SUMMARY: We introduce DNABERT-S, a tailored genome model that develops species-aware embeddings to naturally cluster and segregate DNA sequences of different species in the embedding space. Differentiating species from genomic sequences (i.e. DNA and RNA) is vital yet challenging, since many real-world species remain uncharacterized, lacking known genomes for reference. Embedding-based methods are therefore used to differentiate species in an unsupervised manner. DNABERT-S builds upon a pre-trained genome foundation model named DNABERT-2. To encourage effective embeddings to error-prone long-read DNA sequences, we introduce Manifold Instance Mixup (MI-Mix), a contrastive objective that mixes the hidden representations of DNA sequences at randomly selected layers and trains the model to recognize and differentiate these mixed proportions at the output layer. We further enhance it with the proposed Curriculum Contrastive Learning (C2LR) strategy. Empirical results on 28 diverse datasets show DNABERT-S's effectiveness, especially in realistic label-scarce scenarios. For example, it identifies twice more species from a mixture of unlabeled genomic sequences, doubles the Adjusted Rand Index (ARI) in species clustering, and outperforms the top baseline's performance in 10-shot species classification with just a 2-shot training. AVAILABILITY AND IMPLEMENTATION: Model, codes, and data are publically available at https://github.com/MAGICS-LAB/DNABERT_S.

BACKGROUND: The assembly of metagenomes decomposes members of complex microbe communities and allows the characterization of these genomes without laborious cultivation or single-cell metagenomics. Metagenome assembly is a process that is memory intensive and time consuming. Multi-terabyte sequences can become too large to be assembled on a single computer node, and there is no reliable method to predict the memory requirement due to data-specific memory consumption pattern. Currently, out-of-memory (OOM) is one of the most prevalent factors that causes metagenome assembly failures. RESULTS: In this study, we explored the possibility of using Persistent Memory (PMem) as a less expensive substitute for dynamic random access memory (DRAM) to reduce OOM and increase the scalability of metagenome assemblers. We evaluated the execution time and memory usage of three popular metagenome assemblers (MetaSPAdes, MEGAHIT, and MetaHipMer2) in datasets up to one terabase. We found that PMem can enable metagenome assemblers on terabyte-sized datasets by partially or fully substituting DRAM. Depending on the configured DRAM/PMEM ratio, running metagenome assemblies with PMem can achieve a similar speed as DRAM, while in the worst case it showed a roughly two-fold slowdown. In addition, different assemblers displayed distinct memory/speed trade-offs in the same hardware/software environment. CONCLUSIONS: We demonstrated that PMem is capable of expanding the capacity of DRAM to allow larger metagenome assembly with a potential tradeoff in speed. Because PMem can be used directly without any application-specific code modification, these findings are likely to be generalized to other memory-intensive bioinformatics applications.

MOTIVATION: Whole genome shotgun based next-generation transcriptomics and metagenomics studies often generate 100-1000 GB sequence data derived from tens of thousands of different genes or microbial species. Assembly of these data sets requires tradeoffs between scalability and accuracy. Current assembly methods optimized for scalability often sacrifice accuracy and vice versa. An ideal solution would both scale and produce optimal accuracy for individual genes or genomes. RESULTS: Here we describe an Apache Spark-based scalable sequence clustering application, SparkReadClust (SpaRC), that partitions reads based on their molecule of origin to enable downstream assembly optimization. SpaRC produces high clustering performance on transcriptomes and metagenomes from both short and long read sequencing technologies. It achieves near-linear scalability with input data size and number of compute nodes. SpaRC can run on both cloud computing and HPC environments without modification while delivering similar performance. Our results demonstrate that SpaRC provides a scalable solution for clustering billions of reads from next-generation sequencing experiments, and Apache Spark represents a cost-effective solution with rapid development/deployment cycles for similar large-scale sequence data analysis problems. AVAILABILITY AND IMPLEMENTATION: https://bitbucket.org/berkeleylab/jgi-sparc.

BACKGROUND: Long read sequencing technologies such as Oxford Nanopore can greatly decrease the complexity of de novo genome assembly and large structural variation identification. Currently Nanopore reads have high error rates, and the errors often cluster into low-quality segments within the reads. The limited sensitivity of existing read-based error correction methods can cause large-scale mis-assemblies in the assembled genomes, motivating further innovation in this area. RESULTS: Here we developed a Convolutional Neural Network (CNN) based method, called MiniScrub, for identification and subsequent "scrubbing" (removal) of low-quality Nanopore read segments to minimize their interference in downstream assembly process. MiniScrub first generates read-to-read overlaps via MiniMap2, then encodes the overlaps into images, and finally builds CNN models to predict low-quality segments. Applying MiniScrub to real world control datasets under several different parameters, we show that it robustly improves read quality, and improves read error correction in the metagenome setting. Compared to raw reads, de novo genome assembly with scrubbed reads produces many fewer mis-assemblies and large indel errors. CONCLUSIONS: MiniScrub is able to robustly improve read quality of Oxford Nanopore reads, especially in the metagenome setting, making it useful for downstream applications such as de novo assembly. We propose MiniScrub as a tool for preprocessing Nanopore reads for downstream analyses. MiniScrub is open-source software and is available at https://bitbucket.org/berkeleylab/jgi-miniscrub .

In this work we describe a method to automatically detect errors in de novo assembled genomes. The method extends a Bayesian assembly quality evaluation framework, ALE, which computes the likelihood of an assembly given a set of unassembled data. Starting from ALE output, this method applies outlier detection algorithms to identify the precise locations of assembly errors. We show results from a microbial genome with manually curated assembly errors. Our method detects all deletions, 82.3% of insertions, and 88.8% of single base substitutions. It was also able to detect an inversion error that spans more than 400 bases.

MOTIVATION: Researchers need general purpose methods for objectively evaluating the accuracy of single and metagenome assemblies and for automatically detecting any errors they may contain. Current methods do not fully meet this need because they require a reference, only consider one of the many aspects of assembly quality or lack statistical justification, and none are designed to evaluate metagenome assemblies. RESULTS: In this article, we present an Assembly Likelihood Evaluation (ALE) framework that overcomes these limitations, systematically evaluating the accuracy of an assembly in a reference-independent manner using rigorous statistical methods. This framework is comprehensive, and integrates read quality, mate pair orientation and insert length (for paired-end reads), sequencing coverage, read alignment and k-mer frequency. ALE pinpoints synthetic errors in both single and metagenomic assemblies, including single-base errors, insertions/deletions, genome rearrangements and chimeric assemblies presented in metagenomes. At the genome level with real-world data, ALE identifies three large misassemblies from the Spirochaeta smaragdinae finished genome, which were all independently validated by Pacific Biosciences sequencing. At the single-base level with Illumina data, ALE recovers 215 of 222 (97%) single nucleotide variants in a training set from a GC-rich Rhodobacter sphaeroides genome. Using real Pacific Biosciences data, ALE identifies 12 of 12 synthetic errors in a Lambda Phage genome, surpassing even Pacific Biosciences' own variant caller, EviCons. In summary, the ALE framework provides a comprehensive, reference-independent and statistically rigorous measure of single genome and metagenome assembly accuracy, which can be used to identify misassemblies or to optimize the assembly process. AVAILABILITY: ALE is released as open source software under the UoI/NCSA license at http://www.alescore.org. It is implemented in C and Python.

MOTIVATION: The recent revolution in sequencing technologies has led to an exponential growth of sequence data. As a result, most of the current bioinformatics tools become obsolete as they fail to scale with data. To tackle this 'data deluge', here we introduce the BioPig sequence analysis toolkit as one of the solutions that scale to data and computation. RESULTS: We built BioPig on the Apache's Hadoop MapReduce system and the Pig data flow language. Compared with traditional serial and MPI-based algorithms, BioPig has three major advantages: first, BioPig's programmability greatly reduces development time for parallel bioinformatics applications; second, testing BioPig with up to 500 Gb sequences demonstrates that it scales automatically with size of data; and finally, BioPig can be ported without modification on many Hadoop infrastructures, as tested with Magellan system at National Energy Research Scientific Computing Center and the Amazon Elastic Compute Cloud. In summary, BioPig represents a novel program framework with the potential to greatly accelerate data-intensive bioinformatics analysis.

Gene synthesis is a key step to convert digitally predicted proteins to functional proteins. However, it is a relatively expensive and labor-intensive process. About 30-50% of the synthesized proteins are not soluble, thereby further reduces the efficacy of gene synthesis as a method for protein function characterization. Solubility prediction from primary protein sequences holds the promise to dramatically reduce the cost of gene synthesis. This work presents a framework that creates models of solubility from sequence information. From the primary protein sequences of the genes to be synthesized, sequence features can be used to build computational models for solubility. This way, biologists can focus the effort on synthesizing genes that are highly likely to generate soluble proteins. We have developed a framework that employs several machine learning algorithms to model protein solubility. The framework is used to predict protein solubility in the Escherichia coli expression system. The analysis is performed on over 1,600 quantified proteins. The approach successfully predicted the solubility with more than 80% accuracy, and enabled in depth analysis of the most important features affecting solubility. The analysis pipeline is general and can be applied to any set of sequence features to predict any binary measure. The framework also provides the biologist with a comprehensive comparison between different learning algorithms, and insightful feature analysis.

A significant number of human X-linked genes escape X chromosome inactivation and are thus expressed from both the active and inactive X chromosomes. The basis for escape from inactivation and the potential role of the X chromosome primary DNA sequence in determining a gene's X inactivation status is unclear. Using a combination of the X chromosome sequence and a comprehensive X inactivation profile of more than 600 genes, two independent yet complementary approaches were used to systematically investigate the relationship between X inactivation and DNA sequence features. First, statistical analyses revealed that a number of repeat features, including long interspersed nuclear element (LINE) and mammalian-wide interspersed repeat repetitive elements, are significantly enriched in regions surrounding transcription start sites of genes that are subject to inactivation, while Alu repetitive elements and short motifs containing ACG/CGT are significantly enriched in those that escape inactivation. Second, linear support vector machine classifiers constructed using primary DNA sequence features were used to correctly predict the X inactivation status for >80% of all X-linked genes. We further identified a small set of features that are important for accurate classification, among which LINE-1 and LINE-2 content show the greatest individual discriminatory power. Finally, as few as 12 features can be used for accurate support vector machine classification. Taken together, these results suggest that features of the underlying primary DNA sequence of the human X chromosome may influence the spreading and/or maintenance of X inactivation.