Optimizing Pharmacokinetic Property Prediction Based on Integrated Datasets and a Deep Learning Approach by Xiting Wang (9327613)

“…Then, a novel molecular property prediction model, called a multiembedding-based synthetic network (MESN), was generated by applying a deep learning algorithm based on the synthesis of multiple types of molecular embeddings. …”

Optimizing Pharmacokinetic Property Prediction Based on Integrated Datasets and a Deep Learning Approach by Xiting Wang (9327613)

“…Then, a novel molecular property prediction model, called a multiembedding-based synthetic network (MESN), was generated by applying a deep learning algorithm based on the synthesis of multiple types of molecular embeddings. …”

Optimizing Pharmacokinetic Property Prediction Based on Integrated Datasets and a Deep Learning Approach by Xiting Wang (9327613)

“…Then, a novel molecular property prediction model, called a multiembedding-based synthetic network (MESN), was generated by applying a deep learning algorithm based on the synthesis of multiple types of molecular embeddings. …”

Example medication days generated for patients P4 and P6, medication times (red dots), patient’s state—TRS score (blue line) with bounds for the states (red lines) and optimal stat... by Tomasz Gutowski (17200042)

Cell fishing: A similarity based approach and machine learning strategy for multiple cell lines-compound sensitivity prediction by E. Tejera (7470644)

“…We also compare the performance of the proposed method to machine learning predictions on the same problem. A curated database of compounds-cell lines associations derived from ChemBL version 22 was created for algorithm construction and cross-validation. …”

Spearman correlation coefficient results for classification algorithms (predicted probabilities) and regression algorithms (predicted IC50 values). by Sofia P. Miranda (11418930)

Subjects:

DMTD algorithm. by Yunhu Huang (21402795)

“…In this paper, expert knowledge is combined with deep reinforcement learning algorithm (Proximal Policy Optimization, PPO) and two enhanced intelligent train operation algorithms (EITO) are proposed. …”

Classification results for all subsampling scenarios and algorithms for Gefitinib. by Sofia P. Miranda (11418930)

Subjects:

Selecting an optimal machine learning classifier. by Ramu Anandakrishnan (294535)

Regression results for all combinations of subsampling scenarios and algorithms for Gefitinib. by Sofia P. Miranda (11418930)

Subjects:

Average RMSE rank for all combinations of subsampling scenarios and algorithms. by Sofia P. Miranda (11418930)

Subjects:

Proposed deep learning model. by Rana Ahmed (4923127)

Summary of AUC values across all combinations of subsampling scenario and algorithm. by Sofia P. Miranda (11418930)

Subjects:

Most informative genes for predicting cell-line responses for Gefitinib. by Sofia P. Miranda (11418930)

Subjects:

Bivariate analysis using line plot for casing, bearing & impeller vs pressure. by Gaurav Sandeep Dave (21519884)

Construction of kinetic data based on the Arrhenius equation with distributed activation energy. by László Zimányi (2649973)

Descriptions of the algorithms we tested and hyperparameters that we evaluated via nested cross validation. by Sofia P. Miranda (11418930)

Subjects:

Model selection by BO based on RCV(nv) from the simulated data with different noise levels. by László Zimányi (2649973)

Relative predictive performance when using default algorithm hyperparameters and all features vs. tuning hyperparameters or selecting features. by Stephen R. Piccolo (8367780)

Learning dynamics on training tasks. by Sam Hall-McMaster (10343795)