Kyle Kloster
Research Subjects
Kyle Kloster has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Blair D. Sullivan
University of Utah, Salt Lake City, Utah, USA
5 shared publications - Casey Stephen. Greene
Department of Biomedical Informatics, University of Colorado Anschutz, Aurora, CO, USA
4 shared publications - Daniel Scott Himmelstein
Department of Systems Pharmacology and Translational Therapeutics, University of Pennsylvania , Philadelphia, PA 19104
4 shared publications - Michael W. Nagle
Pfizer Worldwide Research & Development, 1 Portland St, Cambridge, MA, USA
4 shared publications - Michael Zietz
Department of Computational Biomedicine, Cedars-Sinai Medical Center, West Hollywood, USA
4 shared publications - Benjamin J. Heil
Genomics and Computational Biology Graduate Group, Perelman School of Medicine, University of Pennsylvania · Funded by The Gordon and Betty Moore Foundation (GBMF4552)
2 shared publications
Latest Publications
- Open Access
- 2 January 2024
- Published by Oxford University Press (OUP) in GigaScience
- Vol. 13
The probability of edge existence due to node degree: a baseline for network-based predictions
Important tasks in biomedical discovery such as predicting gene functions, gene–disease associations, and drug repurposing opportunities are often framed as network edge prediction. The number of edges connecting to a node, termed degree, can vary greatly across nodes in real biomedical networks, and the distribution of degrees varies between networks. If degree strongly influences edge prediction, then imbalance or bias in the distribution of degrees could lead to nonspecific or misleading predictions. We introduce a network permutation framework to quantify the effects of node degree on edge prediction. Our framework decomposes performance into the proportions attributable to degree and the network’s specific connections using network permutation to generate features that depend only on degree. We discover that performance attributable to factors other than degree is often only a small portion of overall performance. Researchers seeking to predict new or missing edges in biological networks should use our permutation approach to obtain a baseline for performance that may be nonspecific because of degree. We released our methods as an open-source Python package (https://github.com/hetio/xswap/).
- 2 January 2024
- Published by Oxford University Press (OUP) in GigaScience
- Vol. 13
Open AccessThe probability of edge existence due to node degree: a baseline for network-based predictions
Important tasks in biomedical discovery such as predicting gene functions, gene–disease associations, and drug repurposing opportunities are often framed as network edge prediction. The number of edges connecting to a node, termed degree, can vary greatly across nodes in real biomedical networks, and the distribution of degrees varies between networks. If degree strongly influences edge prediction, then imbalance or bias in the distribution of degrees could lead to nonspecific or misleading predictions. We introduce a network permutation framework to quantify the effects of node degree on edge prediction. Our framework decomposes performance into the proportions attributable to degree and the network’s specific connections using network permutation to generate features that depend only on degree. We discover that performance attributable to factors other than degree is often only a small portion of overall performance. Researchers seeking to predict new or missing edges in biological networks should use our permutation approach to obtain a baseline for performance that may be nonspecific because of degree. We released our methods as an open-source Python package (https://github.com/hetio/xswap/).
- Open Access
Hetnet connectivity search provides rapid insights into how two biomedical entities are related
Hetnets, short for “heterogeneous networks”, contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet connects 11 types of nodes — including genes, diseases, drugs, pathways, and anatomical structures — with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious not only how metformin is related to breast cancer, but also how the GJA1 gene might be involved in insomnia. We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any two nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). We find that predictions are broadly similar to those from previously described supervised approaches for certain node type pairs. Scoring of individual paths is based on the most specific paths of a given type. Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. We implemented the method on Hetionet and provide an online interface at https://het.io/search . We provide an open source implementation of these methods in our new Python package named hetmatpy .
Open AccessHetnet connectivity search provides rapid insights into how two biomedical entities are related
Hetnets, short for “heterogeneous networks”, contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet connects 11 types of nodes — including genes, diseases, drugs, pathways, and anatomical structures — with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious not only how metformin is related to breast cancer, but also how the GJA1 gene might be involved in insomnia. We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any two nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). We find that predictions are broadly similar to those from previously described supervised approaches for certain node type pairs. Scoring of individual paths is based on the most specific paths of a given type. Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. We implemented the method on Hetionet and provide an online interface at https://het.io/search . We provide an open source implementation of these methods in our new Python package named hetmatpy .
- Open Access
The probability of edge existence due to node degree: a baseline for network-based predictions
Important tasks in biomedical discovery such as predicting gene functions, gene-disease associations, and drug repurposing opportunities are often framed as network edge prediction. The number of edges connecting to a node, termed degree, can vary greatly across nodes in real biomedical networks, and the distribution of degrees varies between networks. If degree strongly influences edge prediction, then imbalance or bias in the distribution of degrees could lead to nonspecific or misleading predictions. We introduce a network permutation framework to quantify the effects of node degree on edge prediction. Our framework decomposes performance into the proportions attributable to degree and the network’s specific connections. We discover that performance attributable to factors other than degree is often only a small portion of overall performance. Degree’s predictive performance diminishes when the networks used for training and testing—despite measuring the same biological relationships—were generated using distinct techniques and hence have large differences in degree distribution. We introduce the permutation-derived edge prior as the probability that an edge exists based only on degree. The edge prior shows excellent discrimination and calibration for 20 biomedical networks (16 bipartite, 3 undirected, 1 directed), with AUROCs frequently exceeding 0.85. Researchers seeking to predict new or missing edges in biological networks should use the edge prior as a baseline to identify the fraction of performance that is nonspecific because of degree. We released our methods as an open-source Python package ( https://github.com/hetio/xswap/ ).
Open AccessThe probability of edge existence due to node degree: a baseline for network-based predictions
Important tasks in biomedical discovery such as predicting gene functions, gene-disease associations, and drug repurposing opportunities are often framed as network edge prediction. The number of edges connecting to a node, termed degree, can vary greatly across nodes in real biomedical networks, and the distribution of degrees varies between networks. If degree strongly influences edge prediction, then imbalance or bias in the distribution of degrees could lead to nonspecific or misleading predictions. We introduce a network permutation framework to quantify the effects of node degree on edge prediction. Our framework decomposes performance into the proportions attributable to degree and the network’s specific connections. We discover that performance attributable to factors other than degree is often only a small portion of overall performance. Degree’s predictive performance diminishes when the networks used for training and testing—despite measuring the same biological relationships—were generated using distinct techniques and hence have large differences in degree distribution. We introduce the permutation-derived edge prior as the probability that an edge exists based only on degree. The edge prior shows excellent discrimination and calibration for 20 biomedical networks (16 bipartite, 3 undirected, 1 directed), with AUROCs frequently exceeding 0.85. Researchers seeking to predict new or missing edges in biological networks should use the edge prior as a baseline to identify the fraction of performance that is nonspecific because of degree. We released our methods as an open-source Python package ( https://github.com/hetio/xswap/ ).
- Open Access
- 28 December 2022
- Published by Oxford University Press (OUP) in GigaScience
- Vol. 12
Hetnet connectivity search provides rapid insights into how biomedical entities are related
Hetnets, short for “heterogeneous networks,” contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet, connects 11 types of nodes—including genes, diseases, drugs, pathways, and anatomical structures—with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious about not only how metformin is related to breast cancer but also how a given gene might be involved in insomnia. We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any 2 nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. We implemented the method on Hetionet and provide an online interface at https://het.io/search. We provide an open-source implementation of these methods in our new Python package named hetmatpy.
- 28 December 2022
- Published by Oxford University Press (OUP) in GigaScience
- Vol. 12
Open AccessHetnet connectivity search provides rapid insights into how biomedical entities are related
Hetnets, short for “heterogeneous networks,” contain multiple node and relationship types and offer a way to encode biomedical knowledge. One such example, Hetionet, connects 11 types of nodes—including genes, diseases, drugs, pathways, and anatomical structures—with over 2 million edges of 24 types. Previous work has demonstrated that supervised machine learning methods applied to such networks can identify drug repurposing opportunities. However, a training set of known relationships does not exist for many types of node pairs, even when it would be useful to examine how nodes of those types are meaningfully connected. For example, users may be curious about not only how metformin is related to breast cancer but also how a given gene might be involved in insomnia. We developed a new procedure, termed hetnet connectivity search, that proposes important paths between any 2 nodes without requiring a supervised gold standard. The algorithm behind connectivity search identifies types of paths that occur more frequently than would be expected by chance (based on node degree alone). Several optimizations were required to precompute significant instances of node connectivity at the scale of large knowledge graphs. We implemented the method on Hetionet and provide an online interface at https://het.io/search. We provide an open-source implementation of these methods in our new Python package named hetmatpy.
- 1 June 2019
- Published by Elsevier in Linear Algebra and its Applications
- Vol. 570, 225-244
Subgraph centrality and walk-regularity
- 1 June 2019
- Published by Elsevier in Linear Algebra and its Applications
- Vol. 570, 225-244
Subgraph centrality and walk-regularity
- Open Access
Structural Rounding: Approximation Algorithms for Graphs Near an Algorithmically Tractable Class
We develop a new framework for generalizing approximation algorithms from the structural graph algorithm literature so that they apply to graphs somewhat close to that class (a scenario we expect is common when working with real-world networks) while still guaranteeing approximation ratios. The idea is to $\textit{edit}$ a given graph via vertex- or edge-deletions to put the graph into an algorithmically tractable class, apply known approximation algorithms for that class, and then $\textit{lift}$ the solution to apply to the original graph. We give a general characterization of when an optimization problem is amenable to this approach, and show that it includes many well-studied graph problems, such as Independent Set, Vertex Cover, Feedback Vertex Set, Minimum Maximal Matching, Chromatic Number, ($\ell$-)Dominating Set, Edge ($\ell$-)Dominating Set, and Connected Dominating Set. To enable this framework, we develop new editing algorithms that find the approximately-fewest edits required to bring a given graph into one of several important graph classes (in some cases, also approximating the target parameter of the family). For bounded degeneracy, we obtain a bicriteria $(4,4)$-approximation which also extends to a smoother bicriteria trade-off. For bounded treewidth, we obtain a bicriteria $(O(\log^{1.5} n), O(\sqrt{\log w}))$-approximation, and for bounded pathwidth, we obtain a bicriteria $(O(\log^{1.5} n), O(\sqrt{\log w} \cdot \log n))$-approximation. For treedepth $2$ (also related to bounded expansion), we obtain a $4$-approximation. We also prove complementary hardness-of-approximation results assuming $\mathrm{P} \neq \mathrm{NP}$: in particular, these problems are all log-factor inapproximable, except the last which is not approximable below some constant factor ($2$ assuming UGC).Open AccessStructural Rounding: Approximation Algorithms for Graphs Near an Algorithmically Tractable Class
We develop a new framework for generalizing approximation algorithms from the structural graph algorithm literature so that they apply to graphs somewhat close to that class (a scenario we expect is common when working with real-world networks) while still guaranteeing approximation ratios. The idea is to $\textit{edit}$ a given graph via vertex- or edge-deletions to put the graph into an algorithmically tractable class, apply known approximation algorithms for that class, and then $\textit{lift}$ the solution to apply to the original graph. We give a general characterization of when an optimization problem is amenable to this approach, and show that it includes many well-studied graph problems, such as Independent Set, Vertex Cover, Feedback Vertex Set, Minimum Maximal Matching, Chromatic Number, ($\ell$-)Dominating Set, Edge ($\ell$-)Dominating Set, and Connected Dominating Set. To enable this framework, we develop new editing algorithms that find the approximately-fewest edits required to bring a given graph into one of several important graph classes (in some cases, also approximating the target parameter of the family). For bounded degeneracy, we obtain a bicriteria $(4,4)$-approximation which also extends to a smoother bicriteria trade-off. For bounded treewidth, we obtain a bicriteria $(O(\log^{1.5} n), O(\sqrt{\log w}))$-approximation, and for bounded pathwidth, we obtain a bicriteria $(O(\log^{1.5} n), O(\sqrt{\log w} \cdot \log n))$-approximation. For treedepth $2$ (also related to bounded expansion), we obtain a $4$-approximation. We also prove complementary hardness-of-approximation results assuming $\mathrm{P} \neq \mathrm{NP}$: in particular, these problems are all log-factor inapproximable, except the last which is not approximable below some constant factor ($2$ assuming UGC). - 1 June 2018
- Published by Elsevier in Linear Algebra and its Applications
- Vol. 546, 115-121
Walk entropy and walk-regularity
- 1 June 2018
- Published by Elsevier in Linear Algebra and its Applications
- Vol. 546, 115-121
Walk entropy and walk-regularity
- Open Access
Scalable and Robust Local Community Detection via Adaptive Subgraph Extraction and Diffusions
Local community detection, the problem of identifying a set of relevant nodes nearby a small set of input seed nodes, is an important graph primitive with a wealth of applications and research activity. Recent approaches include using local spectral information, graph diffusions, and random walks to determine a community from input seeds. As networks grow to billions of nodes and exhibit diverse structures, it is important that community detection algorithms are not only efficient, but also robust to different structural features. Toward this goal, we explore pre-processing techniques and modifications to existing local methods aimed at improving the scalability and robustness of algorithms related to community detection. Experiments show that our modifications improve both speed and quality of existing methods for locating ground truth communities, and are more robust across graphs and communities of varying sizes, densities, and diameters. Our subgraph extraction method uses adaptively selected PageRank parameters to improve on the recall and runtime of a walk-based pre-processing technique of Li et al. for extracting subgraphs before searching for a community. We then use this technique to enable the first scalable implementation of the recent Local Fiedler method of Mahoney et al. Our experimental evaluation shows our pre-processed version of Local Fiedler, as well as our novel simplification of the LEMON community detection framework of Li et al., offer significant speedups over their predecessors and obtain cluster quality competitive with the state of the art.
Open AccessScalable and Robust Local Community Detection via Adaptive Subgraph Extraction and Diffusions
Local community detection, the problem of identifying a set of relevant nodes nearby a small set of input seed nodes, is an important graph primitive with a wealth of applications and research activity. Recent approaches include using local spectral information, graph diffusions, and random walks to determine a community from input seeds. As networks grow to billions of nodes and exhibit diverse structures, it is important that community detection algorithms are not only efficient, but also robust to different structural features. Toward this goal, we explore pre-processing techniques and modifications to existing local methods aimed at improving the scalability and robustness of algorithms related to community detection. Experiments show that our modifications improve both speed and quality of existing methods for locating ground truth communities, and are more robust across graphs and communities of varying sizes, densities, and diameters. Our subgraph extraction method uses adaptively selected PageRank parameters to improve on the recall and runtime of a walk-based pre-processing technique of Li et al. for extracting subgraphs before searching for a community. We then use this technique to enable the first scalable implementation of the recent Local Fiedler method of Mahoney et al. Our experimental evaluation shows our pre-processed version of Local Fiedler, as well as our novel simplification of the LEMON community detection framework of Li et al., offer significant speedups over their predecessors and obtain cluster quality competitive with the state of the art.