Contamination sensing physical design method for microfluidic FPVA biochip

Abstract

The application discloses a kind of microfluidic FPVA biochip pollution perception physical design methods, it is related to the technical field of biochip.The method includes based on microfluidic FPVA biochip, respectively defining the framework description of pollution perception layout model and pollution perception wiring model;Obtain trained layout model and wiring model;Through the trained layout model and wiring model of synchronization and coordination, let the trained layout model and wiring model be able to globally perceive the change of all resources on FPVA biochip when executing respective task, obtain the physical design scheme of pollution perception.The application significantly improves the overall performance of the chip by designing a new physical design framework based on deep reinforcement learning, reduces the total cleaning cost of biological determination to the greatest extent, and optimizes the total length of fluid transportation path.

Description

Technical Field

[0001] The present invention relates to the technical field of biochips, and in particular to a pollution perception physical design method for a microfluidic FPVA biochip. Background Art

[0002] Microfluidic biochips enable automated biochemical experiments, such as immunoassays and DNA analysis, by precisely manipulating microscale fluid samples and reagents. These devices, often referred to as "labs on a chip," offer significant advantages, including high precision, throughput, and reliability. Therefore, they hold promise as an alternative to traditional manual laboratories.

[0003] Combining the advantages of flow microfluidic biochips and digital microfluidic biochips, a new generation of fully programmable valve array (FPVA) biochips has been proposed, realizing the "digital" operation of continuous fluids. Figure 1 The general logic structure of the FPVA biochip is shown, in which valves are regularly arranged along the fluid channels in the horizontal and vertical directions on the chip. These valves are connected to a Boolean logic-based multiplexing control system on the periphery of the biochip to switch between open and closed states. By opening any two valves in the cell and closing the rest, the fluid flow can be flexibly directed in any direction, such as Figure 1 shown.

[0004] Despite significant technological advances, these biochips still face the challenge of fluid cross-contamination, which can affect the accuracy and reliability of experimental results. To alleviate this problem, residues need to be dissolved in a buffer and rinsed out. This cleaning operation effectively removes residues from the channel surface, allowing the contaminated flow channel to be quickly reused for other fluids. However, the cleaning time is mainly determined by the dissolution time of the residues; if the required cleaning time is long, it will delay the completion time of the entire bioassay. Therefore, effectively allocating on-chip channel resources during the physical design process to minimize the impact of residues that require a long time to dissolve, thereby reducing the cleaning cost, is a key issue that needs to be addressed.

[0005] Currently, only a few automated methods have been proposed to address the cross-contamination problem of FPVA biochips. The existing art proposes an efficient cleaning algorithm that groups contaminated areas together for unified cleaning. Simultaneously, an efficient flow layer architecture synthesis has been developed to minimize the total number of contamination points, thereby reducing cleaning overhead and bioassay completion time. Furthermore, a cleaning optimization method that considers buffer volume consumption has been developed to ensure that all contaminants are removed in the shortest possible cleaning time. However, they do not systematically consider the actual cost of contamination removal for each contamination point generated during the physical design process. Therefore, although efforts have been made to reduce the total number of contamination points, the serious problem of long cleaning times caused by the presence of difficult-to-clean contamination points has not yet been addressed. Summary of the Invention

[0006] To address the shortcomings of the aforementioned background technologies, the present invention addresses the contamination-aware physical design of FPVA biochips. This invention provides a contamination-aware physical design method for microfluidic FPVA biochips. This method, based on a deep reinforcement learning framework, effectively improves chip design quality. The method involves three key technologies: a contamination-aware layout algorithm based on deep reinforcement learning, a contamination-aware wiring algorithm based on deep reinforcement learning, and a contamination-aware physical design algorithm based on collaborative design. The method aims to minimize the total length of the fluid transport path and the total cleaning cost of the bioassay.

[0007] The purpose of the present invention is to provide a contamination-sensing physical design method for a microfluidic FPVA biochip, comprising:

[0008] Based on the microfluidic FPVA biochip, a framework description of a pollution-aware layout model and a pollution-aware wiring model is defined respectively; wherein the framework description includes an action space, a state space, mask generation, and a reward function;

[0009] According to the framework description of the pollution-aware layout model and the framework description of the pollution-aware routing model, the pollution-aware layout model and the pollution-aware routing model are trained based on a deep reinforcement learning algorithm to obtain a trained layout model and routing model respectively.

[0010] By synchronizing and coordinating the trained layout model and routing model, the trained layout model and routing model can globally perceive the changes of all resources on the FPVA biochip when performing their respective tasks, and obtain a contamination-aware physical design solution.

[0011] Preferably, the framework description of the pollution-aware layout model includes a first action space, a first state space, a first mask generation, and a first reward function;

[0012] Wherein, the first action space is composed of all layout positions;

[0013] The first state space is composed of four core parts, namely, the information of the components of the current layout, the information of the components, the dissolution time of the fluid, and the cleaning cost matrix;

[0014] The first mask generation is to mask the action when the component exceeds the boundary of the biochip or there is overlap between units of different types of components.

[0015] Preferably, the first reward function is:

[0016]

[0017] Where α, β, γ and ψ are hyperparameters; F o It is a binary flag, a value of "1" indicates that the source component and the target component have overlapping units, and a value of "0" indicates no overlap; S r Indicates the minimum rectangular area that contains the laid-out components; C w is the cleaning cost after executing the layout action; △ represents the difference between time step t and time step t-1.

[0018] Preferably, the framework description of the pollution-aware wiring model includes a second action space, a second state space, a second mask generation, and a second reward function;

[0019] Among them, the second action space is composed of all flow directions of the fluid on the FPVA biochip;

[0020] The second state space is composed of three core components, namely, the information of the fluid being routed, the target location of the fluid, and the cleaning cost of each unit on the chip;

[0021] The second mask generation is to cover up the action when the fluid exceeds the boundary of the biochip or flows back along its historical path.

[0022] Preferably, the second reward function is:

[0023]

[0024] Where ε, θ, μ, τ are hyperparameters; Indicates the total length of the path planned for the transportation task; represents the total cleaning cost; -ε represents the negative reward; θ represents the endpoint reward; (fx, fy) represents the position reached by the fluid at the current time step; Indicates the target position of the fluid.

[0025] Preferably, the deep reinforcement learning algorithm adopts a proximal policy optimization algorithm with an Actor-Critic architecture.

[0026] Preferably, obtaining a pollution-aware physical design solution includes:

[0027] When the layout subtask is completed, the resource updates on the chip are input into the routing environment. The routing agent perceives changes in the layout scheme, cell occupancy, and pollution, and performs routing tasks based on the updated information. Similarly, after completing the routing subtask, the resource updates are fed back into the routing environment.

[0028] Preferably, the pollution-aware layout model is used to determine the on-chip locations of all components; and the pollution-aware routing model is used to find a set of flow paths for all transport tasks.

[0029] The present invention also provides a contamination sensing physical design system for a microfluidic FPVA biochip, comprising:

[0030] A definition module is used to define a framework description of a pollution-aware layout model and a pollution-aware wiring model based on a microfluidic FPVA biochip, wherein the framework description includes an action space, a state space, mask generation, and a reward function;

[0031] A training module is used to train the pollution-aware layout model and the pollution-aware routing model based on a deep reinforcement learning algorithm according to the framework description of the pollution-aware layout model and the framework description of the pollution-aware routing model, respectively, to obtain a trained layout model and a trained routing model;

[0032] The collaborative design module is used to synchronize and coordinate the trained layout model and routing model so that the trained layout model and routing model can globally perceive the changes of all resources on the FPVA biochip when performing their respective tasks, and obtain a contamination-aware physical design solution.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] This paper provides a contamination-aware physical design method for microfluidic FPVA biochips. This approach addresses this issue by proposing a deep reinforcement learning-based framework to effectively improve chip design quality. This method involves three key technologies: a contamination-aware layout algorithm based on deep reinforcement learning, a contamination-aware wiring algorithm based on deep reinforcement learning, and a contamination-aware physical design algorithm based on collaborative design. The method aims to minimize the total length of the fluid transport path and the total cleaning cost of the bioassay. Specifically, it includes the following steps:

[0035] The pollution-aware layout algorithm based on deep reinforcement learning in this invention: A pollution-aware layout algorithm based on deep reinforcement learning is proposed, a reinforcement learning environment for multiple layout tasks is designed, and a neural network model that can efficiently perform layout tasks is trained using the PPO algorithm. The optimization goals are to minimize the total cleaning cost, reduce fluid wiring tasks, and reduce the area of ​​the approximate shortest path region, thereby generating a high-quality pollution-aware layout solution.

[0036] The pollution-aware wiring algorithm based on deep reinforcement learning in this invention: A pollution-aware wiring algorithm based on deep reinforcement learning is proposed, and a reinforcement learning environment for multiple wiring tasks is designed. Similarly, the PPO algorithm is used to train a neural network model that can efficiently perform wiring tasks, with minimizing the total cleaning cost and reducing the total path length as the optimization goals, to generate a high-quality pollution-aware wiring solution.

[0037] The pollution-aware physical design algorithm based on collaborative design in the present invention: by synchronizing and coordinating two convergent layout neural network models and routing neural network models, the two models can globally perceive the changes of all resources on the FPVA biochip when performing their respective tasks, thereby making the most favorable decision for the entire physical design, thereby improving the quality of the physical design and reducing the total cleaning cost and total path length of the entire physical design.

[0038] The present invention provides a contamination-aware physical design method for FPVA biochips, which comprehensively considers layout and wiring issues. By designing a new physical design framework based on deep reinforcement learning, the overall performance of the chip is significantly improved, the total cleaning cost of the bioassay is minimized, and the total length of the fluid transport path is optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 The logical structure of the FPVA biochip.

[0040] Figure 2 (a) is a timing diagram of the biometrics and (b) is a binding and scheduling scheme corresponding to the biometrics shown in (a);

[0041] Figure 3 for Figure 2 Two physical design options for the bioassay shown in (a);

[0042] Figure 4 The proposed DRL-based collaborative physical design process. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand and implement the technical solution of the present invention, the present invention is further described below with reference to specific embodiments and drawings, but the embodiments are not intended to limit the present invention.

[0044] The present invention primarily targets reducing the number of contamination points, which intuitively shortens the total cleaning time. In practice, even a few contamination points can require a significant cleaning time. Each contaminated channel can be cleaned with buffer before being reused with any functional fluid. To ensure complete removal, the contaminant must be completely dissolved in the buffer and discharged from the biochip. The dissolution time of the contaminant is primarily determined by its diffusion coefficient; the lower the diffusion coefficient, the longer the dissolution time. Because dissolution time is a core component of the total cleaning time, ignoring the impact of the fluid diffusion coefficient during physical design can extend the time it takes to reuse the flow channel, which in turn increases the time it takes to complete the bioassay. Suboptimal physical design can lead to increased cleaning costs, including more contamination points. More critically, the total dissolution time for these contamination points can be significantly prolonged. Therefore, the present invention proposes a contamination-aware physical design method for FPVA biochips. This method comprehensively considers layout and routing issues. By designing a new physical design framework based on deep reinforcement learning, it significantly improves the overall chip performance, minimizes the total cleaning cost of the bioassay, and optimizes the total length of the fluid transport path.

[0045] To achieve the above objectives, the present invention provides a contamination-aware physical design method for a microfluidic FPVA biochip, comprising:

[0046] S1. Based on the microfluidic FPVA biochip, define the framework description of the pollution-aware layout model and the pollution-aware wiring model respectively; wherein the framework description includes the action space, state space, mask generation, and reward function;

[0047] The framework description of the pollution-aware layout model includes a first action space, a first state space, a first mask generation, and a first reward function;

[0048] Wherein, the first action space is composed of all layout positions;

[0049] The first state space is composed of four core parts, namely, the information of the components of the current layout, the information of the components, the dissolution time of the fluid, and the cleaning cost matrix;

[0050] The first mask generation is to mask the action when the component exceeds the boundary of the biochip or there is overlap between units of different types of components.

[0051] The first reward function is:

[0052]

[0053] Where α, β, γ and ψ are hyperparameters; F oIt is a binary flag, a value of "1" indicates that the source component and the target component have overlapping units, and a value of "0" indicates no overlap; S r Indicates the minimum rectangular area that contains the laid-out components; C w is the cleaning cost after executing the layout action; △ represents the difference between time step t and time step t-1.

[0054] The framework description of the pollution-aware wiring model includes a second action space, a second state space, a second mask generation, and a second reward function;

[0055] Among them, the second action space is composed of all flow directions of the fluid on the FPVA biochip;

[0056] The second state space is composed of three core components, namely, the information of the fluid being routed, the target location of the fluid, and the cleaning cost of each unit on the chip;

[0057] The second mask generation is to cover up the action when the fluid exceeds the boundary of the biochip or flows back along its historical path.

[0058] The second reward function is:

[0059]

[0060] Where ε, θ, μ, τ are hyperparameters; Indicates the total length of the path planned for the transportation task; represents the total cleaning cost; -ε represents the negative reward; θ represents the endpoint reward; (fx, fy) represents the position reached by the fluid at the current time step; Indicates the target position of the fluid.

[0061] S2. Based on the framework description of the pollution-aware layout model and the framework description of the pollution-aware routing model, respectively train the pollution-aware layout model and the pollution-aware routing model based on a deep reinforcement learning algorithm to obtain a trained layout model and routing model, respectively;

[0062] The deep reinforcement learning algorithm adopts a proximal policy optimization algorithm with an Actor-Critic architecture.

[0063] The pollution-aware placement model is used to determine the on-chip locations of all components; the pollution-aware routing model is used to find a set of flow paths for all transport tasks.

[0064] S3. By synchronizing and coordinating the trained layout model and routing model, the trained layout model and routing model can globally perceive the changes of all resources on the FPVA biochip when performing their respective tasks, and obtain a contamination-aware physical design solution.

[0065] When acquiring pollution-aware physical design solutions, include:

[0066] When the layout subtask is completed, the resource updates on the chip are input into the routing environment. The routing agent perceives changes in the layout scheme, cell occupancy, and pollution, and performs routing tasks based on the updated information. Similarly, after completing the routing subtask, the resource updates are fed back into the routing environment.

[0067] In order to illustrate the contamination perception physical design method of a microfluidic FPVA biochip provided by the present invention, it is described in conjunction with the accompanying drawings.

[0068] In one embodiment, a contamination-aware physical design method for a microfluidic FPVA biochip is provided, based on an FPVA simulation environment: a W×H FPVA biochip is considered as a collection of multifunctional units with W units in each row and H units in each column. Each unit consists of a flow channel and four valves that control the direction of fluid flow, such as Figure 1 shown.

[0069] Model a component as a four-tuple δ = (dx, dy, dw, dh), where (dx, dy) is the coordinate of the upper left corner of the component and (dw, dh) is the width and height of the component.

[0070] The fluid is modeled as a quaternion ζ = (fx, fy, fp, fd), where (fx, fy) is the position reached by the fluid at the current time step, fp is the path of fluid transport, and fd is the dissolution time of the fluid.

[0071] Let (x,y) be the coordinates of the FPVA unit; C x,y ∈R ≥0 is its contamination degree, where 0 means the unit is completely clean and greater than 0 means the unit is contaminated.

[0072] It is worth noting that the degree of contamination of the unit is equal to the dissolution time of the residual liquid. Represents the cleaning cost matrix of the FPVA biochip.

[0073] Specific pollution-aware physical design methods include:

[0074] (1) Pollution-aware layout algorithm based on deep reinforcement learning:

[0075] This application provides an efficient DRL-based layout tool to determine the on-chip location of all components. The layout tool design is described as follows:

[0076] Action space: Since the action at time step t is to place components, the action space consists of all possible layout positions and is defined as:

[0077] A1={a t |a t ∈{P1,P2,…,P w×h},P i =(px i ,py i )|px i ∈[1,W],py i ∈[1,H]}(1)

[0078] where (px i ,py i ) are the coordinates of the upper left corner of the on-chip cells occupied by the component.

[0079] State space: In order for the agent to make effective layout decisions by perceiving valuable information in the environment, the state space should consist of four core parts, namely the components m(o i ) Component m(o k )(e k,i ∈E) information Fluid (o i ) dissolution time and the cleaning cost matrix C t . Therefore, the entire state space is expressed as:

[0080]

[0081] Mask Generation: The agent must mask actions when it encounters the following situations: a) a component is outside the biochip boundary (i.e., dx+dw-1>W∨dy-dh<0); b) there is overlap between units of different types of components (e.g., ). Among them, U m and U q are the sets of cells occupied by m and q respectively. m and t q are the functional types of m and q respectively. Therefore, the mask matrix M1∈{0,1} W×H It can be defined as:

[0082]

[0083] Reward function: The primary goal of placement is to properly arrange the placement of each pair of source and target components. In this case, the performance metrics include the on-chip area of ​​the minimum rectangle containing all components and the cleaning cost caused by cell reuse.

[0084] Accordingly, in state s t Rewards obtained after executing the layout action It can be calculated as:

[0085]

[0086] Where α, β, γ and ψ are hyperparameters. The variable F o It is a binary flag. A value of "1" indicates that the source component and the target component have overlapping units, and a value of "0" indicates no overlap. When the source component and the target component have overlap, there is no need to set up a flow channel for the fluid transport task between them, thereby reducing the use of channel resources. r S represents the area of ​​the approximate shortest path region

[11] , which is defined as the minimum rectangular area containing the laid-out components. r The smaller it is, the more conducive it is to generating a routing solution with a smaller total path length. w is the cleaning cost after executing the layout action. △ represents the difference between time step t and time step t-1.

[0087] (2) Pollution-aware wiring algorithm based on deep reinforcement learning:

[0088] This application provides an efficient DRL-based router to find a set of flow paths for all transportation tasks. The router framework is described as follows:

[0089] Action space: Since the action at time step t is to realize the flow channel wiring, the action space consists of all possible flow directions of the fluid on the FPVA biochip and is defined as:

[0090] A2={a t |a t ∈{D1,D2,D3,D4},D i =i}(7)

[0091] Among them, D1, D2, D3, and D4 represent the four flow directions of the flow channel, namely, up, down, left, and right.

[0092] State space: In order to enable the agent to perceive valuable information from the environment and make efficient routing decisions, the state space at time step t should consist of three core parts, namely, the fluid being routed out (o i ) Fluid out(o i ) target location And the cleaning cost of each unit on the chip. Therefore, the entire state space is expressed as:

[0093]

[0094] Mask generation: After executing an action, the agent must mask the action if it encounters the following situations: a) The fluid exceeds the boundaries of the biochip (i.e. [1,H]); b) The fluid moves along its historical path (i.e. (fx t ,fy t )∈fp t-1 ) backflow. Therefore, the mask matrix M2∈{0,1} W×H It can be defined as:

[0095]

[0096] Reward function: The main goal of routing is to properly allocate flow channels for each transport task. In this case, the performance indicators include the total length of the transport path and the cleaning cost caused by the reuse unit. t Rewards received after performing a wiring operation It can be calculated as:

[0097]

[0098] Where ε, θ, μ, and τ are hyperparameters. To converge the routing agent's exploration process and optimize the path length, the agent is penalized with a negative reward ε for each step. The destination reward θ helps to converge faster by associating reaching the target location with an additional reward. After completing each routing task, the total length of the path planned for this transport task is calculated. and total cleaning cost Therefore, negative rewards are needed to encourage the agent to optimize these two objectives.

[0099] The placer and router are trained using the pollution-aware placement algorithm based on deep reinforcement learning and the pollution-aware routing algorithm based on deep reinforcement learning. The training process is described in Algorithm 1: Training process of deep reinforcement learning agents

[0100]

[0101] Among them, the relevant configuration settings during the training process are as follows:

[0102] Training configuration: To increase sample diversity and enhance the generalization ability of the agent, random sampling is performed based on the {washing time}-{diffusion coefficient} graph [7] to determine the dissolution time of various fluids, which are then used as input to the layout and routing environment. When the environment is initialized, a three-dimensional matrix is ​​used to represent the state of component layout or fluid routing. Each dimension of the matrix records the properties, location, and potential cleaning cost of the component or fluid. Convolutional neural networks (CNNs) extract features from these matrices, enhancing the ability of the DRL model to handle complex states.

[0103] PPO Architecture: During the training phase, we use the Proximal Policy Optimization (PPO) algorithm with an Actor-Critic architecture

[12] ,

[13] . The PPO architecture first extracts high-level features of the input state through a four-layer CNN. The extracted features are then unfolded and fed into two multi-layer perceptron (MLP) modules: the actor and the critic. The actor network predicts the probability distribution of the action based on the current state, while the critic network evaluates the value of the current state. ReLU is used as the activation function between each hidden layer. The actor network is optimized using the PPO algorithm, while the critic network helps the actor train by providing state value estimates. The overall architecture combines convolutional feature extraction with the actor-critic structure to achieve policy learning and state evaluation.

[0104] Training process: The placement and routing agents use a unified training framework. Algorithm 1 aims to train a DRL agent that can effectively perform placement / routing tasks. The input of the algorithm includes a set of tasks and an FPVA simulation environment. The final output is a trained and converged DRL agent. The algorithm first initializes the policy network parameters θ0, the value function parameters φ0, and a set of key hyperparameters. Then, the algorithm performs n iterations, each of which aims to collect state-action samples from the environment for subsequent training. At the beginning of each iteration, all parameters of the environment are reset. During the sampling phase, the agent and the environment interact T s Step (Lines 5-9 in Algorithm 1). At each step, the agent passes through the current policy network Select an action. After the action is executed, the system generates rewards based on the current state and action. and transition to the next state s t+1 This process is repeated for T s Step, all state-action samples Store in a buffer for future training use.

[0105] Based on the data sampled from the current policy, calculate the advantage function for each sample To estimate whether a particular action performs better or worse than the expected action under the policy. The advantage function can be calculated using methods such as time difference or generalized advantage estimation. At the same time, the discounted return Based on instant rewards and discount factor λ, which is used to evaluate the total reward that the agent will receive in the future starting from the current state. Finally, the collected samples are divided into smaller batches, and the samples of each small batch are used for multiple updates (lines 12-15 in Algorithm 1). In each update, the policy θ is updated by maximizing the PPO objective function k+1 , which is calculated as follows:

[0106]

[0107] Among them, argmax represents the variable that maximizes the function value. Represents the probability ratio between the new and old strategies. In the PPO algorithm, r c It is a hyperparameter of the policy clipping range, which is used to limit the degree of change between the old and new policies during the update. Its role is to prevent policy collapse or overfitting during training, thereby improving the stability and performance of the training process.

[0108] In addition, the parameters of the value network are updated by minimizing the mean squared error of the value function, thereby improving its ability to estimate future rewards. Therefore, the value network parameter φk+1 can be calculated as follows:

[0109]

[0110] Among them, argmin represents the variable that minimizes the function value, V φ (s t ) is the value function of the current state. This training process continues until the agent converges, enabling it to make effective decisions based on the current state. (3) Pollution-aware physical design algorithm based on collaborative design:

[0111] See also Figure 4 As shown, the DRL-based placer and router, through the collaborative design module, globally perceive on-chip resource changes, guiding the agent to make efficient decisions. Upon completion of the placement subtask, the updated on-chip resource status is fed into the routing environment. The routing agent perceives changes in the placement scheme, cell occupancy, and contamination status and executes the routing task based on this updated information. Similarly, after completing the routing subtask, the resource updates are fed back to the placement environment.

[0112] It should be noted that the DRL placer and DRL router proposed in this invention can only handle their own placement / routing tasks respectively. Therefore, the individual modules cannot globally consider resource usage and are prone to falling into local optimal solutions. The collaborative design module adopted can synchronize the chip resources occupied by the placer and router in real time, reasonably model the bioassay as their respective problem models, and then schedule the placer and router according to the progress of physical design, so that the placement and routing stages are combined into one stage, allowing the placer and router to efficiently cooperate to complete the physical design tasks.

[0113] Among them, the pollution-aware physical design algorithm based on collaborative design, the collaborative design process is shown in Algorithm 2.

[0114] Algorithm 2: Pollution-aware physical design algorithm based on collaborative design

[0115]

[0116]

[0117] It should be noted that a low-cost physical design solution that is pollution-aware through cleaning cost is finally output, including a pollution-aware layout solution and a pollution-aware wiring solution. The present invention mainly performs pollution awareness through cleaning cost. Pollution awareness is a method of considering the difficulties of the subsequent cleaning stage in advance during the physical design stage, thereby performing advance optimization, which can reduce the completion time of the bioassay of the biochip.

[0118] Five real-world bioassays and five synthetic benchmarks were conducted on FPVA biochips of varying sizes to validate the effectiveness of the proposed cleaning cost-based contamination-aware technology and the collaborative-design-based contamination-aware physical design algorithm. Furthermore, the proposed method was compared with existing state-of-the-art heuristic FPVA physical designs, demonstrating its high efficiency.

[0119] Table 1 lists the 10 standard test cases used in the experiment. Each case includes parameters such as the number of fluids, the number of mixing operations, and the array size. The experiments were conducted at 8×8, 10×10, 12×12, and 13×13 FPVA scales, respectively.

[0120] Table 1 10 groups of standard test cases

[0121]

[0122]

[0123] Since no research has yet investigated the physical design of FPVA biochips considering cleaning costs, we conducted two sets of experiments to validate the performance of several optimization strategies within the proposed design flow. First, we modified the proposed method by removing the consideration of cleaning costs per contamination point and named it WCAS. In the second set of experiments, we implemented another DRL-based algorithm, NCDS, to perform placement and routing design without using the co-design-based contamination-aware physical design algorithm. We compared these methods by running them 10 times on each benchmark and taking the average of the results. Tables 2 and 3 present the corresponding comparison results, respectively, where the "Imp (%)" column provides the improvement of the proposed method over the other two methods. Compared to WCAS, the total fluid transport path length of this method is shortened by an average of 6.8%. Specifically, the total path length of IVD2 and Synthetic4 increases slightly, which is acceptable for most biochemical experiments. Furthermore, this method reduces cleaning costs by 2.9% to 24.7%, with an average reduction of 10.4%. Similarly, compared with NCDS, the proposed method reduces the total path length and cleaning cost by an average of 7.9% and 10.2%. These results demonstrate that our proposed DRL-based design framework performs well in path planning and contamination control, providing a new solution for the physical design of FPVA biochips.

[0124] Table 2 Comparison results before and after the introduction of the cleaning cost strategy

[0125]

[0126]

[0127] Table 3 Comparison results before and after the introduction of collaborative design strategy

[0128]

[0129] To validate the effectiveness of the proposed DRL-based physical design method, we compared it with a state-of-the-art heuristic physical design method proposed in the paper: Liu G, Zhu Y, Guo W, et al. Fault-tolerance-oriented physical design for fully programmable valve array biochips [C] / / 2023 60th ACM / IEEE Design Automation Conference (DAC). IEEE, 2023, pp. 1-6. This method utilizes a PSO-based placement algorithm and an A*-based routing algorithm. We modified this method by removing fault tolerance considerations and incorporating purge cost awareness, naming it CAPD. We compared these two methods, running each benchmark 10 times and taking the average as the final result. The comparative results are shown in Table 4. As shown in Table 4, the DRL-based physical design method reduces the total fluid transport path length by 0.7% to 43.4%, with an average reduction of 24.5%. Furthermore, across all benchmarks, the total purge cost is reduced by an average of 37.5%, significantly shortening the total buffer dissolution time during practical fluid scheduling. These results demonstrate the effectiveness of the physical design approach.

[0130] Table 4 Comparison results with state-of-the-art heuristic physical design methods

[0131]

[0132] Table 5 is Figure 2 Diffusion coefficients and dissolution times corresponding to the fluids in the bioassay shown in (a)

[0133]

[0134] by Figure 2 The bioassay described in [ 1 ] is used as an example. The diffusion coefficients of the input / intermediate fluids and their corresponding dissolution times are shown in Table 1. Figure 3 Expressed Figure 2 Two physical designs of the bioassay are shown, with darker contaminated cells indicating longer lysis times. Figure 3(a) shows a non-contamination-aware physical design with 14 cross-contamination points and a total dissolution time of 89 seconds for all cross-contamination points. The residual material left by the fluid input to m2 (i.e., in(o2)) takes 6 seconds to dissolve, and the flow path used by in(o2) needs to be used by the fluid input to m3 (i.e., in(o3)), resulting in a long delay. Furthermore, the four cells of m2 are reused by m6, and the residual material left by the output fluid of m2 (i.e., outflow (o2)) takes 10 seconds to dissolve. This results in a long delay before the input fluid of m6 is delivered to m6, ultimately extending the overall execution time of the bioassay. Figure 3 The solution shown in (b) takes into account both the number of cross-contamination points and the corresponding dissolution time. There are eight cross-contamination points, and the total dissolution time for all cross-contamination points is 27 seconds. Because the residues left by inputs m1 and m3 require 3 seconds to dissolve, and the flow channels used by these inputs are used by inputs m2 and m4, respectively, this does not cause a long delay.

[0135] The present invention provides a contamination sensing physical design system for a microfluidic FPVA biochip, comprising:

[0136] A definition module is used to define a framework description of a pollution-aware layout model and a pollution-aware wiring model based on a microfluidic FPVA biochip, wherein the framework description includes an action space, a state space, mask generation, and a reward function;

[0137] A training module is used to train the pollution-aware layout model and the pollution-aware routing model based on a deep reinforcement learning algorithm according to the framework description of the pollution-aware layout model and the framework description of the pollution-aware routing model, respectively, to obtain a trained layout model and a trained routing model;

[0138] The collaborative design module is used to synchronize and coordinate the trained layout model and routing model so that the trained layout model and routing model can globally perceive the changes of all resources on the FPVA biochip when performing their respective tasks, and obtain a contamination-aware physical design solution.

Claims

1. A contamination sensing physical design method for a microfluidic FPVA biochip, characterized in that: include: Based on the microfluidic FPVA biochip, a framework description of a pollution-aware layout model and a pollution-aware wiring model is defined respectively; wherein the framework description includes an action space, a state space, mask generation, and a reward function; According to the framework description of the pollution-aware layout model and the framework description of the pollution-aware routing model, the pollution-aware layout model and the pollution-aware routing model are trained based on a deep reinforcement learning algorithm to obtain a trained layout model and routing model respectively. By synchronizing and coordinating the trained layout model and routing model, the trained layout model and routing model can globally perceive the changes of all resources on the FPVA biochip when performing their respective tasks, and obtain a contamination-aware physical design solution; The framework description of the pollution-aware layout model includes a first action space, a first state space, a first mask generation, and a first reward function; Wherein, the first action space is composed of all layout positions; The first state space is composed of four core parts, namely, the information of the components of the current layout, the information of the components, the dissolution time of the fluid, and the cleaning cost matrix; The first mask generation is to mask the action when the component exceeds the boundary of the biochip or there is overlap between units of different types of components; The first reward function is: Where, α , β , γ and ψ is a hyperparameter; F o It is a binary flag, a value of "1" indicates that the source component and the target component have overlapping cells, and a value of "0" indicates no overlap; S r Indicates the minimum rectangular area that contains the laid out components; C w is the cleaning cost after executing the layout action; △ represents the difference between time step t and time step t-1; The framework description of the pollution-aware wiring model includes a second action space, a second state space, a second mask generation, and a second reward function; Among them, the second action space is composed of all flow directions of the fluid on the FPVA biochip; The second state space is composed of three core components, namely, the information of the fluid being routed, the target location of the fluid, and the cleaning cost of each unit on the chip; The second mask generation is to mask the action when the fluid exceeds the boundary of the biochip or the fluid flows back along its historical path; The second reward function is: Where ε, θ, µ, and τ are hyperparameters; Indicates the total length of the path planned for the transportation task; represents the total cleaning cost; represents a negative reward; θ represents the endpoint reward; (fx, fy) represents the position reached by the fluid at the current time step; Indicates the target position of the fluid.

2. The pollution sensing physical design method of the microfluidic FPVA biochip according to claim 1 is characterized in that: The deep reinforcement learning algorithm adopts a proximal policy optimization algorithm with an Actor-Critic architecture.

3. The pollution sensing physical design method of the microfluidic FPVA biochip according to claim 1 is characterized in that: When acquiring pollution-aware physical design solutions, include: When the layout subtask is completed, the resource updates on the chip are input into the routing environment. The routing agent perceives changes in the layout scheme, cell occupancy, and pollution, and performs routing tasks based on the updated information. Similarly, after completing the routing subtask, the resource updates are fed back into the routing environment.

4. The contamination-sensing physical design method for a microfluidic FPVA biochip according to claim 1, characterized in that: The pollution-aware placement model is used to determine the on-chip locations of all components; the pollution-aware routing model is used to find a set of flow paths for all transport tasks.

5. A contamination-aware physical design system for a microfluidic FPVA biochip, applied to the contamination-aware physical design method for a microfluidic FPVA biochip according to claim 1, characterized in that: include: A definition module is used to define a framework description of a pollution-aware layout model and a pollution-aware wiring model based on a microfluidic FPVA biochip, wherein the framework description includes an action space, a state space, mask generation, and a reward function; A training module is used to train the pollution-aware layout model and the pollution-aware routing model based on a deep reinforcement learning algorithm according to the framework description of the pollution-aware layout model and the framework description of the pollution-aware routing model, respectively, to obtain a trained layout model and a trained routing model; The collaborative design module is used to synchronize and coordinate the trained layout model and routing model so that the trained layout model and routing model can globally perceive the changes of all resources on the FPVA biochip when performing their respective tasks, and obtain a contamination-aware physical design solution.

Images