Influenza virus genotype to phenotype predictions through machine learning: a systematic review

Background: There is great interest in understanding the viral genomic predictors of phenotypic traits that allow influenza A viruses to adapt to or become more virulent in different hosts. Machine learning techniques have demonstrated promise in addressing this critical need for other pathogens because the underlying algorithms are especially well equipped to uncover complex patterns in large datasets and produce generalizable predictions for new data. As the body of research where these techniques are applied for influenza A virus phenotype prediction continues to grow, it is useful to consider the strengths and weaknesses of these approaches to understand what has prevented these models from seeing widespread use by surveillance laboratories and to identify gaps that are underexplored with this technology. Methods and Results: We present a systematic review of English literature published through 15 April 2021 of studies employing machine learning methods to generate predictions of influenza A virus phenotypes from genomic or proteomic input. Forty-nine studies were included in this review, spanning the topics of host discrimination, human adaptability, subtype and clade assignment, pandemic lineage assignment, characteristics of infection, and antiviral drug resistance. Conclusions: Our findings suggest that biases in model design and a dearth of wet laboratory follow-up may explain why these models often go underused. We, therefore, offer guidance to overcome these limitations, aid in improving predictive models of previously studied influenza A virus phenotypes, and extend those models to unexplored phenotypes in the ultimate pursuit of tools to enable the characterization of virus isolates across surveillance laboratories.

Transcriptome Sequencing of Peripheral Blood Mononuclear Cells from Elite Controller-Long Term Non Progressors

The elite controller (EC)-long term non-progressor (LTNP) phenotype represent a spontaneous and advantageous model of HIV-1 control in the absence of therapy. The transcriptome of peripheral blood mononuclear cells (PBMCs) collected from EC-LTNPs was sequenced by RNA-Seq and compared with the transcriptomes from other phenotypes of disease progression. The transcript abundance estimation combined with the use of supervised classification algorithms allowed the selection of 20 genes and pseudogenes, mainly involved in interferon-regulated antiviral mechanisms and cell machineries of transcription and translation, as the best predictive genes of disease progression. Differential expression analyses between phenotypes showed an altered calcium homeostasis in EC-LTNPs evidenced by the upregulation of several membrane receptors implicated in calcium-signaling cascades and intracellular calcium-mobilization and by the overrepresentation of NFAT1/Elk-1-binding sites in the promoters of the genes differentially expressed in these individuals. A coordinated upregulation of host genes associated with HIV-1 reverse transcription and viral transcription was also observed in EC-LTNPs –i.e. p21/CDKN1A, TNF, IER3 and GADD45B. We also found an upregulation of ANKRD54 in EC-LTNPs and viremic LTNPs in comparison with typical progressors and a clear alteration of type-I interferon signaling as a consequence of viremia in typical progressors before and after receiving antiretroviral therapy.

Deep-Sequencing Analysis of the Dynamics of HIV-1 Quasiespecies in Naive Patients during a Short Exposure to Maraviroc

In this study, we have characterized quasispecies dynamics and the evolution of viral tropism in naive HIV-1-infected patients treated with a short course of maraviroc monotherapy (ClinicalTrials.gov registration no. NCT01060618) independently of the tropism of the infecting virus. We randomly selected 20 patients infected with viruses displaying different basal tropisms-10 carrying R5 and 10 carrying dual/mixed X4 (DM/X4) viruses-at recruitment as determined by phenotypic assay (Trofile). Evolution of viral quasiespecies at the end of treatment was determined by ultradeep sequencing of the V3 region using a 454 Life Sciences Platform and geno2pheno (g2p) algorithm for viral tropism prediction. The false-positive rate (FPR) that defines the probability of classifying an R5 virus falsely as X4 was set at 10%. X4-specific HIV-1 viral load (VL) was calculated from sequences with an FPR of <3.75%. Virological response as defined as >1-log₁₀ copies/ml reduction in VL was detected in 70% of patients independently of the basal tropism of the infecting virus. Viral tropism remained stable, and nonsignificant differences in FPR values before and after treatment were found for the majority of patients in both tropism groups. Only three patients (one with R5 and two with DM/X4 viruses) showed an increased (>1 log) X4 VL, and one patient harboring a DM/X4-tropic virus displayed a significant reduction in FPR values at the end of treatment. Fast changes in the composition of viral populations were observed in all patients after 10 days of maraviroc (MVC) monotherapy treatment, and a complete replacement of viral quasiespecies was found in 3/10 patients carrying R5-using viruses and 4/10 patients carrying DM/X4-using viruses.IMPORTANCE Initiation of treatment with maraviroc requires previous determination of viral tropism by genotypic or phenotypic methods because of the risk of treatment failure and selection of DM/X4-tropic variants. In this study, we confirm previous work showing that the virologic response to maraviroc is independent of basal tropism. By deep-sequencing analysis, we determined that fast changes in viral populations were due to the emergence of minority variants in some patients whereas in others generation of new strains was detected. The risk of DM/X4 selection was very low as FPR values remained stable, and only one patient showed a detrimental switch to DM/X4 variants. Our data show that some DM/X4 viruses are sensitive to maraviroc treatment probably because only a low proportion of DM/X4 viruses use preferentially the X4 receptor and contain authentically maraviroc-resistant viruses that are not accurately detected by current assays.

Statistical correlation of nonconservative substitutions of HIV gp41 variable amino acid residues with the R5X4 HIV-1 phenotype

BACKGROUND

The interaction of the envelope glycoprotein of HIV-1 (gp120/gp41) with coreceptor molecules has important implications for specific cellular targeting and pathogenesis. Experimental and theoretical evidences have shown a role for gp41 in coreceptor tropism, although there is no consensus about the positions involved. Here we analyze the association of physicochemical properties of gp41 amino acid residues with viral tropism (X4, R5, and R5X4) using a large set of HIV-1 sequences. Under the assumption that conserved regions define the complex structural features essential for protein function, we focused our search only on amino acids in the gp41 variable regions.

METHODS

Gp41 amino acid sequences of 2823 HIV-1 strains from all clades with known coreceptor tropism were retrieved from Los Alamos HIV Database. Consensus sequences were constructed for homologous sequences (those obtained from the same patient and having the same tropism) in order to avoid bias due to sequence overrepresentation, and the variability (entropy) per site was determined. Comparisons of hydropathy index (HI) and charge (Q) of amino acid residues at highly variable positions between coreceptor groups were performed using two non-parametrical tests and Benjamini-Hochberg correction. Pearson's correlation analysis was performed to determine covariance of HI and Q values.

RESULTS

Calculation of variability per site rendered 58 highly variable amino acid positions. Of these, statistical analysis rendered significantly different HI or Q only for the R5 vs. R5X4 comparison at twelve positions: 535, 602, 619, 636, 640, 641, 658, 662, 667, 723, 756 and 841. The largest differences in particular amino acid frequencies between coreceptor groups were found at 619, 636, 640, 641, 662, 723 and 756. A hydrophobic tendency of residues 619, 640, 641, 723 and 756, along with a hydrophilic/charged tendency at residues 636 and 662 was observed in R5X4 with respect to R5 sequences. HI of position 640 covariated with that of 602, 619, 636, 662, and 756.

CONCLUSIONS

Variability and significant correlations of physicochemical properties with viral phenotype suggest that substitutions at residues in the loop (602 and 619), the HR2 (636, 640, 641, 662), and the C-terminal tail (723, 756) of gp41 may contribute to phenotype of R5X4 strains.

Reliable genotypic tropism tests for the major HIV-1 subtypes

Over the past decade antiretroviral drugs have dramatically improved the prognosis for HIV-1 infected individuals, yet achieving better access to vulnerable populations remains a challenge. The principal obstacle to the CCR5-antagonist, maraviroc, from being more widely used in anti-HIV-1 therapy regimens is that the pre-treatment genotypic "tropism tests" to determine virus susceptibility to maraviroc have been developed primarily for HIV-1 subtype B strains, which account for only 10% of infections worldwide. We therefore developed PhenoSeq, a suite of HIV-1 genotypic tropism assays that are highly sensitive and specific for establishing the tropism of HIV-1 subtypes A, B, C, D and circulating recombinant forms of subtypes AE and AG, which together account for 95% of HIV-1 infections worldwide. The PhenoSeq platform will inform the appropriate use of maraviroc and future CCR5 blocking drugs in regions of the world where non-B HIV-1 predominates, which are burdened the most by the HIV-1 pandemic.

IDEPI: rapid prediction of HIV-1 antibody epitopes and other phenotypic features from sequence data using a flexible machine learning platform

Since its identification in 1983, HIV-1 has been the focus of a research effort unprecedented in scope and difficulty, whose ultimate goals--a cure and a vaccine--remain elusive. One of the fundamental challenges in accomplishing these goals is the tremendous genetic variability of the virus, with some genes differing at as many as 40% of nucleotide positions among circulating strains. Because of this, the genetic bases of many viral phenotypes, most notably the susceptibility to neutralization by a particular antibody, are difficult to identify computationally. Drawing upon open-source general-purpose machine learning algorithms and libraries, we have developed a software package IDEPI (IDentify EPItopes) for learning genotype-to-phenotype predictive models from sequences with known phenotypes. IDEPI can apply learned models to classify sequences of unknown phenotypes, and also identify specific sequence features which contribute to a particular phenotype. We demonstrate that IDEPI achieves performance similar to or better than that of previously published approaches on four well-studied problems: finding the epitopes of broadly neutralizing antibodies (bNab), determining coreceptor tropism of the virus, identifying compartment-specific genetic signatures of the virus, and deducing drug-resistance associated mutations. The cross-platform Python source code (released under the GPL 3.0 license), documentation, issue tracking, and a pre-configured virtual machine for IDEPI can be found at https://github.com/veg/idepi.

A simple structure-based model for the prediction of HIV-1 co-receptor tropism

Background

Human Immunodeficiency Virus 1 enters host cells through interaction of its V3 loop (which is part of the gp120 protein) with the host cell receptor CD4 and one of two co-receptors, namely CCR5 or CXCR4. Entry inhibitors binding the CCR5 co-receptor can prevent viral entry. As these drugs are only available for CCR5-using viruses, accurate prediction of this so-called co-receptor tropism is important in order to ensure an effective personalized therapy. With the development of next-generation sequencing technologies, it is now possible to sequence representative subpopulations of the viral quasispecies.

Results

Here we present T-CUP 2.0, a model for predicting co-receptor tropism. Based on our recently published T-CUP model, we developed a more accurate and even faster solution. Similarly to its predecessor, T-CUP 2.0 models co-receptor tropism using information of the electrostatic potential and hydrophobicity of V3-loops. However, extracting this information from a simplified structural vacuum-model leads to more accurate and faster predictions. The area-under-the-ROC-curve (AUC) achieved with T-CUP 2.0 on the training set is 0.968±0.005 in a leave-one-patient-out cross-validation. When applied to an independent dataset, T-CUP 2.0 has an improved prediction accuracy of around 3% when compared to the original T-CUP.

Conclusions

We found that it is possible to model co-receptor tropism in HIV-1 based on a simplified structure-based model of the V3 loop. In this way, genotypic prediction of co-receptor tropism is very accurate, fast and can be applied to large datasets derived from next-generation sequencing technologies. The reduced complexity of the electrostatic modeling makes T-CUP 2.0 independent from third-party software, making it easy to install and use.

Development of a contemporary globally diverse HIV viral panel by the EQAPOL program

The significant diversity among HIV-1 variants poses serious challenges for vaccine development and for developing sensitive assays for screening, surveillance, diagnosis, and clinical management. Recognizing a need to develop a panel of HIV representing the current genetic and geographic diversity NIH/NIAID contracted the External Quality Assurance Program Oversight Laboratory (EQAPOL) to isolate, characterize and establish panels of HIV-1 strains representing global diverse subtypes and circulating recombinant forms (CRFs), and to make them available to the research community. HIV-positive plasma specimens and previously established isolates were collected through a variety of collaborations with a preference for samples from acutely/recently infected persons. Source specimens were cultured to high-titer/high-volume using well-characterized cryopreserved PBMCs from National y donors. Panel samples were stored as neat culture supernatant or diluted into defibrinated plasma. Characterization for the final expanded virus stocks included viral load, p24 antigen, infectivity (TCID), sterility, coreceptor usage, and near full-length genome sequencing. Viruses are made available to approved, interested laboratories using an online ordering application. The current EQAPOL Viral Diversity panel includes 100 viral specimens representing 6 subtypes (A, B, C, D, F, and G), 2 sub-subtypes (F1 and F2), 7 CRFs (01, 02, 04, 14, 22, 24, and 47), 19 URFs and 3 group O viruses from 22 countries. The EQAPOL Viral Diversity panel is an invaluable collection of well-characterized reagents that are available to the scientific community, including researchers, epidemiologists, and commercial manufacturers of diagnostics and pharmaceuticals to support HIV research, as well as diagnostic and vaccine development.

Bioinformatic analysis of HIV-1 entry and pathogenesis

The evolution of human immunodeficiency virus type 1 (HIV-1) with respect to co-receptor utilization has been shown to be relevant to HIV-1 pathogenesis and disease. The CCR5-utilizing (R5) virus has been shown to be important in the very early stages of transmission and highly prevalent during asymptomatic infection and chronic disease. In addition, the R5 virus has been proposed to be involved in neuroinvasion and central nervous system (CNS) disease. In contrast, the CXCR4-utilizing (X4) virus is more prevalent during the course of disease progression and concurrent with the loss of CD4(+) T cells. The dual-tropic virus is able to utilize both co-receptors (CXCR4 and CCR5) and has been thought to represent an intermediate transitional virus that possesses properties of both X4 and R5 viruses that can be encountered at many stages of disease. The use of computational tools and bioinformatic approaches in the prediction of HIV-1 co-receptor usage has been growing in importance with respect to understanding HIV-1 pathogenesis and disease, developing diagnostic tools, and improving the efficacy of therapeutic strategies focused on blocking viral entry. Current strategies have enhanced the sensitivity, specificity, and reproducibility relative to the prediction of co-receptor use; however, these technologies need to be improved with respect to their efficient and accurate use across the HIV-1 subtypes. The most effective approach may center on the combined use of different algorithms involving sequences within and outside of the env-V3 loop. This review focuses on the HIV-1 entry process and on co-receptor utilization, including bioinformatic tools utilized in the prediction of co-receptor usage. It also provides novel preliminary analyses for enabling identification of linkages between amino acids in V3 with other components of the HIV-1 genome and demonstrates that these linkages are different between X4 and R5 viruses.

Predominance of CXCR4 tropism in HIV-1 CRF14_BG strains from newly diagnosed infections

OBJECTIVES

R5-tropic viruses are associated with HIV-1 transmission and predominate during the early stages of infection. X4-tropic populations have been detected in ~50% of patients with late-stage disease infected with subtype B viruses. In this study, we compared the frequency of X4 tropism in individuals infected with HIV-1 CRF14_BG viruses, which have a V3 loop of subtype B, with a control group of individuals infected with subtype B viruses.

METHODS

Sixty-three individuals infected with HIV-1 CRF14_BG (n = 31) or subtype B (n = 32) were studied. Similar proportions of newly diagnosed and chronically infected individuals were included in the subtype B and CRF14_BG groups. V3 sequences were obtained and coreceptor tropism was predicted using the Geno2pheno[coreceptor] algorithm. V3 net charge and 11/25 rules were also used for coreceptor prediction.

RESULTS

Overall, X4 tropism was more frequent among individuals infected with CRF14_BG viruses (87.1%) than subtype B viruses (34.3%), a difference that was statistically highly significant (P = 0.00001). Importantly, the frequencies among newly diagnosed individuals were 90% and 13.3%, respectively (P = 0.0007). Characteristic amino acids in the V3 loop (T13, M14, V19 and W20) were identified at higher frequencies in CRF14_BG viruses (54%) than subtype B viruses (0%; P < 0.000001).

CONCLUSIONS

CRF14_BG is the genetic form with the highest proportion of X4-tropic viruses reported to date in newly diagnosed and chronic infections. This suggests high pathogenicity for CRF14_BG viruses, potentially leading to rapid disease progression. CCR5 antagonists will be ineffective in most CRF14_BG-infected patients, even at early stages of infection.