Active learning for efficient analysis of high-throughput nanopore data

Abstract

As the third-generation sequencing technology, nanopore sequencing has been used for high-throughput sequencing of DNA, RNA, and even proteins. Recently, many studies have begun to use machine learning technology to analyze the enormous data generated by nanopores. Unfortunately, the success of this technology is due to the extensive labeled data, which often suffer from enormous labor costs. Therefore, there is an urgent need for a novel technology that can not only rapidly analyze nanopore data with high-throughput, but also significantly reduce the cost of labeling. To achieve the above goals, we introduce active learning to alleviate the enormous labor costs by selecting the samples that need to be labeled. This work applies several advanced active learning technologies to the nanopore data, including the RNA classification dataset (RNA-CD) and the Oxford Nanopore Technologies barcode dataset (ONT-BD). Due to the complexity of the nanopore data (with noise sequence), the bias constraint is introduced to improve the sample selection strategy in active learning. The experimental results show that for the same performance metric, 50% labeling amount can achieve the best baseline performance for ONT-BD, while only 15% labeling amount can achieve the best baseline performance for RNA-CD. Crucially, the experiments show that active learning technology can assist experts in labeling samples, and significantly reduce the labeling cost. Active learning can greatly reduce the dilemma of difficult labeling of high-capacity nanopore data. We hope active learning can be applied to other problems in nanopore sequence analysis. Availability The main program is available at https://github.com/guanxiaoyu11/AL-for-nanopore. Supplementary information Supplementary data are available at Bioinformatics online.

Biomass carbon mining to develop nature-inspired materials for a circular economy

“…Applying methods that have been proved successful in other areas to biobased molecules and materials is expected to revolutionize the development of nature-inspired computational materials for a circular economy. Examples are the use of active learning for free energy calculations, 217 efficient analysis of high-throughput nanopore data, 218 chemical dynamics simulations of interfacial systems, 219 or physics-informed ML models. 220 …”

Online meta-learned gradient norms for active learning in science and technology

“…Data labels in this context are numeric or categorical properties, which an ML model is trained to predict. Obtaining those labels, called annotation, might require a domain expert categorisation, an experiment, a measurement or a simulation [4][5][6]. Active learning (AL) is an ML method that applies when we have a large pool of fully characterised feature data and a far smaller amount of annotated label data.…”

Active learning of enhancer and silencer regulatory grammar in photoreceptors

“…In contrast to current approaches that rely on a single round of training data, active learning offers a way to iteratively improve models by selecting new training examples based on their potential to improve the model. Active learning has been successfully applied to model metabolic networks (47), optimize cell culture media (48), perform in silico drug screens (49)(50)(51)(52), identify TFs that drive cellular differentiation (53), select optimal training data for nanopore base calling (54), and design Perturb-seq experiments (55). Here we apply active learning to the problem of cisregulation for the first time, using it to iteratively train models of a cell type-specific cis-regulatory grammar in the early postnatal mouse retina, an experimentally accessible portion of the developing central nervous system.…”

“…By prioritizing these perturbations at each iteration, we efficiently sample the space of possible sequences for informative examples, and thereby train accurate machine learning models with less data [40][41][42] . Active learning has been successfully applied to model metabolic networks 43 , optimize cell culture media 44 , perform in silico drug screens [45][46][47][48] , improve text and image classifiers 42,49 , discover energy-efficient materials 50,51 , identify TFs that drive cellular differentiation 52 , and select optimal training data for nanopore base calling 53 . However, active learning has not yet been applied to train models of cis-regulatory grammars.…”