PILOT PROJECTS
The goal of the pilot projects is to broaden the research objectives of the hub by including projects that assess the effects of climate change on health, and projects that explore additional pathogens beyond SARS-CoV-2 and HIV. Additionally, the pilot projects seek to extend the geographical scope of INFORM Africa’s research focus to additional regions in Africa with the purpose of generating new data to bear on already existing data.
In December 2022, the INFORM Africa research hub published a call for letters of interest (LOIs), and subsequently conducted a series of reviews to select applicants eligible for a full proposal submission. The selection process was concluded in July, 2023, with the selection of five (5) projects from both internal and external applicants. The pilot projects are intended to run for a period of 12 months, with total funding of $30,000 for each project selected.
PILOT PROJECT 1
Project Title: Predicting COVID-19 variants in Africa through Active Learning and Hierarchical Classification
Joicymara Xavier, PhD
Project Lead
Dr. Joicymara Xavier is a PhD in Bioinformatics from the Federal University of Minas Gerais (UFMG, Belo Horizonte, Brazil) with a Research Internship at the Center of Epidemic Response and Innovation (CERI, Stellenbosch University, South Africa). She is currently a tenured Assistant Professor at the Federal University of Vales of Jequitinhonha and Mucuri (Brazil), a Research Fellow at the School for Data Science and Computational Thinking (CERI, Stellenbosch University), a Data Science consultant in the DS-I INFORM Africa project, and the Principal Investigator of the INFORM Africa pilot project titled “Predicting COVID-19 variants in Africa through Active Learning and Hierarchical Classification.”
During her doctoral journey, Dr. Xavier received three prestigious awards, including the best thesis in Biological Sciences defended in Brazil in 2022. Her thesis, “ThermoMutDB and SARS-CoV-2 Africa Dashboard: data science approaches for biological data integration, analytics, and surveillance”, has generated attention for its innovative solutions to integrate biomedical and surveillance data.
Dr. Xavier also leads an NGO, Code X, that aims to introduce technological concepts to young and vulnerable girls. Prior to her PhD., Dr. Xavier also earned a Master’s in Computer Science and Bachelor’s degree in Information Systems, gaining valuable experience in Software Engineering and Computer Science projects.
Dr. Xavier has published her research in leading Bioinformatics journals, including Nature Microbiology, Nucleic Acids Research, and Briefings in Bioinformatics. Her research interests include Biological Data Engineering, Health Informatics, Machine Learning, and Mutation Effects Analysis.
PROJECT DESCRIPTION
An ongoing challenge in the COVID-19 pandemic is the timely and accurate classification of SARS-CoV-2 sequences with the plethora of available genomic data. Two popular tools for the dynamic classification of SARS-CoV-2 genetic lineages are Phylogenetic Assignment of Named Global Outbreak Lineages (PANGOLIN) and Nextclade (of Nextstrain). However, these tools are not designed to automatically identify new variants. Potential new variants need to be flagged by users and these alerts are then addressed by manual curation and assignment of new lineages. Fast identification of new variants is very important for public health response, particularly now that the sequencing rates are decreasing. Here, we propose to develop a new machine learning pipeline that classifies SARS-CoV-2 sequences and can detect new variants. We plan to use a hierarchical classification framework in tandem with an Active Learning (AL) technique to detect potential new SARS-CoV-2 variants in near real time. AL is a type of machine learning technique where, in addition to training on known truth data, the algorithm identifies the most relevant unknown data points and queries for human input. The output of this project will be directly usable by public health officials thereby enabling informed and timely public health responses. Furthermore, lessons learned in this classification task may be transferred to other pathogens.
AIMS
To evaluate and identify the most efficient features to classify hierarchy SARS-CoV-2 lineages. We will analyze existing sequence-based signatures to use in the hierarchical classification of SARS-CoV-2 sequences, generating classes of features that will be used to predict Pango nomenclature.
To develop a Machine Learning model using Active Learning techniques to identify unknown lineages. We will use the identified features to develop a method capable of identifying and reporting unknown SARS-CoV-2 lineages to identify variants from these lineages.
To use a statistical method to identify and report new variants to specialists. We will evaluate statistical models that can be used to identify characteristics of potential new variants and inform specialists. This model will be applied to the lineages identified for Aim 2.
ACTIVITIES
1. Documentation and publication of Python hierarchical libraries
2. Development and validation of the proposed methodology using the South African and the Nigerian datasets
3. Publication of the Machine Learning model
4. Establishment of new collaborations in order to implement the methodology for different countries
5. Replication of the methodology for other pathogens
PILOT PROJECT 2
Project Title: Vaccine coverage mapping: important tool for pandemic preparedness
Kenneth Enwerem,MBBS,MSc
Project Lead
Kenneth Enwerem is public health physician and epidemiologist with more than ten years of experience in Humanitarian Emergency Program Management and community health programs planning, implementation and monitoring. He is currently the Surveillance and Epidemiology Lead with the Global Health Security (SECURE Nigeria) Project at the International Research Centre of Excellence, Institute of Human Virology in Abuja, Nigeria where he provides technical and operational leadership in the implementation of surveillance for projects within the SECURE Nigeria project including Acute Febrile Illness (AFI) and Adverse Events following Immunization (AEFI), Infection Prevention and Control (IPC) as well as Integrated Disease Surveillance Research for priority diseases. He also coordinates the implementation of the Acute Febrile Illness Surveillance Project at NCDC and leads the Vaccine Coverage Mapping Project at INFORM Africa (IHVN).
Victoria Etuk, MSc
Co-Lead
Victoria Etuk is an early career, infectious disease epidemiologist, with research interests in Global Health Security, HIV, TB and vaccination. She holds a Bachelor of Pharmacy degree, and a Master’s degree in Field Epidemiology. She currently serves as a Surveillance and Epidemiology Specialist/Data Analyst at the International Research Centre of Excellence of the Institute of Human Virology, Nigeria.
PROJECT DESCRIPTION
The vaccine coverage mapping project aims to determine the effect of COVID-19 vaccination coverage on COVID-19 disease incidence across different states in Nigeria. The project seeks to achieve this by developing a mapping tool/ dashboard which triangulates COVID-19 vaccination coverage data and COVID-19 incidence data. The mapping tool will serve as evidence for pandemic preparedness for future pandemics utilizing vaccines in prevention and response.
AIMS
To determine the Impact of Vaccination Coverage on Geographical Disease Prevalence
To identify Factors Associated with Vaccine Coverage Variations Across Regions
ACTIVITIES
1.Engagement of Government of Nigeria stakeholders on COVID-19 vaccination and disease surveillance programmes.
2.Development of demo dashboards.
3.Development and validation of live dashboard.
4.Deployment of live dashboard
PILOT PROJECT 3
Project Title: Vaccine coverage mapping: important tool for pandemic preparedness
TEAM MEMBERS
Kennedy Otwombe, PhD
Project Lead
Jude Igumbor, PhD
Co-Lead
Marta Vicente-Crespo
TEAM MEMBER
PROJECT DESCRIPTION
The global designation of COVID-19 as a pandemic posed substantial challenges for both affluent and impoverished nations. While wealthier countries experienced a rapid surge in infections and mortality rates, concerns were raised about the potential impact on resource-poor regions, particularly Africa. Leaders and scientists in Africa initiated strategic planning to address the anticipated high rates of infection and mortality. Contrary to expectations, Africa did not witness the projected surge, prompting inquiries into resilience and pandemic preparedness. The lack of reliable, Africa-specific COVID-19 data hindered understanding, emphasizing the need for a comprehensive policy framework incorporating diverse data sources and utilizing AI and machine learning.
AIMS
Our primary goal is to utilise cutting-edge data science approaches to understand drivers of COVID-19 resilience and plan for future pandemics drawing from lessons learned from containing COVID-19 in Africa
Specific Aim 1
To collate and curate COVID-19 data from different regions of Africa using the CARTA-Evidence platform
Specific Aim 2
To determine the primary drivers of COVID-19 resilience in the different regions of Africa
Specific Aim 3
To evaluate the level of preparedness for future pandemics in the African continent through lessons learn from COVID-19
ACTIVITIES
Two interns with MSc/MA degree level qualification have been Identified and will participate in the project by assisting in desktop review and downloading of datasets. Desktop review of existing literature on COVID-19. Africa specific literature is currently being reviewed using the CARTA evidence website. All published papers providing their datasets in open access are being identified and downloaded. A data curation algorithm is being prepared based on the nature of data collated to allow for appending and creating a master dataset to address the study specific aims.
PILOT PROJECT 4
Project Title: The Social Vulnerability Index (SVI) has the potential to be a critical tool for Ministries of Health and Public Health organizations to prepare for and manage infectious disease outbreaks or natural disasters in Africa.
Dr. Olanrewaju Lawal
Project Lead
Dr Olanrewaju Lawal, is a highly motivated individual with a diverse background spanning the biophysical and social sciences. His expertise in Geographic Information Science, Remote Sensing, and Geocomputation has enabled him to develop cutting-edge tools, insights, and analyses for tackling complex social, economic, and environmental problems. With a passion for exploring the intersection between physical and social sciences, He have leveraged the latest advancements in big data, AI, and Machine Learning to uncover new insights from data across natural and social systems. Working as a Principal Investigator and Co-Investigator on several funded and unfunded research projects, He played a pivotal role in leading teams to complete projects successfully across a broad spectrum of disciplines. His collaborations have
resulted in the development of nationally relevant spatial models and datasets, including moderate resolution economic activities, social vulnerability indexes (Multi-hazard and COVID-19 specific), spacetime risk assessments of armed conflict, space-time risk assessments for oil and gas pipeline interdiction, models of shoreline sensitivity to oiling, maize yield vulnerability to climate change, healthcare service accessibility, flood vulnerability models, and many others. With a track record of publishing over 70 technical reports and articles in local and international peer-reviewed journals, I am a consistently diligent and methodical worker, equally confident and enthusiastic as an individual or working in a team. His extensive experience in spatial database development, geocomputational techniques, and Geospatial Data Science has equipped him with the expertise, training, and motivation needed to successfully collaborate on and deliver on any proposed research project. He is always excited about the opportunity to continue pushing the boundaries of what’s possible in the world of geospatial analysis and making a meaningful contribution to the field
PROJECT DESCRIPTION
The Social Vulnerability Index (SVI) has the potential to be a critical tool for Ministries of Health and Public Health organizations to prepare for and manage infectious disease outbreaks or natural disasters in Africa. However, SVI availability selected African countries at the 3rd-order administrative level through three specific aims. AIM 1 develops and shares SVIs for selected African countries using recent population-based HIV impact assessments (P for the African continent is limited and often, when available, is only at the national or regional level. The overall goal of this project is to leverage pre-existing African data sources to develop and use SVIs for HIAs) and other pre-existing data sources. AIM 2 identifies patterns and associations between SVI and HIV and COVID-19 epidemics. AIM 3 builds the capacity of researchers and public health officials to use their countries’ indexes.
AIMS
The aim of this project is to leverage pre-existing African data sources to develop and use SVIs for selected African countries at the 3rd-order administrative level through three specific aims.
Develop and share SVIs for selected African countries using recent population-based HIV impact assessments (PHIAs) and other pre-existing data sources.
Identify patterns and associations between SVI and HIV and COVID-19 epidemics.
Build the capacity of researchers and public health officials to use their countries’ indexes.
ACTIVITIES
To provide the public with free and easy access to the SVIs, including researchers in Africa and around the World, we will work with our administrative core to incorporate these datasets into the upcoming INFORM Africa website. The newly developed SVIs will be merged with other datasets previously accessed or requested by Inform Africa (i.e. COVID-19 seroprevalence surveys, COVID-19 clinical and laboratory data, PHIA outcomes) to identify epidemiological and spatial patterns and associations between SVI and HIV and COVID-19 epidemics. For this purpose, several methods will be utilized including local and global spatial autocorrelation. Additionally, the SVIs will be incorporated into the Akros’ Reveal tool as part of Inform Projects 1 and 3. The Reveal tool is an open-source precision public health and spatial intelligence platform that provides a microplanning and mapping interface, linked with a mobile application to drive the delivery of health interventions to ensure all targeted recipients receive them. This tool will allow government and stakeholders’ staff to use the estimated SVIs.
A virtual capacity-building workshop will be organized to train selected users from the Ministry of Health, the National Emergency Management Agencies, and other stakeholders across the study areas. The potential user organizations from the selected countries would be asked to nominate participants. The workshop would cover theoretical aspects and hands.
PILOT PROJECT 5
Project Title: A Training Platform for Human Mobility and Health Data, Analytics, and Data-Driven Modeling- Preparing Future Data Scientists Crossing the Disciplines
Dr. Chenfeng Xiong, PhD
Project Lead
Chenfeng Xiong is an assistant Professor at the Department of Civil and Environmental Engineering, Villanova University. He holds a Bachelor’s degree in Civil Engineering from Tsinghua University, and an M.S degree in Civil Engineering, an M.A in Economics and a Ph.D in Transportation Engineering, from the University of Maryland. Chenfeng’s areas of interest include, transportation big data, human mobility and travel behavior modeling, transportation economics, carbon neutralization, large-scale agent-based analysis modeling and simulation (AMS). As a researcher, Chenfeng has published over 80 peer reviewed articles. Chenfeng is also the principal investigator of INFORM Africa project 2, and currently serves as the chairperson of DSI-Africa consortium steering committee.
PROJECT DESCRIPTION
Enabled by the multidisciplinary collaboration of the INFORM-Africa (“Role of Data Streams in Informing Infection Dynamics in Africa”) team, the proposed research team is in the process of producing individual level trip data that reveals large-scale time-dependent travel patterns and human mobility. While this unique dataset has huge potential to enable innovation in pandemic tracking/prediction, public health, and climate change research and trigger new collaborations, the data remains as an engineering product that requires significant domain knowledge of transportation, data science, and statistical modeling to comprehend. To bridge this gap between engineering and health for INFORM-Africa team, the larger DSI consortium, and the even broader research community, we propose a pilot project focusing on technology and knowledge transfer of transportation data and related supplementary analytical tools.
ACTIVITIES
The following two activities are proposed:
1) Develop an online training module for geospatial analysis and modeling using personal trips data. The module shall include a data user guide, a detailed tutorial on how to use the data, and a series of video lectures regarding analyses, visualization, modeling, and fusion using such data with other supplementary information such as GIS, health records, and climatic data.
2) Start seed collaboration that can bring interested researchers on INFORM Africa team on board to work closely with Villanova University research team on topics of mutual interests including retrospective analysis of five-waves of COVID-19 outbreak in South Africa, climate change and mobility, and 2022 Ebola outbreak, using transportation data products.
