File size: 6,313 Bytes
2b084d3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 | # Requires vllm>=0.8.5
import torch
import vllm
from vllm import LLM
from pathlib import Path
import os
import json
def get_detailed_instruct(task_description: str, query: str) -> str:
return f'Instruct: {task_description}\nQuery:{query}'
keywords = ["Quantum mechanics",
"Gene editing",
"Folding",
"System biology",
"Antibody",
"Heterogeneity",
"Ligand",
"Drug repurpose",
"Kinetics",
"Next-generation sequencing",
"Pharmacogenetics",
"Phase-field technique",
"Human",
"Potential",
"Hartree-Fock",
"Flow matching",
"Lipid",
"Biomedical",
"Antigen",
"Stochastic modeling",
"Coupled cluster",
"Quantum biology",
"Spatial biology",
"Antagonist",
"Free energy perturbation",
"Cycle",
"Pharmacology",
"Redox",
"Physiology",
"Protein-Protein Interactions",
"Single-cell",
"Screening",
"Hydrophobic",
"First-principles based DFT",
"Molecular biology",
"Mechanism",
"Reproduction number",
"Spatial Transcriptomics",
"Ion",
"Computational Materials",
"Absorption",
"Pharmacometrics",
"GAN",
"Compartmental model",
"Diagnostics",
"Lead discovery",
"QAPR",
"Rosettafold",
"Autoregressive",
"Pharmacokinetics",
"Biotechnology",
"Hydrophilic",
"3D",
"Protein",
"QM/MM",
"Activation",
"AMR",
"Networks",
"Genotype",
"Gene regulatory networks",
"Biologics",
"Phenotype",
"Nowcasting",
"DFT",
"AlphaFold",
"Pandemic",
"Immunology",
"Pathology",
"Chemical space",
"Transformer",
"Homeostasis",
"Score",
"High-throughput",
"Cheminformatics",
"Hit-to-lead",
"Sequencing",
"Enzyme",
"Antimicrobial resistance modeling",
"Allosteric",
"Inhibition",
"Computational Biochemistry",
"Bioinformatics",
"Transcriptomics",
"Diffusion",
"Anomaly detection",
"Multi-omics",
"Biology",
"Pathway",
"Metabolomics",
"Synthetic biology",
"Microbial",
"Proteomics",
"Pharmaceutics",
"Organoid",
"Network pharmacology",
"Imaging",
"Generative adversarial networks",
"Microbiology",
"Organ-on-a-chip",
"De novo",
"Substrate",
"Personalized",
"Drug",
"Transcription",
"RNA",
"Explainable AI",
"Generate",
"Docking",
"Pathogens",
"Bio foundation model",
"Reinforcement learning",
"Mechanism of action",
"Generative",
"Metabolic",
"Metabolic Flux Analysis",
"Computational Chemistry",
"Vaccine",
"Biophysics",
"Integration",
"Biochemistry",
"Physiologically based pharmacokinetics model",
"Medicine",
"Crystal",
"Conjugate",
"Variational autoencoders",
"In Silico",
"Protein-protein",
"CRISPR",
"Spatial transcriptomics",
"Gene",
"Translation",
"Glycomics",
"Lead optimization",
"Pharmacodynamics",
"Ab initio",
"System immunology",
"Pseudotime analysis",
"Generative AI",
"RNN",
"Regulatory networks",
"PBPK model",
"Beta-blocker",
"Lipidomics",
"Reaction",
"Bio",
"Genesis",
"Evolution",
"Computational Biology",
"VAE",
"Pharmacogenomics",
"Assay",
"Sensors",
"Conformation",
"Finite element method",
"Human atlas",
"Translational medicine",
"Neurology",
"Genomics",
"Cell biology",
"Porous",
"Biomarker",
"Bioengineering",
"Allele",
"Recurrent neural networks",
"Carbohydrate",
"Metamaterial",
"Virtual human",
"DNA",
"Omics",
"Agonist",
"Receptor",
"Cofactor",
"Metabolic flux analysis",
"Cell atlas",
"Signaling",
"Electronic structure",
"Monte Carlo",
"Genomic surveillance",
"Agent-based model",
"Biosensors",
"2D",
"QSAR",
"Codon",
"Coenzyme",
"Nucleic acids",
"Dynamics",
"Ensemble",
"Spectrometry",
"Multi-scale modeling",
"ADMET",
"Marker",
"Toxicology",
"Profiling",
"Design",
"Viral",
"Chemistry",
"Epigenetics",
"Homo-Lumo",
"Modeling",
"Prediction",
"Quantum Chemistry",
"Half-life",
"Material",
"Disease",
"Phylodynamic model",
"Metagenomics",
"Digital twin",
"Cancer biology",
"Discovery",
"Bioavailability",
"Digital PCR"
]
# Each query must come with a one-sentence instruction that describes the task
task = 'Given a web search query, retrieve relevant passages that answer the query'
queries = [
get_detailed_instruct(task, ' '.join(keywords))
]
def get_md_contents(dir):
subdirs = sorted([d for d in os.listdir(dir) if os.path.isdir(os.path.join(dir, d))])
contents = []
for subdir in subdirs:
json_path = os.path.join(dir, subdir, 'readme_summary.json')
if os.path.exists(json_path):
with open(json_path, 'r', encoding='utf-8') as f:
contents.append(json.load(f)['readme_summary'])
return contents
md_contents = get_md_contents('/home/weifengsun/tangou1/step2/step22/dataset')
# print(len(md_contents))
# print(md_contents[0])
# No need to add instruction for retrieval documents
documents = md_contents
input_texts = queries + documents
model = LLM(model="Qwen/Qwen3-Embedding-0.6B", task="embed")
outputs = model.embed(input_texts)
embeddings = torch.tensor([o.outputs.embedding for o in outputs])
scores = (embeddings[0] @ embeddings[1:].T)
# print(scores.tolist())
# [[0.7620252966880798, 0.14078938961029053], [0.1358368694782257, 0.6013815999031067]]
dataset_dir = '/home/weifengsun/tangou1/step2/step22/dataset'
subdirs = sorted([d for d in os.listdir(dataset_dir) if os.path.isdir(os.path.join(dataset_dir, d))])
valid_subdirs = [d for d in subdirs if os.path.exists(os.path.join(dataset_dir, d, 'readme_summary.json'))]
score_list = scores.tolist()
for i, subdir in enumerate(valid_subdirs):
json_path = os.path.join(dataset_dir, subdir, 'readme_summary.json')
with open(json_path, 'r', encoding='utf-8') as f:
data = json.load(f)
data['score'] = score_list[i]
with open(json_path, 'w', encoding='utf-8') as f:
json.dump(data, f, ensure_ascii=False, indent=4)
|