OSCR

MethyAnno: An Interpretable Automated Annotation Method Leveraging Multi-Scale Information and Metric Learning Framework for scDNAm Data.

Code ↔ Paper

9 matches between paragraphs of the paper and lines of its authors' code, computed by the harvester (lexical-v1). Click a colored paragraph or line to see its counterpart.

The 9 matches · 1 of them tie a paragraph to a whole file, not to given lines: a weak match, whose lines are not tinted
  1. [1] § Methods › Model Structure—Cross‐Attention Mechanism for Feature Fusion ↔ Script/model.py, lines 41–161 · score 0.71 · Layer normalization, cross attention, positional, query, linear, tensors
  2. [2] § Methods › The Overview of MethyAnno ↔ Script/model.py, lines 204–266 · score 0.54 · prototype subspace, cross attention, fuse, module, classification, model
  3. [3] § Methods › Composite Loss Function for Model Training ↔ Script/loss.py, lines 74–86 · score 0.53 · cross entropy, contrastive loss, vectors, subspace
  4. [4] § Methods › Model Structure—Cross‐Attention Mechanism for Feature Fusion ↔ Script/model.py, lines 41–161 · score 0.51 · FFN, residual, layer, query, linear, tensor
  5. [5] § Results › The Overview of MethyAnno ↔ Script/novel_discover.py, lines 116–215 · score 0.51 · Gaussian mixture model, GMM, component, density, threshold, discovery
  6. [6] § Results › The Overview of MethyAnno ↔ scMethyAnno/novel_discover.py, lines 117–216 · score 0.51 · Gaussian mixture model, GMM, component, density, threshold, discovery
  7. [7] § Methods › Model Structure—Identification of Novel Cell Types ↔ Script/novel_discover.py, lines 116–215 · score 0.50 · Gaussian mixture model, component, density, threshold, scores
  8. [8] § Methods › Model Structure—Identification of Novel Cell Types ↔ scMethyAnno/novel_discover.py, lines 117–216 · score 0.50 · Gaussian mixture model, component, density, threshold, scores
  9. [9] § Methods › Composite Loss Function for Model Training ↔ Script/config.py, the whole file · a weak match · score 0.50 · hyperparameter configurations, weights, prototypes, loss, subspace, training

Paper

Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC

The paper is loaded when this pane is shown.

The authors' code

Python · 266 lines · 10 KB · MIT · 3 matches

  1. # --- Python 标准库 ---
  2. import os
  3. import gc
  4. import random
  5. import warnings
  7. # --- 第三方核心科学计算库 ---
  8. import numpy as np
  9. import pandas as pd
  10. import scipy.stats # 只导入需要的子模块
  12. import torch
  13. import torch.nn as nn
  14. import torch.nn.functional as F
  17. # --- 脚本级别的设置 ---
  18. warnings.filterwarnings("ignore")
  19. gc.collect()
  21. def setup_seed(seed):
  22. """
  23. Set random seed.
  25. Parameters
  26. ----------
  27. seed
  28. Number to be set as random seed for reproducibility.
  30. """
  31. np.random.seed(seed)
  32. random.seed(seed)
  33. torch.manual_seed(seed)
  34. if torch.cuda.is_available():
  35. torch.cuda.manual_seed_all(seed)
  37. setup_seed(123)
  41. class CrossAttention(nn.Module):
  42. def __init__(self, query_dim, context_dim, dropout_rate, embedding_dim = 64, head_dim=64, num_heads=1):
  43. """
  44. 改进的交叉注意力模块，将特征维度视为序列元素。
  46. Args:
  47. query_feature_dim (int): 查询输入张量的原始特征维度 (例如，feat1的维度)
  48. context_feature_dim (int): 上下文输入张量的原始特征维度 (例如，feat2的维度)
  49. embedding_dim (int): 每个特征元素将被映射到的嵌入维度
  50. dropout_rate (float): Dropout比率
  51. head_dim (int): 每个注意力头的维度
  52. num_heads (int): 注意力头的数量
  53. """
  54. super().__init__()
  56. self.query_feature_dim = query_dim
  57. self.context_feature_dim = context_dim
  58. self.embedding_dim = embedding_dim
  59. self.num_heads = num_heads
  60. self.head_dim = head_dim
  61. self.scale = head_dim ** -0.5
  63. inner_dim = num_heads * head_dim # 每个头的维度 * 头数量
  65. # 线性层用于将 (batch_size, feature_dim) -> (batch_size, feature_dim, embedding_dim)
  66. self.query_to_embedding = nn.Linear(1, embedding_dim) # 每个独立的特征值映射到embedding
  67. self.context_to_embedding = nn.Linear(1, embedding_dim)
  69. # 用于生成Q, K, V的线性层
  70. self.to_q = nn.Linear(embedding_dim, inner_dim, bias=False)
  71. self.to_k = nn.Linear(embedding_dim, inner_dim, bias=False)
  72. self.to_v = nn.Linear(embedding_dim, inner_dim, bias=False)
  74. # 最终输出的线性层
  75. self.to_out = nn.Sequential(
  76. nn.Linear(inner_dim, embedding_dim), # 从合并的头维度映射回embedding_dim
  77. nn.Dropout(dropout_rate)
  78. )
  80. self.output_to_original_dim = nn.Linear(embedding_dim, 1)
  82. self.pos_enc_query = nn.Parameter(torch.randn(query_dim, embedding_dim))
  83. self.pos_enc_context = nn.Parameter(torch.randn(context_dim, embedding_dim))
  85. self.norm_query = nn.LayerNorm(embedding_dim)
  86. self.norm_context = nn.LayerNorm(embedding_dim)
  87. self.ffn = nn.Sequential(
  88. nn.LayerNorm(embedding_dim),
  89. nn.Linear(embedding_dim, embedding_dim * 4),
  90. nn.GELU(),
  91. nn.Dropout(dropout_rate),
  92. nn.Linear(embedding_dim * 4, embedding_dim)
  93. )
  95. def forward(self, query, context):
  96. """
  97. Args:
  98. query (torch.Tensor): 查询张量，形状为 [B, query_feature_dim]
  99. context (torch.Tensor): 上下文张量，形状为 [B, context_feature_dim]
  101. Returns:
  102. torch.Tensor: 更新后的查询张量，形状为 [B, query_feature_dim] (融合后，维度与原始query一致)
  103. """
  104. # --- 1. 将输入特征转换为序列形式并应用位置编码 ---
  106. # query: [B, query_feature_dim] -> [B, query_feature_dim, 1]
  107. query_expanded = query.unsqueeze(-1)
  108. # [B, query_feature_dim, 1] -> [B, query_feature_dim, embedding_dim]
  109. query_seq = self.query_to_embedding(query_expanded) + self.pos_enc_query
  111. # context: [B, context_feature_dim] -> [B, context_feature_dim, 1]
  112. context_expanded = context.unsqueeze(-1)
  113. # [B, context_feature_dim, 1] -> [B, context_feature_dim, embedding_dim]
  114. context_seq = self.context_to_embedding(context_expanded) + self.pos_enc_context
  116. residual_query_seq = query_seq
  118. # --- 2. 归一化输入序列 ---
  119. query_seq = self.norm_query(query_seq)
  120. context_seq = self.norm_context(context_seq)
  122. # --- 3. 计算 Q, K, V ---
  123. # Q: [B, query_feature_dim, embedding_dim] -> [B, query_feature_dim, inner_dim]
  124. # K, V: [B, context_feature_dim, embedding_dim] -> [B, context_feature_dim, inner_dim]
  125. q = self.to_q(query_seq)
  126. k = self.to_k(context_seq)
  127. v = self.to_v(context_seq)
  129. # [B, seq_len, inner_dim] -> [B, num_heads, seq_len, head_dim]
  130. q = q.view(q.shape[0], q.shape[1], self.num_heads, self.head_dim).transpose(1, 2)
  131. k = k.view(k.shape[0], k.shape[1], self.num_heads, self.head_dim).transpose(1, 2)
  132. v = v.view(v.shape[0], v.shape[1], self.num_heads, self.head_dim).transpose(1, 2)
  134. # --- 4. 计算注意力分数 ---
  135. # attention_scores: [B, num_heads, query_seq_len, context_seq_len]
  136. attention_scores = torch.matmul(q, k.transpose(-1, -2)) * self.scale
  137. attention_probs = attention_scores.softmax(dim=-1)
  139. # attention_output: [B, num_heads, query_seq_len, head_dim]
  140. attention_output = torch.matmul(attention_probs, v)
  142. # --- 5. 合并多头的结果 ---
  143. # [B, num_heads, query_seq_len, head_dim] -> [B, query_seq_len, num_heads, head_dim]
  144. attention_output = attention_output.transpose(1, 2).contiguous()
  145. # [B, query_seq_len, num_heads, head_dim] -> [B, query_seq_len, inner_dim]
  146. attention_output = attention_output.view(attention_output.shape[0], attention_output.shape[1], -1)
  148. # [B, query_seq_len, inner_dim] -> [B, query_seq_len, embedding_dim]
  149. attention_output = self.to_out(attention_output)
  151. # --- 6. 残差连接和FFN ---
  152. x = residual_query_seq + attention_output # [B, query_feature_dim, embedding_dim]
  153. x = x + self.ffn(x) # [B, query_feature_dim, embedding_dim]
  155. # --- 7. 将融合后的嵌入序列转换回原始特征维度 ---
  156. # [B, query_feature_dim, embedding_dim] -> [B, query_feature_dim, 1]
  157. final_output = self.output_to_original_dim(x)
  158. # [B, query_feature_dim, 1] -> [B, query_feature_dim]
  159. final_output = final_output.squeeze(-1)
  161. return final_output
  164. def projection_distance(x, subspace):
  165. # x: [B, H], subspace: [D, H]
  166. # 投影矩阵：P = U.T @ U
  167. # proj_x = x @ P.T
  168. P = subspace.T @ subspace # [H, H]
  169. x_proj = x @ P # [B, H]
  170. dist = F.mse_loss(x_proj, x, reduction='none').sum(dim=-1) # 投影误差
  171. return dist
  173. class PrototypeSubspace(nn.Module):
  174. def __init__(self, num_classes, subspace_dim, hidden_dim):
  175. super().__init__()
  176. self.num_classes = num_classes
  177. self.subspace_dim = subspace_dim
  178. self.hidden_dim = hidden_dim
  180. # 类别的子空间表示：[num_classes, subspace_dim, hidden_dim]
  181. self.subspaces = nn.Parameter(torch.randn(num_classes, subspace_dim, hidden_dim))
  182. nn.init.orthogonal_(self.subspaces.view(-1, hidden_dim)) # 初始化每个子空间为正交向量组
  184. def forward(self, x):
  185. """
  186. 输入：
  187. x: [B, hidden_dim] --- 样本嵌入表示
  188. 输出：
  189. logits: [B, num_classes] --- 类别相似性得分
  190. """
  191. B = x.size(0)
  193. subspaces = self.subspaces # [C, D, H]
  195. # 投影距离：计算 fused_feat 到每类原型子空间的投影误差
  196. logits = []
  197. for c in range(self.num_classes):
  198. dist = projection_distance(x, subspaces[c])
  199. logits.append(-dist)
  200. logits = torch.stack(logits, dim=1)
  202. return logits
  204. class MultiScalePrototypeModel(nn.Module):
  205. def __init__(self, input_dims, num_classes, hidden_dim, dropout_rate, subspace_dim):
  206. super().__init__()
  208. self.encoder1 = nn.Sequential(
  209. nn.Linear(input_dims[0], hidden_dim*4),
  210. nn.BatchNorm1d(hidden_dim*4),
  211. nn.GELU(),
  212. nn.Dropout(dropout_rate),
  213. nn.Linear(hidden_dim*4, hidden_dim*2),
  214. nn.BatchNorm1d(hidden_dim*2),
  215. nn.GELU(),
  216. nn.Dropout(dropout_rate),
  217. nn.Linear(hidden_dim*2, hidden_dim),
  218. nn.GELU()
  219. )
  221. self.encoder2 = nn.Sequential(
  222. nn.Linear(input_dims[1], hidden_dim*2),
  223. nn.BatchNorm1d(hidden_dim*2),
  224. nn.GELU(),
  225. nn.Dropout(dropout_rate),
  226. nn.Linear(hidden_dim*2, hidden_dim),
  227. nn.GELU()
  228. )
  230. self.projection1 = nn.Sequential(
  231. nn.Linear(hidden_dim, hidden_dim//2),
  232. nn.GELU(),
  233. nn.Linear(hidden_dim//2, hidden_dim//2)
  234. )
  236. self.projection2 = nn.Sequential(
  237. nn.Linear(hidden_dim, hidden_dim//2),
  238. nn.GELU(),
  239. nn.Linear(hidden_dim//2, hidden_dim//2)
  240. )
  243. # 1. 定义两个交叉注意力模块
  244. # 一个用于 feat1 查询 feat2
  245. self.cross_attn_1_to_2 = CrossAttention(query_dim=hidden_dim, context_dim=hidden_dim, dropout_rate=dropout_rate)
  246. # 另一个用于 feat2 查询 feat1
  247. self.cross_attn_2_to_1 = CrossAttention(query_dim=hidden_dim, context_dim=hidden_dim, dropout_rate=dropout_rate)
  249. self.classifier = PrototypeSubspace(num_classes=num_classes,
  250. subspace_dim=subspace_dim,
  251. hidden_dim=hidden_dim * 2)
  253. def forward(self, x1, x2):
  254. feat1 = self.encoder1(x1)
  255. feat2 = self.encoder2(x2)
  257. z1 = F.normalize(self.projection1(feat1), dim=-1)
  258. z2 = F.normalize(self.projection2(feat2), dim=-1)
  260. fused_feat1 = self.cross_attn_1_to_2(query=feat1, context=feat2)
  261. fused_feat2 = self.cross_attn_2_to_1(query=feat2, context=feat1)
  262. fused_intermediate = torch.cat([fused_feat1, fused_feat2], dim=-1)
  264. logits = self.classifier(fused_intermediate)
  266. return z1, z2, logits, fused_intermediate

model.py at commit b98fde4, under MIT · at the source

Overview

Authors: Yuhang Jia1, Siyu Li1, Songming Tang1, Keju Gu1,2, Shengquan Chen1,3
ORCID iDs: Siyu Li, Shengquan Chen
  1. School of Mathematical Sciences and LPMC, Nankai University, Tianjin, China
  2. College of Life Sciences, Nankai University, Tianjin, China
  3. Academy for Advanced Interdisciplinary Studies, Nankai University, Tianjin, China
Institutions: Nankai University (China)
Journal: Advanced science (Weinheim, Baden-Wurttemberg, Germany), article e77524
Dates: received 11 January 2026; accepted 21 August 2026; published online 1 September 2026; in print September 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1002/advs.77524 · PMID 42681808 · PMCID PMC13534786 · OpenAlex W7205016821
Open access: gold, a free copy (OpenAlex)
Status: code verified
Categories: genetics / omics (modality)
Methods: Statistics, Machine learning, Smoothing, state filtering, decompositions
Keywords: cell type annotation, deep metric learning, epigenetic signatures, multi‐scale information, single‐cell DNA methylation
Topic: Epigenetics and DNA Methylation (Molecular Biology, Biochemistry, Genetics and Molecular Biology), according to OpenAlex
Funding: National Key Research and Development Program of China (2024YFA1307703); National Natural Science Foundation of China (62473212); Fundamental Research Funds for the Central Universities (050-63253077, 050‐63253077)
Citations: not cited yet (Europe PMC); 53 references in the paper

Abstract

Single‐cell DNA methylation (scDNAm) sequencing provides unique insights into epigenetic heterogeneity and cell‐specific regulatory landscapes. However, accurate cell type annotation for scDNAm data remains challenging, as the distinct data distribution of scDNAm hinders the adaptation of annotation methods from other omics, and specialized annotation tools for scDNAm are currently lacking. Here, MethyAnno is proposed as an interpretable deep metric learning framework that leverages multi‐scale information for accurate cell type annotation of scDNAm data. Additionally, MethyAnno enables generalized category discovery in open‐set scenarios by utilizing density‐based clustering to automatically estimate the number of novel cell types, while simultaneously deciphering cell‐type‐specific epigenetic signatures for biological interpretability. Extensive experiments demonstrate that MethyAnno excels in cross‐dataset annotation and novel type discovery, showing exceptional robustness in few‐shot scenarios for rare cell types. Moreover, interpretability analysis in the human brain dataset correctly recovers the genetic link between Sst interneurons and epilepsy heritability, the association of OPC cells with Alzheimer's disease, as well as the regulatory role of Pvalb cells in synaptic plasticity. Taken together, these findings establish MethyAnno as a robust and biologically interpretable tool for accurate cell type annotation and downstream epigenetic analysis.

Reproduced under the paper's license (CC BY), from the paper cited above.

Repository

Its files are read in the Code ↔ Paper reader above, with 9 matches between paragraphs and lines of code.

BioX-NKU/MethyAnno

License: MIT
State: the link answers, verified on 26 September 2026
Evidence: files inventoried
Commit: b98fde428f459286e51b11a29fd8f0612d292d47, 16 August 2026
Languages: Python (20)
Size: 40 files, 20 scripts
Software Heritage: not archived
Found in: “Data Availability Statement”
Holds: README, license file, environment (setup.cfg, setup.py)
Not found: CITATION.cff, tests, continuous integration, documentation
Tools: PyTorch (16 files), anndata (14 files), NumPy (14 files), pandas (14 files), scikit-learn (10 files), SciPy (10 files), Scanpy (8 files), Matplotlib (6 files), seaborn (6 files)
Availability: 1 check, the latest on 26 September 2026: the link answers
  • 26 September 2026: the link answers
22 files
At the source: github.com/BioX-NKU/MethyAnno

The paper's code and data availability statement is in the Data section.

Tracing map

Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.

What the map holds:

  • 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
  • 20 scripts, each with its path and the digest of its content;
  • 9 matches between paragraphs of the paper and lines of the code (method lexical-v1);
  • neither the text of the paper nor the code itself.

Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.

Data

Datasets cited

Data Availability Statement

All datasets used in this study are publicly available from the National Center for Biotechnology Information (NCBI) Gene Expression Omnibus (GEO). For the human cerebral cortex datasets, the corresponding accession number is GSE215353 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE215353). Detailed information and associated accession numbers regarding all specific brain regions used in this study are provided in Table S3. The mouse brain datasets can be derived from GSE132489 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132489) and GSE213262 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE213262), detailed accession numbers for each subdataset are also summarized in the Table S3. Moreover, the accession number of the human adipose dataset is GSE297262 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE297262). The source codes of MethyAnno are publicly available in the GitHub repository at https://github.com/BioX‐NKU/MethyAnno (https://github.com/BioX-NKU/MethyAnno) under an MIT license. We have released MethyAnno as a python package for easy installation, and provided detailed tutorials on GitHub.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, pages, dates, 5 authors, 5 keywords, 3 funders, 48 references.

Cite

This paper

Jia, Y., Li, S., Tang, S., Gu, K., & Chen, S. (2026). MethyAnno: An Interpretable Automated Annotation Method Leveraging Multi-Scale Information and Metric Learning Framework for scDNAm Data. Advanced science (Weinheim, Baden-Wurttemberg, Germany), e77524. https://doi.org/10.1002/advs.77524

BibTeX

@article{jia2026methyanno,
author = {Jia, Yuhang and Li, Siyu and Tang, Songming and Gu, Keju and Chen, Shengquan},
title = {{MethyAnno: An Interpretable Automated Annotation Method Leveraging Multi-Scale Information and Metric Learning Framework for scDNAm Data}},
journal = {Advanced science (Weinheim, Baden-Wurttemberg, Germany)},
year = {2026},
month = sep,
pages = {e77524},
publisher = {Wiley},
issn = {2198-3844},
doi = {10.1002/advs.77524},
url = {https://doi.org/10.1002/advs.77524},
pmid = {42681808},
pmcid = {PMC13534786}
}

RIS

TY - JOUR
AU - Jia, Yuhang
AU - Li, Siyu
AU - Tang, Songming
AU - Gu, Keju
AU - Chen, Shengquan
TI - MethyAnno: An Interpretable Automated Annotation Method Leveraging Multi-Scale Information and Metric Learning Framework for scDNAm Data
T2 - Advanced science (Weinheim, Baden-Wurttemberg, Germany)
J2 - Adv Sci (Weinh)
PY - 2026
DA - 2026/09/01
SP - e77524
SN - 2198-3844
PB - Wiley
DO - 10.1002/advs.77524
UR - https://doi.org/10.1002/advs.77524
LA - en
ER -

CSL-JSON

{
"id": "10.1002/advs.77524",
"type": "article-journal",
"title": "MethyAnno: An Interpretable Automated Annotation Method Leveraging Multi-Scale Information and Metric Learning Framework for scDNAm Data",
"container-title": "Advanced science (Weinheim, Baden-Wurttemberg, Germany)",
"author": [
{
"family": "Jia",
"given": "Yuhang"
},
{
"family": "Li",
"given": "Siyu"
},
{
"family": "Tang",
"given": "Songming"
},
{
"family": "Gu",
"given": "Keju"
},
{
"family": "Chen",
"given": "Shengquan"
}
],
"container-title-short": "Adv Sci (Weinh)",
"page": "e77524",
"DOI": "10.1002/advs.77524",
"PMID": "42681808",
"PMCID": "PMC13534786",
"ISSN": "2198-3844",
"publisher": "Wiley",
"URL": "https://doi.org/10.1002/advs.77524",
"language": "en",
"issued": {
"date-parts": [
[
2026,
9,
1
]
]
}
}

The tracing map gets a citation of its own once an author has validated it and it has a DOI.

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s41467-026-73171-4 [code]
Dissecting epigenetic heterogeneity in single-cell DNA methylomes with a unified framework.
Journal: Nature communications
In common: anndata, Scanpy, PyTorch, 6 other tools, genetics / omics, 10 references, author Shengquan Chen
[2] doi:10.1101/gr.281350.125 [code]
High-fidelity bidirectional translation between single-cell transcriptomes and DNA methylomes with scBOND.
Journal: Genome research
In common: anndata, Scanpy, PyTorch, 6 other tools, genetics / omics, 6 references
[3] doi:10.1093/bioinformatics/btag652 [code]
mmVelo: a deep generative model for estimating cell state-dependent dynamics across multiple modalities.
Journal: Bioinformatics (Oxford, England)
In common: anndata, Scanpy, PyTorch, 6 other tools, genetics / omics, 3 references
[4] doi:10.1038/s41467-026-71331-0 [code]
A multimodal approach for visualizing and identifying electrophysiological cell types in vivo.
Journal: Nature communications
In common: anndata, Scanpy, PyTorch, 6 other tools, genetics / omics, 2 references
[5] doi:10.1016/j.xgen.2026.101217 [code]
ProtoCloud: A prototypical self-explaining model for single-cell analysis.
Journal: Cell genomics
In common: anndata, Scanpy, PyTorch, 6 other tools, genetics / omics, 1 reference
[6] doi:10.1038/s42003-026-10462-y [code]
SpaDC enables sequence-based integrative analysis and regulatory inference of spatial chromatin accessibility data.
Journal: Communications biology
In common: anndata, Scanpy, PyTorch, 5 other tools, genetics / omics, 2 references
[7] doi:10.1016/j.isci.2026.117206 [code]
ReliST: A model-agnostic risk layer for spatial transcriptomics deconvolution.
Journal: iScience
In common: anndata, Scanpy, PyTorch, 6 other tools, genetics / omics, 1 reference
[8] doi:10.1038/s41592-026-03057-2 [code]
CREsted: modeling genomic and synthetic cell-type-specific enhancers across tissues and species.
Journal: Nature methods
In common: anndata, Scanpy, PyTorch, 6 other tools, genetics / omics, 1 reference
[9] doi:10.1093/bioinformatics/btag540 [code]
Deciphering spatial heterogeneity by multimodal spatial transcriptomics modelling with SpatialModal.
Journal: Bioinformatics (Oxford, England)
In common: anndata, Scanpy, PyTorch, 6 other tools, genetics / omics, 1 reference
[10] doi:10.21203/rs.3.rs-9676637/v1 [code]
A Comprehensive Benchmarking of Spatial Deconvolution and Domain Detection Methods across Diverse Tissues and Spatial Transcriptomic Technologies
Journal: Research Square (preprint)
In common: anndata, Scanpy, PyTorch, 6 other tools, genetics / omics, 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.