target interactions (DTIs) has intensified. Results We treat the prediction of DTIs as a ranking problem and propose a neural network architecture, NeuRank, to address it. Also, we assume that similar drug compounds are likely to interact with similar target proteins. Thus, in our model, we add drug and target similarities, which are very effective at improving the prediction of DTIs. Then, we develop NeuRank from a point-wise to a pair-wise, and further to list-wise model. Conclusion Finally, results from extensive experiments on five public data sets (DrugBank, Enzymes, Ion Channels, G-Protein-Coupled Receptors, and Nuclear Receptors) show that, in identifying DTIs, our models achieve better performance than other state-of-the-art methods.

Identifying important nodes from content-associated heterogeneous graph by LeaderRank

Most real-world systems consist of a large number of interacting entities of many types. However, most of the current researches on systems are based on the assumption that the type of node or link in the network is unique. In other words, the network is homogeneous, containing the same type of nodes and links. Based on this assumption, differential information between nodes and edges is ignored. This paper firstly introduces the research background, challenges and significance of this research. Secondly, the basic concepts of the model are introduced. Thirdly, a novel type-sensitive LeaderRank algorithm is proposed and combined with distance rule to solve the importance ranking problem of content-associated heterogeneous graph nodes. Finally, the writer influence data set is used for experimental analysis to further prove the validity of the model.

FUZZY AGGREGATION FOR RANKING IN BUSINESS

Today, businesses depend strongly on data and the opinion of customers or the experience of managers or experts. The large databases contain non-heterogeneous data, which is the ground for further decisions. Business uses multicriterial decisions in more areas (e.g., customer care, marketing, product development, risk management, HR, etc.) and often it is based on assessment. One of the assessment methods is the ranking, which can be done by crisp values of data where the sharp borders between evaluated entities do not give the adequate ranking result. On the other hand, the ranking process is based on the qualitative assessment, which has linguistic expression. It is more familiar and understandable for people. The article shows how to treat non-heterogeneous data to prepare them for a ranking process using fuzzy sets theory. The article aims at offering several types of ranking methods based on different inputs and preferences of the user and describes appropriate fuzzy aggregations for solving the ranking problem.

Word-embedding Based Text Vectorization Using Clustering

It is known that in the tasks of natural language processing, the representation of texts by vectors of fixed length using word-embedding models makes sense in cases where the vectorized texts are short.The longer the texts being compared, the worse the approach works. This situation is due to the fact that when using word-embedding models, information is lost when converting the vector representations of the words that make up the text into a vector representation of the entire text, which usually has the same dimension as the vector of a single word.This paper proposes an alternative way for using pre-trained word-embedding models for text vectorization. The essence of the proposed method consists in combining semantically similar elements of the dictionary of the existing text corpus by clustering their (dictionary elements) embeddings, as a result of which a new dictionary is formed with a size smaller than the original one, each element of which corresponds to one cluster. The original corpus of texts is reformulated in terms of this new dictionary, after which vectorization is performed on the reformulated texts using one of the dictionary approaches (TF-IDF was used in the work). The resulting vector representation of the text can be additionally enriched using the vectors of words of the original dictionary obtained by decreasing the dimension of their embeddings for each cluster.A series of experiments to determine the optimal parameters of the method is described in the paper, the proposed approach is compared with other methods of text vectorization for the text ranking problem – averaging word embeddings with TF-IDF weighting and without weighting, as well as vectorization based on TF-IDF coefficients.