Open-source tools & models

Base model and reference implementation — stochastic attention via Langevin dynamics on the modern Hopfield energy, underpinning the protein and patient generation studies.

Training-free generation of protein sequences from small family alignments via stochastic attention.

Conditioning protein binder generation via Hopfield pattern multiplicity and stochastic attention.

Validated synthetic patient generation for small longitudinal cohorts — coagulation dynamics across pregnancy.

A generative pre-trained transformer for modeling financial time series and replicating limit order book dynamics.

Agent-based financial market simulation platform with multiple assets, distributed computing, and heterogeneous agents.

Continuous Hidden Markov Models as a digital twin for equity returns — Gaussian, Student-t, and Laplace emissions with cross-asset copula composition.

A Julia package implementing a hybrid Hidden Markov Model with Poisson jump-diffusion for synthetic equity time-series generation.

Jump-HMM-driven Heston implied-volatility model for synthetic American option pricing.

Constructing, solving, and analyzing biochemical network models using Biochemical Systems Theory (BST).

JuPOETs: a constrained multiobjective optimization approach to estimate biochemical model ensembles via Pareto optimal ensemble techniques.

Simplified English Modeling Language for constructing biological models in Julia using a human-readable syntax.

Dynamic Optimization with Particle Swarms — a meta-heuristic for parameter estimation in biochemical models.

Genome-scale, sequence-specific dynamic model of cell-free protein synthesis in E. coli.

Sequence-specific constraint-based modeling framework for cell-free protein synthesis systems.

Hybrid cybernetic modeling with flux balance analysis for effective dynamic models of metabolic networks.

Dynamic modeling of the human coagulation cascade using reduced-order effective kinetic models.

Reduced-order modeling and analysis of the human complement system.

Model-guided metabolic engineering for improving designer glycan production in E. coli.

Effective model of the retinoic-acid-induced HL-60 differentiation program signal transduction.

Modeling and analysis of hormone and mitogenic signal integration in prostate cancer.

Population heterogeneity in the epithelial-to-mesenchymal transition controlled by NFAT and phosphorylated Sp1.

Kinetic modeling of coagulation and fibrinolysis with platelets.

Financial Data, Markets, and Mayhem — quantitative finance for scientists and engineers.

Principles of Computational Thinking for Engineers — data science, ML, and mathematical modeling.

Machine Learning and AI Methods for Engineers — supervised, deep, and reinforcement learning.