Tumor cell analysis using aptamers and microfluidic systems

A system comprising:

• a microfluidic device configured to perform an assay on a sample of tumor cells, wherein the microfluidic device comprises:
• a surface comprising randomly affixed tumor cells comprising one or more unknown subtypes of the tumor cells,
• a channel configured to deliver the sample to the surface and flow a plurality of aptamers over the tumor cells to allow the aptamers to interact and bind to the tumor cells, wherein the plurality of aptamers comprises a plurality of aptamer families, and each aptamer family of the plurality of aptamer families is determined by a prediction model to bind to at least one possible subtype of the tumor cells, and
• a detector configured to obtain data points that make up a data signal associated with a measure of binding affinity of each of the plurality of aptamer families to the tumor cells;
• one or more data processors;
• and
• a non-transitory computer readable storage medium containing instructions that, when executed on the one or more data processors, cause the one or more data processors to perform actions including:
• obtaining the data signal from the microfluidic device;
• analyzing the measure of the binding affinity of each aptamer family to the tumor cells, wherein the analyzing comprises classifying the binding affinity of each aptamer family to the tumor cells;
• and
• determining one or more aptamer families that characterize the one or more unknown subtypes of the tumor cells based on the classifying.

A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause one or more data processors to perform actions including:

• obtaining a data signal from a microfluidic device configured to perform an assay on a sample of tumor cells, wherein the data signal is obtained by:
• flowing a plurality of aptamers over the tumor cells randomly affixed to a surface of the microfluid device, which allows the aptamers to interact and bind to the tumor cells, and
• obtaining data points that make up the data signal associated with a measure of binding affinity of each aptamer family of a plurality of aptamer families to the tumor cells, wherein the plurality of aptamers comprises the plurality of aptamer families, and each aptamer family of the plurality of aptamer families is determined by a prediction model to bind to at least one possible subtype of the tumor cells;
• analyzing the measure of the binding affinity of each aptamer family to the tumor cells, wherein the analyzing comprises classifying the binding affinity of each aptamer family to the tumor cells;
• and
• determining one or more aptamer families that characterize the one or more unknown subtypes of the tumor cells based on the classifying.