Comparative Genomic Analysis of Bacterial Data in BV-BRC: An Example Exploring Antimicrobial Resistance.

As genomic and related data continue to expand, research biologists are often hampered by the computational hurdles required to analyze their data. The National Institute of Allergy and Infectious Diseases (NIAID) established the Bioinformatics Resource Centers (BRC) to assist researchers with their analysis of genome sequence and other omics-related data. Recently, the PAThosystems Resource Integration Center (PATRIC), the Influenza Research Database (IRD), and the Virus Pathogen Database and Analysis Resource (ViPR) BRCs merged to form the Bacterial and Viral Bioinformatics Resource Center (BV-BRC) at https://www.bv-brc.org/ . The combined BV-BRC leverages the functionality of the original resources for bacterial and viral research communities with a unified data model, enhanced web-based visualization and analysis tools, and bioinformatics services. Here we demonstrate how antimicrobial resistance data can be analyzed in the new resource.

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening.

It is well-known that cancers of the same histology type can respond differently to a treatment. Thus, computational drug response prediction is of paramount importance for both preclinical drug screening studies and clinical treatment design. To build drug response prediction models, treatment response data need to be generated through screening experiments and used as input to train the prediction models. In this study, we investigate various active learning strategies of selecting experiments to generate response data for the purposes of (1) improving the performance of drug response prediction models built on the data and (2) identifying effective treatments. Here, we focus on constructing drug-specific response prediction models for cancer cell lines. Various approaches have been designed and applied to select cell lines for screening, including a random, greedy, uncertainty, diversity, combination of greedy and uncertainty, sampling-based hybrid, and iteration-based hybrid approach. All of these approaches are evaluated and compared using two criteria: (1) the number of identified hits that are selected experiments validated to be responsive, and (2) the performance of the response prediction model trained on the data of selected experiments. The analysis was conducted for 57 drugs and the results show a significant improvement on identifying hits using active learning approaches compared with the random and greedy sampling method. Active learning approaches also show an improvement on response prediction performance for some of the drugs and analysis runs compared with the greedy sampling method.

Engineering of increased L-Threonine production in bacteria by combinatorial cloning and machine learning.

The goal of this study is to develop a general strategy for bacterial engineering using an integrated synthetic biology and machine learning (ML) approach. This strategy was developed in the context of increasing L-threonine production in Escherichia coli ATCC 21277. A set of 16 genes was initially selected based on metabolic pathway relevance to threonine biosynthesis and used for combinatorial cloning to construct a set of 385 strains to generate training data (i.e., a range of L-threonine titers linked to each of the specific gene combinations). Hybrid (regression/classification) deep learning (DL) models were developed and used to predict additional gene combinations in subsequent rounds of combinatorial cloning for increased L-threonine production based on the training data. As a result, E. coli strains built after just three rounds of iterative combinatorial cloning and model prediction generated higher L-threonine titers (from 2.7 g/L to 8.4 g/L) than those of patented L-threonine strains being used as controls (4-5 g/L). Interesting combinations of genes in L-threonine production included deletions of the tdh, metL, dapA, and dhaM genes as well as overexpression of the pntAB, ppc, and aspC genes. Mechanistic analysis of the metabolic system constraints for the best performing constructs offers ways to improve the models by adjusting weights for specific gene combinations. Graph theory analysis of pairwise gene modifications and corresponding levels of L-threonine production also suggests additional rules that can be incorporated into future ML models.

Causal Discovery and Optimal Experimental Design for Genome-Scale Biological Network Recovery.

Causal discovery of genome-scale networks is important for identifying pathways from genes to observable traits -e.g. differences in cell function, disease, drug resistance and others. Causal learners based on graphical models rely on interventional samples to orient edges in the network. However, these models have not been shown to scale up the size of the genome, which are on the order of 103-104 genes. We introduce a new learner, SP-GIES, that jointly learns from interventional and observational datasets and achieves almost 4x speedup against an existing learner for 1,000 node networks. SP-GIES achieves an AUC-PR score of 0.91 on 1,000 node networks, and scales up to 2,000 node networks - this is 4x larger than existing works. We also show how SP-GIES improves downstream optimal experimental design strategies for selecting interventional experiments to perform on the system. This is an important step forward in realizing causal discovery at scale via autonomous experimental design.

Deep learning methods for drug response prediction in cancer: Predominant and emerging trends.

Cancer claims millions of lives yearly worldwide. While many therapies have been made available in recent years, by in large cancer remains unsolved. Exploiting computational predictive models to study and treat cancer holds great promise in improving drug development and personalized design of treatment plans, ultimately suppressing tumors, alleviating suffering, and prolonging lives of patients. A wave of recent papers demonstrates promising results in predicting cancer response to drug treatments while utilizing deep learning methods. These papers investigate diverse data representations, neural network architectures, learning methodologies, and evaluations schemes. However, deciphering promising predominant and emerging trends is difficult due to the variety of explored methods and lack of standardized framework for comparing drug response prediction models. To obtain a comprehensive landscape of deep learning methods, we conducted an extensive search and analysis of deep learning models that predict the response to single drug treatments. A total of 61 deep learning-based models have been curated, and summary plots were generated. Based on the analysis, observable patterns and prevalence of methods have been revealed. This review allows to better understand the current state of the field and identify major challenges and promising solution paths.

Data augmentation and multimodal learning for predicting drug response in patient-derived xenografts from gene expressions and histology images.

Patient-derived xenografts (PDXs) are an appealing platform for preclinical drug studies. A primary challenge in modeling drug response prediction (DRP) with PDXs and neural networks (NNs) is the limited number of drug response samples. We investigate multimodal neural network (MM-Net) and data augmentation for DRP in PDXs. The MM-Net learns to predict response using drug descriptors, gene expressions (GE), and histology whole-slide images (WSIs). We explore whether combining WSIs with GE improves predictions as compared with models that use GE alone. We propose two data augmentation methods which allow us training multimodal and unimodal NNs without changing architectures with a single larger dataset: 1) combine single-drug and drug-pair treatments by homogenizing drug representations, and 2) augment drug-pairs which doubles the sample size of all drug-pair samples. Unimodal NNs which use GE are compared to assess the contribution of data augmentation. The NN that uses the original and the augmented drug-pair treatments as well as single-drug treatments outperforms NNs that ignore either the augmented drug-pairs or the single-drug treatments. In assessing the multimodal learning based on the MCC metric, MM-Net outperforms all the baselines. Our results show that data augmentation and integration of histology images with GE can improve prediction performance of drug response in PDXs.

AI-accelerated protein-ligand docking for SARS-CoV-2 is 100-fold faster with no significant change in detection.

Protein-ligand docking is a computational method for identifying drug leads. The method is capable of narrowing a vast library of compounds down to a tractable size for downstream simulation or experimental testing and is widely used in drug discovery. While there has been progress in accelerating scoring of compounds with artificial intelligence, few works have bridged these successes back to the virtual screening community in terms of utility and forward-looking development. We demonstrate the power of high-speed ML models by scoring 1 billion molecules in under a day (50 k predictions per GPU seconds). We showcase a workflow for docking utilizing surrogate AI-based models as a pre-filter to a standard docking workflow. Our workflow is ten times faster at screening a library of compounds than the standard technique, with an error rate less than 0.01% of detecting the underlying best scoring 0.1% of compounds. Our analysis of the speedup explains that another order of magnitude speedup must come from model accuracy rather than computing speed. In order to drive another order of magnitude of acceleration, we share a benchmark dataset consisting of 200 million 3D complex structures and 2D structure scores across a consistent set of 13 million "in-stock" molecules over 15 receptors, or binding sites, across the SARS-CoV-2 proteome. We believe this is strong evidence for the community to begin focusing on improving the accuracy of surrogate models to improve the ability to screen massive compound libraries 100 × or even 1000 × faster than current techniques and reduce missing top hits. The technique outlined aims to be a fast drop-in replacement for docking for screening billion-scale molecular libraries.

Introducing the Bacterial and Viral Bioinformatics Resource Center (BV-BRC): a resource combining PATRIC, IRD and ViPR.

The National Institute of Allergy and Infectious Diseases (NIAID) established the Bioinformatics Resource Center (BRC) program to assist researchers with analyzing the growing body of genome sequence and other omics-related data. In this report, we describe the merger of the PAThosystems Resource Integration Center (PATRIC), the Influenza Research Database (IRD) and the Virus Pathogen Database and Analysis Resource (ViPR) BRCs to form the Bacterial and Viral Bioinformatics Resource Center (BV-BRC) https://www.bv-brc.org/. The combined BV-BRC leverages the functionality of the bacterial and viral resources to provide a unified data model, enhanced web-based visualization and analysis tools, bioinformatics services, and a powerful suite of command line tools that benefit the bacterial and viral research communities.

Integration of Computational Docking into Anti-Cancer Drug Response Prediction Models.

Cancer is a heterogeneous disease in that tumors of the same histology type can respond differently to a treatment. Anti-cancer drug response prediction is of paramount importance for both drug development and patient treatment design. Although various computational methods and data have been used to develop drug response prediction models, it remains a challenging problem due to the complexities of cancer mechanisms and cancer-drug interactions. To better characterize the interaction between cancer and drugs, we investigate the feasibility of integrating computationally derived features of molecular mechanisms of action into prediction models. Specifically, we add docking scores of drug molecules and target proteins in combination with cancer gene expressions and molecular drug descriptors for building response models. The results demonstrate a marginal improvement in drug response prediction performance when adding docking scores as additional features, through tests on large drug screening data. We discuss the limitations of the current approach and provide the research community with a baseline dataset of the large-scale computational docking for anti-cancer drugs.

GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics.

We seek to transform how new and emergent variants of pandemic-causing viruses, specifically SARS-CoV-2, are identified and classified. By adapting large language models (LLMs) for genomic data, we build genome-scale language models (GenSLMs) which can learn the evolutionary landscape of SARS-CoV-2 genomes. By pre-training on over 110 million prokaryotic gene sequences and fine-tuning a SARS-CoV-2-specific model on 1.5 million genomes, we show that GenSLMs can accurately and rapidly identify variants of concern. Thus, to our knowledge, GenSLMs represents one of the first whole genome scale foundation models which can generalize to other prediction tasks. We demonstrate scaling of GenSLMs on GPU-based supercomputers and AI-hardware accelerators utilizing 1.63 Zettaflops in training runs with a sustained performance of 121 PFLOPS in mixed precision and peak of 850 PFLOPS. We present initial scientific insights from examining GenSLMs in tracking evolutionary dynamics of SARS-CoV-2, paving the path to realizing this on large biological data.

TULIP: An RNA-seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural Networks.

Background: With cancer as one of the leading causes of death worldwide, accurate primary tumor type prediction is critical in identifying genetic factors that can inhibit or slow tumor progression. There have been efforts to categorize primary tumor types with gene expression data using machine learning, and more recently with deep learning, in the last several years. Methods: In this paper, we developed four 1-dimensional (1D) Convolutional Neural Network (CNN) models to classify RNA-seq count data as one of 17 highly represented primary tumor types or 32 primary tumor types regardless of imbalanced representation. Additionally, we adapted the models to take as input either all Ensembl genes (60,483) or protein coding genes only (19,758). Unlike previous work, we avoided selection bias by not filtering genes based on expression values. RNA-seq count data expressed as FPKM-UQ of 9,025 and 10,940 samples from The Cancer Genome Atlas (TCGA) were downloaded from the Genomic Data Commons (GDC) corresponding to 17 and 32 primary tumor types respectively for training and validating the models. Results: All 4 1D-CNN models had an overall accuracy of 94.7% to 97.6% on the test dataset. Further evaluation indicates that the models with protein coding genes only as features performed with better accuracy compared to the models with all Ensembl genes for both 17 and 32 primary tumor types. For all models, the accuracy by primary tumor type was above 80% for most primary tumor types. Conclusions: We packaged all 4 models as a Python-based deep learning classification tool called TULIP (TUmor CLassIfication Predictor) for performing quality control on primary tumor samples and characterizing cancer samples of unknown tumor type. Further optimization of the models is needed to improve the accuracy of certain primary tumor types.

Early detection of emerging SARS-CoV-2 variants of interest for experimental evaluation.

Since the beginning of the COVID-19 pandemic, SARS-CoV-2 has demonstrated its ability to rapidly and continuously evolve, leading to the emergence of thousands of different sequence variants, many with distinctive phenotypic properties. Fortunately, the broad application of next generation sequencing (NGS) across the globe has produced a wealth of SARS-CoV-2 genome sequences, offering a comprehensive picture of how this virus is evolving so that accurate diagnostics, reliable therapeutics, and prophylactic vaccines against COVID-19 can be developed and maintained. The millions of SARS-CoV-2 sequences deposited into genomic sequencing databases, including GenBank, BV-BRC, and GISAID, are annotated with the dates and geographic locations of sample collection, and can be aligned to and compared with the Wuhan-Hu-1 reference genome to extract their constellation of nucleotide and amino acid substitutions. By aggregating these data into concise datasets, the spread of variants through space and time can be assessed. Variant tracking efforts have initially focused on the Spike protein due to its critical role in viral tropism and antibody neutralization. To identify emerging variants of concern as early as possible, we developed a computational pipeline to process the genomic data and assign risk scores based on both epidemiological and functional parameters. Epidemiological dynamics are used to identify variants exhibiting substantial growth over time and spread across geographical regions. Experimental data that quantify Spike protein regions targeted by adaptive immunity and critical for other virus characteristics are used to predict variants with consequential immunogenic and pathogenic impacts. The growth assessment and functional impact scores are combined to produce a Composite Score for any set of Spike substitutions detected. With this systematic method to routinely score and rank emerging variants, we have established an approach to identify threatening variants early and prioritize them for experimental evaluation.

A cross-study analysis of drug response prediction in cancer cell lines.

To enable personalized cancer treatment, machine learning models have been developed to predict drug response as a function of tumor and drug features. However, most algorithm development efforts have relied on cross-validation within a single study to assess model accuracy. While an essential first step, cross-validation within a biological data set typically provides an overly optimistic estimate of the prediction performance on independent test sets. To provide a more rigorous assessment of model generalizability between different studies, we use machine learning to analyze five publicly available cell line-based data sets: National Cancer Institute 60, ancer Therapeutics Response Portal (CTRP), Genomics of Drug Sensitivity in Cancer, Cancer Cell Line Encyclopedia and Genentech Cell Line Screening Initiative (gCSI). Based on observed experimental variability across studies, we explore estimates of prediction upper bounds. We report performance results of a variety of machine learning models, with a multitasking deep neural network achieving the best cross-study generalizability. By multiple measures, models trained on CTRP yield the most accurate predictions on the remaining testing data, and gCSI is the most predictable among the cell line data sets included in this study. With these experiments and further simulations on partial data, two lessons emerge: (1) differences in viability assays can limit model generalizability across studies and (2) drug diversity, more than tumor diversity, is crucial for raising model generalizability in preclinical screening.

High-Throughput Virtual Screening and Validation of a SARS-CoV-2 Main Protease Noncovalent Inhibitor.

Despite the recent availability of vaccines against the acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the search for inhibitory therapeutic agents has assumed importance especially in the context of emerging new viral variants. In this paper, we describe the discovery of a novel noncovalent small-molecule inhibitor, MCULE-5948770040, that binds to and inhibits the SARS-Cov-2 main protease (Mpro) by employing a scalable high-throughput virtual screening (HTVS) framework and a targeted compound library of over 6.5 million molecules that could be readily ordered and purchased. Our HTVS framework leverages the U.S. supercomputing infrastructure achieving nearly 91% resource utilization and nearly 126 million docking calculations per hour. Downstream biochemical assays validate this Mpro inhibitor with an inhibition constant (Ki) of 2.9 µM (95% CI 2.2, 4.0). Furthermore, using room-temperature X-ray crystallography, we show that MCULE-5948770040 binds to a cleft in the primary binding site of Mpro forming stable hydrogen bond and hydrophobic interactions. We then used multiple µs-time scale molecular dynamics (MD) simulations and machine learning (ML) techniques to elucidate how the bound ligand alters the conformational states accessed by Mpro, involving motions both proximal and distal to the binding site. Together, our results demonstrate how MCULE-5948770040 inhibits Mpro and offers a springboard for further therapeutic design.

Intelligent resolution: Integrating Cryo-EM with AI-driven multi-resolution simulations to observe the severe acute respiratory syndrome coronavirus-2 replication-transcription machinery in action.

The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) replication transcription complex (RTC) is a multi-domain protein responsible for replicating and transcribing the viral mRNA inside a human cell. Attacking RTC function with pharmaceutical compounds is a pathway to treating COVID-19. Conventional tools, e.g., cryo-electron microscopy and all-atom molecular dynamics (AAMD), do not provide sufficiently high resolution or timescale to capture important dynamics of this molecular machine. Consequently, we develop an innovative workflow that bridges the gap between these resolutions, using mesoscale fluctuating finite element analysis (FFEA) continuum simulations and a hierarchy of AI-methods that continually learn and infer features for maintaining consistency between AAMD and FFEA simulations. We leverage a multi-site distributed workflow manager to orchestrate AI, FFEA, and AAMD jobs, providing optimal resource utilization across HPC centers. Our study provides unprecedented access to study the SARS-CoV-2 RTC machinery, while providing general capability for AI-enabled multi-resolution simulations at scale.

Analysis of the ARTIC Version 3 and Version 4 SARS-CoV-2 Primers and Their Impact on the Detection of the G142D Amino Acid Substitution in the Spike Protein.

The ARTIC Network provides a common resource of PCR primer sequences and recommendations for amplifying SARS-CoV-2 genomes. The initial tiling strategy was developed with the reference genome Wuhan-01, and subsequent iterations have addressed areas of low amplification and sequence drop out. Recently, a new version (V4) was released, based on new variant genome sequences, in response to the realization that some V3 primers were located in regions with key mutations. Herein, we compare the performance of the ARTIC V3 and V4 primer sets with a matched set of 663 SARS-CoV-2 clinical samples sequenced with an Illumina NovaSeq 6000 instrument. We observe general improvements in sequencing depth and quality, and improved resolution of the SNP causing the D950N variation in the spike protein. Importantly, we also find nearly universal presence of spike protein substitution G142D in Delta-lineage samples. Due to the prior release and widespread use of the ARTIC V3 primers during the initial surge of the Delta variant, it is likely that the G142D amino acid substitution is substantially underrepresented among early Delta variant genomes deposited in public repositories. In addition to the improved performance of the ARTIC V4 primer set, this study also illustrates the importance of the primer scheme in downstream analyses. IMPORTANCE ARTIC Network primers are commonly used by laboratories worldwide to amplify and sequence SARS-CoV-2 present in clinical samples. As new variants have evolved and spread, it was found that the V3 primer set poorly amplified several key mutations. In this report, we compare the results of sequencing a matched set of samples with the V3 and V4 primer sets. We find that adoption of the ARTIC V4 primer set is critical for accurate sequencing of the SARS-CoV-2 spike region. The absence of metadata describing the primer scheme used will negatively impact the downstream use of publicly available SARS-Cov-2 sequencing reads and assembled genomes.

Pandemic drugs at pandemic speed: infrastructure for accelerating COVID-19 drug discovery with hybrid machine learning- and physics-based simulations on high-performance computers.

The race to meet the challenges of the global pandemic has served as a reminder that the existing drug discovery process is expensive, inefficient and slow. There is a major bottleneck screening the vast number of potential small molecules to shortlist lead compounds for antiviral drug development. New opportunities to accelerate drug discovery lie at the interface between machine learning methods, in this case, developed for linear accelerators, and physics-based methods. The two in silico methods, each have their own advantages and limitations which, interestingly, complement each other. Here, we present an innovative infrastructural development that combines both approaches to accelerate drug discovery. The scale of the potential resulting workflow is such that it is dependent on supercomputing to achieve extremely high throughput. We have demonstrated the viability of this workflow for the study of inhibitors for four COVID-19 target proteins and our ability to perform the required large-scale calculations to identify lead antiviral compounds through repurposing on a variety of supercomputers.

A genomic data resource for predicting antimicrobial resistance from laboratory-derived antimicrobial susceptibility phenotypes.

Antimicrobial resistance (AMR) is a major global health threat that affects millions of people each year. Funding agencies worldwide and the global research community have expended considerable capital and effort tracking the evolution and spread of AMR by isolating and sequencing bacterial strains and performing antimicrobial susceptibility testing (AST). For the last several years, we have been capturing these efforts by curating data from the literature and data resources and building a set of assembled bacterial genome sequences that are paired with laboratory-derived AST data. This collection currently contains AST data for over 67 000 genomes encompassing approximately 40 genera and over 100 species. In this paper, we describe the characteristics of this collection, highlighting areas where sampling is comparatively deep or shallow, and showing areas where attention is needed from the research community to improve sampling and tracking efforts. In addition to using the data to track the evolution and spread of AMR, it also serves as a useful starting point for building machine learning models for predicting AMR phenotypes. We demonstrate this by describing two machine learning models that are built from the entire dataset to show where the predictive power is comparatively high or low. This AMR metadata collection is freely available and maintained on the Bacterial and Viral Bioinformatics Center (BV-BRC) FTP site ftp://ftp.bvbrc.org/RELEASE_NOTES/PATRIC_genomes_AMR.txt.