CV

Mahbuba Tasmin — Computational Biology, Biological Foundation Models, and Predictive Biology University of Massachusetts Amherst · mtasmin@umass.edu Website · GitHub · LinkedIn · Google Scholar

Download full CV (PDF)

Profile

Ph.D. candidate developing interpretable and robust machine-learning methods for biological sequences, mutation-effect prediction, and predictive biology. Experienced in biological foundation-model adaptation, protein and genomic sequence modeling, benchmark development, model evaluation, multimodal biological data integration, and GPU/HPC pipelines. Dissertation proposal planned for early Fall 2026. Available for full-time research roles with flexible start dates throughout 2027.

Research Interests

Interpretable machine learning for biological sequences; protein foundation models; antimicrobial resistance; mutation-effect prediction; structure-aware modeling; multimodal biological data; robust evaluation under data scarcity.

Education

• University of Massachusetts Amherst, Amherst, MA Ph.D. Candidate in Computer Science (Advisor: Prof. Anna G. Green) — Sep 2022 – Present GPA: 3.9/4.0. Research concentration: Computational Biology, Machine Learning. Dissertation title: “Integrating Biological Signal to Improve Generalizability and Interpretability of Machine Learning in Genomics.”

• University of Massachusetts Amherst, Amherst, MA M.S. in Computer Science — Sep 2022 – May 2025 GPA: 3.9/4.0. Research aligned with predictive and interpretable modeling of antibiotic resistance.

• North South University, Dhaka, Bangladesh B.S. in Computer Science and Engineering, Summa Cum Laude — Jan 2016 – Dec 2019 GPA: 3.89/4.0. Concentration in Artificial Intelligence and Algorithms.

Employment and Academic Appointments

• Graduate Research Assistant, Sequence Analysis and Genomics (SAGE) Lab, University of Massachusetts Amherst — Sep 2023 – Present Lead and co-lead research in interpretable biological sequence modeling, antibiotic resistance forecasting, protein foundation-model benchmarking, multimodal biological data integration, and evolutionary augmentation.

• Head Teaching Assistant / Teaching Assistant, COMPSCI 520 (Theory and Practice of Software Engineering), UMass Amherst — Jan 2023 – May 2026 Served four semesters as Head TA and additional semesters as TA; supported classes of more than 140 students, designed instructional materials, coordinated teaching staff, oversaw grading, and maintained GitHub Classroom and Gradescope infrastructure.

• Course Developer, COMPSCI 520, UMass Amherst — May 2023 – Aug 2023 Redesigned assignments and lab materials, established GitHub Classroom workflows, and developed automated grading infrastructure.

• AI Engineer, NITEX Solutions Ltd., Dhaka, Bangladesh — Mar 2022 – Jul 2022 Developed Detectron2-based instance-segmentation, OCR, and image-processing pipelines, along with NLP/CV tools for automated product identification and fashion-trend analysis.

• Software Engineer, AI & ML, M2SYS Technology, Dhaka, Bangladesh — Jul 2020 – Feb 2022 Developed image-spoofing detection, contextual recommendation systems, workflow automation with Camunda, and production ML deployments in distributed environments.

Selected Publications

Full list with abstracts on the Publications page.

Preprints and Manuscripts Under Review

• Tasmin, M., Barethiya, S., Wang, Y., Kang, L., Chen, J., Green, A. G. “FARM: Forecasting Antibiotic Resistance in Mycobacterium tuberculosis Using Biophysics and Machine Learning.” bioRxiv, 2026. Manuscript under review at Proceedings of the National Academy of Sciences (PNAS).
• Tasmin, M., Mohanty, S., Kulkarni, S., Farhat, M. R., Green, A. G. “BIG-TB: A Benchmark for Prediction and Interpretability of Sequence-Based Machine Learning Using Mycobacterium tuberculosis Genomes.” bioRxiv, 2026. Manuscript submitted; under revision following peer review.

Peer-Reviewed Journal Articles & Book Chapters

• Green, A. G., Tasmin, M., Vargas Jr., R., Farhat, M. R. “The structural context of mutations in proteins predicts their effect on antibiotic resistance.” eLife, 14:RP109450, 2025.
• Yang, Z., Yao, Z., Tasmin, M., et al. “Unveiling GPT-4V’s hidden challenges behind high accuracy on USMLE questions: Observational Study.” Journal of Medical Internet Research, 27:e65146, 2025.
• Tasmin, M., et al. “Assessment of Deep Learning Models for Human Activity Recognition on Multivariate Time Series Data and Non-targeted Adversarial Attack.” In Advances in Intelligent Systems Research and Innovation, SSDC vol. 379, Springer, pp. 129–159, 2022.
• Tasmin, M., Nag, P., Hoque, Z. T., Molla, M. M. “Non-Newtonian effect on heat transfer and entropy generation of natural convection nanofluid flow inside a vertical wavy porous cavity.” SN Applied Sciences, 3:299, 2021.

Peer-Reviewed Conference and Workshop Papers

• Tasmin, M., Green, A. “Beyond Sequence-only Models: Leveraging Structural Constraints for Antibiotic Resistance Prediction in Sparse Genomic Datasets.” ICLR 2025 MLGenX Workshop, 2025.
• Tasmin, M., et al. “Comparative Study of Classifiers on Human Activity Recognition by Different Feature Engineering Techniques.” IEEE 10th International Conference on Intelligent Systems, pp. 93–101, 2020.

Extended Abstracts

• Tasmin, M. “Multi-Dimensional Aspect Analysis of Text Input through Human Emotion and Social Factors.” ACM UbiComp, pp. 1779–1781, 2018.

Technical Skills

• Programming & Tools: Python, Bash, PyTorch, Scikit-learn, Pandas, Java, LaTeX
• Machine Learning: Deep learning, regression and classification, high-dimensional modeling, model evaluation and experimental design, baseline selection, cross-validation, ablation studies
• Foundation Models: Protein and genomic language models, ESM, large pretrained model adaptation, parameter-efficient tuning (LoRA), fine-tuning, zero-shot evaluation, model probing, embedding engineering, PCA-based representation compression
• Computational Biology: Biological sequence modeling, functional genomics, protein structure analysis, sequence alignment, variant annotation, DNA-to-protein translation, proteomics
• Interpretability & Reliability: SHAP, feature attribution, causal-variant recovery, model diagnostics, robustness evaluation, error analysis
• Computing Infrastructure: Linux, Docker, SLURM/HPC, GPU computing, distributed multi-GPU training, memory-mapped datasets, reproducible pipelines
• Scientific Communication: Scientific writing, manuscript development, benchmark and dataset release, research presentations, interdisciplinary collaboration

Selected Predictive Biology Research Contributions

• BIG-TB (2024–Present) — Led benchmark design and protein-model analyses for 17,942 Mycobacterium tuberculosis isolates across 11 antibiotics, including defensible train/test splits, classical and deep-learning baselines, interpretability evaluation, causal-variant recovery, and robustness analysis.
• Biophysics-Aware Resistance Forecasting (2024–Present) — Developed interpretable models integrating protein structure, Rosetta energetics, evolutionary features, and protein-language-model signals to predict mutation-level antibiotic resistance under data scarcity.
• Evolutionary Protein Data Augmentation (2025–Present) — Designed and evaluated homolog-aware and biologically constrained augmentation strategies for mutation-sensitive prediction, including pretrained protein language-model scoring, transfer-learning experiments, and controlled ablations across sparse biological datasets.

Software and Data Resources

• BIG-TB Benchmark (2024–Present) — Open-source pipelines for preprocessing, training, cross-validation, robustness analysis, and interpretability evaluation across classical ML, deep neural networks, and biological foundation-model representations.
• Structure-Aware Variant Analysis Toolkit (2023–Present) — Research code for mapping mutations to protein structures, quantifying spatial clustering, and supporting structure-informed prediction and mechanistic interpretation.
• Resistance Forecasting in Mycobacterium tuberculosis (2024–Present) — Reproducible data-preparation, multimodal feature-engineering, model-training, and temporal-evaluation workflows for prioritizing antibiotic-resistance variants of uncertain significance.

Talks and Posters

• BIG-TB: A Benchmark Dataset for Genomic Resistance Prediction and Interpretability in Mycobacterium tuberculosis — Machine Learning for Computational Biology (MLCB) Workshop, 2025 · Spotlight/lightning talk.
• Protein Structure-Informed Regularized Linear Model Outperforms ESM for Predicting Antibiotic Resistance in Mycobacterium tuberculosis — Harvard Program in Quantitative Genomics (PQG) Conference, 2024 · Poster.

Research Funding

• Graduate researcher supported by a UMass interdisciplinary research award for multimodal antibiotic-resistance forecasting, 2024. Principal Investigator: Anna G. Green.

Honors, Awards, and Sponsored Participation

• Selected as a fully funded graduate participant, Tapia Conference, September 2026.
• Fully funded selected participant, CRA-WP Grad Cohort for Women, 2023.
• Sudha and Rajesh Jha Scholarship, UMass Amherst, 2023.
• Fully funded Student Volunteer and ACM Student Travel Grant recipient, ACM UbiComp, Singapore, 2018.
• Merit-Based Financial Aid, North South University, 2017–2019.

Public Engagement and Research Outreach

• Featured Graduate Researcher, AI at UMass public-engagement campaign, University of Massachusetts Amherst, 2026. Appeared in a university-produced outreach video explaining how computational biology and machine learning can support antibiotic-resistance prediction and the development of more effective disease treatments.

Research Mentoring

• Shakir Sahibul, M.S. student, Fall 2024 — Mentored a transformer-based antibiotic-resistance prediction project; subsequently joined Amazon.
• Shuqi Hong, M.S. student, Fall 2025 – Summer 2026 — Mentored synthetic and evolutionary augmentation research for protein resistance modeling, resulting in a co-authored full-length manuscript submitted to MLCB 2026.

Professional and University Service

Peer Review

• Reviewer, Bioinformatics Advances, 2026.
• Reviewer, ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies Posters Track (COMPASS 2026).
• Reviewer, MLCSB: Machine Learning in Computational and Systems Biology at ISMB, 2026.
• Reviewer, ACM CHI Late-Breaking Work, 2023 and 2025.
• Reviewer, Machine Learning in Computational Biology, 2026.

Academic and Community Leadership

• Elected Graduate Representative for Ph.D. students, Faculty Senate / CICS, UMass Amherst, 2025–2026; represented graduate concerns in faculty meetings and participated in faculty-candidate evaluation.
• Chapter Chair, North South University ACM Student Chapter, 2017–2019; led technical competitions, workshops, research training, and outreach, including ACM SIGCHI schools and an inter-university girls’ programming contest.