Abstract: Disclosed herein is a luminaire chilled beam that can incorporate lighting into a chilled beam unit without affecting the capacity, performance, or dimensions of the chilled beam. The luminaire chilled beam can include a pressure chamber configured to receive primary air through a primary air inlet. A nozzle plate in a lower portion of the pressure chamber can allow the primary air to be expelled from the pressure chamber and thereby cause an induction of air from an external setting through an induction face and into an induction chamber. A water coil can be configured to treat the induced air within the induction chamber. The induced air and the primary air can be expelled from the induction chamber and into the setting through discharge channels. The luminaire chilled beam can further include a luminaire assembly including a luminaire positioned between the induction face and the discharge channel at the lower portion of the induction chamber, the luminaire configured to illuminate the external setting.

Abstract: A drug IC50 deep learning model prediction method based on molecular structure and gene expression includes establishing a deep learning model to predict drug IC50 in different cell lines; predicting the drug IC50 in different cell lines based on the deep learning model. Also disclosed are prediction systems, electronic devices and computer readable storage media, which use grammar variational autoencoder to encode the chemical molecular formula of drugs and use autoencoder to encode cell line expression data, predict the drug IC50 in different cell lines through neural network methods, and predict the drug IC50 values of drugs in different types of cancer cell lines directly through the molecular information of drugs, which can reduce the investment of funds and time in preclinical development. Applying the model to patients helps screen out the applicable population of drugs, reduces unnecessary clinical trials, and improves the success rate of clinical trials.