references2.bib

@article{murphy_molecular_2019,
	title = {Molecular surveillance of hepatitis {C} virus genotypes identifies the emergence of a genotype 4d lineage among men in {Quebec}, 2001-2017},
	volume = {45},
	issn = {1188-4169},
	doi = {10.14745/ccdr.v45i09a02},
	abstract = {BACKGROUND: Molecular phylogenetics are generally used to confirm hepatitis C virus (HCV) transmission events. In addition, the Laboratoire de santé publique du Québec (LSPQ) has been using molecular phylogenetics for surveillance of HCV genotyping since November 2001.
OBJECTIVES: To describe the emergence of a specific lineage of HCV genotype 4d (G4d) and its characteristics using molecular phylogenetics as a surveillance tool for identifying HCV strain clustering.
METHODS: The LSPQ prospectively applied Sanger sequencing and phylogenetic analysis to determine the HCV genotype on samples collected from November 2001 to December 2017. When a major G4d cluster was identified, demographic information, HIV-infection status and syphilis test results were analyzed.
RESULTS: Phylogenetic analyses performed on approximately 22,000 cases identified 122 G4d cases. One major G4d cluster composed of 37 cases was singled out. Two cases were identified in 2010, 10 from 2011-2014 and 25 from 2015-2017. Cases in the cluster were concentrated in two urban health regions. Compared to the other G4d cases, cluster cases were all male (p{\textless}0.001) and more likely to be HIV-positive (adjusted risk ratio: 4.4; 95\% confidence interval: 2.5-7.9). A positive syphilis test result was observed for 27 (73\%) of the cluster cases. The sequences in this cluster and of four outlier cases were located on the same monophyletic lineage as G4d sequences reported in HIV-positive men who have sex with men (MSM) in Europe.
CONCLUSION: Molecular phylogenetics enabled the identification and surveillance of ongoing transmission of a specific HCV G4d lineage in HIV-positive and HIV-negative men in Quebec and its cross-continental spread. This information can orient intervention strategies to avoid transmission of HCV in MSM.},
	number = {9},
	journal = {Canada Communicable Disease Report = Releve Des Maladies Transmissibles Au Canada},
	author = {Murphy, D. G. and Dion, R. and Simard, M. and Vachon, M. L. and Martel-Laferrière, V. and Serhir, B. and Longtin, J.},
	month = sep,
	year = {2019},
	pmid = {31650986},
	pmcid = {PMC6781953},
	keywords = {G4d, HCV, MSM, cluster, genotype, men who have sex with men, molecular epidemiology, phylogenetic analyses, surveillance},
	pages = {230--237},
}

@article{paraskevis_application_2016,
	title = {The application of {HIV} molecular epidemiology to public health},
	volume = {46},
	issn = {1567-7257},
	doi = {10.1016/j.meegid.2016.06.021},
	abstract = {HIV is responsible for one of the largest viral pandemics in human history. Despite a concerted global response for prevention and treatment, the virus persists. Thus, urgent public health action, utilizing novel interventions, is needed to prevent future transmission events, critical to eliminating HIV. For public health planning to prove effective and successful, we need to understand the dynamics of regional epidemics and to intervene appropriately. HIV molecular epidemiology tools as implemented in phylogenetic, phylodynamic and phylogeographic analyses have proven to be powerful tools in public health planning across many studies. Numerous applications with HIV suggest that molecular methods alone or in combination with mathematical modelling can provide inferences about the transmission dynamics, critical epidemiological parameters (prevalence, incidence, effective number of infections, Re, generation times, time between infection and diagnosis), or the spatiotemporal characteristics of epidemics. Molecular tools have been used to assess the impact of an intervention and outbreak investigation which are of great public health relevance. In some settings, molecular sequence data may be more readily available than HIV surveillance data, and can therefore allow for molecular analyses to be conducted more easily. Nonetheless, classic methods have an integral role in monitoring and evaluation of public health programmes, and should supplement emerging techniques from the field of molecular epidemiology. Importantly, molecular epidemiology remains a promising approach in responding to viral diseases.},
	journal = {Infection, Genetics and Evolution: Journal of Molecular Epidemiology and Evolutionary Genetics in Infectious Diseases},
	author = {Paraskevis, D. and Nikolopoulos, G. K. and Magiorkinis, G. and Hodges-Mameletzis, I. and Hatzakis, A.},
	month = dec,
	year = {2016},
	pmid = {27312102},
	keywords = {HIV Infections, HIV-1, Humans, Molecular Epidemiology, Molecular epidemiology, Public Health, Public health},
	pages = {159--168},
}

@article{von_rotz_systematic_2023,
	title = {A systematic outbreak investigation of {SARS}-{CoV}-2 transmission clusters in a tertiary academic care center},
	volume = {12},
	issn = {2047-2994},
	doi = {10.1186/s13756-023-01242-y},
	abstract = {BACKGROUND: We sought to decipher transmission pathways in healthcare-associated infections with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) within our hospital by epidemiological work-up and complementary whole genome sequencing (WGS). We report the findings of the four largest epidemiologic clusters of SARS-CoV-2 transmission occurring during the second wave of the pandemic from 11/2020 to 12/2020.
METHODS: At the University Hospital Basel, Switzerland, systematic outbreak investigation is initiated at detection of any nosocomial case of SARS-CoV-2 infection, as confirmed by polymerase chain reaction, occurring more than five days after admission. Clusters of nosocomial infections, defined as the detection of at least two positive patients and/or healthcare workers (HCWs) within one week with an epidemiological link, were further investigated by WGS on respective strains.
RESULTS: The four epidemiologic clusters included 40 patients and 60 HCWs. Sequencing data was available for 70\% of all involved cases (28 patients and 42 HCWs), confirmed epidemiologically suspected in house transmission in 33 cases (47.1\% of sequenced cases) and excluded transmission in the remaining 37 cases (52.9\%). Among cases with identical strains, epidemiologic work-up suggested transmission mainly through a ward-based exposure (24/33, 72.7\%), more commonly affecting HCWs (16/24, 66.7\%) than patients (8/24, 33.3\%), followed by transmission between patients (6/33, 18.2\%), and among HCWs and patients (3/33, 9.1\%, respectively two HCWs and one patient).
CONCLUSIONS: Phylogenetic analyses revealed important insights into transmission pathways supporting less than 50\% of epidemiologically suspected SARS-CoV-2 transmissions. The remainder of cases most likely reflect community-acquired infection randomly detected by outbreak investigation. Notably, most transmissions occurred between HCWs, possibly indicating lower perception of the risk of infection during contacts among HCWs.},
	number = {1},
	journal = {Antimicrobial Resistance and Infection Control},
	author = {von Rotz, Matthias and Kuehl, Richard and Durovic, Ana and Zingg, Sandra and Apitz, Anett and Wegner, Fanny and Seth-Smith, Helena M. B. and Roloff, Tim and Leuzinger, Karoline and Hirsch, Hans H. and Kuster, Sabine and Battegay, Manuel and Mariani, Luigi and Schaeren, Stefan and Bassetti, Stefano and Banderet-Uglioni, Florian and Egli, Adrian and Tschudin-Sutter, Sarah},
	month = apr,
	year = {2023},
	pmid = {37085891},
	pmcid = {PMC10119817},
	keywords = {COVID-19, Cross Infection, Disease Outbreaks, Epidemiologic cluster, Humans, Nosocomial outbreaks, Outbreak investigation, Phylogeny, SARS-CoV-2, SARS-CoV-2 cluster, Tertiary Care Centers, Whole genome sequencing},
	pages = {38},
}

@article{campigotto_utility_2023,
	title = {Utility of {SARS}-{CoV}-2 {Genomic} {Sequencing} for {Understanding} {Transmission} and {School} {Outbreaks}},
	volume = {42},
	issn = {0891-3668},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9990487/},
	doi = {10.1097/INF.0000000000003834},
	abstract = {An understanding of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) transmission in schools is important. It is often difficult, using epidemiological information alone, to determine whether cases associated with schools represent multiple introductions from the community or transmission within the school. We describe the use of whole genome sequencing (WGS) in multiple schools to investigate outbreaks of SARS-CoV-2 in the pre-Omicron period.},
	number = {4},
	urldate = {2023-08-03},
	journal = {The Pediatric Infectious Disease Journal},
	author = {Campigotto, Aaron and Chris, Allison and Orkin, Julia and Lau, Lynette and Marshall, Christian and Bitnun, Ari and Buchan, Sarah A and MacDonald, Liane and Thampi, Nisha and McCready, Janine and Juni, Peter and Parekh, Rulan S and Science, Michelle},
	month = apr,
	year = {2023},
	pmid = {36795555},
	pmcid = {PMC9990487},
	pages = {324--331},
}

@article{thoma_challenge_2022,
	title = {The challenge of preventing and containing outbreaks of multidrug-resistant organisms and {Candida} auris during the coronavirus disease 2019 pandemic: report of a carbapenem-resistant {Acinetobacter} baumannii outbreak and a systematic review of the literature},
	volume = {11},
	issn = {2047-2994},
	shorttitle = {The challenge of preventing and containing outbreaks of multidrug-resistant organisms and {Candida} auris during the coronavirus disease 2019 pandemic},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8777447/},
	doi = {10.1186/s13756-022-01052-8},
	abstract = {Background
Despite the adoption of strict infection prevention and control measures, many hospitals have reported outbreaks of multidrug-resistant organisms (MDRO) during the Coronavirus 2019 (COVID-19) pandemic. Following an outbreak of carbapenem-resistant Acinetobacter baumannii (CRAB) in our institution, we sought to systematically analyse characteristics of MDRO outbreaks in times of COVID-19, focussing on contributing factors and specific challenges in controlling these outbreaks.

Methods
We describe results of our own CRAB outbreak investigation and performed a systematic literature review for MDRO (including Candida auris) outbreaks which occurred during the COVID-19 pandemic (between December 2019 and March 2021). Search terms were related to pathogens/resistance mechanisms AND COVID-19. We summarized outbreak characteristics in a narrative synthesis and contrasted contributing factors with implemented control measures.

Results
The CRAB outbreak occurred in our intensive care units between September and December 2020 and comprised 10 patients (thereof seven with COVID-19) within two distinct genetic clusters (both ST2 carrying OXA-23). Both clusters presumably originated from COVID-19 patients transferred from the Balkans. Including our outbreak, we identified 17 reports, mostly caused by Candida auris (n = 6) or CRAB (n = 5), with an overall patient mortality of 35\% (68/193). All outbreaks involved intensive care settings. Non-adherence to personal protective equipment (PPE) or hand hygiene (n = 11), PPE shortage (n = 8) and high antibiotic use (n = 8) were most commonly reported as contributing factors, followed by environmental contamination (n = 7), prolonged critical illness (n = 7) and lack of trained HCW (n = 7). Implemented measures mainly focussed on PPE/hand hygiene audits (n = 9), environmental cleaning/disinfection (n = 9) and enhanced patient screening (n = 8). Comparing potentially modifiable risk factors and control measures, we found the largest discrepancies in the areas of PPE shortage (risk factor in 8 studies, addressed in 2 studies) and patient overcrowding (risk factor in 5 studies, addressed in 0 studies).

Conclusions
Reported MDRO outbreaks during the COVID-19 pandemic were most often caused by CRAB (including our outbreak) and C. auris. Inadequate PPE/hand hygiene adherence, PPE shortage, and high antibiotic use were the most commonly reported potentially modifiable factors contributing to the outbreaks. These findings should be considered for the prevention of MDRO outbreaks during future COVID-19 waves.

Supplementary Information
The online version contains supplementary material available at 10.1186/s13756-022-01052-8.},
	urldate = {2023-07-28},
	journal = {Antimicrobial Resistance and Infection Control},
	author = {Thoma, Reto and Seneghini, Marco and Seiffert, Salomé N. and Vuichard Gysin, Danielle and Scanferla, Giulia and Haller, Sabine and Flury, Domenica and Boggian, Katia and Kleger, Gian-Reto and Filipovic, Miodrag and Nolte, Oliver and Schlegel, Matthias and Kohler, Philipp},
	month = jan,
	year = {2022},
	pmid = {35063032},
	pmcid = {PMC8777447},
	pages = {12},
}

@article{jombart_reconstructing_2011,
	title = {Reconstructing disease outbreaks from genetic data: a graph approach},
	volume = {106},
	copyright = {2011 The Genetics Society},
	issn = {1365-2540},
	shorttitle = {Reconstructing disease outbreaks from genetic data},
	url = {https://www.nature.com/articles/hdy201078},
	doi = {10.1038/hdy.2010.78},
	abstract = {Epidemiology and public health planning will increasingly rely on the analysis of genetic sequence data. In particular, genetic data coupled with dates and locations of sampled isolates can be used to reconstruct the spatiotemporal dynamics of pathogens during outbreaks. Thus far, phylogenetic methods have been used to tackle this issue. Although these approaches have proved useful for informing on the spread of pathogens, they do not aim at directly reconstructing the underlying transmission tree. Instead, phylogenetic models infer most recent common ancestors between pairs of isolates, which can be inadequate for densely sampled recent outbreaks, where the sample includes ancestral and descendent isolates. In this paper, we introduce a novel method based on a graph approach to reconstruct transmission trees directly from genetic data. Using simulated data, we show that our approach can efficiently reconstruct genealogies of isolates in situations where classical phylogenetic approaches fail to do so. We then illustrate our method by analyzing data from the early stages of the swine-origin A/H1N1 influenza pandemic. Using 433 isolates sequenced at both the hemagglutinin and neuraminidase genes, we reconstruct the likely history of the worldwide spread of this new influenza strain. The presented methodology opens new perspectives for the analysis of genetic data in the context of disease outbreaks.},
	language = {en},
	number = {2},
	urldate = {2023-07-28},
	journal = {Heredity},
	author = {Jombart, T. and Eggo, R. M. and Dodd, P. J. and Balloux, F.},
	month = feb,
	year = {2011},
	note = {Number: 2
Publisher: Nature Publishing Group},
	keywords = {Infectious-disease epidemiology, Phylogenetics},
	pages = {383--390},
}

@article{mai_mycobacterium_2018,
	title = {Mycobacterium tuberculosis {Drug} {Resistance} and {Transmission} among {Human} {Immunodeficiency} {Virus}–{Infected} {Patients} in {Ho} {Chi} {Minh} {City}, {Vietnam}},
	volume = {99},
	issn = {0002-9637},
	url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6283501/},
	doi = {10.4269/ajtmh.18-0185},
	abstract = {Vietnam has a high burden of tuberculosis (TB) and multidrug-resistant (MDR) TB, but drug resistance patterns and TB transmission dynamics among TB/human immunodeficiency virus (HIV) coinfected patients are not well described. We characterized 200 Mycobacterium tuberculosis isolates from TB/HIV coinfected patients diagnosed at the main TB referral hospital in Ho Chi Minh City, Vietnam. Phenotypic drug susceptibility testing (DST) for first-line drugs, spoligotyping, and 24-locus mycobacterial interspersed repetitive unit (MIRU-24) analysis was performed on all isolates. The 24-locus mycobacterial interspersed repetitive unit clusters and MDR isolates were subjected to whole genome sequencing (WGS). Most of the TB/HIV coinfected patients were young (162/174; 93.1\% aged {\textless} 45 years) males (173; 86.5\% male). Beijing (98; 49.0\%) and Indo-Oceanic (70; 35.0\%) lineage strains were most common. Phenotypic drug resistance was detected in 84 (42.0\%) isolates, of which 17 (8.5\%) were MDR; three additional MDR strains were identified on WGS. Strain clustering was reduced from 84.0\% with spoligotyping to 20.0\% with MIRU-24 typing and to 13.5\% with WGS. Whole genome sequencing identified five additional clusters, or members of clusters, not recognized by MIRU-24. In total, 13 small (two to three member) WGS clusters were identified, with less clustering among drug susceptible (2/27; 7.4\%) than among drug-resistant strains (25/27; 92.6\%). On phylogenetic analysis, strains from TB/HIV coinfected patients were interspersed among strains from the general community; no major clusters indicating transmission among people living with HIV were detected. Tuberculosis/HIV coinfection in Vietnam was associated with high rates of drug resistance and limited genomic evidence of ongoing M. tuberculosis transmission among HIV-infected patients.},
	number = {6},
	urldate = {2023-07-28},
	journal = {The American Journal of Tropical Medicine and Hygiene},
	author = {Mai, Trinh Quynh and Martinez, Elena and Menon, Ranjeeta and Van Anh, Nguyen Thi and Hien, Nguyen Tran and Marais, Ben J. and Sintchenko, Vitali},
	month = dec,
	year = {2018},
	pmid = {30382014},
	pmcid = {PMC6283501},
	pages = {1397--1406},
}

@article{golub_how_2012,
	title = {How {Homophily} {Affects} the {Speed} of {Learning} and {Best}-{Response} {Dynamics}},
	volume = {127},
	issn = {0033-5533},
	url = {https://doi.org/10.1093/qje/qjs021},
	doi = {10.1093/qje/qjs021},
	abstract = {We examine how the speed of learning and best-response processes depends on homophily: the tendency of agents to associate disproportionately with those having similar traits. When agents' beliefs or behaviors are developed by averaging what they see among their neighbors, then convergence to a consensus is slowed by the presence of homophily but is not influenced by network density (in contrast to other network processes that depend on shortest paths). In deriving these results, we propose a new, general measure of homophily based on the relative frequencies of interactions among different groups. An application to communication in a society before a vote shows how the time it takes for the vote to correctly aggregate information depends on the homophily and the initial information distribution.},
	number = {3},
	urldate = {2023-07-27},
	journal = {The Quarterly Journal of Economics},
	author = {Golub, Benjamin and Jackson, Matthew O.},
	month = aug,
	year = {2012},
	pages = {1287--1338},
}

@article{tamura_estimation_1993,
	title = {Estimation of the number of nucleotide substitutions in the control region of mitochondrial {DNA} in humans and chimpanzees.},
	volume = {10},
	issn = {0737-4038},
	url = {https://doi.org/10.1093/oxfordjournals.molbev.a040023},
	doi = {10.1093/oxfordjournals.molbev.a040023},
	abstract = {Examining the pattern of nucleotide substitution for the control region of mitochondrial DNA (mtDNA) in humans and chimpanzees, we developed a new mathematical method for estimating the number of transitional and transversional substitutions per site, as well as the total number of nucleotide substitutions. In this method, excess transitions, unequal nucleotide frequencies, and variation of substitution rate among different sites are all taken into account. Application of this method to human and chimpanzee data suggested that the transition/transversion ratio for the entire control region was approximately 15 and nearly the same for the two species. The 95\% confidence interval of the age of the common ancestral mtDNA was estimated to be 80,000-480,000 years in humans and 0.57-2.72 Myr in common chimpanzees.},
	number = {3},
	urldate = {2023-07-26},
	journal = {Molecular Biology and Evolution},
	author = {Tamura, K and Nei, M},
	month = may,
	year = {1993},
	pages = {512--526},
}

@article{bbosa_short_2020,
	title = {Short {Communication}: {Choosing} the {Right} {Program} for the {Identification} of {HIV}-1 {Transmission} {Networks} from {Nucleotide} {Sequences} {Sampled} from {Different} {Populations}},
	volume = {36},
	issn = {1931-8405},
	shorttitle = {Short {Communication}},
	doi = {10.1089/AID.2020.0033},
	abstract = {HIV-TRAnsmission Cluster Engine (HIV-TRACE) and Cluster Picker are some of the most widely used programs for identifying HIV-1 transmission networks from nucleotide sequences. However, choosing between these tools is subjective and often a matter of personal preference. Because these software use different algorithms to detect HIV-1 transmission networks, their optimal use is better suited with different sequence data sets and under different scenarios. The performance of these tools has previously been evaluated across a range of genetic distance thresholds without an assessment of the differences in the structure of networks identified. In this study, we tested both programs on the same HIV-1 pol sequence data set (n = 2,017) from three Ugandan populations to examine their performance across different risk groups and evaluate the structure of networks identified. HIV-TRACE that uses a single-linkage algorithm identified more nodes in the same networks that were connected by sparse links than Cluster Picker. This suggests that the choice of the program used for identifying networks should depend on the study aims, the characteristics of the population being investigated, dynamics of the epidemic, sampling design, and the nature of research questions being addressed for optimum results. HIV-TRACE could be more applicable with larger data sets where the aim is to identify larger clusters that represent distinct transmission chains and in more diverse populations where infection has occurred over a period of time. In contrast, Cluster Picker is applicable in situations where more closely connected clusters are expected in the studied populations.},
	number = {11},
	journal = {AIDS research and human retroviruses},
	author = {Bbosa, Nicholas and Ssemwanga, Deogratius and Kaleebu, Pontiano},
	month = nov,
	year = {2020},
	pmid = {32693608},
	pmcid = {PMC7698971},
	keywords = {Base Sequence, Cluster Analysis, Cluster Picker, HIV Infections, HIV-1, HIV-TRACE, Humans, Molecular Epidemiology, Phylogeny, cluster, pair, transmission network},
	pages = {948--951},
}

@article{brenner_role_2021,
	title = {The {Role} of {Phylogenetics} in {Unravelling} {Patterns} of {HIV} {Transmission} towards {Epidemic} {Control}: {The} {Quebec} {Experience} (2002-2020)},
	volume = {13},
	issn = {1999-4915},
	shorttitle = {The {Role} of {Phylogenetics} in {Unravelling} {Patterns} of {HIV} {Transmission} towards {Epidemic} {Control}},
	doi = {10.3390/v13081643},
	abstract = {Phylogenetics has been advanced as a structural framework to infer evolving trends in the regional spread of HIV-1 and guide public health interventions. In Quebec, molecular network analyses tracked HIV transmission dynamics from 2002-2020 using MEGA10-Neighbour-joining, HIV-TRACE, and MicrobeTrace methodologies. Phylogenetics revealed three patterns of viral spread among Men having Sex with Men (MSM, n = 5024) and heterosexuals (HET, n = 1345) harbouring subtype B epidemics as well as B and non-B subtype epidemics (n = 1848) introduced through migration. Notably, half of new subtype B infections amongst MSM and HET segregating as solitary transmissions or small cluster networks (2-5 members) declined by 70\% from 2006-2020, concomitant to advances in treatment-as-prevention. Nonetheless, subtype B epidemic control amongst MSM was thwarted by the ongoing genesis and expansion of super-spreader large cluster variants leading to micro-epidemics, averaging 49 members/cluster at the end of 2020. The growth of large clusters was related to forward transmission cascades of untreated early-stage infections, younger at-risk populations, more transmissible/replicative-competent strains, and changing demographics. Subtype B and non-B subtype infections introduced through recent migration now surpass the domestic epidemic amongst MSM. Phylodynamics can assist in predicting and responding to active, recurrent, and newly emergent large cluster networks, as well as the cryptic spread of HIV introduced through migration.},
	number = {8},
	journal = {Viruses},
	author = {Brenner, Bluma G. and Ibanescu, Ruxandra-Ilinca and Osman, Nathan and Cuadra-Foy, Ernesto and Oliveira, Maureen and Chaillon, Antoine and Stephens, David and Hardy, Isabelle and Routy, Jean-Pierre and Thomas, Réjean and Baril, Jean-Guy and Leblanc, Roger and Tremblay, Cecile and Roger, Michel and The Montreal Primary Hiv Infection Phi Cohort Study Group, null},
	month = aug,
	year = {2021},
	pmid = {34452506},
	pmcid = {PMC8402830},
	keywords = {Adult, Aged, Aged, 80 and over, Epidemics, Female, HIV Infections, HIV-1, HIV-1 transmission, HIV-TRACE, Homosexuality, Male, Humans, Male, Middle Aged, Phylogeny, Quebec, Young Adult, men having sex with men, migration, non-B subtypes, phylogenetics, treatment-as-prevention},
	pages = {1643},
}

@article{chato_public_2020,
	title = {Public health in genetic spaces: a statistical framework to optimize cluster-based outbreak detection},
	volume = {6},
	issn = {2057-1577},
	shorttitle = {Public health in genetic spaces},
	doi = {10.1093/ve/veaa011},
	abstract = {Genetic clustering is a popular method for characterizing variation in transmission rates for rapidly evolving viruses, and could potentially be used to detect outbreaks in 'near real time'. However, the statistical properties of clustering are poorly understood in this context, and there are no objective guidelines for setting clustering criteria. Here, we develop a new statistical framework to optimize a genetic clustering method based on the ability to forecast new cases. We analysed the pairwise Tamura-Nei (TN93) genetic distances for anonymized HIV-1 subtype B pol sequences from Seattle (n = 1,653) and Middle Tennessee, USA (n = 2,779), and northern Alberta, Canada (n = 809). Under varying TN93 thresholds, we fit two models to the distributions of new cases relative to clusters of known cases: 1, a null model that assumes cluster growth is strictly proportional to cluster size, i.e. no variation in transmission rates among individuals; and 2, a weighted model that incorporates individual-level covariates, such as recency of diagnosis. The optimal threshold maximizes the difference in information loss between models, where covariates are used most effectively. Optimal TN93 thresholds varied substantially between data sets, e.g. 0.0104 in Alberta and 0.016 in Seattle and Tennessee, such that the optimum for one population would potentially misdirect prevention efforts in another. For a given population, the range of thresholds where the weighted model conferred greater predictive accuracy tended to be narrow (±0.005 units), and the optimal threshold tended to be stable over time. Our framework also indicated that variation in the recency of HIV diagnosis among clusters was significantly more predictive of new cases than sample collection dates (ΔAIC {\textgreater} 50). These results suggest that one cannot rely on historical precedence or convention to configure genetic clustering methods for public health applications, especially when translating methods between settings of low-level and generalized epidemics. Our framework not only enables investigators to calibrate a clustering method to a specific public health setting, but also provides a variable selection procedure to evaluate different predictive models of cluster growth.},
	number = {1},
	journal = {Virus Evolution},
	author = {Chato, Connor and Kalish, Marcia L. and Poon, Art F. Y.},
	month = jan,
	year = {2020},
	pmid = {32190349},
	pmcid = {PMC7069216},
	keywords = {HIV prevention, genetic clustering, modifiable areal unit problem, molecular epidemiology, virus evolution},
	pages = {veaa011},
}

@article{dalai_combining_2018,
	title = {Combining {Phylogenetic} and {Network} {Approaches} to {Identify} {HIV}-1 {Transmission} {Links} in {San} {Mateo} {County}, {California}},
	volume = {9},
	issn = {1664-302X},
	doi = {10.3389/fmicb.2018.02799},
	abstract = {The HIV epidemic in San Mateo County is sustained by multiple overlapping risk groups and is an important hub for HIV transmission in northern California. Limited access to care has led historically to delayed clinical presentation, higher rates of opportunistic infections, and an increased prevalence of antiretroviral drug resistance. The virologic and clinical consequences of treatment within these multiple ethnic and behavioral groups are poorly understood, highlighting the need for efficient surveillance strategies that are able to elucidate transmission networks and drug resistance patterns. We obtained sequence data from a group of 316 HIV-positive individuals in the San Mateo AIDS Program over a 14-year period and integrated epidemiologic, phylogenetic, and network approaches to characterize transmission clusters, risk factors and drug resistance. Drug resistance mutations were identified using the Stanford HIV Drug Resistance Database. A maximum likelihood tree was inferred in RAxML and subjected to clustering analysis in Cluster Picker. Network analysis using pairwise genetic distances was performed in HIV-TRACE. Participants were primarily male (60\%), white Hispanics and non-Hispanics (32\%) and African American (20.6\%). The most frequent behavior risk factor was male-male sex (33.5\%), followed by heterosexual (23.4\%) and injection drug use (9.5\%). Nearly all sequences were subtype B (96\%) with subtypes A, C, and CRF01\_AE also observed. Sequences from 65\% of participants had at least one drug resistance mutation. Clustered transmissions included a higher number of women when compared to non-clustered individuals and were more likely to include heterosexual or people who inject drugs (PWID). Detailed analysis of the largest network (N = 47) suggested that PWID played a central role in overall transmission of HIV-1 as well as bridging men who have sex with men (MSM) transmission with heterosexual/PWID among primarily African American men. Combined phylogenetic and network analysis of HIV sequence data identified several overlapping risk factors in the epidemic, including MSM, heterosexual and PWID transmission with a disproportionate impact on African Americans and a high prevalence of drug resistance.},
	journal = {Frontiers in Microbiology},
	author = {Dalai, Sudeb C. and Junqueira, Dennis Maletich and Wilkinson, Eduan and Mehra, Renee and Kosakovsky Pond, Sergei L. and Levy, Vivian and Israelski, Dennis and de Oliveira, Tulio and Katzenstein, David},
	year = {2018},
	pmid = {30574123},
	pmcid = {PMC6292275},
	keywords = {California, HIV, network, phylogenetics, transmission links},
	pages = {2799},
}

@article{di_giallonardo_subtype-specific_2021,
	title = {Subtype-specific differences in transmission cluster dynamics of {HIV}-1 {B} and {CRF01}\_AE in {New} {South} {Wales}, {Australia}},
	volume = {24},
	issn = {1758-2652},
	doi = {10.1002/jia2.25655},
	abstract = {INTRODUCTION: The human immunodeficiency virus 1 (HIV-1) pandemic is characterized by numerous distinct sub-epidemics (clusters) that continually fuel local transmission. The aims of this study were to identify active growing clusters, to understand which factors most influence the transmission dynamics, how these vary between different subtypes and how this information might contribute to effective public health responses.
METHODS: We used HIV-1 genomic sequence data linked to demographic factors that accounted for approximately 70\% of all new HIV-1 notifications in New South Wales (NSW). We assessed differences in transmission cluster dynamics between subtype B and circulating recombinant form 01\_AE (CRF01\_AE). Separate phylogenetic trees were estimated using 2919 subtype B and 473 CRF01\_AE sequences sampled between 2004 and 2018 in combination with global sequence data and NSW-specific clades were classified as clusters, pairs or singletons. Significant differences in demographics between subtypes were assessed with Chi-Square statistics.
RESULTS: We identified 104 subtype B and 11 CRF01\_AE growing clusters containing a maximum of 29 and 11 sequences for subtype B and CRF01\_AE respectively. We observed a {\textgreater} 2-fold increase in the number of NSW-specific CRF01\_AE clades over time. Subtype B clusters were associated with individuals reporting men who have sex with men (MSM) as their transmission risk factor, being born in Australia, and being diagnosed during the early stage of infection (p {\textless} 0.01). CRF01\_AE infections clusters were associated with infections among individuals diagnosed during the early stage of infection (p {\textless} 0.05) and CRF01\_AE singletons were more likely to be from infections among individuals reporting heterosexual transmission (p {\textless} 0.05). We found six subtype B clusters with an above-average growth rate ({\textgreater}1.5 sequences / 6-months) and which consisted of a majority of infections among MSM. We also found four active growing CRF01\_AE clusters containing only infections among MSM. Finally, we found 47 subtype B and seven CRF01\_AE clusters that contained a large gap in time ({\textgreater}1 year) between infections and may be indicative of intermediate transmissions via undiagnosed individuals.
CONCLUSIONS: The large number of active and growing clusters among MSM are the driving force of the ongoing epidemic in NSW for subtype B and CRF01\_AE.},
	number = {1},
	journal = {Journal of the International AIDS Society},
	author = {Di Giallonardo, Francesca and Pinto, Angie N. and Keen, Phillip and Shaik, Ansari and Carrera, Alex and Salem, Hanan and Selvey, Christine and Nigro, Steven J. and Fraser, Neil and Price, Karen and Holden, Joanne and Lee, Frederick J. and Dwyer, Dominic E. and Bavinton, Benjamin R. and Geoghegan, Jemma L. and Grulich, Andrew E. and Kelleher, Anthony D. and {NSW HIV Prevention Partnership Project}},
	month = jan,
	year = {2021},
	pmid = {33474833},
	pmcid = {PMC7817915},
	keywords = {Australia, Cluster Analysis, Female, HIV Infections, HIV-1, HIV1, Heterosexuality, Homosexuality, Male, Humans, Longitudinal Studies, Male, New South Wales, Phylogeny, Recombination, Genetic, Risk Factors, Sexual and Gender Minorities, demographic differences, early infections, public health, subtype B and CRF01\_AE, transmission cluster},
	pages = {e25655},
}

@article{ding_characterizing_2022,
	title = {Characterizing genetic transmission networks among newly diagnosed {HIV}-1 infected individuals in eastern {China}: 2012–2016},
	volume = {17},
	issn = {1932-6203},
	shorttitle = {Characterizing genetic transmission networks among newly diagnosed {HIV}-1 infected individuals in eastern {China}},
	url = {https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0269973},
	doi = {10.1371/journal.pone.0269973},
	abstract = {We aimed to elucidate the characteristics of HIV molecular epidemiology and identify transmission hubs in eastern China using genetic transmission network and lineage analyses. HIV-TRACE was used to infer putative relationships. Across the range of epidemiologically-plausible genetic distance (GD) thresholds (0.1–2.0\%), a sensitivity analysis was performed to determine the optimal threshold, generating the maximum number of transmission clusters and providing reliable resolution without merging different small clusters into a single large cluster. Characteristics of genetically linked individuals were analyzed using logistic regression. Assortativity (shared characteristics) analysis was performed to infer shared attributes between putative partners. 1,993 persons living with HIV-1 were enrolled. The determined GD thresholds within subtypes CRF07\_BC, CRF01\_AE, and B were 0.5\%, 1.2\%, and 1.7\%, respectively, and 826 of 1,993 (41.4\%) sequences were linked with at least one other sequence, forming 188 transmission clusters of 2–80 sequences. Clustering rates for the main subtypes CRF01\_AE, CRF07\_BC, and B were 50.9\% (523/1027), 34.2\% (256/749), and 32.1\% (25/78), respectively. Median cluster sizes of these subtypes were 2 (2–52, n = 523), 2 (2–80, n = 256), and 3 (2–6, n = 25), respectively. Subtypes in individuals diagnosed and residing in Hangzhou city (OR = 1.423, 95\% CI: 1.168–1.734) and men who have sex with men (MSM) were more likely to cluster. Assortativity analysis revealed individuals were more likely to be genetically linked to individuals from the same age group (AIage = 0.090, P{\textless}0.001) and the same area of residency in Zhejiang (AIcity = 0.078, P{\textless}0.001). Additionally, students living with HIV were more likely to be linked with students than show a random distribution (AI student = 0.740, P{\textless}0.01). These results highlight the importance of Hangzhou City in the regional epidemic and show that MSM comprise the population rapidly transmitting HIV in Zhejiang Province. We also provide a molecular epidemiology framework for improving our understanding of HIV transmission dynamics in eastern China.},
	number = {6},
	urldate = {2022-10-05},
	journal = {PLOS ONE},
	author = {Ding, Xiaobei and Chaillon, Antoine and Pan, Xiaohong and Zhang, Jiafeng and Zhong, Ping and He, Lin and Chen, Wanjun and Fan, Qin and Jiang, Jun and Luo, Mingyu and Xia, Yan and Guo, Zhihong and Smith, Davey M.},
	month = jun,
	year = {2022},
	note = {Publisher: Public Library of Science},
	keywords = {China, Genetic linkage, HIV, HIV diagnosis and management, HIV epidemiology, HIV-1, Medical risk factors, Men who have sex with men},
	pages = {e0269973},
}

@article{erly_predictive_2021,
	title = {Predictive {Value} of {Time}-{Space} {Clusters} for {HIV} {Transmission} in {Washington} {State}, 2017-2019},
	volume = {87},
	issn = {1944-7884},
	doi = {10.1097/QAI.0000000000002675},
	abstract = {BACKGROUND: Pillar 4 of the United States' End the HIV Epidemic plan is to respond quickly to HIV outbreaks, but the utility of CDC's tool for identifying HIV outbreaks through time-space cluster detection has not been evaluated. The objective of this evaluation is to quantify the ability of the CDC time-space cluster criterion to predict future HIV diagnoses and to compare it to a space-time permutation statistic implemented in SaTScan software.
SETTING: Washington State from 2017 to 2019.
METHODS: We applied both cluster criteria to incident HIV cases in Washington State to identify clusters. Using a repeated-measures Poisson model, we calculated a rate ratio comparing the 6 months after cluster detection with a baseline rate from 24 to 12 months before the cluster was detected. We also compared the demographics of cases within clusters with all other incident cases.
RESULTS: The CDC criteria identified 17 clusters containing 192 cases in the 6 months after cluster detection, corresponding to a rate ratio of 1.25 (95\% confidence interval: 0.95 to 1.65) relative to baseline. The time-space permutation statistic identified 5 clusters containing 25 cases with a rate ratio of 2.27 (95\% confidence interval: 1.28 to 4.03). Individuals in clusters identified by the new criteria were more likely to be of Hispanic origin (61\% vs 20\%) and in rural areas (51\% vs 12\%).
CONCLUSIONS: The space-time permutation cluster analysis is a promising tool for identification of clusters with the largest growth potential for whom interruption may prove most beneficial.},
	number = {3},
	journal = {Journal of Acquired Immune Deficiency Syndromes (1999)},
	author = {Erly, Steven J. and Naismith, Kelly and Kerani, Roxanne and Buskin, Susan E. and Reuer, Jennifer R.},
	month = jul,
	year = {2021},
	pmid = {33675622},
	keywords = {Cluster Analysis, Disease Outbreaks, HIV Infections, HIV-1, Humans, Population Surveillance, Time Factors, Washington},
	pages = {912--917},
}

@article{fujimoto_methodological_2021,
	title = {Methodological synthesis of {Bayesian} phylodynamics, {HIV}-{TRACE}, and {GEE}: {HIV}-1 transmission epidemiology in a racially/ethnically diverse {Southern} {U}.{S}. context},
	volume = {11},
	copyright = {2021 The Author(s)},
	issn = {2045-2322},
	shorttitle = {Methodological synthesis of {Bayesian} phylodynamics, {HIV}-{TRACE}, and {GEE}},
	url = {https://www.nature.com/articles/s41598-021-82673-8},
	doi = {10.1038/s41598-021-82673-8},
	abstract = {This study introduces an innovative methodological approach to identify potential drivers of structuring HIV-1 transmission clustering patterns between different subpopulations in the culturally and racially/ethnically diverse context of Houston, TX, the largest city in the Southern United States. Using 6332 HIV-1 pol sequences from persons newly diagnosed with HIV during the period 2010–2018, we reconstructed HIV-1 transmission clusters, using the HIV-TRAnsmission Cluster Engine (HIV-TRACE); inferred demographic and risk parameters on HIV-1 transmission dynamics by jointly estimating viral transmission rates across racial/ethnic, age, and transmission risk groups; and modeled the degree of network connectivity by using generalized estimating equations (GEE). Our results indicate that Hispanics/Latinos are most vulnerable to the structure of transmission clusters and serve as a bridge population, acting as recipients of transmissions from Whites (3.0 state changes/year) and from Blacks (2.6 state changes/year) as well as sources of transmissions to Whites (1.8 state changes/year) and to Blacks (1.2 state changes/year). There were high rates of transmission and high network connectivity between younger and older Hispanics/Latinos as well as between younger and older Blacks. Prevention and intervention efforts are needed for transmission clusters that involve younger racial/ethnic minorities, in particular Hispanic/Latino youth, to reduce onward transmission of HIV in Houston.},
	number = {1},
	urldate = {2023-07-12},
	journal = {Scientific Reports},
	author = {Fujimoto, Kayo and Bahl, Justin and Wertheim, Joel O. and Del Vecchio, Natascha and Hicks, Joseph T. and Damodaran, Lambodhar and Hallmark, Camden J. and Lavingia, Richa and Mora, Ricardo and Carr, Michelle and Yang, Biru and Schneider, John A. and Hwang, Lu-Yu and McNeese, Marlene},
	month = feb,
	year = {2021},
	note = {Number: 1
Publisher: Nature Publishing Group},
	keywords = {Bioinformatics, HIV infections, Population genetics, Risk factors, Statistics},
	pages = {3325},
}

@article{gore_hiv_2022,
	title = {{HIV} {Response} {Interventions} that {Integrate} {HIV} {Molecular} {Cluster} and {Social} {Network} {Analysis}: {A} {Systematic} {Review}},
	volume = {26},
	issn = {1573-3254},
	shorttitle = {{HIV} {Response} {Interventions} that {Integrate} {HIV} {Molecular} {Cluster} and {Social} {Network} {Analysis}},
	doi = {10.1007/s10461-021-03525-0},
	abstract = {Due to improved efficiency and reduced cost of viral sequencing, molecular cluster analysis can be feasibly utilized alongside existing human immunodeficiency virus (HIV) prevention strategies. The goal of this paper is to elucidate how HIV molecular cluster and social network analyses are being integrated to implement HIV response interventions. We searched PubMed, Scopus, PsycINFO, and Cochrane Library databases for studies incorporating both HIV molecular cluster and social network data. We identified 32 articles that combined analyses of HIV molecular sequences and social or sexual networks. All studies were descriptive. Six studies described network interventions informed by molecular and social data but did not fully evaluate their efficacy. There is no current standard for incorporating molecular and social network analyses to inform interventions or data demonstrating its utility. More research must be conducted to delineate benefits and best practices for leveraging molecular data for network-based interventions.},
	number = {6},
	journal = {AIDS and behavior},
	author = {Gore, Daniel J. and Schueler, Kellie and Ramani, Santhoshini and Uvin, Arno and Phillips, Gregory and McNulty, Moira and Fujimoto, Kayo and Schneider, John},
	month = jun,
	year = {2022},
	pmid = {34779940},
	pmcid = {PMC9842229},
	keywords = {Cluster analysis, Cluster detection and response, Contact tracing, HIV, HIV Infections, Humans, Sexual Behavior, Social Networking, Social networks, Systematic review},
	pages = {1750--1792},
}

@article{h_acquisition_2021,
	title = {Acquisition and transmission of {HIV}-1 among migrants and {Chinese} in {Guangzhou}, {China} from 2008 to 2012: {Phylogenetic} analysis of surveillance data},
	volume = {92},
	issn = {1567-7257},
	shorttitle = {Acquisition and transmission of {HIV}-1 among migrants and {Chinese} in {Guangzhou}, {China} from 2008 to 2012},
	url = {https://pubmed.ncbi.nlm.nih.gov/33901684/},
	doi = {10.1016/j.meegid.2021.104870},
	abstract = {Our study demonstrates the impact of recent HIV-1 transmission between HIV-infected foreigners and Chinese natives on the HIV-1 epidemic in Guangzhou, China. Moreover, the results highlight the importance of phylogenetic analysis of HIV-1 surveillance data and the need for specific prevention strate …},
	urldate = {2022-12-19},
	journal = {Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases},
	author = {H, Yan and H, Wu and Y, Xia and L, Huang and Y, Liang and Q, Li and L, Chen and Z, Han and S, Tang},
	month = aug,
	year = {2021},
	pmid = {33901684},
	note = {Publisher: Infect Genet Evol},
}

@article{holmes_molecular_1995,
	title = {The molecular epidemiology of human immunodeficiency virus type 1 in {Edinburgh}},
	volume = {171},
	issn = {0022-1899},
	doi = {10.1093/infdis/171.1.45},
	abstract = {Human immunodeficiency virus (HIV) type 1 sequences obtained from HIV-infected persons in different risk groups in Edinburgh were studied to determine the number and origin of virus variants and patterns of virus transmission. Phylogenetic analysis revealed that 12 of 14 hemophiliac patients who had been exposed to a single common batch of factor VIII had closely related gag gene sequences. Sequences from intravenous drug users and patients infected through heterosexual contact formed another distinct group, and 2 other hemophiliacs formed a third group. However, epidemiologic relationships inferred from analysis of the V3 region of the env gene were less conclusive, especially when the V3 loop was taken in isolation. This appears to be due to the length of time since infection and the action of selection, which has favored the independent appearance of similar V3 loop variants.},
	number = {1},
	journal = {The Journal of Infectious Diseases},
	author = {Holmes, E. C. and Zhang, L. Q. and Robertson, P. and Cleland, A. and Harvey, E. and Simmonds, P. and Leigh Brown, A. J.},
	month = jan,
	year = {1995},
	pmid = {7798682},
	keywords = {Base Sequence, Cohort Studies, DNA, Viral, Drug Contamination, Factor VIII, Female, Gene Products, gag, Genetic Variation, HIV Antigens, HIV Envelope Protein gp120, HIV Infections, HIV-1, Hemophilia A, Humans, Male, Molecular Epidemiology, Molecular Sequence Data, Peptide Fragments, Phylogeny, Risk Factors, Scotland, Sexual Behavior, Substance Abuse, Intravenous, Viral Proteins, gag Gene Products, Human Immunodeficiency Virus},
	pages = {45--53},
}

@article{junqueira_factors_2019,
	title = {Factors influencing {HIV}-1 phylogenetic clustering},
	volume = {14},
	issn = {1746-6318},
	doi = {10.1097/COH.0000000000000540},
	abstract = {PURPOSE OF REVIEW: A major goal of public health in relation to HIV/AIDS is to prevent new transmissions in communities. Phylogenetic techniques have improved our understanding of the structure and dynamics of HIV transmissions. However, there is still no consensus about phylogenetic methodology, sampling coverage, gene target and/or minimum fragment size.
RECENT FINDINGS: Several studies use a combined methodology, which includes both a genetic or patristic distance cut-off and a branching support threshold to identify phylogenetic clusters. However, the choice about these thresholds remains an inherently subjective process, which affects the results of these studies. There is still a lack of consensus about the genomic region and the size of fragments that should be used, although there seems to be emerging a consensus that using longer segments, allied with the use of a realistic model of evolution and a codon alignment, increases the likelihood of inferring true transmission clusters. The pol gene is still the most used genomic region, but recent studies have suggested that whole genomes and/or sequences from nef and gp41 are also good targets for cluster reconstruction.
SUMMARY: The development and application of standard methodologies for phylogenetic clustering analysis will advance our understanding of factors associated with HIV transmission. This will lead to the design of more precise public health interventions.},
	number = {3},
	journal = {Current opinion in HIV and AIDS},
	author = {Junqueira, Dennis M. and Sibisi, Zandile and Wilkinson, Eduan and de Oliveira, Tulio},
	month = may,
	year = {2019},
	pmid = {30882487},
	keywords = {Animals, Classification, Cluster Analysis, Genome, Viral, HIV Infections, HIV-1, Humans, Phylogeny, Viral Proteins},
	pages = {161--172},
}

@article{kosakovsky_pond_hiv-trace_2018,
	title = {{HIV}-{TRACE} ({TRAnsmission} {Cluster} {Engine}): a {Tool} for {Large} {Scale} {Molecular} {Epidemiology} of {HIV}-1 and {Other} {Rapidly} {Evolving} {Pathogens}},
	volume = {35},
	issn = {1537-1719},
	shorttitle = {{HIV}-{TRACE} ({TRAnsmission} {Cluster} {Engine})},
	doi = {10.1093/molbev/msy016},
	abstract = {In modern applications of molecular epidemiology, genetic sequence data are routinely used to identify clusters of transmission in rapidly evolving pathogens, most notably HIV-1. Traditional 'shoe-leather' epidemiology infers transmission clusters by tracing chains of partners sharing epidemiological connections (e.g., sexual contact). Here, we present a computational tool for identifying a molecular transmission analog of such clusters: HIV-TRACE (TRAnsmission Cluster Engine). HIV-TRACE implements an approach inspired by traditional epidemiology, by identifying chains of partners whose viral genetic relatedness imply direct or indirect epidemiological connections. Molecular transmission clusters are constructed using codon-aware pairwise alignment to a reference sequence followed by pairwise genetic distance estimation among all sequences. This approach is computationally tractable and is capable of identifying HIV-1 transmission clusters in large surveillance databases comprising tens or hundreds of thousands of sequences in near real time, that is, on the order of minutes to hours. HIV-TRACE is available at www.hivtrace.org and from www.github.com/veg/hivtrace, along with the accompanying result visualization module from www.github.com/veg/hivtrace-viz. Importantly, the approach underlying HIV-TRACE is not limited to the study of HIV-1 and can be applied to study outbreaks and epidemics of other rapidly evolving pathogens.},
	number = {7},
	journal = {Molecular Biology and Evolution},
	author = {Kosakovsky Pond, Sergei L. and Weaver, Steven and Leigh Brown, Andrew J. and Wertheim, Joel O.},
	month = jul,
	year = {2018},
	pmid = {29401317},
	pmcid = {PMC5995201},
	keywords = {Computational Biology, HIV Infections, HIV-1, Humans, Molecular Epidemiology, Software},
	pages = {1812--1819},
}

@article{leung_molecular_2019,
	title = {Molecular {Characterization} of {HIV}-1 {Minority} {Subtypes} in {Hong} {Kong}: {A} {Recent} {Epidemic} of {CRF07}\_BC among the {Men} who have {Sex} with {Men} {Population}},
	volume = {17},
	issn = {1873-4251},
	shorttitle = {Molecular {Characterization} of {HIV}-1 {Minority} {Subtypes} in {Hong} {Kong}},
	doi = {10.2174/1570162X17666190530081355},
	abstract = {BACKGROUND: Over the past years, an increasing trend was noticed for non-B and non- CRF01\_AE HIV-1 strains prevalence in Hong Kong.
OBJECTIVE: In this study, we aimed at using the available HIV-1 pol sequences collected from 1994 to 2013 through our local antiretroviral resistance surveillance program to investigate the molecular epidemiology and evolution of HIV-1 minority subtypes in Hong Kong. We also aimed at investigating their potential association and impact of those transmission risk groups.
METHODS: A total of 2,315 HIV-1 partial pol sequences were included. HIV-1 genotypes were determined by REGA Genotyping Tool and phylogenetic analysis with reference sequences. The viral evolutionary rates and time of the most common ancestor (tMRCA) were estimated by Bayesian Markov Chain Monte Carlo (MCMC) interference.
RESULTS: Apart from the two prevalent HIV-1 genotypes in Hong Kong (subtype B,41.6\%, CRF01\_AE,40.5\%), phylogenetic analysis revealed a broad viral diversity including CRF07\_BC(5.1\%), subtype C(4.5\%), CRF02\_AG(1.1\%), CRF08\_BC(0.8\%), subtype A1(0.8\%), subtype G(0.4\%), subtype D(0.4\%), CRF06\_cpx(0.4\%), subtype F(0.1\%), CRF12\_BF(0·04\%) and other recombinants(4.5\%). The top five minority subtypes were further analyzed which demonstrated distinct epidemiological and phylogenetic patterns. Over 70\% of subtypes A1, C and CRF02\_AG infections were circulated among non-Chinese Asians or African community in Hong Kong and were mainly transmitted between heterosexual regular partners. Instead, over 90\% of CRF07\_BC and CRF08\_BC patients were Chinese. An epidemic cluster was identified in CRF07\_BC and estimated to expand from 2002 onwards based on skyline plot and molecular clock analysis.
CONCLUSION: Our results highlighted the emergence of CRF07\_BC epidemic in local MSM community, public health interventions targeting the community should be further enhanced to tackle the epidemic.},
	number = {1},
	journal = {Current HIV research},
	author = {Leung, Kenneth Siu-Sing and To, Sabrina Wai-Chi and Chen, Jonathan Hon-Kwan and Siu, Gilman Kit-Hang and Chan, Kenny Chi-Wai and Yam, Wing-Cheong},
	year = {2019},
	pmid = {31142258},
	keywords = {Adult, CRF07\_BC, Disease Transmission, Infectious, Epidemics, Female, Genotype, HIV Infections, HIV-1, HIV-1 epidemiology, HIV-1 minority subtypes, HIV-1 partial pol gene, Homosexuality, Male, Hong Kong, Humans, Male, Middle Aged, Molecular Epidemiology, Prevalence, Sequence Analysis, DNA, Young Adult, men-who-have-sexwith-
men, non-B non-AE transmission., pol Gene Products, Human Immunodeficiency Virus},
	pages = {53--64},
}

@article{liu_dynamics_2020,
	title = {Dynamics of {HIV}-1 {Molecular} {Networks} {Reveal} {Effective} {Control} of {Large} {Transmission} {Clusters} in an {Area} {Affected} by an {Epidemic} of {Multiple} {HIV} {Subtypes}},
	volume = {11},
	issn = {1664-302X},
	doi = {10.3389/fmicb.2020.604993},
	abstract = {This study reconstructed molecular networks of human immunodeficiency virus (HIV) transmission history in an area affected by an epidemic of multiple HIV-1 subtypes and assessed the efficacy of strengthened early antiretroviral therapy (ART) and regular interventions in preventing HIV spread. We collected demographic and clinical data of 2221 treatment-naïve HIV-1-infected patients in a long-term cohort in Shenyang, Northeast China, between 2008 and 2016. HIV pol gene sequencing was performed and molecular networks of CRF01\_AE, CRF07\_BC, and subtype B were inferred using HIV-TRACE with separate optimized genetic distance threshold. We identified 168 clusters containing ≥ 2 cases among CRF01\_AE-, CRF07\_BC-, and subtype B-infected cases, including 13 large clusters (≥ 10 cases). Individuals in large clusters were characterized by younger age, homosexual behavior, more recent infection, higher CD4 counts, and delayed/no ART (P {\textless} 0.001). The dynamics of large clusters were estimated by proportional detection rate (PDR), cluster growth predictor, and effective reproductive number (R e ). Most large clusters showed decreased or stable during the study period, indicating that expansion was slowing. The proportion of newly diagnosed cases in large clusters declined from 30 to 8\% between 2008 and 2016, coinciding with an increase in early ART within 6 months after diagnosis from 24 to 79\%, supporting the effectiveness of strengthened early ART and continuous regular interventions. In conclusion, molecular network analyses can thus be useful for evaluating the efficacy of interventions in epidemics with a complex HIV profile.},
	journal = {Frontiers in Microbiology},
	author = {Liu, Mingchen and Han, Xiaoxu and Zhao, Bin and An, Minghui and He, Wei and Wang, Zhen and Qiu, Yu and Ding, Haibo and Shang, Hong},
	year = {2020},
	pmid = {33281803},
	pmcid = {PMC7691493},
	keywords = {HIV-1, antiretroviral therapy, molecular epidemiology, phylodynamics, transmission cluster},
	pages = {604993},
}

@article{novitsky_impact_2014,
	title = {Impact of sampling density on the extent of {HIV} clustering},
	volume = {30},
	issn = {1931-8405},
	doi = {10.1089/aid.2014.0173},
	abstract = {Identifying and monitoring HIV clusters could be useful in tracking the leading edge of HIV transmission in epidemics. Currently, greater specificity in the definition of HIV clusters is needed to reduce confusion in the interpretation of HIV clustering results. We address sampling density as one of the key aspects of HIV cluster analysis. The proportion of viral sequences in clusters was estimated at sampling densities from 1.0\% to 70\%. A set of 1,248 HIV-1C env gp120 V1C5 sequences from a single community in Botswana was utilized in simulation studies. Matching numbers of HIV-1C V1C5 sequences from the LANL HIV Database were used as comparators. HIV clusters were identified by phylogenetic inference under bootstrapped maximum likelihood and pairwise distance cut-offs. Sampling density below 10\% was associated with stochastic HIV clustering with broad confidence intervals. HIV clustering increased linearly at sampling density {\textgreater}10\%, and was accompanied by narrowing confidence intervals. Patterns of HIV clustering were similar at bootstrap thresholds 0.7 to 1.0, but the extent of HIV clustering decreased with higher bootstrap thresholds. The origin of sampling (local concentrated vs. scattered global) had a substantial impact on HIV clustering at sampling densities ≥10\%. Pairwise distances at 10\% were estimated as a threshold for cluster analysis of HIV-1 V1C5 sequences. The node bootstrap support distribution provided additional evidence for 10\% sampling density as the threshold for HIV cluster analysis. The detectability of HIV clusters is substantially affected by sampling density. A minimal genotyping density of 10\% and sampling density of 50-70\% are suggested for HIV-1 V1C5 cluster analysis.},
	number = {12},
	journal = {AIDS research and human retroviruses},
	author = {Novitsky, Vlad and Moyo, Sikhulile and Lei, Quanhong and DeGruttola, Victor and Essex, Myron},
	month = dec,
	year = {2014},
	pmid = {25275430},
	pmcid = {PMC4250956},
	keywords = {Adolescent, Adult, Base Sequence, Cluster Analysis, HIV Envelope Protein gp120, HIV Infections, HIV-1, Humans, Middle Aged, Molecular Sequence Data, Phylogeny, Population Density, Sampling Studies, Young Adult},
	pages = {1226--1235},
}

@article{oster_identifying_2018,
	title = {Identifying {Clusters} of {Recent} and {Rapid} {HIV} {Transmission} {Through} {Analysis} of {Molecular} {Surveillance} {Data}},
	volume = {79},
	issn = {1944-7884},
	doi = {10.1097/QAI.0000000000001856},
	abstract = {BACKGROUND: Detecting recent and rapid spread of HIV can help prioritize prevention and early treatment for those at highest risk of transmission. HIV genetic sequence data can identify transmission clusters, but previous approaches have not distinguished clusters of recent, rapid transmission. We assessed an analytic approach to identify such clusters in the United States.
METHODS: We analyzed 156,553 partial HIV-1 polymerase sequences reported to the National HIV Surveillance System and inferred transmission clusters using 2 genetic distance thresholds (0.5\% and 1.5\%) and 2 periods for diagnoses (all years and 2013-2015, ie, recent diagnoses). For rapidly growing clusters (with ≥5 diagnoses during 2015), molecular clock phylogenetic analysis estimated the time to most recent common ancestor for all divergence events within the cluster. Cluster transmission rates were estimated using these phylogenies.
RESULTS: A distance threshold of 1.5\% identified 103 rapidly growing clusters using all diagnoses and 73 using recent diagnoses; at 0.5\%, 15 clusters were identified using all diagnoses and 13 using recent diagnoses. Molecular clock analysis estimated that the 13 clusters identified at 0.5\% using recent diagnoses had been diversifying for a median of 4.7 years, compared with 6.5-13.2 years using other approaches. The 13 clusters at 0.5\% had a transmission rate of 33/100 person-years, compared with previous national estimates of 4/100 person-years.
CONCLUSIONS: Our approach identified clusters with transmission rates 8 times those of previous national estimates. This method can identify groups involved in rapid transmission and help programs effectively direct and prioritize limited public health resources.},
	number = {5},
	journal = {Journal of Acquired Immune Deficiency Syndromes (1999)},
	author = {Oster, Alexandra M. and France, Anne Marie and Panneer, Nivedha and Bañez Ocfemia, M. Cheryl and Campbell, Ellsworth and Dasgupta, Sharoda and Switzer, William M. and Wertheim, Joel O. and Hernandez, Angela L.},
	month = dec,
	year = {2018},
	pmid = {30222659},
	pmcid = {PMC6231979},
	keywords = {Adult, Aged, Cluster Analysis, Epidemiological Monitoring, Female, Genotype, HIV Infections, HIV-1, Humans, Male, Middle Aged, Molecular Epidemiology, Sequence Analysis, DNA, United States, Young Adult, pol Gene Products, Human Immunodeficiency Virus},
	pages = {543--550},
}

@article{oster_hiv_2021,
	title = {{HIV} {Cluster} and {Outbreak} {Detection} and {Response}: {The} {Science} and {Experience}},
	volume = {61},
	issn = {1873-2607},
	shorttitle = {{HIV} {Cluster} and {Outbreak} {Detection} and {Response}},
	doi = {10.1016/j.amepre.2021.05.029},
	abstract = {The Respond pillar of the Ending the HIV Epidemic in the U.S. initiative, which consists of activities also known as cluster and outbreak detection and response, offers a framework to guide tailored implementation of proven HIV prevention strategies where transmission is occurring most rapidly. Cluster and outbreak response involves understanding the networks in which rapid transmission is occurring; linking people in the network to essential services; and identifying and addressing gaps in programs and services such as testing, HIV and other medical care, pre-exposure prophylaxis, and syringe services programs. This article reviews the experience gained through 30 HIV cluster and outbreak responses in North America during 2000-2020 to describe approaches for implementing these core response strategies. Numerous jurisdictions that have implemented these response strategies have demonstrated success in improving outcomes related to HIV care and viral suppression, testing, use of prevention services, and reductions in transmission or new diagnoses. Efforts to address important gaps in service delivery revealed by cluster and outbreak detection and response can strengthen prevention efforts broadly through multidisciplinary, multisector collaboration. In this way, the Respond pillar embodies the collaborative, data-guided approach that is critical to the overall success of the Ending the HIV Epidemic in the U.S. initiative.},
	number = {5 Suppl 1},
	journal = {American Journal of Preventive Medicine},
	author = {Oster, Alexandra M. and Lyss, Sheryl B. and McClung, R. Paul and Watson, Meg and Panneer, Nivedha and Hernandez, Angela L. and Buchacz, Kate and Robilotto, Susan E. and Curran, Kathryn G. and Hassan, Rashida and Ocfemia, M. Cheryl Bañez and Linley, Laurie and Perez, Stephen M. and Phillip, Stanley A. and France, Anne Marie},
	month = nov,
	year = {2021},
	pmid = {34686282},
	keywords = {Disease Outbreaks, HIV Infections, Humans, North America, Pre-Exposure Prophylaxis},
	pages = {S130--S142},
}

@article{paraskevis_application_2016-1,
	title = {The application of {HIV} molecular epidemiology to public health},
	volume = {46},
	issn = {1567-7257},
	doi = {10.1016/j.meegid.2016.06.021},
	abstract = {HIV is responsible for one of the largest viral pandemics in human history. Despite a concerted global response for prevention and treatment, the virus persists. Thus, urgent public health action, utilizing novel interventions, is needed to prevent future transmission events, critical to eliminating HIV. For public health planning to prove effective and successful, we need to understand the dynamics of regional epidemics and to intervene appropriately. HIV molecular epidemiology tools as implemented in phylogenetic, phylodynamic and phylogeographic analyses have proven to be powerful tools in public health planning across many studies. Numerous applications with HIV suggest that molecular methods alone or in combination with mathematical modelling can provide inferences about the transmission dynamics, critical epidemiological parameters (prevalence, incidence, effective number of infections, Re, generation times, time between infection and diagnosis), or the spatiotemporal characteristics of epidemics. Molecular tools have been used to assess the impact of an intervention and outbreak investigation which are of great public health relevance. In some settings, molecular sequence data may be more readily available than HIV surveillance data, and can therefore allow for molecular analyses to be conducted more easily. Nonetheless, classic methods have an integral role in monitoring and evaluation of public health programmes, and should supplement emerging techniques from the field of molecular epidemiology. Importantly, molecular epidemiology remains a promising approach in responding to viral diseases.},
	journal = {Infection, Genetics and Evolution: Journal of Molecular Epidemiology and Evolutionary Genetics in Infectious Diseases},
	author = {Paraskevis, D. and Nikolopoulos, G. K. and Magiorkinis, G. and Hodges-Mameletzis, I. and Hatzakis, A.},
	month = dec,
	year = {2016},
	pmid = {27312102},
	keywords = {HIV Infections, HIV-1, Humans, Molecular Epidemiology, Molecular epidemiology, Public Health, Public health},
	pages = {159--168},
}

@article{patil_exploring_2022,
	title = {Exploring the {Evolutionary} {History} and {Phylodynamics} of {Human} {Immunodeficiency} {Virus} {Type} 1 {Outbreak} {From} {Unnao}, {India} {Using} {Phylogenetic} {Approach}},
	volume = {13},
	issn = {1664-302X},
	doi = {10.3389/fmicb.2022.848250},
	abstract = {Certain rural and semiurban settings in the Unnao district, Uttar Pradesh, India observed an unprecedented increase in the detection of HIV cases during July 2017. Subsequent investigations through health camps and a follow-up case-control study attributed the outbreak to the unsafe injection exposures during treatment. In this study, we have undertaken a secondary analysis to understand the phylogenetic aspects of the outbreak-associated HIV-1 sequences along with the origin and phylodynamics of these sequences. The initial phylogenetic analysis indicated separate monophyletic grouping and there was no mixing of outbreak-associated sequences with sequences from other parts of India. Transmission network analysis using distance-based and non-distance-based methods revealed the existence of transmission clusters within the monophyletic Unnao clade. The median time to the most recent common ancestor (tMRCA) for sequences from Unnao using the pol gene region was observed to be 2011.87 [95\% highest posterior density (HPD): 2010.09-2013.53], while the estimates using envelope (env) gene region sequences traced the tMRCA to 2010.33 (95\% HPD: 2007.76-2012.99). Phylodynamics estimates demonstrated that the pace of this local epidemic has slowed down in recent times before the time of sampling, but was certainly on an upward track since its inception till 2014.},
	journal = {Frontiers in Microbiology},
	author = {Patil, Ajit and Patil, Sandip and Rao, Amrita and Gadhe, Sharda and Kurle, Swarali and Panda, Samiran},
	year = {2022},
	pmid = {35663884},
	pmcid = {PMC9158528},
	keywords = {HIV-1, Unnao, evolution, phylodynamics, transmission cluster},
	pages = {848250},
}

@article{peters_hiv_2016,
	title = {{HIV} {Infection} {Linked} to {Injection} {Use} of {Oxymorphone} in {Indiana}, 2014-2015},
	volume = {375},
	issn = {1533-4406},
	doi = {10.1056/NEJMoa1515195},
	abstract = {BACKGROUND: In January 2015, a total of 11 new diagnoses of human immunodeficiency virus (HIV) infection were reported in a small community in Indiana. We investigated the extent and cause of the outbreak and implemented control measures.
METHODS: We identified an outbreak-related case as laboratory-confirmed HIV infection newly diagnosed after October 1, 2014, in a person who either resided in Scott County, Indiana, or was named by another case patient as a syringe-sharing or sexual partner. HIV polymerase (pol) sequences from case patients were phylogenetically analyzed, and potential risk factors associated with HIV infection were ascertained.
RESULTS: From November 18, 2014, to November 1, 2015, HIV infection was diagnosed in 181 case patients. Most of these patients (87.8\%) reported having injected the extended-release formulation of the prescription opioid oxymorphone, and 92.3\% were coinfected with hepatitis C virus. Among 159 case patients who had an HIV type 1 pol gene sequence, 157 (98.7\%) had sequences that were highly related, as determined by phylogenetic analyses. Contact tracing investigations led to the identification of 536 persons who were named as contacts of case patients; 468 of these contacts (87.3\%) were located, assessed for risk, tested for HIV, and, if infected, linked to care. The number of times a contact was named as a syringe-sharing partner by a case patient was significantly associated with the risk of HIV infection (adjusted risk ratio for each time named, 1.9; P{\textless}0.001). In response to this outbreak, a public health emergency was declared on March 26, 2015, and a syringe-service program in Indiana was established for the first time.
CONCLUSIONS: Injection-drug use of extended-release oxymorphone within a network of persons who inject drugs in Indiana led to the introduction and rapid transmission of HIV. (Funded by the state government of Indiana and others.).},
	number = {3},
	journal = {The New England Journal of Medicine},
	author = {Peters, Philip J. and Pontones, Pamela and Hoover, Karen W. and Patel, Monita R. and Galang, Romeo R. and Shields, Jessica and Blosser, Sara J. and Spiller, Michael W. and Combs, Brittany and Switzer, William M. and Conrad, Caitlin and Gentry, Jessica and Khudyakov, Yury and Waterhouse, Dorothy and Owen, S. Michele and Chapman, Erika and Roseberry, Jeremy C. and McCants, Veronica and Weidle, Paul J. and Broz, Dita and Samandari, Taraz and Mermin, Jonathan and Walthall, Jennifer and Brooks, John T. and Duwve, Joan M. and {Indiana HIV Outbreak Investigation Team}},
	month = jul,
	year = {2016},
	pmid = {27468059},
	keywords = {Adolescent, Adult, Coinfection, Contact Tracing, Disease Outbreaks, HIV Infections, HIV-1, Hepatitis C, Humans, Indiana, Male, Middle Aged, Needle Sharing, Oxymorphone, Phylogeny, Social Support, Substance Abuse, Intravenous, Young Adult},
	pages = {229--239},
}

@article{potterat_risk_2002,
	title = {Risk network structure in the early epidemic phase of {HIV} transmission in {Colorado} {Springs}},
	volume = {78},
	copyright = {Copyright 2002 Sexually Transmitted Infections},
	issn = {1368-4973, 1472-3263},
	url = {https://sti.bmj.com/content/78/suppl_1/i159},
	doi = {10.1136/sti.78.suppl_1.i159},
	abstract = {This study describes the risk network structure of persons with HIV infection during its early epidemic phase in Colorado Springs, USA, using analysis of community-wide HIV/AIDS contact tracing records (sexual and injecting drug partners) from 1985 to 1999. Paired partner information from other STD/HIV programme records was used to augment network connections. Analyses were conducted with and without this supplemental information. The results suggest that a combined dendritic and cyclic structural network pattern is associated with low to moderate HIV propagation in Colorado Springs, and may account for the absence of intense propagation of the virus.},
	number = {suppl 1},
	urldate = {2023-07-12},
	journal = {Sexually Transmitted Infections},
	author = {Potterat, J. J. and Phillips-Plummer, L. and Muth, S. Q. and Rothenberg, R. B. and Woodhouse, D. E. and Maldonado-Long, T. S. and Zimmerman, H. P. and Muth, J. B.},
	month = apr,
	year = {2002},
	pmid = {12083437},
	note = {Publisher: The Medical Society for the Study of Venereal Disease
Section: Symposium},
	keywords = {HIV, epidemic phase, epidemiology, sexual network},
	pages = {i159--i163},
}

@article{ragonnet-cronin_forecasting_2022,
	title = {Forecasting {HIV}-1 {Genetic} {Cluster} {Growth} in {Illinois},{United} {States}},
	volume = {89},
	issn = {1944-7884},
	doi = {10.1097/QAI.0000000000002821},
	abstract = {BACKGROUND: HIV intervention activities directed toward both those most likely to transmit and their HIV-negative partners have the potential to substantially disrupt HIV transmission. Using HIV sequence data to construct molecular transmission clusters can reveal individuals whose viruses are connected. The utility of various cluster prioritization schemes measuring cluster growth have been demonstrated using surveillance data in New York City and across the United States, by the Centers for Disease Control and Prevention (CDC).
METHODS: We examined clustering and cluster growth prioritization schemes using Illinois HIV sequence data that include cases from Chicago, a large urban center with high HIV prevalence, to compare their ability to predict future cluster growth.
RESULTS: We found that past cluster growth was a far better predictor of future cluster growth than cluster membership alone but found no substantive difference between the schemes used by CDC and the relative cluster growth scheme previously used in New York City (NYC). Focusing on individuals selected simultaneously by both the CDC and the NYC schemes did not provide additional improvements.
CONCLUSION: Growth-based prioritization schemes can easily be automated in HIV surveillance tools and can be used by health departments to identify and respond to clusters where HIV transmission may be actively occurring.},
	number = {1},
	journal = {Journal of Acquired Immune Deficiency Syndromes (1999)},
	author = {Ragonnet-Cronin, Manon and Hayford, Christina and D'Aquila, Richard and Ma, Fangchao and Ward, Cheryl and Benbow, Nanette and Wertheim, Joel O.},
	month = jan,
	year = {2022},
	pmid = {34878434},
	pmcid = {PMC8667185},
	keywords = {Cluster Analysis, HIV Infections, HIV Seropositivity, HIV-1, Humans, Illinois, United States},
	pages = {49--55},
}

@article{rhee_national_2019,
	title = {National and {International} {Dimensions} of {Human} {Immunodeficiency} {Virus}-1 {Sequence} {Clusters} in a {Northern} {California} {Clinical} {Cohort}},
	volume = {6},
	issn = {2328-8957},
	doi = {10.1093/ofid/ofz135},
	abstract = {BACKGROUND: Recent advances in high-throughput molecular epidemiology are transforming the analysis of viral infections.
METHODS: Human immunodeficiency virus (HIV)-1 pol sequences from a Northern Californian cohort (NCC) of 4553 antiretroviral-naive individuals sampled between 1998 and 2016 were analyzed together with 140 000 previously published global pol sequences. The HIV-TRAnsmission Cluster Engine (HIV-TRACE) was used to infer a transmission network comprising links between NCC and previously published sequences having a genetic distance ≤1.5\%.
RESULTS: Twenty-five percent of NCC sequences were included in 264 clusters linked to a published sequence, and approximately one third of these (8.0\% of the total) were linked to 1 or more non-US sequences. The largest cluster, containing 512 NCC sequences (11.2\% of the total), comprised the subtype B lineage that traced its origin to the earliest North American sequences. Approximately 5 percent of NCC sequences belonged to a non-B subtype, and these were more likely to cluster with a non-US sequence. Twenty-two NCC sequences belonged to 1 of 4 large clusters containing sequences from rapidly growing regional epidemics: CRF07\_BC (East Asia), subtype A6 (former Soviet Union), a Japanese subtype B lineage, and an East/Southeast Asian CRF01\_AE lineage. Bayesian phylogenetics suggested that most non-B sequences resulted from separate introductions but that local spread within the largest CRF01\_AE cluster occurred twice.
CONCLUSIONS: The NCC contains national and international links to previously published sequences including many to the subtype B strain that originated in North America and several to rapidly growing Asian epidemics. Despite their rapid regional growth, the Asian epidemic strains demonstrated limited NCC spread.},
	number = {4},
	journal = {Open Forum Infectious Diseases},
	author = {Rhee, Soo-Yon and Magalis, Brittany R. and Hurley, Leo and Silverberg, Michael J. and Marcus, Julia L. and Slome, Sally and Kosakovsky Pond, Sergei L. and Shafer, Robert W.},
	month = apr,
	year = {2019},
	pmid = {31041344},
	pmcid = {PMC6483754},
	keywords = {HIV-1, network analysis, pol sequence, transmission},
	pages = {ofz135},
}

@article{rose_persistence_2020,
	title = {Persistence of {HIV} transmission clusters among people who inject drugs},
	volume = {34},
	issn = {1473-5571},
	doi = {10.1097/QAD.0000000000002662},
	abstract = {OBJECTIVE: We investigated the duration of HIV transmission clusters.
DESIGN: Fifty-four individuals newly infected at enrollment in the ALIVE cohort were included, all of whom had sequences at an intake visit (T1) and from a second (T2) and/or a third (T3) follow-up visit, median 2.9 and 5.4 years later, respectively.
METHODS: Sequences were generated using the 454 DNA sequencing platform for portions of HIV pol and env (HXB2 positions 2717-3230; 7941-8264). Genetic distances were calculated using tn93 and sequences were clustered over a range of thresholds (1--5\%) using HIV-TRACE. Analyses were performed separately for individuals with pol sequences for T1 + T2 (n = 40, 'Set 1') and T1 + T3 (n = 25; 'Set 2'), and env sequences for T1 + T2 (n = 47, 'Set 1'), and T1 + T3 (n = 30; 'Set 2').
RESULTS: For pol, with one exception, a single cluster contained more than 75\% of samples at all thresholds, and cluster composition was at least 90\% concordant between time points/thresholds. For env, two major clusters (A and B) were observed at T1 and T2/T3, although cluster composition concordance between time points/thresholds was low ({\textless}60\%) at lower thresholds for both sets 1 and 2. In addition, several individuals were included in clusters at T2/T3, although not at T1.
CONCLUSION: Caution should be used in applying a single threshold in population studies where seroconversion dates are unknown. However, the retention of some clusters even after 5 + years is evidence for the robustness of the clustering approach in general.},
	number = {14},
	journal = {AIDS (London, England)},
	author = {Rose, Rebecca and Cross, Sissy and Lamers, Susanna L. and Astemborski, Jacquie and Kirk, Greg D. and Mehta, Shruti H. and Sievers, Matthew and Martens, Craig and Bruno, Daniel and Redd, Andrew D. and Laeyendecker, Oliver},
	month = nov,
	year = {2020},
	pmid = {32773483},
	pmcid = {PMC9421556},
	keywords = {Cluster Analysis, Genes, env, HIV Infections, HIV-1, High-Throughput Nucleotide Sequencing, Humans, Phylogeny, Seroconversion, Substance Abuse, Intravenous, env Gene Products, Human Immunodeficiency Virus, pol Gene Products, Human Immunodeficiency Virus},
	pages = {2037--2044},
}

@article{sivay_hiv-1_2018,
	title = {{HIV}-1 diversity among young women in rural {South} {Africa}: {HPTN} 068},
	volume = {13},
	issn = {1932-6203},
	shorttitle = {{HIV}-1 diversity among young women in rural {South} {Africa}},
	doi = {10.1371/journal.pone.0198999},
	abstract = {BACKGROUND: South Africa has one of the highest rates of HIV-1 (HIV) infection world-wide, with the highest rates among young women. We analyzed the molecular epidemiology and evolutionary history of HIV in young women attending high school in rural South Africa.
METHODS: Samples were obtained from the HPTN 068 randomized controlled trial, which evaluated the effect of cash transfers for school attendance on HIV incidence in women aged 13-20 years (Mpumalanga province, 2011-2015). Plasma samples from HIV-infected participants were analyzed using the ViroSeq HIV-1 Genotyping assay. Phylogenetic analysis was performed using 200 pol gene study sequences and 2,294 subtype C reference sequences from South Africa. Transmission clusters were identified using Cluster Picker and HIV-TRACE, and were characterized using demographic and other epidemiological data. Phylodynamic analyses were performed using the BEAST software.
RESULTS: The study enrolled 2,533 young women who were followed through their expected high school graduation date (main study); some participants had a post-study assessment (follow-up study). Two-hundred-twelve of 2,533 enrolled young women had HIV infection. HIV pol sequences were obtained for 94\% (n = 201/212) of the HIV-infected participants. All but one of the sequences were HIV-1 subtype C; the non-C subtype sequence was excluded from further analysis. Median pairwise genetic distance between the subtype C sequences was 6.4\% (IQR: 5.6-7.2). Overall, 26\% of study sequences fell into 21 phylogenetic clusters with 2-6 women per cluster. Thirteen (62\%) clusters included women who were HIV-infected at enrollment. Clustering was not associated with study arm, demographic or other epidemiological factors. The estimated date of origin of HIV subtype C in the study population was 1958 (95\% highest posterior density [HPD]: 1931-1980), and the median estimated substitution rate among study pol sequences was 1.98x10-3 (95\% HPD: 1.15x10-3-2.81x10-3) per site per year.
CONCLUSIONS: Phylogenetic analysis suggests that multiple HIV subtype C sublineages circulate among school age girls in South Africa. There were no substantive differences in the molecular epidemiology of HIV between control and intervention arms in the HPTN 068 trial.},
	number = {7},
	journal = {PloS One},
	author = {Sivay, Mariya V. and Hudelson, Sarah E. and Wang, Jing and Agyei, Yaw and Hamilton, Erica L. and Selin, Amanda and Dennis, Ann and Kahn, Kathleen and Gomez-Olive, F. Xavier and MacPhail, Catherine and Hughes, James P. and Pettifor, Audrey and Eshleman, Susan H. and Grabowski, Mary Kathryn},
	year = {2018},
	pmid = {29975689},
	pmcid = {PMC6033411},
	keywords = {Adolescent, Adult, Female, Genes, pol, HIV Infections, HIV-1, Humans, Molecular Epidemiology, Phylogeny, South Africa, Young Adult},
	pages = {e0198999},
}

@article{vrancken_multi-faceted_2017,
	title = {The multi-faceted dynamics of {HIV}-1 transmission in {Northern} {Alberta}: {A} combined analysis of virus genetic and public health data},
	volume = {52},
	issn = {1567-7257},
	shorttitle = {The multi-faceted dynamics of {HIV}-1 transmission in {Northern} {Alberta}},
	doi = {10.1016/j.meegid.2017.04.005},
	abstract = {Molecular epidemiology has become a key tool for tracking infectious disease epidemics. Here, the spread of the most prevalent HIV-1 subtypes in Northern Alberta, Canada, was characterized with a Bayesian phylogenetic approach using 1146 HIV-1 pol sequences collected between 2007 and 2013 for routine clinical management purposes. Available patient metadata were qualitatively interpreted and correlated with onwards transmission using Fisher exact tests and logistic regression. Most infections were from subtypes A (n=36), B (n=815) and C (n=211). Africa is the dominant origin location for subtypes A and C while the subtype B epidemic was seeded from the USA and Middle America and, from the early 1990s onwards, mostly by interprovincial spread. Subtypes A (77.8\%) and C (74.0\%) were usually heterosexually transmitted and circulate predominantly among Blacks (61.1\% and 85\% respectively). Subtype B was mostly found among Caucasians (48.6\%) and First Nations (36.8\%), and its modes of transmission were stratified by ethnic origin. Compared to subtypes A (5.6\%) and C (3.8-10.0\%), a larger portion of subtype B patients were found within putative provincial transmission networks (20.3-29.5\%), and this almost doubled when focusing on nationwide transmission clusters (37.9-57.5\%). No clear association between cluster membership and particular patient characteristics was found. This study reveals complex and multi-faceted transmission dynamics of the HIV-1 epidemic in this otherwise low HIV prevalence population in Northern Alberta, Canada. These findings can aid public health planning.},
	journal = {Infection, Genetics and Evolution: Journal of Molecular Epidemiology and Evolutionary Genetics in Infectious Diseases},
	author = {Vrancken, B. and Adachi, D. and Benedet, M. and Singh, A. and Read, R. and Shafran, S. and Taylor, G. D. and Simmonds, K. and Sikora, C. and Lemey, P. and Charlton, C. L. and Tang, J. W.},
	month = aug,
	year = {2017},
	pmid = {28427935},
	keywords = {Adolescent, Adult, Africa, Aged, Alberta, Bayes Theorem, Bayesian phylogenetics, Central America, Female, HIV Infections, HIV-1, Humans, Male, Middle Aged, Phylodynamics, Phylogeny, Phylogeography, Public Health, Subtype A, Subtype B, Subtype C, United States, Young Adult, pol Gene Products, Human Immunodeficiency Virus},
	pages = {100--105},
}

@article{sizemore_using_2020,
	title = {Using an {Established} {Outbreak} {Response} {Plan} and {Molecular} {Epidemiology} {Methods} in an {HIV} {Transmission} {Cluster} {Investigation}, {Tennessee}, {January}-{June} 2017},
	volume = {135},
	issn = {1468-2877},
	doi = {10.1177/0033354920915445},
	abstract = {INTRODUCTION: In April 2017, the Tennessee Department of Health (TDH) was notified of an increase in the number of persons newly diagnosed with HIV in eastern Tennessee in the same month. Two were identified as persons with a history of injection drug use (IDU) and named each other as syringe-sharing partners, prompting an investigation into a possible HIV cluster among persons with a history of IDU.
MATERIALS AND METHODS: TDH and public health staff members in eastern Tennessee collaborated to implement procedures outlined in TDH's HIV/hepatitis C virus (HCV) Outbreak Response Plan, including conducting enhanced interviewing and using a preestablished database for data collection and management. To complement contact tracing and enhanced interviewing, TDH partnered with the Centers for Disease Control and Prevention to conduct molecular HIV analyses.
RESULTS: By June 27, 2017, the investigation had identified 31 persons newly diagnosed with HIV infection; 8 (26\%) self-reported IDU, 4 of whom were also men who have sex with men (MSM). Of the remaining 23 persons newly diagnosed with HIV infection, 10 were MSM who did not report IDU, 9 reported high-risk heterosexual contact, and 4 had other or unknown risk factors. Molecular analysis of the 14 HIV-1 polymerase genes (including 7 of the 8 persons self-reporting IDU) revealed 3 distinct molecular clusters, one of which included 3 persons self-reporting IDU.
PRACTICE IMPLICATIONS: This investigation highlights the importance of implementing an established Outbreak Response Plan and using HIV molecular analyses in the event of a transmission cluster or outbreak investigations. Future HIV outbreak surveillance will include using Global Hepatitis Outbreak Surveillance Technology to identify HCV gene sequences as a potential harbinger for HIV transmission networks.},
	number = {3},
	journal = {Public Health Reports (Washington, D.C.: 1974)},
	author = {Sizemore, Lindsey and Fill, Mary-Margaret and Mathieson, Samantha A. and Black, Jennifer and Brantley, Meredith and Cooper, Kelly and Garrett, Joy and Switzer, William M. and Peters, Philip J. and Wester, Carolyn},
	year = {2020},
	pmid = {32228123},
	pmcid = {PMC7238710},
	keywords = {Female, HIV, HIV Infections, Hepatitis C, Homosexuality, Male, Humans, Male, Molecular Epidemiology, Public Health Surveillance, Risk Factors, Sexual Behavior, Substance Abuse, Intravenous, Tennessee, investigation, risk factors, surveillance},
	pages = {329--333},
}

@article{tookes_rapid_2020,
	title = {Rapid {Identification} and {Investigation} of an {HIV} {Risk} {Network} {Among} {People} {Who} {Inject} {Drugs} -{Miami}, {FL}, 2018},
	volume = {24},
	issn = {1573-3254},
	doi = {10.1007/s10461-019-02680-9},
	abstract = {Prevention of HIV outbreaks among people who inject drugs remains a challenge to ending the HIV epidemic in the United States. The first legal syringe services program (SSP) in Florida implemented routine screening in 2018 leading to the identification of ten anonymous HIV seroconversions. The SSP collaborated with the Department of Health to conduct an epidemiologic investigation. All seven acute HIV seroconversions were linked to care (86\% within 30 days) and achieved viral suppression (mean 70 days). Six of the seven individuals are epidemiologically and/or socially linked to at least two other seroconversions. Analysis of the HIV genotypes revealed that two individuals are connected molecularly at 0.5\% genetic distance. We identified a risk network with complex transmission dynamics that could not be explained by epidemiological methods or molecular analyses alone. Providing wrap-around services through the SSP, including routine screening, intensive linkage and patient navigation, could be an effective model for achieving viral suppression for people who inject drugs.},
	number = {1},
	journal = {AIDS and behavior},
	author = {Tookes, Hansel and Bartholomew, Tyler S. and Geary, Shana and Matthias, James and Poschman, Karalee and Blackmore, Carina and Philip, Celeste and Suarez, Edward and Forrest, David W. and Rodriguez, Allan E. and Kolber, Michael A. and Knaul, Felicia and Colucci, Leah and Spencer, Emma},
	month = jan,
	year = {2020},
	pmid = {31555932},
	pmcid = {PMC6954140},
	keywords = {Adult, Aged, Disease Outbreaks, Female, Florida, HIV, HIV Infections, Humans, Male, Middle Aged, Molecular surveillance, Outbreak investigation, People who inject drugs, Risk-Taking, Sexual and Gender Minorities, Substance Abuse, Intravenous, United States},
	pages = {246--256},
}

@article{tumpney_human_2020,
	title = {Human {Immunodeficiency} {Virus} ({HIV}) {Outbreak} {Investigation} {Among} {Persons} {Who} {Inject} {Drugs} in {Massachusetts} {Enhanced} by {HIV} {Sequence} {Data}},
	volume = {222},
	issn = {1537-6613},
	doi = {10.1093/infdis/jiaa053},
	abstract = {BACKGROUND: The Massachusetts Department of Public Health and the Centers for Disease Control and Prevention collaborated to characterize a human immunodeficiency virus (HIV) outbreak in northeastern Massachusetts and prevent further transmission. We determined the contributions of HIV sequence data to defining the outbreak.
METHODS: Human immunodeficiency virus surveillance and partner services data were analyzed to understand social and molecular links within the outbreak. Cases were defined as HIV infections diagnosed during 2015-2018 among people who inject drugs with connections to northeastern Massachusetts or HIV infections among other persons named as partners of a case or whose HIV polymerase sequence linked to another case, regardless of diagnosis date or geography.
RESULTS: Of 184 cases, 65 (35\%) were first identified as part of the outbreak through molecular analysis. Twenty-nine cases outside of northeastern Massachusetts were molecularly linked to the outbreak. Large molecular clusters (75, 28, and 11 persons) were identified. Among 161 named partners, 106 had HIV; of those, 40 (38\%) diagnoses occurred through partner services.
CONCLUSIONS: Human immunodeficiency virus sequence data increased the case count by 55\% and expanded the geographic scope of the outbreak. Human immunodeficiency virus sequence and partner services data each identified cases that the other method would not have, maximizing prevention and care opportunities for HIV-infected persons and their partners.},
	number = {Suppl 5},
	journal = {The Journal of Infectious Diseases},
	author = {Tumpney, Matthew and John, Betsey and Panneer, Nivedha and McClung, R. Paul and Campbell, Ellsworth M. and Roosevelt, Kathleen and DeMaria, Alfred and Buchacz, Kate and Switzer, William M. and Lyss, Sheryl and Cranston, Kevin},
	month = sep,
	year = {2020},
	pmid = {32877558},
	keywords = {Adolescent, Adult, Contact Tracing, Disease Outbreaks, Drug Users, Epidemiological Monitoring, Female, HIV Infections, HIV outbreak investigation, HIV-1, Humans, Male, Massachusetts, Middle Aged, RNA, Viral, Sequence Analysis, RNA, Substance Abuse, Intravenous, Young Adult, molecular epidemiology, pol Gene Products, Human Immunodeficiency Virus, prevention, response},
	pages = {S259--S267},
}

@article{wang_targeting_2015,
	title = {Targeting {HIV} {Prevention} {Based} on {Molecular} {Epidemiology} {Among} {Deeply} {Sampled} {Subnetworks} of {Men} {Who} {Have} {Sex} {With} {Men}},
	volume = {61},
	issn = {1537-6591},
	doi = {10.1093/cid/civ526},
	abstract = {BACKGROUND: Molecular epidemiology can be useful in identifying clusters of human immunodeficiency virus (HIV) transmission that can be targeted for prevention.
METHODS: Regular screening of 2000 men who have sex with men (MSM) in Beijing, China, for HIV infection every 2 months identified 179 primary infections (2007-2010). HIV-1 pol sequences were obtained and used to infer the transmission network and identify transmitted drug resistance (TDR) among these individuals. We evaluated the use of clinical and network information to target prevention efforts. Prevention efficiency was calculated as the number of infections saved per number of interventions.
RESULTS: This cohort was infected with HIV-1 subtype B (28\%), circulating recombinant form (CRF)\_01 AE (53\%), and CRF\_07 BC (16\%). The overall rate of TDR was low (5\%), but the rate of clustering was high (64\%), suggesting deep sampling of the subnetwork. Provision of a theoretically high-efficacy intervention like antiretroviral therapy to all participants had a prevention efficiency of 23\%. The efficiency of targeting prevention based on lower CD4 counts ({\textless}200 cells/mL, {\textless}350 cells/mL, or {\textless}500 cells/mL) and higher viral loads ({\textgreater}100 000 copies/mL and {\textgreater}50 000 copies/mL) was between 10\% and 18\%. The efficiency of targeting prevention based on number of network connections was much higher (30\%-42\%). For example, treating the 33 participants with ≥5 connections in 2009 would have theoretically prevented 14 infections in 2010 (42\% prevention efficiency).
CONCLUSIONS: Regular HIV testing of MSM in Beijing can deeply sample the local transmission subnetwork, and targeting prevention efforts based on network connectivity may be an efficient way to deliver prevention interventions.},
	number = {9},
	journal = {Clinical Infectious Diseases: An Official Publication of the Infectious Diseases Society of America},
	author = {Wang, Xicheng and Wu, Yasong and Mao, Lin and Xia, Wei and Zhang, Weiwei and Dai, Lili and Mehta, Sanjay R. and Wertheim, Joel O. and Dong, Xingqi and Zhang, Tong and Wu, Hao and Smith, Davey M.},
	month = nov,
	year = {2015},
	pmid = {26129754},
	pmcid = {PMC4599390},
	keywords = {Adult, Aged, China, Cluster Analysis, Cohort Studies, Communicable Disease Control, Disease Transmission, Infectious, Genotype, HIV, HIV Infections, HIV-1, Homosexuality, Male, Humans, MSM, Male, Middle Aged, Molecular Epidemiology, Sequence Analysis, DNA, Young Adult, molecular epidemiology, pol Gene Products, Human Immunodeficiency Virus, targeted prevention},
	pages = {1462--1468},
}

@article{wolf_short_2017,
	title = {Short {Communication}: {Phylogenetic} {Evidence} of {HIV}-1 {Transmission} {Between} {Adult} and {Adolescent} {Men} {Who} {Have} {Sex} with {Men}},
	volume = {33},
	issn = {1931-8405},
	shorttitle = {Short {Communication}},
	doi = {10.1089/AID.2016.0061},
	abstract = {HIV-1 incidence among youth, especially men who have sex with men (MSM), is increasing in the United States. We aimed to better understand the patterns of adolescent HIV-1 acquisition, to help guide future prevention interventions. We conducted a study combining epidemiologic and HIV-1 pol sequence data from a retrospective cohort of HIV-infected adults and adolescents in Seattle, WA between 2000 and 2013. Adolescents were defined as 13-24 years of age at the time of first HIV-1 care. Maximum-likelihood phylogenetic trees were reconstructed to identify putative viral transmission clusters of two or more individuals, followed by multivariable regression tests of associations between clustering and demographic and clinical parameters. The dataset included 3,102 sequences from 1,953 individuals; 72 putative transmission clusters were identified, representing 168 individuals (8.6\%). MSM and MSM/intravenous drug use (IDU) were positively associated with clustering, with aOR 3.18 (95\% CI: 1.34-7.55) and 2.59 (95\% CI: 1.04-6.49), respectively. African American race was negatively associated with clustering (aOR 0.54 95\% CI: 0.32-0.91). Twenty-five clusters contained one adolescent and five clusters contained two adolescents. Other individuals who clustered with adolescents were predominantly male (95\%), white (85\%), and either MSM (66\%) or MSM/IDU (16\%), with a greater mean age (34 years vs. 22 years; p {\textless} .01). In this Seattle cohort, HIV-1 transmission linkages were identified between white male adolescents and older MSM adults. Interventions aimed at age-discrepant pairs may reduce HIV-1 infections in adolescent males.},
	number = {4},
	journal = {AIDS research and human retroviruses},
	author = {Wolf, Elizabeth and Herbeck, Joshua T. and Van Rompaey, Stephen and Kitahata, Mari and Thomas, Katherine and Pepper, Gregory and Frenkel, Lisa},
	month = apr,
	year = {2017},
	pmid = {27762596},
	pmcid = {PMC5372772},
	keywords = {Adolescent, Cluster Analysis, Female, Genotype, HIV Infections, HIV-1, Homosexuality, Male, Humans, Male, Molecular Epidemiology, Phylogeny, Retrospective Studies, Risk Factors, Sequence Analysis, DNA, Sequence Homology, Washington, Young Adult, adolescent, phylogenetics, pol Gene Products, Human Immunodeficiency Virus, transmission},
	pages = {318--322},
}

@article{yan_central_2020,
	title = {The {Central} {Role} of {Nondisclosed} {Men} {Who} {Have} {Sex} {With} {Men} in {Human} {Immunodeficiency} {Virus}-1 {Transmission} {Networks} in {Guangzhou}, {China}},
	volume = {7},
	issn = {2328-8957},
	doi = {10.1093/ofid/ofaa154},
	abstract = {BACKGROUND: Men who have sex with men (MSM) are vulnerable risk group for human immunodeficiency virus (HIV)-1 infection. However, some MSM do not disclose their same-sex behavior and could impact the transmission and prevention of HIV-1 infection. Here, we evaluated the role of nondisclosed MSM in HIV-1 transmission in Guangzhou, China.
METHODS: The HIV-1 pol sequences were obtained from HIV-infected subjects from 2008 to 2015. A transmission network was constructed using HIV TRAnsmission Cluster Engine (HIV-TRACE) at a pairwise genetic distance of 0.5\%. The position of nondisclosed MSM in the network was determined by centrality analysis.
RESULTS: Nondisclosed MSM were inferred in 9.92\% (61 of 615) of slightly older, self-reported non-MSM (P = .006). They were more likely to be married (P = .002) and less educated (P {\textless} .001) than the MSM with whom they clustered. Closeness centrality was bigger for nondisclosed MSM than for MSM (P {\textless} .001), indicating the central position of nondisclosed MSM in the networks. The average shortest path length was smaller for nondisclosed MSM than for MSM (P {\textless} .001), whereas radiality was bigger for nondisclosed MSM than for MSM, suggesting a relatively greater contribution of nondisclosed MSM in transmitting HIV-1 than MSM. Assortativity analysis indicated that nondisclosed MSM were more likely to link each other with coefficient of 0.025.
CONCLUSIONS: Nondisclosed MSM are a specific group, and they play an important role in HIV-1 transmission. They could be bisexual and might increase the risk of HIV-1 infection to their sex partners. Therefore, specific prevention and intervention targeting nondisclosed MSM are urgently needed.},
	number = {5},
	journal = {Open Forum Infectious Diseases},
	author = {Yan, Huanchang and He, Weiyun and Huang, Liping and Wu, Hao and Liang, Yuanhao and Li, Qingmei and Shui, Jingwei and Wang, Cheng and Dzakah, Emmanuel E. and Han, Zhigang and Tang, Shixing},
	month = may,
	year = {2020},
	pmid = {32500089},
	pmcid = {PMC7255645},
	keywords = {HIV-1, cluster analysis, men who have sex with men (MSM), nondisclosed MSM, transmission network},
	pages = {ofaa154},
}

@article{campbell_detailed_2017,
	title = {Detailed {Transmission} {Network} {Analysis} of a {Large} {Opiate}-{Driven} {Outbreak} of {HIV} {Infection} in the {United} {States}},
	volume = {216},
	issn = {0022-1899},
	url = {https://doi.org/10.1093/infdis/jix307},
	doi = {10.1093/infdis/jix307},
	abstract = {In January 2015, an outbreak of undiagnosed human immunodeficiency virus (HIV) infections among persons who inject drugs (PWID) was recognized in rural Indiana. By September 2016, 205 persons in this community of approximately 4400 had received a diagnosis of HIV infection. We report results of new approaches to analyzing epidemiologic and laboratory data to understand transmission during this outbreak. HIV genetic distances were calculated using the polymerase region. Networks were generated using data about reported high-risk contacts, viral genetic similarity, and their most parsimonious combinations. Sample collection dates and recency assay results were used to infer dates of infection. Epidemiologic and laboratory data each generated large and dense networks. Integration of these data revealed subgroups with epidemiologic and genetic commonalities, one of which appeared to contain the earliest infections. Predicted infection dates suggest that transmission began in 2011, underwent explosive growth in mid-2014, and slowed after the declaration of a public health emergency. Results from this phylodynamic analysis suggest that the majority of infections had likely already occurred when the investigation began and that early transmission may have been associated with sexual activity and injection drug use. Early and sustained efforts are needed to detect infections and prevent or interrupt rapid transmission within networks of uninfected PWID.},
	number = {9},
	urldate = {2023-07-12},
	journal = {The Journal of Infectious Diseases},
	author = {Campbell, Ellsworth M and Jia, Hongwei and Shankar, Anupama and Hanson, Debra and Luo, Wei and Masciotra, Silvina and Owen, S Michele and Oster, Alexandra M and Galang, Romeo R and Spiller, Michael W and Blosser, Sara J and Chapman, Erika and Roseberry, Jeremy C and Gentry, Jessica and Pontones, Pamela and Duwve, Joan and Peyrani, Paula and Kagan, Ron M and Whitcomb, Jeannette M and Peters, Philip J and Heneine, Walid and Brooks, John T and Switzer, William M},
	month = nov,
	year = {2017},
	pages = {1053--1062},
}

@article{weaver_datamonkey_2018,
	title = {Datamonkey 2.0: {A} {Modern} {Web} {Application} for {Characterizing} {Selective} and {Other} {Evolutionary} {Processes}},
	volume = {35},
	issn = {1537-1719},
	shorttitle = {Datamonkey 2.0},
	doi = {10.1093/molbev/msx335},
	abstract = {Inference of how evolutionary forces have shaped extant genetic diversity is a cornerstone of modern comparative sequence analysis. Advances in sequence generation and increased statistical sophistication of relevant methods now allow researchers to extract ever more evolutionary signal from the data, albeit at an increased computational cost. Here, we announce the release of Datamonkey 2.0, a completely re-engineered version of the Datamonkey web-server for analyzing evolutionary signatures in sequence data. For this endeavor, we leveraged recent developments in open-source libraries that facilitate interactive, robust, and scalable web application development. Datamonkey 2.0 provides a carefully curated collection of methods for interrogating coding-sequence alignments for imprints of natural selection, packaged as a responsive (i.e. can be viewed on tablet and mobile devices), fully interactive, and API-enabled web application. To complement Datamonkey 2.0, we additionally release HyPhy Vision, an accompanying JavaScript application for visualizing analysis results. HyPhy Vision can also be used separately from Datamonkey 2.0 to visualize locally executed HyPhy analyses. Together, Datamonkey 2.0 and HyPhy Vision showcase how scientific software development can benefit from general-purpose open-source frameworks. Datamonkey 2.0 is freely and publicly available at http://www.datamonkey.org, and the underlying codebase is available from https://github.com/veg/datamonkey-js.},
	number = {3},
	journal = {Molecular Biology and Evolution},
	author = {Weaver, Steven and Shank, Stephen D. and Spielman, Stephanie J. and Li, Michael and Muse, Spencer V. and Kosakovsky Pond, Sergei L.},
	month = mar,
	year = {2018},
	pmid = {29301006},
	pmcid = {PMC5850112},
	keywords = {evolutionary inference, natural selection, recombination, statistical methods, web application},
	pages = {773--777},
}