[FINAL ENTRY]: Genomic Error Correction And Resequencing With GPU-Accelerated QCNN
Team Name:
BCQEntangleMen
Members:
Ethan Rajkumar
Pranav Kairon
Luis Mantilla Calderon
Mohammed Mostaan
Project Summary:
In the past, genomics sequencing encountered challenges in error correction of readings that could introduce errors and complicate downstream analyses. While deep neural networks made impressive progress in this field, errors in sequence readings remained a major concern [1]. Although convolutional neural networks (CNNs) could be effective for error correction, inconsistent results could arise depending on sequence length. Thus, error correction remained an open issue in genomics sequencing that required innovative solutions [1-4]. Quantum convolutional neural networks (QCNNs) showed promise for addressing this challenge because they could perform complex computations in parallel and potentially leverage quantum entanglement to enhance feature detection and classification [5].
The project aimed to explore the use of quantum neural networks (QNNs) for correcting sequencing errors in genomics. A QNN architecture was developed specifically for error correction in genomic sequences and trained on a large dataset with known errors. Afterwards, the GPU-Accelerated QNN's performance was evaluated on a separate set of genomic sequences with known errors. The accuracy and computational performance of the QNN-based method was also assessed against other traditional error-correction methods.
[1] "Canu: scalable and accurate long-read assembly via adaptive k-mer weighting and repeat separation" by Koren S, et al. Genome Research, 2017.
[2 ]"Deep learning for error correction in nanopore sequencing" by Liu et al. BMC Genomics, 2019.
[3] "DeepCov: predicting 3D genome folding using megabase-scale transfer learning from neural machine translation" by Hiranuma et al. Nature Communications, 2021.
[4] "Highly accurate read mapping with an extended Kalman filter" by Zhang et al. PLoS ONE, 2017.
[5] Bokhan, D., Mastiukova, A. S., Boev, A. S., Trubnikov, D. N., & Fedorov, A. K. (2022). Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning. Frontiers in Physics, 10. doi:10.3389/fphy.2022.1069985
[FINAL ENTRY]: Genomic Error Correction And Resequencing With GPU-Accelerated QCNN
Team Name:
BCQEntangleMen
Members:
Ethan Rajkumar Pranav Kairon Luis Mantilla Calderon Mohammed Mostaan
Project Summary:
In the past, genomics sequencing encountered challenges in error correction of readings that could introduce errors and complicate downstream analyses. While deep neural networks made impressive progress in this field, errors in sequence readings remained a major concern [1]. Although convolutional neural networks (CNNs) could be effective for error correction, inconsistent results could arise depending on sequence length. Thus, error correction remained an open issue in genomics sequencing that required innovative solutions [1-4]. Quantum convolutional neural networks (QCNNs) showed promise for addressing this challenge because they could perform complex computations in parallel and potentially leverage quantum entanglement to enhance feature detection and classification [5]. The project aimed to explore the use of quantum neural networks (QNNs) for correcting sequencing errors in genomics. A QNN architecture was developed specifically for error correction in genomic sequences and trained on a large dataset with known errors. Afterwards, the GPU-Accelerated QNN's performance was evaluated on a separate set of genomic sequences with known errors. The accuracy and computational performance of the QNN-based method was also assessed against other traditional error-correction methods.
Project Presentation:
Google Slides Can be found here PDF Can be found here
Project Source Code:
Can be found here
References:
[1] "Canu: scalable and accurate long-read assembly via adaptive k-mer weighting and repeat separation" by Koren S, et al. Genome Research, 2017. [2 ]"Deep learning for error correction in nanopore sequencing" by Liu et al. BMC Genomics, 2019. [3] "DeepCov: predicting 3D genome folding using megabase-scale transfer learning from neural machine translation" by Hiranuma et al. Nature Communications, 2021. [4] "Highly accurate read mapping with an extended Kalman filter" by Zhang et al. PLoS ONE, 2017.
[5] Bokhan, D., Mastiukova, A. S., Boev, A. S., Trubnikov, D. N., & Fedorov, A. K. (2022). Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning. Frontiers in Physics, 10. doi:10.3389/fphy.2022.1069985
What Challenges would you like to apply for?
NVIDIA Challenge Quantum computing today! Amazon Braket Challenge Hybrid Quantum-Classical Computing Challenge Visualization Challenge