PURPOSE: Large Language Models (LLMs) like Generative Pre-trained Transformer (GPT) from OpenAI and LLaMA (Large Language Model Meta AI) from Meta AI are increasingly recognized for their potential in the field of cheminformatics, particularly in understanding Simplified Molecular Input Line Entry System (SMILES), a standard method for representing chemical structures. These LLMs also have the ability to decode SMILES strings into vector representations. METHOD: We investigate the performance of GPT and LLaMA compared to pre-trained models on SMILES in embedding SMILES strings on downstream tasks, focusing on two key applications: molecular property prediction and drug-drug interaction prediction. RESULTS: We find that SMILES embeddings generated using LLaMA outperform those from GPT in both molecular property and DDI prediction tasks. Notably, LLaMA-based SMILES embeddings show results comparable to pre-trained models on SMILES in molecular prediction tasks and outperform the pre-trained models for the DDI prediction tasks. CONCLUSION: The performance of LLMs in generating SMILES embeddings shows great potential for further investigation of these models for molecular embedding. We hope our study bridges the gap between LLMs and molecular embedding, motivating additional research into the potential of LLMs in the molecular representation field. GitHub: https://github.com/sshaghayeghs/LLaMA-VS-GPT .

With the development of chromosome conformation capture technology, the genome-wide investigation of higher-order chromatin structure by using high-throughput chromatin conformation capture (Hi-C) technology is emerging as an important component for understanding the mechanism of gene regulation. Considering genetic and epigenetic differences are typically used to explore the pathological reasons on the chromosome and gene level, visualizing multi-omics data and performing an intuitive analysis by using an interactive browser become a powerful and welcomed way. In this paper, we develop an effective sequence and chromatin interaction data display browser called HiBrowser for visualizing and analyzing Hi-C data and their associated genetic and epigenetic annotations. The advantages of HiBrowser are flexible multi-omics navigation, novel multidimensional synchronization comparisons and dynamic interaction system. In particular, HiBrowser first provides an out of the box web service and allows flexible and dynamic reconstruction of custom annotation tracks on demand during running. In order to conveniently and intuitively analyze the similarities and differences among multiple samples, such as visual comparisons of normal and tumor tissue samples, and pan genomes of multiple (consanguineous) species, HiBrowser develops a clone mode to synchronously display the genome coordinate positions or the same regions of multiple samples on the same page of visualization. HiBrowser also supports a pluralistic and precise search on correlation data of distal cis-regulatory elements and navigation to any region on Hi-C heatmap of interest according to the searching results. HiBrowser is a no-build tool, and could be easily deployed in local server. The source code is available at https://github.com/lyotvincent/HiBrowser.

MOTIVATION: Drug repurposing is a potential alternative to the traditional drug discovery process. Drug repurposing can be formulated as a recommender system that recommends novel indications for available drugs based on known drug-disease associations. This article presents a method based on non-negative matrix factorization (NMF-DR) to predict the drug-related candidate disease indications. This work proposes a recommender system-based method for drug repurposing to predict novel drug indications by integrating drug and diseases related data sources. For this purpose, this framework first integrates two types of disease similarities, the associations between drugs and diseases, and the various similarities between drugs from different views to make a heterogeneous drug-disease interaction network. Then, an improved non-negative matrix factorization-based method is proposed to complete the drug-disease adjacency matrix with predicted scores for unknown drug-disease pairs. RESULTS: The comprehensive experimental results show that NMF-DR achieves superior prediction performance when compared with several existing methods for drug-disease association prediction. AVAILABILITY AND IMPLEMENTATION: The program is available at https://github.com/sshaghayeghs/NMF-DR. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The number of triangles (hereafter denoted by$\Delta$) is an important metric to analyze massive graphs. It is also used to compute clustering coefficient in networks. This paper proposes a new algorithm called PES (Priority Edge Sampling) to estimate the number of triangles in the streaming model where we need to minimize the memory window. PES combines edge sampling and reservoir sampling. Compared with the state-of-the-art streaming algorithms, PES outperforms consistently. The results are verified extensively in 48 large real-world networks in different domains and structures. The performance ratio can be as large as 11. More importantly, the ratio grows with data size almost exponentially. This is especially important in the era of big data–while we can tolerate existing algorithms for smaller datasets, our method is indispensable when sampling very large data. In addition to empirical comparisons, we also proved that the estimator is unbiased, and derived the variance.

Learning network representations is essential for many downstream tasks such as node classification, link prediction, and recommendation. Many algorithms derived from SGNS (skip-gram with negative sampling) have been proposed, such as LINE, DeepWalk, and node2vec. In this paper, we show that these algorithms suffer from norm convergence problem, and propose to use L2 regularization to rectify the problem. The proposed method improves the embeddings consistently. This is verified on seven different datasets with various sizes and structures. The best improvement is 46.41% for the task of node classification.

Clustering coefficient (C) is an important structural property to understand the complex structure of a graph. Calculating C is a computationally intensive task. Thereby, sampling-based methods have attracted substantial research for estimating C, and the closely related metric, the number of triangles. Unfortunately, widely used estimators for C are biased. We quantify the bias using Taylor expansion and find that the bias can be determined by the number of shared wedges and triangles in the sample. Based on the understanding of the bias, we give a new estimator that corrects the bias. The results are derived analytically and verified extensively in 56 networks ranging in different size and structure. The experiments reveal that the bias ranges widely from data to data. The relative bias can be as high as 4% or can be negative. For most of the graphs, the bias is small, although every graph does have a bias as quantified by our analytical results. Negative or small biases occur in online social networks where clustering coefficient is typically high. Positive and large biases typically occur in Web graphs, where there are nodes with high degrees but few neighboring nodes connecting with each other.

The number of triangles in a graph is an important metric for understanding the graph. It is also directly related to the clustering coefficient of a graph, which is one of the most important indicator for social networks. Counting the number of triangles is computationally expensive for very large graphs. Hence, estimation is necessary for large graphs, particularly for graphs that are hidden behind searchable interfaces where the graphs in their entirety are not available. For instance, user networks in Twitter and Facebook are not available for third parties to explore their properties directly. This paper proposes a new method to estimate the number of triangles based on random edge sampling. It improves the traditional random edge sampling by probing the edges that have a higher probability of forming triangles. The method outperforms the traditional method consistently, and can be better by orders of magnitude when the graph is very large. The result is demonstrated on 20 graphs, including the largest graphs we can find. More importantly, we proved the improvement ratio, and verified our result on all the datasets. The analytical results are achieved by simplifying the variances of the estimators based on the assumption that the graph is very large. We believe that such big data assumption can lead to interesting results not only in triangle estimation, but also in other sampling problems.

MOTIVATION: Whole genome sequencing (WGS) of parent-offspring trios is a powerful approach for identifying disease-associated genes via detecting copy number variations (CNVs). Existing approaches, which detect CNVs for each individual in a trio independently, usually yield low-detection accuracy. Joint modeling approaches leveraging Mendelian transmission within the parent-offspring trio can be an efficient strategy to improve CNV detection accuracy. RESULTS: In this study, we developed TrioCNV, a novel approach for jointly detecting CNVs in parent-offspring trios from WGS data. Using negative binomial regression, we modeled the read depth signal while considering both GC content bias and mappability bias. Moreover, we incorporated the family relationship and used a hidden Markov model to jointly infer CNVs for three samples of a parent-offspring trio. Through application to both simulated data and a trio from 1000 Genomes Project, we showed that TrioCNV achieved superior performance than existing approaches. AVAILABILITY AND IMPLEMENTATION: The software TrioCNV implemented using a combination of Java and R is freely available from the website at https://github.com/yongzhuang/TrioCNV CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Weibo is the Twitter counterpart in China that has attracted hundreds of millions of users. We crawled an almost complete Weibo user network that contains 222 million users and 27 billion links in 2013. This paper analyzes the structural properties of this network, and compares it with a Twitter user network. The topological properties we studied include the degree distributions, reciprocity, clustering coefficient, PageRank centrality, and degree assortativity. We find that Weibo users have a higher diversity index, higher Gini index, but a lower reciprocity and clustering coefficient for most of the nodes. A surprising observation is that the reciprocity of Weibo is only about a quarter of the reciprocity of the Twitter user network. We also show that Weibo adoption rate correlates with economic development positively, and Weibo network can be used to quantify the connections between provinces and regions in China. In particular, point-wise mutual information is shown to be accurate in quantifying the strength of connections.

The sizes of hidden data sources are of great interests to public, researchers and even business competitors. Estimating the size of hidden data sources has been a challenging problem. Most existing methods are derived from the classic capture-recapture methods. Another approach is based on a large query pool. This method is not accurate due to the large variance of the document frequencies of queries in the query pool. Targeting this problem, we propose a new method to reduce the variance by constructing a query pool from a sample of the target data source so that document frequency variance is reduced, yet most of the documents can be covered. Our method is tested on a variety of large textual corpora, and outperforms the baseline random query method and the Broder et al's estimation method on all the datasets.

The properties of online social networks (OSNs) are of great interests to the general public as well as IT professionals. Often the raw data are not available and the summary released by the service providers are sketchy. Thus sampling is needed to reveal the hidden properties of the underlying data. While uniform random sampling is often preferred, some properties such as the top bloggers need to be obtained using PPS (probability proportional to size) sampling. Although PPS sampling can be approximated using simple random walk, it is not efficient because only one sample is taken in every step. This paper introduces an efficient sampling method, called star sampling, that takes all the neighbours as valid samples. It is more efficient than random walk sampling by a factor of the average degrees. We derive the estimator and its variance, and verify the result using six large real-networks locally where the ground-truth are known and the estimations can be evaluated.

What do large networks look like? Can we visually tell the topological difference between networks such as the Web graph and Facebook network? Due to the huge size of the network, the overall structure will not be discernible if all the nodes and edges are plotted regardless of the graph layout. We reduce the number of nodes and edges by producing a representative subgraph. The nodes are sampled with probability proportional to their degrees, so that large nodes with more connections have a higher probability of being sampled. The edges are reduced further using uniform random spanning tree. The efficacy of the method is demonstrated to preserve the community structure that is characterized by the Network Community Profile (NCP). The result is supported by six real-world large networks, and demonstrated on Twitter user network which contains 4.1 x 107 nodes.

This paper discusses the bias problem when estimating the population size of big data such as online social networks (OSN) using uniform random sampling and simple random walk. Unlike the traditional estimation problem where the sample size is not very small relative to the data size, in big data, a small sample relative to the data size is already very large and costly to obtain. We point out that when small samples are used, there is a bias that is no longer negligible. This paper shows analytically that the relative bias can be approximated by the reciprocal of the number of collisions; thereby, a bias correction estimator is introduced. The result is further supported by both simulation studies and the real Twitter network that contains 41.7 million nodes.

This paper studies the problem of selecting queries to efficiently crawl a deep web data source using a set of sample documents. Crawling deep web is the process of collecting data from search interfaces by issuing queries. One of the major challenge

No abstract available.

Crawling deep web is the process of collecting data from search interfaces by issuing queries. With wide availability of programmable interface encoded in Web services, deep web crawling has received a large variety of applications. One of the major challenges crawling deep web is the selection of the queries so that most of the data can be retrieved at a low cost. We propose a general method in this regard. In order to minimize the duplicates retrieved, we reduced the problem of selecting an optimal set of queries from a sample of the data source into the well-known set-covering problem and adopt a classical algorithm to resolve it. To verify that the queries selected from a sample also produce a good result for the entire data source, we carried out a set of experiments on large corpora including Wikipedia and Reuters. We show that our sampling-based method is effective by empirically proving that 1) The queries selected from samples can harvest most of the data in the original database; 2) The queries with low overlapping rate in samples will also result in a low overlapping rate in the original database; and 3) The size of the sample and the size of the terms from where to select the queries do not need to be very large.

Software metrics are vital for the management of software development, especially when a new technology is being adopted and established practices have yet to emerge. As a kind of software components, Web service technology has flourished and attracted a flurry of research activities. Despite the vast amount of research on mechanisms of Web services, there have been little investigations of the overall nature of existing Web services from a software component point of view. This paper is the first attempt to compare Web services with other software components in terms of established metrics in software engineering, including object oriented metrics and interface metrics. In this study we conclude that there are statistical differences between the interface, variable name and other OO metrics when one compares a large sample of Web services with typical OO systems. The distributions obtained give insight into the typical characteristics of Web services and can be used to identify candidates for wrapping into Web services.

XML Schema matching problem can be formulated as follows: given two XML Schemas, find the best mapping between the elements and attributes of the schemas, and the overall similarity between them. XML Schema matching is an important problem in data integration, schema evolution, and software reuse. This paper describes a matching system that can find accurate matches and scales to large XML Schemas with hundreds of nodes. In our system, XML Schemas are modeled as labeled and unordered trees, and the schema matching problem is turned into a tree matching problem. We proposed Approximate Common Structures in trees, and developed a tree matching algorithm based on this concept. Compared with the traditional tree edit-distance algorithm and other schema matching systems, our algorithm is faster and more suitable for large XML Schema matching.

In name and in practice, the World-Wide Web (hereafter Web) is used around the World beyond English-speaking areas. This creates a tremendous need to internationalize standard terminology used in the technologies that make the Web possible. Existing efforts on XML internationalization (i18n) and localization (i10n) have focused on the content of XML documents instead of the terms used in markup (annotations) such as elements and attributes. The SGML standard ISO 8879 supports the use of Unicode (ISO 10646) throughout a document, including markups. However, most elements and attributes of XML documents are still defined in English, thereby limiting their use among non-English speakers. This paper presents an XSLT-based method that can completely localize the markup of XML documents into different natural languages. We also describe how the proposed technique can be applied to translation problems in programming (e.g. C and Java) or documentation (e.g. LATEX or other formatting languages) so that a program or a document can be converted to and from an XML format. Copyright © 2004 John Wiley & Sons, Ltd.

Enterprise JavaBean (hereafter EJB) technology has been widely adopted in software industry to develop Web information systems. However, most of EJB applications are reengineered from legacy database applications. This means that legacy SQL statements need to be translated into EJB client code. Since many methods in Enterprise Beans can be regarded as view definitions of the underlying database, the EJB client code generation can be mapped to the problem of query rewriting using views. This paper addresses the automatic generation of EJB client code using query rewriting.

Summary form only given. The Enterprise JavaBeans (EJB) architecture has become the norm in software application development, especially in the large, multi-tier, e-commerce environment. This is a report based on the IBM/spl reg/ WebSphere/spl reg/ Commerce Suite product, which provides a complete set of tools and interfaces to develop large-scale e-commerce systems and solutions. We share the experience of moving its e-commerce database applications over to an EJB environment. This project discusses the problems and issues encountered in the re-engineering of traditional database access applications (SQL) to the EJB programming model.