Steven Sam Lumetta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Steven Sam Lumetta has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Deming Chen
University of Illinois Urbana-Champaign, Urbana, IL, USA
2 shared publications - Anand Ramachandran
University of Illinois at Urbana-Champaign
1 shared publication Angela L. Chiu
AT&T Labs¿Research, Middletown, NY, USA
1 shared publication- Eric W. Klee
Center for Individualized Medicine Mayo Clinic Rochester Minnesota USA
1 shared publication - Jong Bin Lim
Electrical and Computer Engineering, University of Illinois at urbana-Champaign, Urbana, Illinois United States
1 shared publication Mohamed Aly
Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, Illinois United States
1 shared publication
Latest Publications
- Open Access
HELLO: A hybrid variant calling approach
Next Generation Sequencing (NGS) technologies that cost-effectively characterize genomic regions and identify sequence variations using short reads are the current standard for genome sequencing. However, calling small indels in low-complexity regions of the genome using NGS is challenging. Recent advances in Third Generation Sequencing (TGS) provide long reads, which call large-structural variants accurately. However, these reads have context-dependent indel errors in low-complexity regions, resulting in lower accuracy of small indel calls compared to NGS reads. When both small and large-structural variants need to be called, both NGS and TGS reads may be available. Integration of the two data types with unique error profiles could improve robustness of small variant calling in challenging cases. However, there isn’t currently such a method integrating both types of data. We present a novel method that integrates NGS and TGS reads to call small variants. We leverage the Mixture of Experts paradigm which uses an ensemble of Deep Neural Networks (DNN), each processing a different data type to make predictions. We present improvements in our DNN design compared to previous work such as sequence processing using one-dimensional convolutions instead of image processing using two-dimensional convolutions and an algorithm to efficiently process sites with many variant candidates, which help us reduce computations. Using our method to integrate Illumina and PacBio reads, we find a reduction in the number of erroneous small variant calls of up to ~30%, compared to the state-of-the-art using only Illumina data. We also find improvements in calling small indels in low-complexity regions.
Open AccessHELLO: A hybrid variant calling approach
Next Generation Sequencing (NGS) technologies that cost-effectively characterize genomic regions and identify sequence variations using short reads are the current standard for genome sequencing. However, calling small indels in low-complexity regions of the genome using NGS is challenging. Recent advances in Third Generation Sequencing (TGS) provide long reads, which call large-structural variants accurately. However, these reads have context-dependent indel errors in low-complexity regions, resulting in lower accuracy of small indel calls compared to NGS reads. When both small and large-structural variants need to be called, both NGS and TGS reads may be available. Integration of the two data types with unique error profiles could improve robustness of small variant calling in challenging cases. However, there isn’t currently such a method integrating both types of data. We present a novel method that integrates NGS and TGS reads to call small variants. We leverage the Mixture of Experts paradigm which uses an ensemble of Deep Neural Networks (DNN), each processing a different data type to make predictions. We present improvements in our DNN design compared to previous work such as sequence processing using one-dimensional convolutions instead of image processing using two-dimensional convolutions and an algorithm to efficiently process sites with many variant candidates, which help us reduce computations. Using our method to integrate Illumina and PacBio reads, we find a reduction in the number of erroneous small variant calls of up to ~30%, compared to the state-of-the-art using only Illumina data. We also find improvements in calling small indels in low-complexity regions.
- 12 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 68 (3) , 331-346
ASAP: Accelerated Short-Read Alignment on Programmable Hardware
The proliferation of high-throughput sequencing machines ensures rapid generation of up to billions of short nucleotide fragments in a short period of time. This massive amount of sequence data can quickly overwhelm today's storage and compute infrastructure. This paper explores the use of hardware acceleration to significantly improve the runtime of short-read alignment, a crucial step in preprocessing sequenced genomes. We focus on the Levenshtein distance (edit-distance) computation kernel and propose the ASAP accelerator, which utilizes the intrinsic delay of circuits for edit-distance computation elements as a proxy for computation. Our design is implemented on an Xilinx Virtex 7 FPGA in an IBM POWER8 system that uses the CAPI interface for cache coherence across the CPU and FPGA. Our design is 200x faster than an equivalent Smith-Waterman-C implementation of the kernel running on the host processor, 40-60x faster than an equivalent Landau-Vishkin-C++ implementation of the kernel running on the IBM Power8 host processor, and 2x faster for an end-to-end alignment tool for 120--150 base-pair short-read sequences. Further the design represents a 3760x improvement over the CPU in performance/Watt terms.
- 12 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 68 (3) , 331-346
ASAP: Accelerated Short-Read Alignment on Programmable Hardware
The proliferation of high-throughput sequencing machines ensures rapid generation of up to billions of short nucleotide fragments in a short period of time. This massive amount of sequence data can quickly overwhelm today's storage and compute infrastructure. This paper explores the use of hardware acceleration to significantly improve the runtime of short-read alignment, a crucial step in preprocessing sequenced genomes. We focus on the Levenshtein distance (edit-distance) computation kernel and propose the ASAP accelerator, which utilizes the intrinsic delay of circuits for edit-distance computation elements as a proxy for computation. Our design is implemented on an Xilinx Virtex 7 FPGA in an IBM POWER8 system that uses the CAPI interface for cache coherence across the CPU and FPGA. Our design is 200x faster than an equivalent Smith-Waterman-C implementation of the kernel running on the host processor, 40-60x faster than an equivalent Landau-Vishkin-C++ implementation of the kernel running on the IBM Power8 host processor, and 2x faster for an end-to-end alignment tool for 120--150 base-pair short-read sequences. Further the design represents a 3760x improvement over the CPU in performance/Watt terms.
- 24 January 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Journal of Lightwave Technology
- Vol. 29 (5) , 756-769
Optimal Resource Provisioning for Dynamic Wavelength Services With Access Port Constraints
With increasing demands for dynamic high data-rate private line services from large customers, network carriers have begun to provide flexible on-demand connections to construct these customers' networks. Advances in optical devices have greatly improved the reconfigurability of the optical layer, which makes it possible to provide optical on-demand services at wavelength granularity (10 Gbps to 40 Gbps per channel). This new dynamic wavelength service model allows a customer owning or leasing a few terminal ports in the network to connect these ports on demand. The network must be pre-dimensioned with enough resources to support any possible connection configuration between the pre allocated ports of a dynamic wavelength customer. In this paper, we introduce a resource optimization problem for dynamic wave length services and propose a few efficient techniques to tackle this challenging problem. A heuristic optimizer based on a combination of simulated annealing and genetic algorithms is developed to solve the problem efficiently for large networks. We show that our solver can produce optimization solutions within 7% overhead of a lower bound with a small amount of computation.
- 24 January 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Journal of Lightwave Technology
- Vol. 29 (5) , 756-769
Optimal Resource Provisioning for Dynamic Wavelength Services With Access Port Constraints
With increasing demands for dynamic high data-rate private line services from large customers, network carriers have begun to provide flexible on-demand connections to construct these customers' networks. Advances in optical devices have greatly improved the reconfigurability of the optical layer, which makes it possible to provide optical on-demand services at wavelength granularity (10 Gbps to 40 Gbps per channel). This new dynamic wavelength service model allows a customer owning or leasing a few terminal ports in the network to connect these ports on demand. The network must be pre-dimensioned with enough resources to support any possible connection configuration between the pre allocated ports of a dynamic wavelength customer. In this paper, we introduce a resource optimization problem for dynamic wave length services and propose a few efficient techniques to tackle this challenging problem. A heuristic optimizer based on a combination of simulated annealing and genetic algorithms is developed to solve the problem efficiently for large networks. We show that our solver can produce optimization solutions within 7% overhead of a lower bound with a small amount of computation.
- 8 April 2009
- Published by Springer Nature in Design Automation for Embedded Systems
- Vol. 13 (1-2) , 89
CASES 2007 guest editors’ introduction
- 8 April 2009
- Published by Springer Nature in Design Automation for Embedded Systems
- Vol. 13 (1-2) , 89
CASES 2007 guest editors’ introduction