Data-Driven COVID-19 Vaccine Development for Janssen

The COVID-19 pandemic has spurred extensive vaccine research worldwide. One crucial part of vaccine development is the phase III clinical trial that assesses the vaccine for safety and efficacy in the prevention of COVID-19. In this work, we enumerate the first successful implementation of using machine learning models to accelerate phase III vaccine trials, working with the single-dose Johnson & Johnson vaccine to predictively select trial sites with naturally high incidence rates ("hotspots"). We develop DELPHI, a novel, accurate, policy-driven machine learning model that serves as the basis of our predictions. During the second half of 2020, the DELPHI-driven site selection identified hotspots with more than 90% accuracy, shortened trial duration by six to eight weeks (approximately 33%), and reduced enrollment by 15,000 (approximately 25%). In turn, this accelerated time to market enabled Janssen's vaccine to receive its emergency use authorization and realize its public health impact earlier than expected. Several geographies identified by DELPHI have since been the first areas to report variants of concern (e.g., Omicron in South Africa), and thus DELPHI's choice of these areas also produced early data on how the vaccine responds to new threats. Johnson & Johnson has also implemented a similar approach across its business including supporting trial site selection for other vaccine programs, modeling surgical procedure demand for its Medical Device unit, and providing guidance on return-to-work programs for its 130,000 employees. Continued application of this methodology can help shorten clinical development and change the economics of drug development by reducing the level of risk and cost associated with investing in novel therapies. This will allow Johnson & Johnson and others to enable more effective delivery of medicines to patients.

Inference from longitudinal laboratory tests characterizes temporal evolution of COVID-19-associated coagulopathy (CAC).

Temporal inference from laboratory testing results and triangulation with clinical outcomes extracted from unstructured electronic health record (EHR) provider notes is integral to advancing precision medicine. Here, we studied 246 SARS-CoV-2 PCR-positive (COVIDpos) patients and propensity-matched 2460 SARS-CoV-2 PCR-negative (COVIDneg) patients subjected to around 700,000 lab tests cumulatively across 194 assays. Compared to COVIDneg patients at the time of diagnostic testing, COVIDpos patients tended to have higher plasma fibrinogen levels and lower platelet counts. However, as the infection evolves, COVIDpos patients distinctively show declining fibrinogen, increasing platelet counts, and lower white blood cell counts. Augmented curation of EHRs suggests that only a minority of COVIDpos patients develop thromboembolism, and rarely, disseminated intravascular coagulopathy (DIC), with patients generally not displaying platelet reductions typical of consumptive coagulopathies. These temporal trends provide fine-grained resolution into COVID-19 associated coagulopathy (CAC) and set the stage for personalizing thromboprophylaxis.

Durability of Protection Post-Primary COVID-19 Vaccination in the United States.

The durability of immune responses after COVID-19 vaccination will drive long-term vaccine effectiveness across settings and may differ by vaccine type. To determine durability of protection of COVID-19 vaccines (BNT162b2, mRNA-1273, and Ad26.COV2.S) following primary vaccination in the United States, a matched case-control study was conducted in three cohorts between 1 January and 7 September 2021 using de-identified data from a database covering 168 million lives. Odds ratios (ORs) for developing outcomes of interest (breakthrough SARS-CoV-2 infection, hospitalization, or intensive care unit admission) were determined for each vaccine (no direct comparisons). In total, 17,017,435 individuals were identified. Relative to the baseline, stable protection was observed for Ad26.COV2.S against infections (OR [95% confidence interval (CI)], 1.31 [1.18-1.47]) and hospitalizations (OR [95% CI], 1.25 [0.86-1.80]). Relative to the baseline, protection waned over time against infections for BNT162b2 (OR [95% CI], 2.20 [2.01-2.40]) and mRNA-1273 (OR [95% CI], 2.07 [1.87-2.29]) and against hospitalizations for BNT162b2 (OR [95% CI], 2.38 [1.79-3.17]). Baseline protection remained stable for intensive care unit admissions for all three vaccines. Calculated baseline VE was consistent with published literature. This study suggests that the three vaccines in three separate populations may have different durability profiles.

Durability of Protection Post–Primary COVID-19 Vaccination in the United States

The durability of immune responses after COVID-19 vaccination will drive long-term vaccine effectiveness across settings and may differ by vaccine type. To determine durability of protection of COVID-19 vaccines (BNT162b2, mRNA-1273, and Ad26.COV2.S) following primary vaccination in the United States, a matched case-control study was conducted in three cohorts between 1 January and 7 September 2021 using de-identified data from a database covering 168 million lives. Odds ratios (ORs) for developing outcomes of interest (breakthrough SARS-CoV-2 infection, hospitalization, or intensive care unit admission) were determined for each vaccine (no direct comparisons). In total, 17,017,435 individuals were identified. Relative to the baseline, stable protection was observed for Ad26.COV2.S against infections (OR [95% confidence interval (CI)], 1.31 [1.18–1.47]) and hospitalizations (OR [95% CI], 1.25 [0.86–1.80]). Relative to the baseline, protection waned over time against infections for BNT162b2 (OR [95% CI], 2.20 [2.01–2.40]) and mRNA-1273 (OR [95% CI], 2.07 [1.87–2.29]) and against hospitalizations for BNT162b2 (OR [95% CI], 2.38 [1.79–3.17]). Baseline protection remained stable for intensive care unit admissions for all three vaccines. Calculated baseline VE was consistent with published literature. This study suggests that the three vaccines in three separate populations may have different durability profiles.

An infodemiological framework for tracking the spread of SARS-CoV-2 using integrated public data.

The outbreak of the SARS-CoV-2 novel coronavirus has caused a health crisis of immeasurable magnitude. Signals from heterogeneous public data sources could serve as early predictors for infection waves of the pandemic, particularly in its early phases, when infection data was scarce. In this article, we characterize temporal pandemic indicators by leveraging an integrated set of public data and apply them to a Prophet model to predict COVID-19 trends. An effective natural language processing pipeline was first built to extract time-series signals of specific articles from a news corpus. Bursts of these temporal signals were further identified with Kleinberg's burst detection algorithm. Across different US states, correlations for Google Trends of COVID-19 related terms, COVID-19 news volume, and publicly available wastewater SARS-CoV-2 measurements with weekly COVID-19 case numbers were generally high with lags ranging from 0 to 3 weeks, indicating them as strong predictors of viral spread. Incorporating time-series signals of these effective predictors significantly improved the performance of the Prophet model, which was able to predict the COVID-19 case numbers between one and two weeks with average mean absolute error rates of 0.38 and 0.46 respectively across different states.

Durability of the Single-Dose Ad26.COV2.S Vaccine in the Prevention of COVID-19 Infections and Hospitalizations in the US Before and During the Delta Variant Surge.

Importance: Vaccination against the SARS-CoV-2 virus is critical to control the pandemic. Randomized clinical trials demonstrated efficacy of the single-dose Ad26.COV2.S COVID-19 vaccine, but data on longer-term protection in clinical practice and effectiveness against variants are needed. Objective: To assess the association between receiving the Ad26.COV2.S vaccine and COVID-19-related infections and hospitalizations before and during the Delta variant surge. Design, Setting, and Participants: This cohort study included adults aged 18 years and older who were newly Ad26.COV2.S-vaccinated matched to as many as 10 unvaccinated individuals by date, location, age, sex, and comorbidity index. This was followed by 1:4 propensity score matching on COVID-19 risk factors. Data were collected from US insurance claims data from March 1, 2020, through August 31, 2021. Exposures: Vaccination with Ad26.COV2.S vs no vaccination. Main Outcomes and Measures: Vaccine effectiveness (VE) was estimated for recorded COVID-19 infection and COVID-19-related hospitalization, nationwide and in subgroups by age, high-risk factors, calendar time, and states with high incidences of the Delta variant. VE estimates were corrected for underrecording of vaccinations in insurance data. Results: Among 422 034 vaccinated individuals (mean [SD] age, 54.7 [17.4] years; 236 437 [56.0%] women) and 1 645 397 matched unvaccinated individuals (mean [SD] age, 54.5 [17.5] years; 922 937 [56.1%] women), VE was 76% (95% CI, 75%-77%) for COVID-19 infections and 81% (95% CI, 78%-82%) for COVID-19-related hospitalizations. VE was stable for at least 180 days after vaccination and over calendar time. Among states with high Delta variant incidence, VE during June to August 2021 was 74% (95% CI, 71%-77%) for infections and 81% (95% CI, 75%-86%) for hospitalizations. VE for COVID-19 was higher in individuals younger than 65 years (78%; 95% CI, 77%-79%) and lower in immunocompromised patients (64%; 95% CI, 59%-68%). All estimates were corrected for vaccination underrecording; uncorrected VE, which served as a lower bound, was 66% (95% CI, 64%-67%) for any recorded COVID-19 infection and 72% (95% CI, 69%-74%) for COVID-19-related hospitalization. Conclusions and Relevance: This cohort study in US clinical practice showed stable VE of Ad26.COV2.S for at least 6 months before as well as during the time the Delta variant emerged and became dominant.

Knowledge synthesis of 100 million biomedical documents augments the deep expression profiling of coronavirus receptors.

The COVID-19 pandemic demands assimilation of all biomedical knowledge to decode mechanisms of pathogenesis. Despite the recent renaissance in neural networks, a platform for the real-time synthesis of the exponentially growing biomedical literature and deep omics insights is unavailable. Here, we present the nferX platform for dynamic inference from over 45 quadrillion possible conceptual associations from unstructured text, and triangulation with insights from single-cell RNA-sequencing, bulk RNA-seq and proteomics from diverse tissue types. A hypothesis-free profiling of ACE2 suggests tongue keratinocytes, olfactory epithelial cells, airway club cells and respiratory ciliated cells as potential reservoirs of the SARS-CoV-2 receptor. We find the gut as the putative hotspot of COVID-19, where a maturation correlated transcriptional signature is shared in small intestine enterocytes among coronavirus receptors (ACE2, DPP4, ANPEP). A holistic data science platform triangulating insights from structured and unstructured data holds potential for accelerating the generation of impactful biological insights and hypotheses.