MOTIVATION LETTER The gap between a Nigerian patient and a functioning prescription is not a distance problem; it is an information problem. In Lagos, where I worked as a clinical pharmacist at Ramset Pharmacy, I watched patients receive medicines they did not understand, from pharmacies that could not verify their histories, while the country's pharmacist-to-patient ratio remained among the worst in the world. That experience, not a laboratory, is where my healthcare work begins. I am Eniola Ayodele Olutogun, a licensed pharmacist and computational researcher. I currently serve as National Product Manager at Synthcare, where I lead the development of a telepharmacy platform designed to connect underserved Nigerian patients with licensed pharmacists for verification, counseling, and adherence support. The platform addresses a specific failure: Nigeria has roughly one pharmacist per 10,000 people, and most of them are concentrated in urban hospitals. Rural patients often receive medicines with no professional check at all. My work is to build the infrastructure that puts a pharmacist in the loop of every prescription, regardless of location. This venture is one half of my profile. The other half is a research practice built on the same instinct: use computation to solve problems where data is scarce and stakes are high. My CCT model, a tripartite pharmacological framework for reward-memory encoding in addiction, was calibrated against 1,847 literature records and confirmed all five pre-registered hypotheses. My TOPOLOGIX system predicts drug-resistance mutations from protein sequence alone, reaching an AUROC of 0.804 on the Platinum benchmark while covering 100 percent of mutations, compared to roughly 18 percent for structure-limited tools. I also ran a pre-registered replication in cardiotoxicity topology that produced a negative result, and I reported it as such. That discipline, knowing when a hypothesis fails, is the same discipline I bring to product development. The Novartis Reimagining Healthcare Scholarship selects young leaders who demonstrate capacity for leadership and a commitment to delivering positive change in healthcare. My leadership is evidenced by the systems I have built and the teams I have guided: a 62-test-passing brain-circuit simulation engine, four independent data pipelines, and a production telepharmacy platform in active development. My commitment is evidenced by my choice to stay in Nigeria and work on access, rather than pursue only academic outputs. The One Young World Summit is the correct venue for this work because the problem I am solving is not unique to Nigeria. Pharmacist shortages, counterfeit medicines, and weak prescription verification systems affect most of the Global South. I want to learn from peers solving the same problem in different regulatory environments, and I want to share what we have learned at Synthcare about building for low-infrastructure settings. I am 29 years old, a Nigerian national, and I meet the age and eligibility criteria for this scholarship. I am not applying for a research grant. I am applying for a seat at a table where healthcare leaders from underrepresented countries exchange the tools that actually work. The summit's focus on collaboration and navigating complexity matches the way I work: across disciplines, across sectors, and across borders. RESEARCH STATEMENT My research program asks one question across multiple domains: how do we make reliable predictions about biological systems when the data is sparse, noisy, or incomplete? I answer this question with computational models that are explicitly calibrated, pre-registered, and tested against real-world benchmarks. I do not publish a result unless I have tried to falsify it first. The current centerpiece of this program is TOPOLOGIX, a system that predicts drug-resistance mutations from protein sequence alone. The problem is concrete: structure-based tools like mCSM-lig require a resolved protein structure, which exists for only about 18 percent of clinically relevant mutations. That means four out of five mutations cannot be assessed by the standard toolset. TOPOLOGIX uses ESM-2 protein language model delta-embeddings combined with Morgan/ECFP drug fingerprints and a Random Forest classifier. On the Platinum benchmark of 553 mutations, it reaches an AUROC of 0.804 with a standard deviation of 0.025, and 0.634 on SKEMPI 2.0. It beats the structure-based baseline of approximately 0.70 while covering the full mutation space. This is not a theoretical exercise; resistance prediction directly informs whether a patient's therapy will fail before it is prescribed. TOPOLOGIX exists because of a negative result I published first. In my cardiotoxicity topology study, I tested whether bipartite persistent homology could predict hERG cardiotoxicity from protein-ligand interface geometry. The pre-registered, powered replication found that topological features did not beat a plain descriptor baseline, AUROC 0.8426 versus 0.8782. The published literature had never actually run that comparison. I ran it, and the answer was no. That result redirected my work toward sequence representations, which produced TOPOLOGIX. I report this history because it demonstrates the method: when a hypothesis fails, you change the approach, not the story. My second active line is the CCT model, a tripartite pharmacological framework for preventing reward-memory encoding in addiction. The model couples three axes, dopaminergic reward prediction error, NMDAR-dependent long-term potentiation, and affective contrast, into an ODE system solved with RK45. I calibrated it with Bayesian MCMC using PyMC's DEMetropolisZ sampler, with 14 free parameters and literature-elicited priors drawn from a screen of 1,847 records. All five pre-registered hypotheses, H1 through H5, were confirmed, with posterior super-additivity of 13 to 22 percentage points across model versions. Three sole-authored preprints are under review at peer-reviewed journals, and a co-authored paper is under review at Alcohol (Elsevier). This work sits at the intersection of pharmacology and computational neuroscience, and it has direct implications for relapse prevention. My third line is neurocascade, a receptor-to-behavior brain-circuit simulation engine. It couples pharmacokinetics to receptor binding to Wilson-Cowan circuit dynamics to behavioral readouts across three literature-calibrated systems: mu-opioid, D2 dopamine, and GABA-A. The engine is Bayesian-calibrated with PyMC and passes 62 of 62 tests. The circuit-layer parameters are explicitly labeled as illustrative pending real behavioral-data fits. I do not claim validation I have not earned. My fourth line, ergofluids, is methods-validation research. I extended Koopman operator and Dynamic Mode Decomposition methods with a Mori-Zwanzig memory kernel to model macromolecular drug-vehicle transport through dense tumor tissue. The pre-registered pipeline passed its synthetic-data gates, but the first real-data gate, tested against digitized published figures, did not meet its primary criterion. I reported that directly. The method is not dead; it is gated, and the gate is honest. Finally, psyche-twin is a typed, multi-scale knowledge-graph architecture for self-modeling. Multiple evidence streams, including LLM-derived, assessment-derived, behavioral, and document-derived, fuse into an append-only event log. Disagreement between streams becomes an explicit graph edge rather than being averaged away. This is the most exploratory line in my portfolio, and I treat it as such. Across all lines, my methods are consistent: pre-registration, Bayesian calibration, explicit validation gates, and honest reporting of negative results. I am enrolled in the M.Sc. Digital Health program at the Hasso Plattner Institute and the University of Potsdam, starting Winter Semester 2026/27, which will formalize my training in digital health methods. My collaborators and endorsers include Kent Berridge at Michigan, Samuel Gershman at Harvard, Nathaniel Daw at Princeton, and Marcelo Mattar at NYU. The Novartis Reimagining Healthcare Scholarship values innovation and the delivery of results. My research record demonstrates both, including the discipline to report when a result is negative. I am applying as an independent researcher with a strong Africa angle, building tools that work with limited data and limited infrastructure, because that is the environment where most of the world's patients live. ESSAY: LEADERSHIP AND POSITIVE CHANGE IN HEALTHCARE Leadership in healthcare is not a title. It is the ability to identify a failure in the system and build the thing that fixes it. My leadership is demonstrated by two parallel tracks: the teams I have guided and the systems I have built. As National Product Manager at Synthcare, I lead the development of a telepharmacy platform for Nigeria. The problem is specific: Nigeria has roughly one pharmacist per 10,000 people, concentrated in urban centers, leaving rural patients to obtain medicines with no professional verification. My role is to define the product, coordinate the engineering team, and ensure the platform meets the regulatory and clinical requirements of the Nigerian pharmacy system. This is not a side project. It is my primary employment, and it is a direct response to a gap I observed while working as a clinical pharmacist at Ramset Pharmacy in early 2026. My research leadership follows the same pattern. I designed and executed the CCT model study, a tripartite pharmacological framework for addiction, entirely as an independent researcher. I conducted a 1,847-record literature screen, elicited priors, calibrated a 14-parameter Bayesian model, and confirmed all five pre-registered hypotheses. I then wrote three sole-authored preprints and submitted them to peer-reviewed journals. No laboratory, no supervisor, no institutional backing. Just a method and a commitment to pre-registration. I also demonstrate leadership by reporting negative results. My cardiotoxicity topology study was a pre-registered, powered replication that found topological features do not beat a plain descriptor baseline. I published that result. My ergofluids project passed its synthetic-data gates but failed its first real-data gate, and I reported that failure directly rather than reframing it. In a field where negative results are routinely buried, this discipline is a form of leadership. The Novartis scholarship values demonstrated capacity for leadership and a track record of delivering positive change. My track record includes a 62-test-passing simulation engine, a resistance-prediction system that covers 100 percent of mutations, and a telepharmacy platform in active development. I am 29 years old, a Nigerian national, and I meet the age and eligibility criteria. The One Young World Summit is where I want to test these ideas against peers from other low-infrastructure healthcare systems, and where I can contribute what I have learned about building for settings where data and resources are scarce. ESSAY: INNOVATION AND ENTREPRENEURIAL APPROACH Innovation in healthcare is not a new molecule. It is a new way of delivering an existing solution to the people who need it. My entrepreneurial approach is defined by the telepharmacy platform at Synthcare, where I serve as National Product Manager. The platform addresses a specific, measurable failure in Nigerian healthcare. The pharmacist-to-patient ratio is approximately one to 10,000, and the pharmacists who exist are concentrated in urban hospitals. Rural patients often receive medicines with no professional check at all, which means drug interactions, contraindications, and counterfeit products go undetected. The telepharmacy platform puts a licensed pharmacist in the loop of every prescription, regardless of the patient's location. This is a social entrepreneurship initiative: it is designed for impact on access, not for extraction of profit from a market that cannot pay. My research practice is entrepreneurial in the same sense. I built TOPOLOGIX, a drug-resistance prediction system, because the standard tools only cover 18 percent of clinically relevant mutations. Structure-based tools require a resolved protein structure, and most mutations do not have one. TOPOLOGIX uses protein language model embeddings and drug fingerprints to predict resistance from sequence alone, reaching an AUROC of 0.804 on the Platinum benchmark while covering the full mutation space. It beats the structure-based baseline of approximately 0.70. This is an innovation in method that directly addresses a coverage gap. I also innovate in process. My CCT model was calibrated with Bayesian MCMC against a 1,847-record literature screen, with all five pre-registered hypotheses confirmed. My cardiotoxicity topology study was a pre-registered replication that produced a negative result, and I reported it. My ergofluids project has explicit validation gates, and I reported when the first real-data gate failed. This is not common practice in computational biology, where pre-registration is rare and negative results are often suppressed. My innovation is the discipline itself. The Novartis scholarship values innovation, creativity, and an entrepreneurial mindset. My ventures, both the telepharmacy platform and my research program, are built on identifying gaps and building the tools to close them. I am applying to attend the One Young World Summit to connect with other young leaders who are solving similar problems in different regulatory environments, and to share the methods I have developed for building in low-infrastructure settings. CHECKLIST - [ ] Confirm current age at time of application is within the 18-30 eligibility window (profile states age 29, verify against application date) - [ ] Verify the Novartis Reimagining Healthcare Scholarship application deadline on the Advance Africa website - [ ] Prepare a current CV in PDF format, including Synthcare role, Ramset Pharmacy role, research preprints, and ORCID - [ ] Gather proof of enrollment or acceptance for M.Sc. Digital Health at Hasso Plattner Institute / University of Potsdam (Winter Semester 2026/27) - [ ] Prepare a one-page summary of the Synthcare telepharmacy platform, including current development stage and target user base - [ ] Obtain a letter of recommendation or endorsement from a collaborator (Kent Berridge, Samuel Gershman, Nathaniel Daw, or Marcelo Mattar) if required - [ ] Prepare a headshot or professional photograph if the application portal requires one - [ ] Verify that all three CCT preprints are listed with their OSF/Zenodo DOIs and current journal submission status - [ ] Confirm the exact word limits for each essay field on the application portal and trim responses to fit - [ ] Review the One Young World Summit theme for the application year and tailor the motivation letter to reference it EDITOR NOTES - Eligibility risk: The profile states age 29, but the scholarship window is 18-30. If the applicant turns 30 before the summit date, eligibility may be lost. Verify the exact date of birth against the summit dates before submitting. - The telepharmacy platform at Synthcare is described as "in active development" and "National Product Manager" is the stated role. No revenue, user count, or regulatory approval is claimed. Do not add any claim of product-market fit, revenue, or regulatory clearance that is not in the profile. - The applicant's research lines are extensive and may overwhelm the application. The essays above deliberately foreground the Synthcare venture and TOPOLOGIX, with the CCT model as supporting evidence. If the application portal has a character limit that forces cuts, remove the ergofluids and psyche-twin descriptions first, as they are the least relevant to this scholarship's healthcare focus. - The profile lists a co-authored paper under review at Alcohol (Elsevier) and three sole-authored preprints under review at IART, PNPBP, and NBR. The applicant must confirm these submission statuses are current before the application goes out, as journals may have responded in the interim. - The applicant's ORCID, GitHub, and personal site are listed in the profile. The application should include these links, but the personal site (zyco.org) should be reviewed for any content that could be considered unprofessional or misaligned with the scholarship's healthcare focus before submission.