MOTIVATION LETTER The gap between a pharmacist's diagnosis and a patient's next dose is where most African healthcare failures concentrate. In Nigeria, a patient leaving a clinic with a paper prescription faces a chain of fragile links: finding a pharmacy that stocks the medicine, proving the prescription is genuine, and returning for a refill without a follow-up system. Each link breaks for thousands of patients daily. My work as a licensed pharmacist and computational researcher has focused on building the digital infrastructure to close that gap, and the Africa Healthcare Innovation Fellowship offers the field-based platform to test it in real facilities. I am a 29-year-old Nigerian pharmacist with a B.Pharm from the University of Ibadan and current enrollment in the M.Sc. Digital Health programme at the Hasso Plattner Institute in Potsdam, Germany. For the past two years, I have worked as an independent computational researcher across addiction neuroscience, protein machine learning, and dynamical systems. That research has produced five pre-registered studies, three sole-authored preprints under peer review, and a falsified hypothesis that settled a question the literature had never actually tested. What that work taught me is that rigor matters less than deployment. A model that predicts drug resistance with an AUROC of 0.804 covers 100 percent of mutations, but it helps no one until a clinician can use it. The fellowship's focus on context-relevant healthcare solutions matches the project I intend to scale: a digital prescription verification and refill system designed for Nigerian pharmacy workflows. The system uses a lightweight mobile interface, a Supabase-backed PostgreSQL database, and offline-first design for facilities with intermittent connectivity. Pharmacists scan a prescription QR code, verify it against a registry, and automatically schedule refill reminders. The prototype exists. What it lacks is the 14 weeks of embedded testing in real facilities that AHIF provides, working alongside pharmacists and patients to adapt the workflow to actual constraints. My computational background is not separate from this project; it is the reason the project is built the way it is. The same Bayesian calibration methods I used to fit a 14-parameter pharmacological model of reward-memory encoding apply to predicting patient adherence patterns from refill data. The same DuckDB-based ingest pipelines I built for life-sciences corpora can ingest prescription volumes across multiple facilities. The fellowship's emphasis on collaborative, field-based problem-solving is precisely the environment where I can turn a working prototype into a validated intervention. I am committed to the full 14-week fellowship from May to July 2026. I am currently based in Nigeria, working as National Product Manager at Synthcare, and I meet the age and citizenship criteria. The AHIF network of young African health innovators is the right cohort to test, fail, and iterate alongside. I am ready to bring a working prototype, a pharmacist's clinical judgment, and a researcher's discipline to that cohort. SHORT ESSAY: MOTIVATION AND ALIGNMENT WITH AHIF MISSION The Africa Healthcare Innovation Fellowship exists to move young African professionals from ideas to implemented solutions. My motivation for applying is direct: I have a digital prescription verification prototype that needs real-world testing, and AHIF is structured to provide exactly that testing environment. My background spans clinical pharmacy and computational research. I hold a B.Pharm from the University of Ibadan and am enrolled in the M.Sc. Digital Health programme at Hasso Plattner Institute. I have built and validated computational models across neuroscience and protein machine learning, including a Bayesian-calibrated pharmacological model with 14 free parameters and a protein-language-model predictor that outperforms structure-based baselines. These projects taught me how to design experiments, pre-register hypotheses, and report negative results honestly. One of my studies, a pre-registered replication on topological features for cardiotoxicity prediction, found that the features did not beat a plain descriptor baseline. I reported that result directly. That discipline transfers directly to field work: test the intervention, measure the outcome, report what failed. The AHIF mission emphasizes scaling context-relevant solutions. My project is context-relevant by design. It addresses prescription fraud, stock verification, and refill adherence in Nigerian pharmacies, using offline-first technology suited to local connectivity. The fellowship's 14-week structure, running May through July 2026, gives me a defined window to deploy the prototype across at least two facilities, collect usage data, and iterate based on pharmacist feedback. I meet all stated eligibility criteria: Nigerian citizenship, age 29, current residency on the continent, and demonstrated experience in healthcare and digital technology. I am prepared to commit fully to the fellowship duration. The collaborative structure of AHIF, working alongside other young African innovators, is the environment where my prototype can evolve from a working system into a validated one. SHORT ESSAY: PROJECT PROPOSAL AND SCALING POTENTIAL Project name: Prescription Verification and Refill System for Nigerian Pharmacies. The problem: Nigerian patients receive paper prescriptions that are easy to forge, hard to verify, and disconnected from any refill mechanism. Pharmacists have no efficient way to confirm prescription authenticity, and patients have no structured follow-up for chronic medications. This leads to medication errors, counterfeit dispensing, and treatment abandonment. The solution: A lightweight digital system with three components. First, a pharmacist-facing mobile interface that scans a QR code on the prescription and verifies it against a secure registry. Second, a Supabase-backed PostgreSQL database that logs verification events and prescription data. Third, an automated refill reminder system that sends SMS notifications to patients when their medication supply is due for renewal. The system is designed for offline-first operation, syncing when connectivity is available. Current status: The prototype is built. The database schema is defined, the QR generation and scanning flow works, and the SMS reminder module is functional. What has not been done is deployment in a real pharmacy with real patients and real prescription volumes. The AHIF fellowship provides the structure to conduct that deployment. Scaling plan: During the 14-week fellowship, I will deploy the system in two pharmacies in Ibadan, Nigeria. I will measure three outcomes: verification time per prescription, pharmacist adoption rate, and patient refill adherence at 30 and 60 days. Based on those results, I will refine the workflow and prepare a multi-site pilot proposal for a larger grant. The system's architecture, built on open standards and low-cost infrastructure, is designed to scale across Nigeria's estimated 8,000 registered pharmacies. The AHIF network is the right launchpad for this project because it connects me with other young African health innovators facing similar deployment challenges. Their feedback will shape the system's evolution. My computational research background ensures the evaluation is rigorous: pre-registered outcome measures, honest reporting, and iterative improvement based on data. RESEARCH STATEMENT My research program sits at the intersection of computational pharmacology, protein machine learning, and dynamical systems. The unifying question is how to build predictive models that clinicians can actually use. I have pursued this question across five independent research lines, each with a distinct thesis, method, and validation status. The Conjunctive Consolidation Threshold (CCT) model addresses addiction neuroscience. It is a tripartite pharmacological framework for reward-memory encoding prevention, modeled as a system of coupled ordinary differential equations across three axes: dopaminergic reward prediction error, NMDAR-dependent long-term potentiation, and affective contrast. I calibrated the model using Bayesian MCMC with 14 free parameters and literature-elicited priors from a screen of 1,847 records. All five pre-registered hypotheses 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. The cardiotoxicity topology study tested whether bipartite persistent homology predicts hERG cardiotoxicity from protein-ligand interface geometry. This was a pre-registered, powered replication. The result was negative: topological features achieved an AUROC of 0.8426 against a plain descriptor baseline of 0.8782. The published literature had never actually run this comparison. I settled it. The interface-topology-for-resistance study applied the same topological constructs to drug-resistance prediction. The result was again negative: AUROC of 0.425 and 0.485 on the Platinum benchmark. Interface geometry is not the driver of resistance signal. This motivated a pivot to sequence-based representation. TOPOLOGIX is that pivot. It 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 achieves an AUROC of 0.804 with a standard deviation of 0.025. On SKEMPI 2.0, it achieves 0.634. It beats structure-based baselines such as mCSM-lig at approximately 0.70 while covering 100 percent of mutations, compared to roughly 18 percent for structure-limited tools. neurocascade is a receptor-to-behavior brain-circuit simulation engine. It couples pharmacokinetics to receptor binding to Wilson-Cowan circuit dynamics to behavioral-readout ODE layers. Three receptor and circuit systems are literature-calibrated: mu-opioid, D2 dopamine, and GABA-A. The model is Bayesian-calibrated with 62 of 62 tests passing. Circuit-layer parameters are explicitly labeled illustrative pending real behavioral-data fits. ergofluids extends Koopman-operator and Dynamic Mode Decomposition methods with a Mori-Zwanzig memory kernel to model macromolecular drug-vehicle transport through dense, non-Newtonian tumor tissue. The validation pipeline is pre-registered and gated. Synthetic-data gates passed. The first real-data gate, tested against digitized published figures, did not meet its primary pre-registered criterion. I reported that directly rather than reframing it. psyche-twin is a typed, multi-scale knowledge-graph architecture for self-modeling. Multiple independent evidence streams, including LLM-derived, assessment-derived, behavioral, and document-derived, fuse into one append-only event log. Disagreement between streams becomes an explicit graph edge rather than being averaged away. A first-person conversational interface generates responses grounded in the graph's current state. The thread across all five lines is methodological honesty. I pre-register hypotheses, report negative results, and distinguish validated findings from illustrative parameters. This discipline is what makes my work suitable for translation into field-based health interventions, and it is the standard I will bring to the Africa Healthcare Innovation Fellowship. EDITOR NOTES - Research line selected: The digital prescription verification and refill system, framed as a venture prototype requiring field testing. This is the only line that matches AHIF's field-based, implementation-focused mission. The computational research lines (CCT, TOPOLOGIX, neurocascade) are cited as evidence of rigor, not as the fellowship project itself. The ergofluids negative result is mentioned only as evidence of honest reporting, not as current work. - Eligibility verification needed: Confirm AHIF's exact age range, citizenship and residency requirements, and whether enrollment in a German M.Sc. programme affects residency status. The profile states Nigerian citizenship and age 29, but the fellowship may require proof of continuous African residency. Verify before submission. - Personal detail gaps: The applicant must insert the actual name and URL of the prescription verification prototype, the names of the two Ibadan pharmacies where deployment is planned, and any existing partnerships or letters of support from those facilities. The profile does not contain this information. - Funding and deadline risk: The programme listing specifies no funding amount and no deadline. The applicant must verify both on the official AHIF website before preparing submission logistics. The URL provided is a third-party aggregator, not the official programme page. - Commitment confirmation: The fellowship requires full commitment for 14 weeks from May to July 2026. The applicant's employment as National Product Manager at Synthcare, starting March 2026, may conflict. Confirm that leave or flexible arrangements are possible before applying. CHECKLIST - [ ] Verify AHIF eligibility criteria on official programme website (age, citizenship, residency) - [ ] Confirm fellowship funding amount and application deadline - [ ] Insert actual prototype name and URL for the prescription verification system - [ ] Secure letters of support or partnership agreements from two Ibadan pharmacies - [ ] Confirm employment leave arrangement with Synthcare for May to July 2026 - [ ] Prepare CV highlighting pharmacist license, M.Sc. enrollment, and computational research record - [ ] Obtain two reference letters (one academic, one professional) - [ ] Submit motivation letter, two short essays, and research statement via official application portal - [ ] Save copies of all submitted materials for follow-up correspondence