ChIP-seq
Datasets
All datasets matching “ChIP-seq”encode-chip-seq-subset
ENCODE Histone ChIP-seq Subset (bigWig signal tracks)
Subset of Histone ChIP-seq signal tracks (bigWig format) downloaded from the
ENCODE consortium. This is a convenience subset
for vectorization / embedding experiments — it is not the full ENCODE release.
Contents
46 bigWig files, ~38.7 GB total
3 histone marks: H3K27ac, H3K4me3, H3K27me3
7 experiments (ENCSR accessions):
ENCSR349EHZ (10 files)
ENCSR491RBV (10 files)
ENCSR527FRO (10 files)
ENCSR714ZJT (10… See the full description on the dataset page: https://huggingface.co/datasets/fabricioslv/encode-chip-seq-subset.encode-chip-seq-vetorizado
ENCODE ChIP-seq Vetorizado
Saída do pipeline de vetorização do fabricioslv/encode-chip-seq-subset.
3 estratégias
Stage 1 — Bins fixos (10kb)
Matriz densa (n_bins × n_tracks) por cromossomo. Formato: .npz.
Stage 2 — Peak detection (5σ) + embeddings
Picos detectados por threshold estatístico. Embedding de 9 features por pico.
Formato: peaks.tsv + embeddings.npz.
Stage 3 — Janelas sliding (10kb, stride 5kb) + DL tensors… See the full description on the dataset page: https://huggingface.co/datasets/fabricioslv/encode-chip-seq-vetorizado.chip-seq-glm-tang
GLM-Tang Task 2: GM12878 ChIP-seq Binding
This dataset contains ten binary transcription-factor binding tasks from
Task 2 of Tang et al. Given an exact 200 nt sequence from GM12878, predict
whether it is centered on a factor-specific ChIP-seq peak or a matched
DNase-accessible negative.
Each transcription factor is an independent task identified by factor.
Loading
from datasets import load_dataset
dataset = load_dataset("Taykhoom/chip-seq-glm-tang", "corrected")… See the full description on the dataset page: https://huggingface.co/datasets/Taykhoom/chip-seq-glm-tang.compressed_chipseqchip-seq-encode-raw
ChIP-seq / Epigenômica — Dados Brutos Reais (2026-08-16)
Dataset público com dados REAIS de ChIP-seq/epigenômica, baixados do Kaggle (datasets de terceiros) em 2026-08-16.
Destino: aprendizado do OmniMind (Kernel Basal) + cruzamento topológico (nós/arestas), independente da informação.
Proveniência (transparência total)
Arquivo
Origem (Kaggle)
Conteúdo
Tamanho
corruption-in-india.zip
usharengaraju/corruption-in-india ("ChIP-seq data for the histone H3 -… See the full description on the dataset page: https://huggingface.co/datasets/fabricioslv/chip-seq-encode-raw.