Automated optimized parameters for T-distributed stochastic neighbor embedding improve visualization and analysis of large datasets

AbstractAccurate and comprehensive extraction of information from high-dimensional single cell datasets necessitates faithful visualizations to assess biological populations. A state-of-the-art algorithm for non-linear dimension reduction, t-SNE, requires multiple heuristics and fails to produce clear representations of datasets when millions of cells are projected. We develop opt-SNE, an automated toolkit for t-SNE parameter selection that utilizes Kullback-Leibler divergence evaluation in real time to tailor the early exaggeration and overall number of gradient descent iterations in a dataset-specific manner. The precise calibration of early exaggeration together with opt-SNE adjustment of gradient descent learning rate dramatically improves computation time and enables high-quality visualization of large cytometry and transcriptomics datasets, overcoming limitations of analysis tools with hard-coded parameters that often produce poorly resolved or misleading maps of fluorescent and mass cytometry data. In summary, opt-SNE enables superior data resolution in t-SNE space and thereby more accurate data interpretation.

Download Full-text

Automated optimized parameters for t-distributed stochastic neighbor embedding improve visualization and allow analysis of large datasets

10.1101/451690 ◽

2018 ◽

Cited By ~ 5

Author(s):

Anna C. Belkina ◽

Christopher O. Ciccolella ◽

Rina Anno ◽

Richard Halpert ◽

Josef Spidlen ◽

...

Keyword(s):

Gradient Descent ◽

Linear Dimension ◽

State Of The Art ◽

Computation Time ◽

Data Interpretation ◽

Large Datasets ◽

High Dimensional ◽

Mass Cytometry ◽

Data Resolution ◽

Specific Manner

Accurate and comprehensive extraction of information from high-dimensional single cell datasets necessitates faithful visualizations to assess biological populations. A state-of-the-art algorithm for non-linear dimension reduction, t-SNE, requires multiple heuristics and fails to produce clear representations of datasets when millions of cells are projected. We developed opt-SNE, an automated toolkit for t-SNE parameter selection that utilizes Kullback-Liebler divergence evaluation in real time to tailor the early exaggeration and overall number of gradient descent iterations in a dataset-specific manner. The precise calibration of early exaggeration together with opt-SNE adjustment of gradient descent learning rate dramatically improves computation time and enables high-quality visualization of large cytometry and transcriptomics datasets, overcoming limitations of analysis tools with hard-coded parameters that often produce poorly resolved or misleading maps of fluorescent and mass cytometry data. In summary, opt-SNE enables superior data resolution in t-SNE space and thereby more accurate data interpretation.

Download Full-text

Enhanced Supervised Principal Component Analysis for Cancer Classification

Iraqi Journal of Science ◽

10.24996/ijs.2021.62.4.28 ◽

2021 ◽

pp. 1321-1333

Author(s):

Ghadeer JM Mahdi ◽

Bayda A. Kalaf ◽

Mundher A. Khaleel

Keyword(s):

Principal Component Analysis ◽

Gradient Descent ◽

Dimensional Space ◽

Principal Component ◽

Component Analysis ◽

Large Datasets ◽

Stochastic Gradient Descent ◽

High Dimensional ◽

Excellent Method ◽

Blue Cell

In this paper, a new hybridization of supervised principal component analysis (SPCA) and stochastic gradient descent techniques is proposed, and called as SGD-SPCA, for real large datasets that have a small number of samples in high dimensional space. SGD-SPCA is proposed to become an important tool that can be used to diagnose and treat cancer accurately. When we have large datasets that require many parameters, SGD-SPCA is an excellent method, and it can easily update the parameters when a new observation shows up. Two cancer datasets are used, the first is for Leukemia and the second is for small round blue cell tumors. Also, simulation datasets are used to compare principal component analysis (PCA), SPCA, and SGD-SPCA. The results show that SGD-SPCA is more efficient than other existing methods.

Download Full-text

Urdu Handwritten Characters Data Visualization and Recognition Using Distributed Stochastic Neighborhood Embedding and Deep Network

Complexity ◽

10.1155/2021/4383037 ◽

2021 ◽

Vol 2021 ◽

pp. 1-15

Author(s):

Mujtaba Husnain ◽

Malik Muhammad Saad Missen ◽

Shahzad Mumtaz ◽

Dost Muhammad Khan ◽

Mickäel Coustaty ◽

...

Keyword(s):

Data Visualization ◽

State Of The Art ◽

Computation Time ◽

Principal Component ◽

Multidimensional Data ◽

High Dimensional ◽

Deep Network ◽

Reduced Dimensions ◽

Handwritten Text ◽

First Time

In this paper, we make use of the 2-dimensional data obtained through t-Stochastic Neighborhood Embedding (t-SNE) when applied on high-dimensional data of Urdu handwritten characters and numerals. The instances of the dataset used for experimental work are classified in multiple classes depending on the shape similarity. We performed three tasks in a disciplined order; namely, (i) we generated a state-of-the-art dataset of both the Urdu handwritten characters and numerals by inviting a number of native Urdu participants from different social and academic groups, since there is no publicly available dataset of such type till date, then (ii) applied classical approaches of dimensionality reduction and data visualization like Principal Component Analysis (PCA), Autoencoders (AE) in comparison with t-Stochastic Neighborhood Embedding (t-SNE), and (iii) used the reduced dimensions obtained through PCA, AE, and t-SNE for recognition of Urdu handwritten characters and numerals using a deep network like Convolution Neural Network (CNN). The accuracy achieved in recognition of Urdu characters and numerals among the approaches for the same task is found to be much better. The novelty lies in the fact that the resulting reduced dimensions are used for the first time for the recognition of Urdu handwritten text at the character level instead of using the whole multidimensional data. This results in consuming less computation time with the same accuracy when compared with processing time consumed by recognition approaches applied to other datasets for the same task using the whole data.

Download Full-text

Evaluating Top-k Skyline Queries Efficiently

Advanced Database Query Systems - Advances in Data Mining and Database Management ◽

10.4018/978-1-60960-475-2.ch004 ◽

2011 ◽

pp. 102-117

Author(s):

Marlene Goncalves ◽

María Esther Vidal

Keyword(s):

State Of The Art ◽

Search Space ◽

Large Datasets ◽

The State ◽

Experimental Results ◽

High Dimensional ◽

Skyline Queries ◽

Speed Up

Criteria that induce a Skyline naturally represent user’s preference conditions useful to discard irrelevant data in large datasets. However, in the presence of high-dimensional Skyline spaces, the size of the Skyline can still be very large. To identify the best k points among the Skyline, the Top-k Skyline approach has been proposed. This chapter describes existing solutions and proposes to use the TKSI algorithm for the Top-k Skyline problem. TKSI reduces the search space by computing only a subset of the Skyline that is required to produce the top-k objects. In addition, the Skyline Frequency Metric is implemented to discriminate among the Skyline objects those that best meet the multidimensional criteria. This chapter’s authors have empirically studied the quality of TKSI, and their experimental results show the TKSI may be able to speed up the computation of the Top-k Skyline in at least 50% percent with regard to the state-of-the-art solutions.

Download Full-text

KMD clustering: Robust generic clustering of biological data

10.1101/2020.10.04.325233 ◽

2020 ◽

Author(s):

Aviv Zelig ◽

Noam Kaplan

Keyword(s):

State Of The Art ◽

Clustering Algorithms ◽

Added Mass ◽

Biological Data ◽

High Dimensional ◽

Mass Cytometry ◽

Average Linkage ◽

Simple Generalization ◽

Clustering Approach ◽

Post Hoc

AbstractThe challenges of clustering noisy high-dimensional biological data have spawned advanced clustering algorithms that are tailored for specific subtypes of biological datatypes. However, the performance of such methods varies greatly between datasets, they require post hoc tuning of cryptic hyperparameters, and they are often not transferable to other types of data. Here we present a novel generic clustering approach called k minimal distances (KMD) clustering, based on a simple generalization of single and average linkage hierarchical clustering. We show how a generalized silhouette-like function is predictive of clustering accuracy and exploit this property to eliminate the main hyperparameter k. We evaluated KMD clustering on standard simulated datasets, simulated datasets with high noise added, mass cytometry datasets and scRNA-seq datasets. When compared to standard generic and state-of-the-art specialized algorithms, KMD clustering’s performance was consistently better or comparable to that of the best algorithm on each of the tested datasets.

Download Full-text

Review of the Applications of Deep Learning in Bioinformatics

Current Bioinformatics ◽

10.2174/1574893615999200711165743 ◽

2021 ◽

Vol 15 (8) ◽

pp. 898-911

Author(s):

Yongqing Zhang ◽

Jianrong Yan ◽

Siyu Chen ◽

Meiqin Gong ◽

Dongrui Gao ◽

...

Keyword(s):

Deep Learning ◽

Drug Discovery ◽

Biomedical Imaging ◽

State Of The Art ◽

Black Box ◽

Medical Data ◽

Biological Data ◽

High Dimensional ◽

Biological Research ◽

Process Data

Rapid advances in biological research over recent years have significantly enriched biological and medical data resources. Deep learning-based techniques have been successfully utilized to process data in this field, and they have exhibited state-of-the-art performances even on high-dimensional, nonstructural, and black-box biological data. The aim of the current study is to provide an overview of the deep learning-based techniques used in biology and medicine and their state-of-the-art applications. In particular, we introduce the fundamentals of deep learning and then review the success of applying such methods to bioinformatics, biomedical imaging, biomedicine, and drug discovery. We also discuss the challenges and limitations of this field, and outline possible directions for further research.

Download Full-text

An All-Batch Loss for Constructing Prediction Intervals

Applied Sciences ◽

10.3390/app11041728 ◽

2021 ◽

Vol 11 (4) ◽

pp. 1728

Author(s):

Hua Zhong ◽

Li Xu

Keyword(s):

Gradient Descent ◽

State Of The Art ◽

Prediction Interval ◽

Feedforward Neural Networks ◽

Important Research ◽

Likelihood Principle ◽

High Quality ◽

Construction Methods ◽

Important Research Topic ◽

Benchmark Datasets

The prediction interval (PI) is an important research topic in reliability analyses and decision support systems. Data size and computation costs are two of the issues which may hamper the construction of PIs. This paper proposes an all-batch (AB) loss function for constructing high quality PIs. Taking the full advantage of the likelihood principle, the proposed loss makes it possible to train PI generation models using the gradient descent (GD) method for both small and large batches of samples. With the structure of dual feedforward neural networks (FNNs), a high-quality PI generation framework is introduced, which can be adapted to a variety of problems including regression analysis. Numerical experiments were conducted on the benchmark datasets; the results show that higher-quality PIs were achieved using the proposed scheme. Its reliability and stability were also verified in comparison with various state-of-the-art PI construction methods.

Download Full-text

Efficient Rank-Based Diffusion Process with Assured Convergence

Journal of Imaging ◽

10.3390/jimaging7030049 ◽

2021 ◽

Vol 7 (3) ◽

pp. 49

Author(s):

Daniel Carlos Guimarães Pedronette ◽

Lucas Pascotti Valem ◽

Longin Jan Latecki

Keyword(s):

Diffusion Process ◽

Learning Strategies ◽

State Of The Art ◽

Representation Learning ◽

Theoretical Background ◽

High Dimensional ◽

Visual Features ◽

Learning Approaches ◽

Previous Decade ◽

Asymptotic Complexity

Visual features and representation learning strategies experienced huge advances in the previous decade, mainly supported by deep learning approaches. However, retrieval tasks are still performed mainly based on traditional pairwise dissimilarity measures, while the learned representations lie on high dimensional manifolds. With the aim of going beyond pairwise analysis, post-processing methods have been proposed to replace pairwise measures by globally defined measures, capable of analyzing collections in terms of the underlying data manifold. The most representative approaches are diffusion and ranked-based methods. While the diffusion approaches can be computationally expensive, the rank-based methods lack theoretical background. In this paper, we propose an efficient Rank-based Diffusion Process which combines both approaches and avoids the drawbacks of each one. The obtained method is capable of efficiently approximating a diffusion process by exploiting rank-based information, while assuring its convergence. The algorithm exhibits very low asymptotic complexity and can be computed regionally, being suitable to outside of dataset queries. An experimental evaluation conducted for image retrieval and person re-ID tasks on diverse datasets demonstrates the effectiveness of the proposed approach with results comparable to the state-of-the-art.

Download Full-text

Efficient Directed Densest Subgraph Discovery

ACM SIGMOD Record ◽

10.1145/3471485.3471494 ◽

2021 ◽

Vol 50 (1) ◽

pp. 33-40

Author(s):

Chenhao Ma ◽

Yixiang Fang ◽

Reynold Cheng ◽

Laks V.S. Lakshmanan ◽

Wenjie Zhang ◽

...

Keyword(s):

Approximation Algorithms ◽

State Of The Art ◽

Exact Algorithms ◽

Large Datasets ◽

Dense Subgraph ◽

Extensive Evaluation ◽

Wide Range ◽

Edge Graph ◽

Community Mining ◽

Densest Subgraph

Given a directed graph G, the directed densest subgraph (DDS) problem refers to the finding of a subgraph from G, whose density is the highest among all the subgraphs of G. The DDS problem is fundamental to a wide range of applications, such as fraud detection, community mining, and graph compression. However, existing DDS solutions suffer from efficiency and scalability problems: on a threethousand- edge graph, it takes three days for one of the best exact algorithms to complete. In this paper, we develop an efficient and scalable DDS solution. We introduce the notion of [x, y]-core, which is a dense subgraph for G, and show that the densest subgraph can be accurately located through the [x, y]-core with theoretical guarantees. Based on the [x, y]-core, we develop both exact and approximation algorithms. We have performed an extensive evaluation of our approaches on eight real large datasets. The results show that our proposed solutions are up to six orders of magnitude faster than the state-of-the-art.

Download Full-text