screening
bbbnuke-screening-1B
BBB-Nuke: 1 Billion Compound Blood-Brain Barrier Permeability Screen
Overview
1.02 billion small molecules screened for blood-brain barrier (BBB) permeability using the BBB-Nuke pipeline (v0.12.0).
Screening Pipeline
Each compound was scored through:
Standardization - SMILES canonicalization via RDKit
Physicochemical properties - MW, LogP, TPSA, HBD, HBA, Fsp3, heavy atom count
pKa prediction - Representative pKa via MolGpKa (batched GCN inference)… See the full description on the dataset page: https://huggingface.co/datasets/ATTN-Lab/bbbnuke-screening-1B.epa-re-powering-screening-sam2-masks-partial
EPA RE-Powering Screening SAM2 candidate masks — partial snapshot
This is a paused, incomplete snapshot of model-generated candidate masks for
EPA RE-Powering Screening sites. It covers approximately
12% of archive-group jobs and
8.2% of processable site points from the
current run. It contains 15,211 successful masks across
15,541 attempted processable rows, plus
1,326 explicit input coverage exclusions.
The source inventory contains 190,976 points in total.… See the full description on the dataset page: https://huggingface.co/datasets/sarkarghya/epa-re-powering-screening-sam2-masks-partial.safemaize-screening3-v3
SafeMaize screening3_v3
Public maize images for screening experiments on northern/turcicum leaf blight-like
symptoms and fall armyworm, with healthy maize as the comparison. Images keep their
original bytes and are stored as Parquet shards, so no loose image files are published.
Class
Core images
healthy
29,448
nlb_tlb_like
23,889
faw_feeding_injury
10,459
Partition
Images
Shards
train
43,945
74
val
5,669
13
calibration
5,669
13
test
8,513
11… See the full description on the dataset page: https://huggingface.co/datasets/saiteja33/safemaize-screening3-v3.Resume-Screening-DatasetEzHit-large-scale-screeningcochrane-screening-sft
Cochrane Screening SFT
Supervised fine-tuning (SFT) chat dataset for Cochrane-style title and abstract screening.
Each example is a chat conversation that asks a model to predict a screening decision
(include / exclude / uncertain) and a short justification (reason).
Code: ljwa2323/cochrane-screening-slm
Dataset summary
Split / config
Records
Role
train
416,799
LoRA SFT training
validation
46,311
Training-time validation (10% stratified holdout from… See the full description on the dataset page: https://huggingface.co/datasets/deepcoder2024/cochrane-screening-sft.