A University of Waterloo researcher has spearheaded the development of a software tool that can provide conclusive answers to some of the world’s most fascinating questions.
The tool, which combines supervised machine learning with digital signal processing (ML-DSP), could for the first time make it possible to definitively answer questions such as how many different species exist on Earth and in the oceans. How are existing, newly-discovered, and extinct species related to each other? What are the bacterial origins of human mitochondrial DNA? Do the DNA of a parasite and its host have a similar genomic signature?
The tool also has the potential to positively impact the personalized medicine industry by identifying the specific strain of a virus and thus allowing for precise drugs to be developed and prescribed to treat it.
ML-DSP is an alignment-free software tool which works by transforming a DNA sequence into a digital (numerical) signal, and uses digital signal processing methods to process and distinguish these signals from each other.
“With this method even if we only have small fragments of DNA we can still classify DNA sequences, regardless of their origin, or whether they are natural, synthetic, or computer-generated,” said Lila Kari, a professor in Waterloo’s Faculty of Mathematics. “Another important potential application of this tool is in the healthcare sector, as in this era of personalized medicine we can classify viruses and customize the treatment of a particular patient depending on the specific strain of the virus that affects them.”
In the study, researchers performed a quantitative comparison with other state-of-the-art classification software tools on two small benchmark datasets and one large 4,322 vertebrate mitochondrial genome dataset. “Our results show that ML-DSP overwhelmingly outperforms alignment-based software in terms of processing time, while having classification accuracies that are comparable in the case of small datasets and superior in the case of large datasets,” Kari said. “Compared with other alignment-free software, ML-DSP has significantly better classification accuracy and is overall faster.”
The authors also conducted preliminary experiments indicating the potential of ML-DSP to be used for other datasets, by classifying 4,271 complete dengue virus genomes into subtypes with 100 per cent accuracy, and 4,710 bacterial genomes into divisions with 95.5 per cent accuracy.
The Latest on: ML-DSP
via Google News
The Latest on: ML-DSP
- AdTheorent Holding Company, Inc.(ADTH) CEO Jim Lawsonon Q12022 Results - Earnings Call Transcripton May 11, 2022 at 7:57 pm
Q1 2022 Earnings Conference Call May11, 2022, 05:00PM ET Company Participants David DiStefano - IR Jim Lawson - CEO Chuck Jordan - ...
- Week In Review: Auto, Security, Pervasive Computingon April 29, 2022 at 6:40 am
Besides performance improvements and endpoint ML/DSP workload support, M85 incorporates Arm TrustZone enhanced security. Infineon added a new member to the CIPOS Tiny Intelligent Power Module (IPM) ...
- Week In Review: Design, Low Poweron April 29, 2022 at 12:03 am
The Cortex-M85 is the highest performance Cortex-M processor to date, with 30% scalar performance uplift compared to the Cortex-M7, technology to support endpoint ML and DSP workloads, and includes ...
- AI/ML Distinguished Technologiston April 28, 2022 at 5:00 pm
Participates in and provides input on process for selection of future technical leaders. ML knowledge for improving picture/video quality and operation Know how to use vision for AI/ML models that ...
- Arm expands IoT solutions and adds to virtual hardware platformon April 27, 2022 at 3:47 am
It offers: A 30% scalar performance uplift compared to the Cortex-M7. Arm Helium technology to support endpoint ML and DSP workloads Enhanced security with Arm TrustZone technology. It also includes ...
- Implementing accelerated machine-learning applications with an advanced MCUon April 26, 2022 at 3:04 pm
Historically, Artificial Intelligence (AI) was a GPU / CPU or even DSP-dependent technology ... Although the terms AI and Machine Learning (ML) are often used interchangeably, they represent two ...
- AMD Targets High-End Signal Processing With New Versal Premium With AI Engineson April 20, 2022 at 3:19 pm
Signal processing can be balanced between the AI and DSP engines within the Versal Premium ... and 5.8x for AI/ML inference processing while reducing the number of FPGAs needed for a design.
- Moloco Updates Moloco Cloud Demand-Side Platformon April 14, 2022 at 7:00 am
Moloco, a provider of machine learning (ML) and growth solutions for performance marketers, has updated its cloud-based programmatic advertising platform, Moloco Cloud Demand-Side Platform (DSP). The ...
- Moloco Announces Moloco Cloud Demand-Side Platform Updateson April 13, 2022 at 6:09 am
April 13, 2022--(BUSINESS WIRE)--Moloco, a leader in machine learning (ML) and growth solutions for ... Moloco Cloud Demand-Side Platform (DSP). The latest updates focus on improving performance ...
- 5 Reasons Embedded Developers Should Care about Machine Learningon March 24, 2022 at 5:00 pm
Artificial intelligence (AI) and machine learning (ML) seem to be in the headlines more and more each ... In order to really improve the execution efficiency, though, developers can make use of ARM ...
via Bing News