A deep learning model for predicting next-generation sequencing depth from DNA sequence

Zhang, Jinny X.; Yordanov, Boyan; Gaunt, Alexander L.; Wang, Michael X.; Dai, Peng; Chen, Yuan-Jyue; Zhang, Kerou; Fang, John; Dalchau, Neil; Li, Jiaming; Phillips, Andrew; Zhang, David Y.

doi:10.1038/s41467-021-24497-8

Cited by 47 publications

(23 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rather than querying for only known variants with molecular probes as with digital PCR, NGS has the capacity to find genetic perturbations in a relatively unbiased fashion, since sequencing, by its very nature, will identify all the base pairs of a given DNA molecule. The flexibility in selectively capturing and/or amplifying only regions of interest has led to approaches for sequencing only parts of a genome, including so-called “exome capture” and also gene panels ( 82 ). Unfortunately, NGS is prone to sequencing errors, due to the inherent nature of strand synthesis, as well as PCR amplification.…”

Section: Analysis Of Ctdnamentioning

confidence: 99%

Circulating tumor DNA: current challenges for clinical utility

Dang¹,

Park²

2022

Journal of Clinical Investigation

102

View full text Add to dashboard Cite

Cancer cells shed naked DNA molecules into the circulation. This circulating tumor DNA (ctDNA) has become the predominant analyte for liquid biopsies to understand the mutational landscape of cancer. Coupled with next-generation sequencing, ctDNA can serve as an alternative substrate to tumor tissues for mutation detection and companion diagnostic purposes. In fact, recent advances in precision medicine have rapidly enabled the use of ctDNA to guide treatment decisions for predicting response and resistance to targeted therapies and immunotherapies. An advantage of using ctDNA over conventional tissue biopsies is the relatively noninvasive approach of obtaining peripheral blood, allowing for simple repeated and serial assessments. Most current clinical practice using ctDNA has endeavored to identify druggable and resistance mutations for guiding systemic therapy decisions, albeit mostly in metastatic disease. However, newer research is evaluating potential for ctDNA as a marker of minimal residual disease in the curative setting and as a useful screening tool to detect cancer in the general population. Here we review the history of ctDNA and liquid biopsies, technologies to detect ctDNA, and some of the current challenges and limitations in using ctDNA as a marker of minimal residual disease and as a general blood-based cancer screening tool. We also discuss the need to develop rigorous clinical studies to prove the clinical utility of ctDNA for future applications in oncology.

show abstract

Section: Analysis Of Ctdnamentioning

confidence: 99%

Circulating tumor DNA: current challenges for clinical utility

Dang¹,

Park²

2022

Journal of Clinical Investigation

102

View full text Add to dashboard Cite

show abstract

“…Machine learning algorithms , build a model based on sample data, known as “training data”, to make predictions or decisions without completely understanding the “black box”, which represents the mechanism and learning process during model training. These characteristics enable machine learning to be successfully applied in the fields of chemistry and biology, such as spectral prediction, − cancer biomarker detection, − biosensor advancement, − and chemical synthesis. − Despite this progress, the application of machine learning algorithms to guide CD synthesis is still limited. In our previous studies, we developed a deep convolution neural network (DCNN) model for predicting the optical properties of CDs .…”

Section: Introductionmentioning

confidence: 99%

Customized Carbon Dots with Predictable Optical Properties Synthesized at Room Temperature Guided by Machine Learning

et al. 2022

View full text Add to dashboard Cite

Fluorescent carbon dots (CDs) have been increasingly used in fluorescence detection and imaging based on their tunable fluorescence (FL) and resistance to photobleaching. However, the fast and reliable design of fluorescent CDs with specific optical properties involves a number of factors, such as the concentration of precursors, reaction time, and solvents. Therefore, it is usually considered difficult to design CDs with favorable optical properties. Herein, we report an extreme gradient boosting (XGBoost) model for guiding the fabrication of CDs with high FL intensity and tunable emission from p-benzoquinone (PBQ) and ethylenediamine (EDA) in different solvents at room temperature. Among a variety of studied machine learning models, XGBoost shows the best performance in the field of material synthesis, with a prediction coefficient of determination (R 2) higher than 0.96. The XGBoost model can effectively predict the optical properties of CDs, including the maximum FL intensity and emission centers. Guided by the XGBoost model, various green or blue fluorescent CDs with adjustable emission centers and solubility properties are designed and fabricated accurately. These CDs are successfully applied for Fe3+ detection, sustained drug release, whole-cell imaging, and poly(vinyl alcohol) (PVA) film preparation. These results suggest the great potential of the combination of machine learning and CD synthesis as an effective strategy to help researchers realize accurate selection of reasonable CDs with individual customized properties to achieve different goals.

show abstract

“…Although numerous studies have been conducted with deep neural networks for natural computing, deep neural networks are still new models for the DNA data storage system. For instance, in 2021, a GRU (gated recurrent unit)-based deep learning model was presented for DNA information storage with next-generation sequence prediction [14]. Similarly, the author proposed a DeepMod system that integrates the RNN and LSTM models to perceive the DNA codes from various Oxford Nanopore sequences.…”

Section: Deep Neural Network For Dna Codesmentioning

confidence: 99%

Bio-Constrained Codes with Neural Network for Density-Based DNA Data Storage

Rasool

Wang

et al. 2022

Mathematics

View full text Add to dashboard Cite

DNA has evolved as a cutting-edge medium for digital information storage due to its extremely high density and durable preservation to accommodate the data explosion. However, the strings of DNA are prone to errors during the hybridization process. In addition, DNA synthesis and sequences come with a cost that depends on the number of nucleotides present. An efficient model to store a large amount of data in a small number of nucleotides is essential, and it must control the hybridization errors among the base pairs. In this paper, a novel computational model is presented to design large DNA libraries of oligonucleotides. It is established by integrating a neural network (NN) with combinatorial biological constraints, including constant GC-content and satisfying Hamming distance and reverse-complement constraints. We develop a simple and efficient implementation of NNs to produce the optimal DNA codes, which opens the door to applying neural networks for DNA-based data storage. Further, the combinatorial bio-constraints are introduced to improve the lower bounds and to avoid the occurrence of errors in the DNA codes. Our goal is to compute large DNA codes in shorter sequences, which should avoid non-specific hybridization errors by satisfying the bio-constrained coding. The proposed model yields a significant improvement in the DNA library by explicitly constructing larger codes than the prior published codes.

show abstract

A deep learning model for predicting next-generation sequencing depth from DNA sequence

Cited by 47 publications

References 32 publications

Circulating tumor DNA: current challenges for clinical utility

Circulating tumor DNA: current challenges for clinical utility

Customized Carbon Dots with Predictable Optical Properties Synthesized at Room Temperature Guided by Machine Learning

Bio-Constrained Codes with Neural Network for Density-Based DNA Data Storage

Contact Info

Product

Resources

About