MOTIVATION LETTER The L'Oréal-UNESCO For Women in Science Sub-Saharan Africa Programme funds research that combines scientific excellence with tangible benefit for African communities. My research does exactly this. I am a Nigerian pharmacist and computational researcher developing TOPOLOGIX, a machine-learning system that predicts drug-resistance mutations from protein sequence alone. The system achieves an AUROC of 0.804 plus or minus 0.025 on the Platinum benchmark of 553 mutations, outperforming structure-based tools like mCSM-lig at approximately 0.70 while covering 100 percent of mutations compared to roughly 18 percent for structure-limited methods. This grant would allow me to expand TOPOLOGIX's validation to African-relevant pathogens, including Mycobacterium tuberculosis and Plasmodium falciparum, where drug resistance directly threatens public health outcomes. My path to this work is unconventional. I earned a B.Pharm from the University of Ibadan with a CGPA of 5.1 out of 7.0, a German equivalent of 1.9, and I am licensed by the Pharmacists Council of Nigeria. I have worked as a clinical pharmacist at Ramset Pharmacy and as National Product Manager at Synthcare. Alongside this clinical practice, I built an independent computational research practice. I have sole-authored three preprints on the Conjunctive Consolidation Threshold model of addiction, each under review at a peer-reviewed journal, and I have co-authored a paper in Alcohol, Elsevier, currently under review. My work has been endorsed by Kent Berridge at Michigan, Samuel Gershman at Harvard, Nathaniel Daw at Princeton, and Marcelo Mattar at NYU. The L'Oréal-UNESCO programme's emphasis on scientific excellence and innovation matches my record of rigorous, pre-registered research. I have published negative results when they were the honest outcome, including a powered replication showing that topological features do not beat a plain descriptor baseline for hERG cardiotoxicity prediction, AUROC 0.8426 versus 0.8782. I have reported a failed real-data validation gate directly rather than reframing it. This commitment to scientific integrity is the foundation of my current work. I am enrolled in the M.Sc. Digital Health programme at the Hasso Plattner Institute, University of Potsdam, starting Winter Semester 2026/27. This grant would support the African component of my research, enabling collaborations with Nigerian institutions and building computational biology capacity on the continent. I am a Nigerian woman, 29 years old, conducting independent research with a strong Africa focus. The L'Oréal-UNESCO For Women in Science Sub-Saharan Africa Programme is the right home for this work, and I am prepared to contribute to its mission of advancing women in science across the region. RESEARCH STATEMENT TOPOLOGIX: Sequence-Based Prediction of Drug-Resistance Mutations for African Pathogens The problem. Antimicrobial and antimalarial resistance is a public health emergency in Sub-Saharan Africa. Tuberculosis kills over 400,000 people annually in the region, and artemisinin-resistant Plasmodium falciparum has been confirmed in East Africa. A central barrier to addressing this crisis is prediction: when a pathogen acquires a mutation that confers drug resistance, clinicians and researchers need to know quickly whether existing drugs will still work. Current tools require protein structures, which exist for only about 18 percent of clinically relevant mutations. The remaining 82 percent are invisible to structure-based methods. The project. TOPOLOGIX predicts drug-resistance mutations from protein sequence alone. The method combines ESM-2 protein language model delta-embeddings with Morgan/ECFP drug fingerprints, fed into a Random Forest classifier. On the Platinum benchmark of 553 mutations, TOPOLOGIX achieves an AUROC of 0.804 plus or minus 0.025. On SKEMPI 2.0, it achieves 0.634. It outperforms structure-based baselines such as mCSM-lig at approximately 0.70 while covering 100 percent of mutations. This is the first system to my knowledge that provides full coverage without requiring structure determination. My pathway to this result included a critical negative finding. I first tested whether bipartite persistent homology, a topological data analysis method, could predict hERG cardiotoxicity from protein-ligand interface geometry. A pre-registered, powered replication showed it could not beat a plain descriptor baseline, AUROC 0.8426 versus 0.8782. I then applied the same topological constructs to drug-resistance prediction and found they carried almost no signal, AUROC 0.425 and 0.485 on the Platinum benchmark. This ruled out interface geometry as the driver and motivated the sequence-representation approach that became TOPOLOGIX. The negative results were published as preprints and reported honestly; they are the reason TOPOLOGIX exists. The African extension. The current TOPOLOGIX model was trained and validated on global benchmarks. The next phase, which this grant would fund, has three components. First, I will assemble a curated dataset of resistance mutations in Mycobacterium tuberculosis and Plasmodium falciparum from published literature and public genomic surveillance databases, targeting at least 500 mutations per pathogen. Second, I will fine-tune the ESM-2 embeddings on African pathogen sequences to capture population-specific variation. Third, I will validate the model against clinical outcomes data from Nigerian and East African cohorts, working with collaborators at the Genomics Research Unit at the University of Ibadan, where I previously contributed to AMR genomics and surveillance pipelines. Methods and infrastructure. I have the technical capacity to execute this project independently. My skills include Python with scipy, numpy, PyMC for Bayesian calibration, RDKit for cheminformatics, and AlphaFold for structure validation. I have built four independent DuckDB-based ingest-to-analyze pipelines across life-sciences and other domains, and I maintain production systems including Linux VPS, systemd, Caddy TLS, and automated backup and disaster recovery. I have used Nextflow and SLURM for HPC workflows. All code will be open-sourced on GitHub under my existing account, github.com/AmunRaPtah. Why this project fits L'Oréal-UNESCO. The programme funds women scientists whose research has both scientific excellence and societal impact. TOPOLOGIX is methodologically innovative, combining protein language models with drug fingerprints in a way that has not been done for this task. It addresses a problem that directly affects African health outcomes. And it builds capacity: I am an independent Nigerian researcher, and this grant would enable me to establish a computational biology research line focused on African pathogens, training students and collaborating with Nigerian institutions. Timeline. Months 1 to 3: dataset assembly and curation. Months 4 to 6: model fine-tuning and validation. Months 7 to 9: clinical validation and manuscript preparation. Months 10 to 12: dissemination, including open-source release and workshops at Nigerian universities. The requested funding, in the range of 10,000 to 100,000 US dollars, would cover compute costs, dataset acquisition, travel for collaboration, and stipend support during the research period. I am prepared to begin immediately upon award. EDITOR NOTES - Research line chosen: TOPOLOGIX, the sequence-based drug-resistance prediction project. This is the best fit for L'Oréal-UNESCO because it is the most mature, externally validated line with direct African health relevance, and it aligns with the programme's emphasis on scientific excellence and societal impact. The CCT model and neurocascade are strong but less directly tied to African health outcomes; ergofluids is behind a validation gate and not appropriate to lead with; psyche-twin is a personal knowledge-graph project with no clear fit to this programme's life-sciences focus. - Eligibility risk: The programme requires applicants to be women citizens of a Sub-Saharan African country conducting research within a recognized institution in Sub-Saharan Africa. The profile states Eniola is Nigerian and an independent researcher, but does not explicitly confirm institutional affiliation in Sub-Saharan Africa. The applicant must verify whether independent researcher status qualifies, or whether she needs to secure an affiliation with a Nigerian university or research institute before applying. This is the single most important fact to confirm. - Facts to verify: The profile lists TOPOLOGIX AUROC values (0.804 plus or minus 0.025 on Platinum, 0.634 on SKEMPI 2.0) and baseline comparisons (mCSM-lig approximately 0.70, 18 percent structure coverage). These numbers must be checked against the actual preprints or code repository before submission. The claim that this is the first system providing full coverage without structure determination should be softened or verified against current literature, as it is a strong claim that a reviewer may challenge. - Gaps to fill: The applicant must insert specific details about the proposed African pathogen dataset, including which public databases she will draw from (for example, the TB Drug Resistance Mutation Database or MalariaGEN) and the names of any collaborators at Nigerian institutions. The research statement mentions the Genomics Research Unit at the University of Ibadan; this affiliation must be confirmed and a named collaborator added. The applicant should also specify the exact funding amount requested, as the programme amount is unspecified in the profile. - Application materials: The submission page content was not captured, so this draft follows the fallback format of a motivation letter and research statement. The applicant must check the actual L'Oréal-UNESCO application portal for additional required sections, such as a CV, publication list, supervisor or mentor statement, or institutional endorsement letter. The checklist below includes these as placeholders. - Tone and voice: The motivation letter opens with the programme's mission rather than with "I," per the formatting rules. The research statement is written in first person with concrete numbers throughout. No AI-slop phrases were used. The negative results from the topology studies are presented honestly as the foundation for TOPOLOGIX, not as current ongoing work. CHECKLIST - [ ] Confirm eligibility: woman citizen of a Sub-Saharan African country, conducting research within a recognized institution in Sub-Saharan Africa. If independent researcher status is not sufficient, secure an affiliation with a Nigerian university or research institute before applying. - [ ] Verify all numerical claims in the research statement against the TOPOLOGIX preprints and code repository: AUROC values, baseline comparisons, coverage percentages. - [ ] Identify and name specific collaborators at Nigerian institutions for the African pathogen extension, and confirm their willingness to be listed. - [ ] Specify the exact funding amount requested, within the 10,000 to 100,000 US dollar range. - [ ] Check the L'Oréal-UNESCO application portal for the full list of required materials, including any CV, publication list, supervisor or mentor statement, or institutional endorsement letter not covered in this draft. - [ ] Confirm the application deadline from the programme website, as the profile lists it as "see programme website." - [ ] Prepare a CV in the format required by the programme, including education, employment, publications, and technical skills. - [ ] Prepare a publication list with links to all preprints and the co-authored Alcohol paper. - [ ] Prepare a budget justification for the requested funding amount, covering compute, dataset acquisition, travel, and stipend. - [ ] Confirm that the M.Sc. Digital Health enrollment at HPI/Potsdam does not conflict with the programme's institutional affiliation requirement.