Build tools for discovery.
Learn the mathematics and computational decisions behind a model. Evaluate biological, physiological, behavioral and cognitive measurements with scientific care.
Biology × Computation / Proposed Course
AI for Bio
Foundations, Debugging
and Biology-Inspired Intelligence
Understand how AI learns.
Find out why it fails.
Turn biological insight into a testable idea.
My ultimate goal is not simply to train biologists to use AI, but to educate a new generation of scientists who can draw inspiration from biology to shape the future of AI itself.
14 weeksTwo classes + one studio / week
4 laboratoriesBuild, break, diagnose, improve
1 capstoneBiology-to-AI Innovation Challenge
Bio + BME + CSUpper undergraduate / graduate
We often forget that, before artificial intelligence became a tool for biology, biology was one of the inspirations for artificial intelligence itself.
Learn from living systems.
Explore adaptation, memory and feedback as sources of computational hypotheses. Translate an idea into an algorithm, then test whether its proposed mechanism matters.
01 / The course
From intuition to evidence.
AI for Bio connects the foundations of machine learning with the systems that biology studies: systems that sense, adapt, regulate and learn. Students build models, diagnose their failures and evaluate what their outputs mean scientifically. A second direction asks how biological principles can become testable ideas for better AI.
Biological inspiration is a starting point for a hypothesis. Students learn to distinguish analogy, prediction, mechanism and causal evidence.
- 01
Formulate a biological, physiological, behavioral or cognitive question as a learning problem with explicit measurements, targets and assumptions.
- 02
Derive and implement a small neural network, explain its loss and gradients, and compare it with a suitable statistical baseline.
- 03
Diagnose training, data and evaluation failures through controlled experiments and interpretable debugging evidence.
- 04
Design leakage-aware evaluation across people, batches and time, and quantify uncertainty and failure under distribution shift.
- 05
Translate a biological mechanism into a computational hypothesis, implement a model change and test it with an ablation.
- 06
Build and critically assess a small dynamical model that connects sensing, hidden states and adaptive measurement.
- 07
Communicate reproducible results with a clear distinction between prediction, mechanism, analogy and causal evidence.
02 / Weekly syllabus
A path through the semester.
Each week connects a question, a computational idea and an experiment. Open a week for both class meetings, studio work, preparation and assessment checkpoints.
Showing all 14 weeks
01FoundationsA shared language for biology and AIWhat is learned, what is measured, and what is assumed?
Class A
Turn a biological question into inputs, targets, a prediction time and a unit of analysis. Separate a scientific explanation from a predictive association.
Class B
Introduce learning, optimization and inductive bias through neural computation, adaptation and feedback. Identify where each analogy breaks.
Studio / experiment
Audit a small synthetic dataset for missing values, units, repeated subjects and unreliable labels; write a data dictionary.
Reading / preparation
ISLP: statistical learning overview; scikit-learn: common pitfalls.
Due / checkpoint Ungraded readiness check and a one-page problem formulation.
02FoundationsFrom measurements to learnable dataCould the model learn the experiment instead of the biology?
Class A
Sampling, noise, artifacts, feature construction and nuisance variables in signals, images and molecular measurements.
Class B
Train/validation/test roles; subject-, batch- and time-aware splitting; preprocessing fit only on training data.
Studio / experiment
Compare a sample-random split with a subject-held-out split on synthetic repeated measurements. Check subject ID and acquisition-order shortcuts.
Reading / preparation
scikit-learn: inconsistent preprocessing, data leakage and controlling randomness.
Due / checkpoint Data audit and split manifest for feedback; no graded submission.
03FoundationsBuild a model you can explainWhat does a useful baseline tell us before deep learning?
Class A
Linear and logistic regression, loss functions, decision boundaries and regularization; derive a gradient update.
Class B
Gradient descent, scaling and optimization diagnostics. Connect parameter fitting to a simple biological dose-response example without claiming mechanism.
Studio / experiment
Start Lab 1: implement a small multilayer perceptron and gradient updates in NumPy, then compare with autograd.
Reading / preparation
ISLP: regression and classification; PyTorch: tensors, autograd and optimization.
Due / checkpoint Concept check 1 (5%): loss, gradients and prediction tasks.
04FoundationsTrain, inspect, debugWhy can a model look successful and still be wrong?
Class A
Backpropagation, activation functions, underfitting, overfitting and learning curves; compare a neural network with a regularized baseline.
Class B
Diagnose shape/label errors, unstable learning rates, preprocessing leakage and train/evaluation mode mistakes.
Studio / experiment
Complete Lab 1: reproduce planted failures, form a diagnosis, change one factor at a time and document the repair.
Reading / preparation
ISLP: deep learning; PyTorch: building a model and optimization; scikit-learn: leakage.
Due / checkpoint Lab 1 (10%): first neural network and debugging dossier.
05FoundationsEvaluate a scientific claimWhat evidence would change your conclusion?
Class A
Class imbalance, confusion matrices, precision/recall, AUROC, AUPRC and regression errors; choose a metric for the biological question.
Class B
Grouped cross-validation, tuning on validation data, calibration and subject-level bootstrap uncertainty. Distinguish discrimination from usefulness.
Studio / experiment
Evaluate a baseline and a tree model under identical splits; write a falsifiable capstone hypothesis and an evaluation plan.
Reading / preparation
ISLP: resampling and tree-based methods; scikit-learn: common pitfalls.
Due / checkpoint Capstone proposal (5% of course grade): question, mechanism, baseline, split, metric and data/compute plan.
06Biology → AIBiological dynamics and feedbackWhen do biological relationships become computational constraints?
Class A
States versus observations; differential equations, equilibrium and local stability. Use a simplified gene-regulation model as a teaching example.
Class B
Negative feedback, adaptation and time scales; translate a mechanism into a model component, constraint or testable prediction.
Studio / experiment
Start Lab 2: simulate gene expression with degradation and negative feedback; apply step disturbances and parameter changes.
Reading / preparation
ISLP: regression review. Preparation: derive dx/dt = production(x, u) − degradation(x) and inspect its equilibria.
Due / checkpoint Concept check 2 (5%): states, observations and feedback.
07Biology → AILearning with mechanistic structureDoes adding biological knowledge improve the right thing?
Class A
Compare black-box, mechanistic and hybrid models; encode bounds, conservation or temporal smoothness only when scientifically justified.
Class B
Identifiability, model mismatch and ablation: distinguish a useful inductive bias from a correct biological explanation.
Studio / experiment
Complete Lab 2: fit model parameters to noisy simulated trajectories; compare feedback/no-feedback systems and test an incorrect prior.
Reading / preparation
ISLP: regularization and model selection. Revisit the gene-regulation equations from Week 6.
Due / checkpoint Lab 2 (10%): gene feedback model, disturbance response and model-mismatch analysis.
08Biology → AIRepresentations across biological scalesWhat information should a representation keep?
Class A
PCA, clustering and autoencoders; representations for molecular measurements, biomedical images, neural/behavioral signals and physiology.
Class B
CNNs, temporal models and self-supervised learning at a conceptual level. Match architecture and augmentations to the measurement process.
Studio / experiment
Compare features and learned representations on a small synthetic multimodal dataset; test a nuisance-variable ablation.
Reading / preparation
ISLP: unsupervised learning and deep learning; PyTorch: model building.
Due / checkpoint Capstone baseline reproduction (5%): runnable baseline, split manifest and initial failure analysis.
09Biology → AILearning in an evolving environmentHow can a learner adapt without losing what it knew?
Class A
Distribution shift, continual learning, catastrophic forgetting and stability/plasticity. Relate adaptation to biological learning with explicit limits.
Class B
Frozen models, fine-tuning and replay; temporal evaluation and retention/adaptation tradeoffs under a matched compute budget.
Studio / experiment
Start Lab 3: train on sequential synthetic environments; measure performance on both old and new environments after each update.
Reading / preparation
Kirkpatrick et al.: Overcoming catastrophic forgetting in neural networks (author preprint).
Due / checkpoint Concept check 3 (5%): representation, shift and forgetting.
10AI → BiologyPersonalization, behavior and contextIs the model detecting a state or a change in context?
Class A
Between-person variation, within-person change, context confounding and cognitive/behavioral proxy labels; limits of latent-state interpretation.
Class B
Population versus personalized models; separate a calibration period from future evaluation. Examine subgroup errors and missing modalities.
Studio / experiment
Complete Lab 3: compare frozen, fine-tuned and replay learners; stress-test a context shortcut and quantify forgetting.
Reading / preparation
Kirkpatrick et al.: revisit evaluation; scikit-learn: leakage and randomness.
Due / checkpoint Lab 3 (10%): adaptation/retention curves, context stress test and compute accounting.
11AI → BiologyA mini digital twin as a scientific modelWhich hidden states can our measurements actually identify?
Class A
Define a digital twin operationally: a personalized dynamical model updated by observations. Separate this from a generic predictor.
Class B
State-space models, filtering, observation models and uncertainty; observability and sensor placement in a simplified human–environment system.
Studio / experiment
Start Lab 4: simulate hidden physiological states and noisy sensors; implement a linear Kalman-filter baseline and compare with direct regression.
Reading / preparation
PyTorch: implementation reference if needed. Preparation: derive the linear state and observation equations and one filtering update.
Due / checkpoint Capstone mechanism test (10%): controlled ablation, sensitivity analysis and claim–evidence table.
12AI → BiologyMeasure, predict, decideWhen should an intelligent system ask for another measurement?
Class A
Active sensing, missing observations, measurement cost and uncertainty-aware decisions; compare periodic and uncertainty-triggered sampling.
Class B
Prediction versus intervention; causal assumptions, counterfactual limits and why simulator success does not establish clinical benefit.
Studio / experiment
Complete Lab 4: compare state-estimation error, uncertainty coverage and sensing cost at matched budgets; introduce sensor failure or model mismatch.
Reading / preparation
scikit-learn: evaluation pitfalls. Revisit Week 11 state-space equations and assumptions.
Due / checkpoint Lab 4 (10%): mini twin and sensing policy. Concept check 4 (5%): state estimation and causal limits.
13SynthesisTrustworthy biological AICan someone else reproduce and challenge your result?
Class A
Interpretation versus explanation; uncertainty, bias, privacy, responsible data use and limits of scientific claims.
Class B
Foundation models and generative assistants: transfer, retrieval and generated hypotheses; inspect hallucination, contamination and unsupported conclusions.
Studio / experiment
Peer audit: run another team’s instructions, challenge a shortcut, inspect citations and write a reproducibility review.
Reading / preparation
scikit-learn: common pitfalls; reread the source documentation for the capstone dataset and methods.
Due / checkpoint Capstone report and reproducible artifact (10%): six-page report plus code, environment, data provenance and limitations.
14SynthesisBiology-to-AI Innovation ChallengeWhat did the experiment teach us about both biology and AI?
Class A
Team presentations: biological motivation → computational hypothesis → controlled evidence → boundary of the claim.
Class B
Individual oral defense and reflection: explain a model failure, an alternative explanation and the next informative experiment.
Studio / experiment
Capstone symposium and cross-disciplinary review. A well-supported negative result is a valid contribution.
Reading / preparation
Peer project reports and method/dataset references; no new required reading.
Due / checkpoint Presentation and individual defense (5%). Submit a final contribution statement.
Preparation names available readings or a mathematical task. Lecture notes and starter notebooks are planned teaching materials; this release provides the syllabus and assignment specifications.
03 / Learning by doing
Every lab has a failure mode.
Four substantial experiments make debugging part of scientific reasoning. Synthetic data provides known ground truth, controlled disturbances and a practical route for students with different backgrounds.
Train and Debug Your First Neural Network
Synthetic labeled measurements with repeated subjects.
Build
Implement a two-layer network, check a gradient numerically, and compare with a linear baseline and a PyTorch implementation.
Test and debug
Diagnose three planted failures: a bad learning rate, an incorrect label mapping and preprocessing leakage. Include before/after evidence and a held-out evaluation.
Deliver
Network notebook; loss/gradient plots; split manifest; a two-page debugging dossier.
Build a Gene Feedback Controller
Simulated gene-expression trajectories with known parameters.
Build
Simulate negative feedback, fit parameters from noisy observations and compare disturbance recovery with a no-feedback model.
Test and debug
Vary time step, measurement noise and parameter values. Compare a correct constraint with a deliberately misspecified one; avoid interpreting the toy system as a validated cell model.
Deliver
Equations and assumptions; simulation code; recovery/stability plots; parameter and mismatch analysis.
Learn from an Evolving Environment
Sequential synthetic environments with controlled context shifts.
Build
Compare a frozen model, sequential fine-tuning and a replay baseline using the same architecture and data budget.
Test and debug
Evaluate old and new environments after every update; report multiple seeds, adaptation, forgetting, context shortcuts and training cost.
Deliver
Learning curves by environment; method comparison; failure analysis; a reproducible experiment configuration.
Build a Mini Human Digital Twin
Synthetic physiological states, contextual inputs and noisy sensor readings.
Build
Estimate hidden states with a linear filtering baseline; compare fixed-rate sensing with an uncertainty-triggered measurement policy.
Test and debug
Use matched measurement budgets and unseen trajectories. Report state error, interval coverage and measurement cost; stress-test sensor dropout and model mismatch.
Deliver
State/observation equations; estimator and sensing policy; error–cost analysis; a limitations statement.
Each lab: implementation and understanding 30%; debugging and controlled checks 30%; valid evaluation 25%; interpretation and reproducibility 15%.
04 / The capstoneBiology-to-AI
Biology-to-AI
Innovation Challenge.
Turn a biological principle into a computational hypothesis that can be disproved. In teams of 2–3, build a baseline, test a mechanism and explain what the evidence supports. A rigorous negative result is a valid contribution.
One idea. A controlled test.
Adaptation and memory
Does a biologically motivated memory or regularization rule improve retention after a context shift?
Compare against fine-tuning and a simple replay baseline; ablate the proposed mechanism and match data/compute.
Feedback and robustness
Can a justified feedback constraint improve robustness to a disturbance without concealing model mismatch?
Use a transparent synthetic system; compare unconstrained and constrained models and perturb the assumed mechanism.
Context and hidden states
Does context improve estimation of a hidden state, or merely create a shortcut?
Use held-out subjects or environments and a context-scrambling control; distinguish state estimation from diagnosis.
Active measurement
Can adaptive sensing reduce measurement cost while preserving estimation quality?
Compare with periodic and random sampling at matched budgets; report uncertainty, failure modes and cost.
| Due | Evidence to deliver | Weight |
|---|---|---|
| Week 5 | One-page proposal: hypothesis, mechanism, baseline, data, evaluation and feasibility | 5% |
| Week 8 | Runnable baseline reproduction, split manifest and failure analysis | 5% |
| Week 11 | Mechanism ablation, sensitivity analysis and claim–evidence table | 10% |
| Week 13 | Six-page report and reproducible artifact | 10% |
| Week 14 | Presentation, individual oral defense and contribution statement | 5% |
Report: biological motivation, mechanism-to-algorithm mapping, methods, evaluation, at least one ablation, results, limitations and the next informative experiment. References and a reproducibility appendix are outside the six-page limit. Include an environment specification, data provenance, split manifest and reproduction commands. Publication-level novelty is not required.
05 / Learning environment
Understanding earns the grade.
Assessment rewards sound decisions, controlled evidence and the ability to explain a model’s behavior. The course is designed around accessible computation and complementary disciplinary strengths.
Four laboratories40%
Four individual concept checks20%
Staged capstone35%
Participation and peer review5%
Concept checks: Weeks 3, 6, 9 and 12, each 5%. Labs: Weeks 4, 7, 10 and 12, each 10%. Written peer reviews count toward participation. Individual reflections and defenses establish each student’s understanding.
Preparation and access
Designed for upper-level undergraduates and early graduate students in biology, bioengineering, BME, neuroscience or CS. Basic Python, introductory probability/statistics and familiarity with vectors, derivatives and basic biology are expected. Prior ML is not required. A preparatory Python/NumPy and linear-algebra refresher is recommended; students can take either a biological or computational role while rotating responsibilities.
Weekly rhythm and tools
Proposed 14-week format: two 75-minute class meetings and one 90-minute studio each week, plus about 5–7 hours of independent work. Use Python, NumPy, pandas, matplotlib, scikit-learn and PyTorch in Jupyter. Core assignments use small CPU-friendly synthetic data; a GPU and paid AI subscription are not required. Official credits and workload must be set by the host institution.
Assessment and collaboration
Four labs contribute 40%; four individual concept checks contribute 20%; the staged capstone contributes 35%; participation and peer review contribute 5%. Labs may be completed in pairs with individual debugging reflections. Capstones use teams of 2–3 with explicit roles and an individual defense. Participation can be demonstrated through written review as well as discussion.
AI tools and academic integrity
Generative tools may be used for explanation and coding assistance when disclosed. Submit a short record of material use, verify generated code and citations, and explain every submitted component. Individual concept checks and oral defenses are completed without generative assistance. Never upload restricted data to an external tool. Evaluation rewards justified decisions and evidence; model output alone is not evidence.
Data and reproducibility
Default to synthetic or appropriately licensed public data. Keep subjects, experimental batches and future observations separated as required by the question. Document data versions, licenses, seeds, preprocessing, splits and software dependencies. PTB-XL is optional: follow its source documentation, patient-level folds and citation requirements. No new human-subject data collection is required.
Feedback and inclusion
Use a diagnostic readiness check, weekly low-stakes feedback and scheduled project checkpoints. As a proposed default, allow three 24-hour grace days across lab submissions; arrange other extensions with the instructor. Provide accessible notebooks, readable figures, written alternatives to live participation and accommodations under the host institution’s process. Meeting times, office hours and institutional policies will be specified for an actual offering.
06 / Read and explore
A focused reading shelf.
Selected book chapters, official implementation guides, one research discussion and an optional biomedical dataset. Assigned sections appear in the weekly syllabus.
- ISLPAn Introduction to Statistical Learning with Applications in Python
James, Witten, Hastie, Tibshirani & Taylor (2023). Selected chapters and Python labs; the core statistical learning reference.
- Practicescikit-learn: common pitfalls and recommended practices
Official documentation on preprocessing, leakage and reproducibility. Read alongside every modeling assignment.
- ImplementationPyTorch: Learn the Basics
Official tutorials for tensors, datasets, autograd, optimization and saving models. Use small CPU-friendly networks.
- PaperOvercoming catastrophic forgetting in neural networks
Kirkpatrick et al., PNAS (2017), DOI: 10.1073/pnas.1611835114. Author preprint linked here; discuss retention, adaptation and limits of biological analogies.
- DataPTB-XL, version 1.0.3
Wagner et al., PhysioNet (2022). Optional ECG project dataset. Follow patient-level folds and the source license; cite both the dataset and its Scientific Data descriptor (2020).
Material availability. This release includes the complete proposed syllabus and laboratory/project specifications. Slides, recordings, starter notebooks, solutions and student results are not included. External materials remain subject to their authors’ and publishers’ terms.