System and methods for in vitro structural toxicity testing
A system and process use artificial intelligence to evaluate the toxicity of drugs on cells. In some embodiments, a convolutional neural network is trained to identify features in cells and thereafter identify when structural changes in cells are signs of damage from exposure to a drug. Some embodiments use a 2-class deep neural network, comparing drug-treated cells to controls, to learn which images may show signs of toxicity as a result of the drug. In some applications, the system may capture images from a time-lapse experiment to determine from the cell cultures how a drug affects a cell type over time.
1 . A computer program product to determine a response of a cell to a drug, the computer program product comprising a non-transitory computer readable storage medium having computer readable program code embodied therewith, the computer readable program code being configured, when executed by a processor, to:
receive images of treated cells, wherein the treated cells are exposed to the drug, at an initial point in time;
receive images of control cells not exposed to the drug;
forward the images of the treated cells and the images of the control cells to a convolutional neural network;
determine by the convolutional neural network whether the images of the treated cells are different from the images of the control cells; and
calculate a metric based on the determination by the convolutional neural network quantifying an amount of change caused by the drug on the treated cells.
2 . The computer program product of claim 1 , further comprising computer readable program code configured to:
wherein the treated cells are exposed to multiple dosages of the drug and the determination is by a series of convolutional neural networks and includes quantifying changes associated with each of the multiple dosages.
3 . The computer program product of claim 1 , wherein the treated cells are exposed to multiple types of drugs and the determination is by a series of convolutional neural networks and includes quantifying changes associated with each of the multiple types of drugs.
4 . The computer program product of claim 1 , wherein the determination is by a series of convolutional neural networks and includes quantifying changes at multiple points in time after the initial point in time.
5 . The computer program product of claim 1 , wherein:
the received images of the treated cells and the received images of the control cells are received on multiple image channel types; and
the determination is by a series of convolutional neural networks and includes quantifying changes shown in each channel type.
6 . The computer program product of claim 1 , wherein the metric calculated is a z-factor measure.
7 . The computer program product of claim 1 , wherein the convolutional neural network uses a 2-class classification basis.
8 . The computer program product of claim 1 , wherein the metric calculated is Tjur’s pseudo R2.
9 . A method for determining an automated response of a cell to a drug, comprising:
receiving images of treated cells, wherein treated cells are exposed to the drug, at an initial point in time;
receiving images of control cells not exposed to the drug;
forwarding the images of the treated cells and the images of the control cells to a convolutional neural network;
determining by the convolutional neural network whether the images of the treated cells are different from the images of the control cells; and
calculating a metric based on the determination by the convolutional neural network quantifying an amount of change caused by the drug on the treated cells.
10 . The method of claim 9 , wherein the treated cells are exposed to multiple dosages of the drug and the determination is by a series of convolutional neural networks includes and quantifying changes associated with each of the multiple dosages.
11 . The method of claim 9 , wherein the treated cells are exposed to multiple types of drugs and the determination is by a series of convolutional neural networks and includes quantifying changes associated with each of the multiple types of drugs.
12 . The method of claim 9 , wherein the determination is by a series of convolutional neural networks and includes quantifying changes at multiple points in time after the initial point in time.
13 . The method of claim 9 , wherein:
the received images of the treated cells and the received images of the control cells are received on multiple image channel types; and
the determination is by a series of convolutional neural networks and includes quantifying changes shown in each channel type.
14 . The method of claim 9 , wherein the metric calculated is a z-factor measure.
15 . The method of claim 9 , wherein the convolutional neural network uses a 2-class classification basis.
16 . The method of claim 9 , wherein the metric calculated is Tjur’s pseudo R2.