arXiv subjects

Zhaojie Chai

Publications and source records attributed to Zhaojie Chai.

6 recordsLinked to original sources

arXiv2026

GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms

Scientific methods are developed for classes of problems, so knowledge transfers across structurally related cases. Language-model agents can execute scientific workflows, but their problem--method relationships remain implicit, so each new problem restarts the search and little of what worked transfers. We introduce GRAFT--ATHENA, which makes this problem-to-method map explicit as an expandable probabilistic structure of admissible problems, methods, and their dependencies. Graph factorization keeps the substrate tractable, and semantic fingerprints measure similarity, so experience guides related problems. As a result, the framework matched or exceeded expert baselines, attaining near-machine-precision losses in physics-informed learning, reproducing clinically consistent blood-rheology trends, and developing a high-order hypersonic-flow solver for the Apollo Command Module that matched experimental measurements within $1.8\%$. It also proposed a certified regularization for ill-posed in vivo brain-flow reconstruction, developed a spectrally convergent physics-informed architecture, and established machine-checked universal-approximation theorems for two widely used architectures. Scientific structure enables cumulative and verifiable agentic discovery.

cs.LG↗

arXiv2026

Quantifying the Biophysical Properties of Red Blood Cells in Gaucher Disease

Gaucher disease (GD), the most common lysosomal storage disorder, alters red blood cell (RBC) mechanics and circulation, contributing to vascular occlusions, bone infarcts, and splenomegaly. However, the individual roles of GD-RBC biophysical properties in these processes remain unclear. Here, we present a combined computational-experimental investigation to quantitatively characterize GD-RBC biophysical properties and determine how specific mechanical parameters drive abnormal RBC behavior. Informed by experimental data, we independently quantify key RBC properties, including shear modulus (mu), surface-to-volume ratio (S/V), and bending modulus (k_c). Based on these parameters, we construct three GD-RBC subtypes (GD-RBC1-3) to systematically isolate their individual contributions. At the single-cell level, optical tweezers simulations show up to ~27% reduction in axial diameter and ~42% reduction in transverse compression. Tank-treading dynamics exhibit non-monotonic behavior, with rotation frequencies increasing by up to ~70% or decreasing under elevated bending rigidity. In confined flow, traversal times through microchannel constrictions increase by more than a factor of two, while splenic slit passage times rise from ~250 ms (control) to >1200 ms for the severe GD-RBC subtype, approaching a functional no-passage threshold. At the population level, viscosity simulations demonstrate that these alterations collectively elevate blood viscosity, with small fractions (~4.0%) of highly rigid cells disproportionately increasing flow resistance. Overall, this study provides a quantitative and mechanistic framework that disentangles the contributions of key RBC parameters to abnormal behavior in GD, linking cellular-scale biophysics to hematologic dysfunction and microvascular occlusion.

physics.bio-ph↗

arXiv2026

Quantifying reticulocyte biomechanics in health and disease

Red blood cell (RBC) populations are mechanically heterogeneous, yet how this shapes transport, clogging, and rheology in confined environments remains unclear. We combine microfluidic microchannel experiments with dissipative particle dynamics (DPD) simulations to study how reticulocyte morphology, deformability, and cell-cell hydrodynamic coupling govern microconfined blood flow, and link these to acute and chronic mountain sickness. Reticulocyte-rich samples show three subtypes (multilobular, cup-shaped, near-discocytic), parameterized (R1-R3) by fitting microchannel transit and shape-under-flow data. Single-cell simulations show that 5-micron microchannels amplify mechanical heterogeneity (R1 transits 30-50% more slowly than softer cells), whereas bending-dominated splenic slits discriminate subtypes by only 10-20%. Pairwise simulations show that a leading cell never lets a follower pass below its own single-cell threshold - so the order-of-magnitude, wake-"unjamming" reduction is absent - but the leader's compliance shapes crowded single-file passage: a soft reticulocyte leader lowers a trailing stiff cell's critical passage pressure by ~12% relative to a stiff (sickle-trait) leader and speeds its transit by ~10%. The controlling variable is the single-cell critical pressure gradient Delta_P_c, which rises monotonically with membrane stiffness from control discocytes through reticulocytes to sickle-cell-trait cells. Our simulations reproduce the shear-thinning viscosity of control blood, against which the reported chronic-mountain-sickness hyperviscosity reflects predominantly hematocrit-driven crowding rather than a change in single-cell rheology. These results place benign acclimatization, chronic-mountain-sickness hyperviscosity, and sickle-cell-trait splenic syndrome on a single mechanical axis defined by Delta_P_c relative to the splenic operating pressure.

cond-mat.soft↗

arXiv2026

Quantifying the biophysical properties of stomatocytes in health and disease

Hereditary stomatocytosis (HS) comprises red blood cell (RBC) disorders characterized by cup-shaped erythrocytes that respond oppositely to splenectomy: curative in overhydrated HS (OHS) but potentially thrombogenic in dehydrated HS (DHS/xerocytosis). This paradox persists because RBC biomechanics is governed by partly independent parameters--shear modulus, bending rigidity, surface-to-volume ratio (S/V), and cytoplasmic viscosity--that existing assays capture only piecemeal. Here we combine dissipative particle dynamics (DPD) simulations with microfluidic imaging to construct a control discocyte and three stomatocyte models (ST-RBC1-3) at fixed membrane area and decreasing volume (109.7, 101.5, 89.8 fL), spanning the OHS-to-DHS range. Tracing this parameter set through five mechanically orthogonal assays, we find that interendothelial-slit (IES) traversal is geometry-dominated: overhydrated ST-RBC1 requires an order of magnitude higher critical pressure than healthy RBCs, whereas dehydrated ST-RBC3 passes freely. ST-RBC3 nonetheless suppresses membrane tank-treading and raises low-shear whole-blood viscosity by ~29% at physiological haematocrit, comparable to Gaucher-disease hyperviscosity. A funnel-obstacle chip amplifies these differences into a label-free centerline-offset signal predicted to separate all four RBC types (~4.5 standard deviations between extreme phenotypes). These results unite single-cell mechanics, splenic filtration, and hemorheology in one framework, resolve the splenectomy paradox, and point toward microfluidic pre-operative risk stratification in HS.

q-bio.CB↗

arXiv2020

Deep reinforcement learning with a particle dynamics environment applied to emergency evacuation of a room with obstacles

A very successful model for simulating emergency evacuation is the social-force model. At the heart of the model is the self-driven force that is applied to an agent and is directed towards the exit. However, it is not clear if the application of this force results in optimal evacuation, especially in complex environments with obstacles. Here, we develop a deep reinforcement learning algorithm in association with the social force model to train agents to find the fastest evacuation path. During training, we penalize every step of an agent in the room and give zero reward at the exit. We adopt the Dyna-Q learning approach. We first show that in the case of a room without obstacles the resulting self-driven force points directly towards the exit as in the social force model and that the median exit time intervals calculated using the two methods are not significantly different. Then, we investigate evacuation of a room with one obstacle and one exit. We show that our method produces similar results with the social force model when the obstacle is convex. However, in the case of concave obstacles, which sometimes can act as traps for agents governed purely by the social force model and prohibit complete room evacuation, our approach is clearly advantageous since it derives a policy that results in object avoidance and complete room evacuation without additional assumptions. We also study evacuation of a room with multiple exits. We show that agents are able to evacuate efficiently from the nearest exit through a shared network trained for a single agent. Finally, we test the robustness of the Dyna-Q learning approach in a complex environment with multiple exits and obstacles. Overall, we show that our model can efficiently simulate emergency evacuation in complex environments with multiple room exits and obstacles where it is difficult to obtain an intuitive rule for fast evacuation.

cs.LG↗

arXiv2020

A deep reinforcement learning model based on deterministic policy gradient for collective neural crest cell migration

Modeling cell interactions such as co-attraction and contact-inhibition of locomotion is essential for understanding collective cell migration. Here, we propose a novel deep reinforcement learning model for collective neural crest cell migration. We apply the deep deterministic policy gradient algorithm in association with a particle dynamics simulation environment to train agents to determine the migration path. Because of the different migration mechanisms of leader and follower neural crest cells, we train two types of agents (leaders and followers) to learn the collective cell migration behavior. For a leader agent, we consider a linear combination of a global task, resulting in the shortest path to the target source, and a local task, resulting in a coordinated motion along the local chemoattractant gradient. For a follower agent, we consider only the local task. First, we show that the self-driven forces learned by the leader cell point approximately to the placode, which means that the agent is able to learn to follow the shortest path to the target. To validate our method, we compare the total time elapsed for agents to reach the placode computed using the proposed method and the time computed using an agent-based model. The distributions of the migration time intervals calculated using the two methods are shown to not differ significantly. We then study the effect of co-attraction and contact-inhibition of locomotion to the collective leader cell migration. We show that the overall leader cell migration for the case with co-attraction is slower because the co-attraction mitigates the source-driven effect. In addition, we find that the leader and follower agents learn to follow a similar migration behavior as in experimental observations. Overall, our proposed method provides useful insight on how to apply reinforcement learning techniques to simulate collective cell migration.

q-bio.CB↗