Index A | B | C | D | E | F | G | H | I | K | L | M | N | O | P | Q | R | S | T | U | V | W | Y | Z A activation Adaptive AvgPool Agent Agglomerative clustering AID alpha, [1] Alpha (λ) aromatic array aspect Attention weights Augmentation axes B Bayesian Optimization Bemis–Murcko scaffold bins boolean mask C Channel CID, [1] CIR Class prior classification CLIP clustering Coefficient importance colormap comment Contrastive learning Contrastive loss Convolution (Conv) Cosine similarity, [1] Cross entropy Cross validation (CV) Cross-entropy loss CSV D DataFrame DBSCAN (Density-Based Spatial Clustering of Applications with Noise) descriptor, [1], [2] dictionary dimension reduction Dropout dtype E early stopping edge feature EditableMol elbow method Elkan–Noto link Embedding Environment Epsilon greedy error Expected Hypervolume Improvement Expected Improvement (EI) Exploitation Exploration extent F Feature map Feature redundancy figsize figure float for loop function G GHS Grad-CAM graph neural network GridSearchCV groupby H Head hidden layer Hypervolume I if statement InChI and InChIKey index InfoNCE InfoNCE loss integer K Kernel (covariance function) Kernel / Filter KMeans L label Lasso Regression LayerNorm Linear probe, [1] list loading Logits loss M macro averaging MAE message passing module MPNN MSE multilayer perceptron N NaN Negative pair node feature O On policy operator optimizer P Padding Pareto dominance Pareto front parity plot, [1] PCA Permutation importance pivot table plot Policy Pooling pooling Pooling that outputs a fixed spatial size regardless of input size. Positional encoding Positive pair Posterior Prior belief Probability of Improvement (PI) Projection head PU probability PUG-REST PUG-View Q Q value Query, Key, Value (Q, K, V) R Receptive field regression regularization residual Residual connection Retrieval, [1] Return ROC AUC, [1] R² (coefficient of determination) S sanitize, [1] SAR Scalarization scaling SCAR scree plot Series SID silhouette score SMILES, [1] string supervised learning Surrogate model T t-SNE Tanimoto / Jaccard similarity Temperature (\tau) Thompson sampling Token train test split U UCB1 UMAP Upper Confidence Bound (UCB) V variable View W while loop Y yerr Z Zero-shot
