[IMPORTANT: The user has invoked the "paper-recommender" skill, indicating they want you to follow its instructions. The full skill content is loaded below.]
---
name: paper-recommender
description: "每日定时推送高质量论文推荐 — PubMed检索 → Hermes+Claude双重评估 → 仅推最优1篇 → HTML深度解读"
version: 2.7.0
author: Hermes
tags: [PubMed, 论文推荐, Claude评估, 文献解读, 科研]
---
# 📚 每日论文推荐工作流 (Paper Recommender)
## 职责
根据用户的6个研究兴趣方向,每日定时从PubMed检索近期高质量论文,经过Hermes+Claude双重评估后,**只选最优的1篇**,下载PDF+提取原图,制作公众号风格的HTML深度解读文件并推送。
## 用户研究方向
1. 帕金森病(PD) / GZR18 / α-synuclein
2. 神经炎症 / 小胶质细胞 / 星形胶质细胞
3. 细胞死亡方式 (Mitoxyperiosis / 铁死亡 / 焦亡 / 泛素化降解)
4. 外泌体 / 细胞外囊泡 / 神经退行性疾病
5. 脑缺血 / 脑卒中 / 神经保护
6. 生信分析 / 单细胞测序 / 多组学
## ⚡ 用户核心课题(跨所有方向的超优先主题)
**博一课题**:Warburg乳酸 → PCAF介导RhoA K118/K162乳酸化 → RhoA持续激活 → 线粒体远离质膜 → 拮抗mitoxyperiosis
所有方向的论文推荐,只要与以下关键词相关的论文**自动获得更高优先级**,应优先于同评分不相关的论文推送:
- Mitoxyperiosis / 线粒体-质膜接触 / 新型细胞死亡
- 乳酸化修饰(Kla) / PCAF / p300 / 组蛋白乳酸化
- RhoA信号 / 细胞骨架重排 / 小G蛋白修饰
- Warburg效应 / 肿瘤代谢 / LDHA抑制
- 糖酵解 / 乳酸代谢 / 肿瘤免疫代谢
- 禁食疗法 / 卡路里限制 / 联合免疫治疗
- 代谢组学 / 能量代谢 / 肿瘤微环境
评估论文时,额外增加一个维度:**"课题借鉴价值"** — 这篇论文中有什么技术、概念、实验设计可以直接复用到用户的mitoxyperiosis-乳酸化课题?
## 定时推送安排
| 时间 | 主题 | 关键词 |
|:----:|------|--------|
| 08:00 | PD/帕金森病 | Parkinson's disease, α-synuclein, MPTP, dopamine neuron |
| 11:00 | 神经炎症/胶质细胞 | neuroinflammation, microglia, astrocyte, NLRP3 |
| 13:00 | 细胞死亡/信号通路 | cell death, mitoxyperiosis, ferroptosis, ubiquitination |
| 15:00 | 外泌体/细胞通讯 | exosome, extracellular vesicle, neural, brain |
| 17:00 | 脑缺血/神经保护 | cerebral ischemia, stroke, neuroprotection, MCAO |
| 19:00 | 生信/前沿技术 | single-cell, multi-omics, bioinformatics, spatial transcriptomics |
## ⚠️ 已知工具陷阱
### 文件系统隔离(重要!)
`execute_code` 运行在沙箱环境中,**不能直接访问** `terminal` 工具写入 `/tmp/` 或 `$HOME/` 的文件。反之亦然。
- ❌ 错误做法:terminal写入`/tmp/fig1_b64.txt`,然后用execute_code的`open()`读取 → 文件不存在
- ✅ 正确做法1:所有数据处理在terminal中完成(Python脚本通过`python script.py`执行)
- ✅ 正确做法2:将数据处理写成`.py`文件写入磁盘,再用terminal(`python path/to/script.py`)执行
### 大文件HTML生成
当HTML嵌入base64图片时(5张Nature原图 ≈ 4MB),`write_file`会因大小限制失败。
- ❌ 不要直接用write_file写4MB+的HTML
- ✅ 策略:写一个Python builder脚本到磁盘(`write_file → build_html.py`),然后`terminal("python build_html.py")`执行它
### Claude CLI 长提示词超时陷阱
claude -p 传入大段文本时容易超时(exit code 124,返回空),特别是在Windows git-bash环境。
- ❌ 一次性传入4篇论文的完整摘要+评估指令 → 超时
- ✅ 策略1:将评估指令简化,每篇论文控制到1-3句关键信息;或拆分为多次调用分别评估单篇
- ✅ 策略2:用 `head -N` 或 `tail -N` 截断输出(如 `claude -p "评估..." 2>&1 | head -60`),防止Claude生成过长内容导致超时。即使Claude内部未完成,前60行通常已包含评分结果
### Cell Press PII清理模式(重要!)
PubMed esummary返回的PII含括号和连字符(如 `S0896-6273(26)00386-7`),CDN URL需要去掉这些字符:
- ❌ `tr -d '()'` → 只去除括号,留下连字符 → CDN返回404
- ✅ `tr -d '()-'` → 同时去除括号和连字符 → CDN返回200
- 详见 `references/figure-download-patterns.md` 中的修正实例
### Python f-string与JavaScript花括号冲突(HTML Builder陷阱)
当用Python f-string构建HTML时,JavaScript代码中的`{}`(如`canvas.width`、`img.onload = function() { }`、`loadImage("fig1", fig1_b64)`)会被Python误解析为f-string占位符,导致SyntaxError。
- ❌ `html = f'''...<script>img.onload = function() { canvas.width = 780; }</script>...'''` → SyntaxError
- ✅ 策略1:用字符串列表拼接代替f-string(将HTML拆分为多个部分append到列表,用`+`或`''.join()`组合)
- ✅ 策略2:将HTML结构和JS作为独立字符串,用`.replace()`注入base64数据
- ✅ 策略3:在JS中所有`{`和`}`都必须加倍成`{{`和`}}`(仅在必须用f-string时)
- 推荐策略:使用函数`build_html(fig_b64, ...)`接受字典参数,返回拼接好的字符串(详见Step 6 HTML模板)
### Windows Python路径陷阱
在 Windows git-bash 中,Python 脚本不识别 MSYS 路径格式(`/c/Users/...`):
- ❌ `open("/c/Users/forgase/fig1_b64.txt")` → FileNotFoundError
- ✅ `open("C:/Users/forgase/fig1_b64.txt")` — 正斜杠在 Windows Python 中可识别
- 同理,`python3` 命令在 Windows 上可能被应用执行别名拦截 → 始终使用 `python`
## 执行流程(完整版)
### Step 1: PubMed检索 — 两阶段策略
**执行位置:terminal 而非 execute_code**
PubMed API调用应在 `terminal` 中通过 `python << 'PYEOF'` heredoc(推荐)或 `python -c "..."` 执行。`terminal` 中的 Python 连接更稳定,且结果可被后续terminal命令使用(写入文件、管道传递)。避免在 `execute_code` 中做PubMed检索——沙箱环境的网络连接可能不稳定,且JSON结果无法跨沙箱传递给terminal。
⚠️ 复杂脚本(含f-string、多行代码、引号嵌套)优先使用 heredoc 而非 `-c`:
```bash
python << 'PYEOF'
import urllib.request, json, re
# 多行代码,可直接使用单引号、双引号、f-string
print(f"IDs: {', '.join(idlist)}")
PYEOF
```
**日期范围两种方式(方式B更可靠)**:
```python
# 方式A: mindate/maxdate 参数(有时返回0结果,不可靠)
params = {
'db': 'pubmed', 'term': query,
'mindate': '<3个月前>', 'maxdate': '<今天>',
'datetype': 'pdat', 'retmax': 15, 'retmode': 'json'
}
# 方式B: [dp] 查询语法(推荐,已验证可靠)
query = '(ferroptosis[Title/Abstract] OR ...) AND ("2026/03/01"[dp] : "2026/06/12"[dp])'
params = {
'db': 'pubmed', 'term': query,
'retmax': 15, 'retmode': 'json'
}
```
`dp` (Date - Publication) 语法格式:`"YYYY/MM/DD"[dp] : "YYYY/MM/DD"[dp]`。日期之间需要空格+冒号+空格。此方式不受 `mindate/maxdate` 参数兼容性问题影响。
详见 `references/pubmed-API-patterns.md` 第4节。
**阶段A — 主题搜索**:用关键词搜该方向近期论文
**阶段B — 高IF期刊过滤**:用主题词 + `("Nature"[Journal] OR "Cell"[Journal] OR ...)` 格式搜
⚠️ 关键陷阱:
- `sort=date` 被PubMed忽略(返回warning),不要用
- 期刊名必须用 `"全称"[Journal]` 格式,裸词会被翻译为MeSH词条
- 复杂查询在curl中容易URL编码失败,优先用Python
- PubMed JSON返回的ID列表键名为小写 `idlist`,不是 `IdList`(驼峰)
### Step 2: 获取论文详情并初筛
```python
import urllib.request, json, time
# 获取元数据
url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=pubmed&id=<PMIDs>&retmode=json'
# 获取摘要(XML模式比esummary更可靠)
url = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=<PMIDs>&retmode=xml'
```
**初筛硬性门槛**(必须同时满足):
1. IF > 10 或领域顶刊
2. 2026年3月后发表
3. 与用户研究方向直接相关
4. 原创研究(pubtype不含Review)
5. 非 News & Views / Letter / 编辑评论
6. **有作者(推荐用 efetch XML 确认,而非 esummary 的 hascreator 字段)**
- `esummary`的`hascreator`字段有时不可靠:已验证所有高IF期刊论文均返回`hascreator='N'`(即使是多作者原创研究)。
- 改用 efetch XML:统计`<LastName>`标签数(`len(re.findall(r'<LastName>', article_text))`),大于0即有作者。注意不要用`r'<Author>'`做regex——XML实际格式为`<Author ValidYN="Y">`(带属性),`r'<Author>'`无法匹配返回0。
- 若只能用 esummary:不要仅因`hascreator='N'`排除——结合`pubtype`综合判断。
⚠️ **esummary 的 HasAbstract 字段同样不可靠**(2026-06-13发现):在脑缺血/卒中方向搜索中,高IF期刊论文(Nat Neurosci, Cell Rep, Brain, Nat Commun等)的 esummary `attributes` 数组均不包含 `HasAbstract`(即使论文明确有完整摘要)。**不要用 `HasAbstract in attributes` 做初筛条件**——这会导致几乎所有高IF论文被误排除。改用 efetch XML 的 `<AbstractText>` 标签计数来确认:`len(re.findall(r'<AbstractText', xml_text)) > 0`。
### Step 3: Claude Code深度评估(Hermes + Claude 双重评判)
将经过初筛的候选论文交给 Claude Code 严格评估:
```
claude -p "严格评估以下论文,从5个维度各评1-10分..."
```
**5维度评分**:
1. **逻辑完整性** (1-10):完整正反验证(gain+loss of function)、KO/KI模型
2. **方法学水平** (1-10):前沿技术(单细胞测序、冷冻电镜、活细胞成像、TurboID等)
3. **创新性** (1-10):新概念/新机制/新方法,首次报道
4. **可借鉴性** (1-10):实验设计是否值得用户在自己的课题中参考 **← 这是最关键的维度**
5. **临床转化潜力** (1-10):体内验证或治疗意义
### Step 4: 唯一推荐(核心规则)
- Claude评分 < 30分(平均<6分)或任何单维度 < 5分 → **不推荐**,跳过
- 多个候选都达标 → **只选最优的1篇**,不要让用户选
- Hermes再次确认质量 + 相关性 + 可借鉴性 → 只有双方都确认才通过
- **如果这篇研究方向不匹配(如planarian flatworm研究),即使评分高也不能推**
### Step 5: 下载PDF + 提取Figure图片
**⚠️ 预清理:删除旧版fig*_b64.txt文件**
在开始下载前,务必先清理用户目录下所有旧fig*_b64.txt文件,避免前一日的残留文件混入当前日期的图片构建:
```bash
rm -f /c/Users/forgase/fig*_b64.txt
```
Python builder脚本使用`glob.glob("C:/Users/forgase/fig*_b64.txt")`读取所有此类文件,若不清理,旧论文的多余图片会污染当前HTML构建。
**PDF下载**:
- Nature系列: `https://www.nature.com/articles/{article_id}.pdf`(已验证:Nature, Nat Neurosci, Nat Med, Nat Commun均可下载)
- Cell Press/Elsevier: PDF有ScienceDirect防护,通常无法通过curl下载
- 所有期刊的Figure图片可通过CDN下载(详见`references/figure-download-patterns.md`)
- 注意:部分期刊有付费墙,PDF可能无法下载,此时跳过PDF但继续下载Figure图片
**PDF真实性验证**:下载PDF后用 `file` 命令确认是否为真实PDF:
```bash
file "/c/Users/forgase/s41593-026-02317-w.pdf"
# 预期输出: "PDF document, version 1.4, N page(s)" ✅
# 若输出: "HTML document" ❌ — 反爬重定向,非真实PDF
# 已验证:Nat Commun的unedited version PDF可能返回HTML document
```
### 提取文章元数据(Nature系列 — 替代efetch XML的简便方法)
Nature文章页HTML的 `<head>` 嵌入了 `citation_*` 元标签,通过 `curl` + Python可干净提取标题、作者、期刊、日期,比解析efetch XML更简洁:
```bash
curl -s -L -H "User-Agent: Mozilla/5.0" "https://www.nature.com/articles/${ARTICLE_ID}" \
| python -c "
import sys, re
html = sys.stdin.read()
authors = re.findall(r'<meta[^>]*name=\"citation_author\"[^>]*content=\"([^\"]+)\"', html)
print('Authors: ' + '; '.join(authors[:5]) + ('...' if len(authors)>5 else ''))
date = re.findall(r'<meta[^>]*name=\"citation_date\"[^>]*content=\"([^\"]+)\"', html)
print('Date: ' + (date[0] if date else 'N/A'))
journal = re.findall(r'<meta[^>]*name=\"citation_journal_title\"[^>]*content=\"([^\"]+)\"', html)
print('Journal: ' + (journal[0] if journal else 'N/A'))
title = re.findall(r'<meta[^>]*name=\"citation_title\"[^>]*content=\"([^\"]+)\"', html)
print('Title: ' + (title[0] if title else 'N/A'))
"
```
将提取到的元数据直接用于Step 6的HTML头部。已验证适用于Nature、Nat Neurosci、Nat Med、Nat Commun。
### Nature系列PDF下载注意
- Nature系列: `https://www.nature.com/articles/{article_id}.pdf`(已验证:Nature, Nat Neurosci, Nat Med可下载真实PDF)
- **Nat Commun PDF ⚠️ 情况不定**:已验证部分Nat Commun文章返回真实PDF(PMID 42098118, 20页PDF),部分返回HTML反爬页面(PMID 42140967)。下载后用`file`命令确认:若为"HTML document"则非真实PDF,跳过;若为"PDF document"则保留使用。
- Cell Press/Elsevier: PDF有ScienceDirect防护,通常无法通过curl下载
**Figure提取(Nature系列通用模式 — 已验证 Nature, Nat Neurosci, Nat Med, Nat Commun)**:
```bash
# 1. 从HTML中提取所有figure图片URL,获取实际图数(推荐,避免硬编码遗漏)
echo "=== Auto-detect figure count from CDN ==="
for fig in $(seq 1 12); do # 枚举到12足以覆盖几乎所有论文
url="https://media.springernature.com/lw1200/springer-static/image/art%3A10.1038%2F${ARTICLE_ID}/MediaObjects/${JOURNAL_ID}_${YEAR}_${ARTICLE_NUM}_Fig${fig}_HTML.png"
code=$(curl -s -o /dev/null -w "%{http_code}" -L "$url" -H "User-Agent: Mozilla/5.0")
if [ "$code" != "404" ]; then
echo "Fig${fig}: HTTP ${code}"
else
FIG_COUNT=$((fig - 1))
echo "Last figure found: Fig${FIG_COUNT}"
break
fi
done
# 2. 暴力枚举法(传统版)— 扩展至1-12,并验证文件实际写入
for fig in $(seq 1 12); do
url="https://media.springernature.com/lw1200/springer-static/image/art%3A10.1038%2F${ARTICLE_ID}/MediaObjects/${JOURNAL_ID}_${YEAR}_${ARTICLE_NUM}_Fig${fig}_HTML.png"
code=$(curl -s -o /dev/null -w "%{http_code}" -L "$url" -H "User-Agent: Mozilla/5.0")
if [ "$code" != "404" ]; then
curl -s -L "$url" -H "User-Agent: Mozilla/5.0" | base64 -w 0 > "/c/Users/forgase/fig${fig}_b64.txt"
fi
done
# 3. ✅ 验证所有文件实际写入成功(2026-06-13 pitfall:curl pipe可能报告成功但文件未写出)
echo "=== Verification ==="
for fig in $(seq 1 12); do
if [ -f "/c/Users/forgase/fig${fig}_b64.txt" ]; then
size=$(wc -c < "/c/Users/forgase/fig${fig}_b64.txt")
echo "Fig${fig}: OK (${size} bytes)"
else
echo "Fig${fig}: MISSING — re-downloading..."
# Re-download individually
url="https://media.springernature.com/lw1200/springer-static/image/art%3A10.1038%2F${ARTICLE_ID}/MediaObjects/${JOURNAL_ID}_${YEAR}_${ARTICLE_NUM}_Fig${fig}_HTML.png"
curl -s -L "$url" -H "User-Agent: Mozilla/5.0" | base64 -w 0 > "/c/Users/forgase/fig${fig}_b64.txt"
fi
done
```
**Figure Caption提取(Nature系列 — 紧跟图片下载之后执行)**:
提取的caption将用于Step 6 HTML的逐图解读部分。
```bash
curl -s -L -H "User-Agent: Mozilla/5.0" "https://www.nature.com/articles/${ARTICLE_ID}" \
| python -c "
import sys, re
html = sys.stdin.read()
figs = re.findall(r'<fig[^>]*>.*?<figcaption[^>]*>(.*?)</figcaption>', html, re.DOTALL)
for i, fig in enumerate(figs):
clean = re.sub(r'<[^>]+>', '', fig).strip()
print(f'{i+1}|{clean}')
"
```
然后将captions嵌入Python builder脚本中的字典变量。
**Cell Press系列Caption处理**(Neuron, Cell Metabolism等):
Cell Press主页面(www.cell.com / sciencedirect.com)使用Cloudflare防护,curl无法获取页面HTML,因此`<figcaption>`标签无法通过解析提取。已验证策略:
- **手动构建**:基于abstract和论文结构(典型结构:Fig1=现象发现, Fig2-3=分子机制, Fig4-5=通路验证, Fig6=体内验证, Fig7-8=深入机制+模型)合理推断各Figure内容。注意Neuron论文可能达8-9张图(PMID 42263678共8张Fig),枚举至少到9。
- **模板**:将描述写为Python字典嵌入builder脚本(详见 `references/figure-download-patterns.md` "Pre-print / Unedited Version Caption 降级策略")
- Cell Press的Figure图片仍可通过 `ars.els-cdn.com` CDN直接下载(JPEG格式),不受Cloudflare影响
⚠️ **预印本降级策略**:若上述caption提取命令输出为空(无 `<figcaption>` 标签命中),检查文章页是否有"unedited version"或"preprint"标记。
但注意:**并非所有unedited version都无caption**——已验证Nat Commun unedited version (s41467-026-72783-0) 可正常提取9条figcaptions。只有在regex确实返回空时才需要降级。
此时Figure图片仍可通过CDN下载,但caption需手动构建。策略:
- 基于abstract和论文结构合理推断各Figure内容(已验证可行)
- 将手动编写的caption以Python字典嵌入builder脚本
- 详见 `references/figure-download-patterns.md` "Pre-print / Unedited Version Caption 降级策略"
详见 `references/figure-download-patterns.md` 中的"Figure Caption Extraction"节。
**分辨率选择**:
- `/full/` — 最高分辨率(推荐用于Fig1)
- `/lw1200/` — 宽1200px(其余Figures用此即可)
- `/m685/` — 宽685px(小尺寸)
**已验证的图片URL模式**:
| 期刊 | article_id 示例 | journal_id | URL模式 |
|------|----------------|------------|---------|
| Nature | s41586-026-10597-2 | 41586 | `41586_{year}_{article_num}_Fig{N}_HTML.png` |
| Nat Neurosci | s41593-026-02317-w | 41593 | `41593_{year}_{article_num}_Fig{N}_HTML.png` |
| Nat Med | s41591-026-04393-8 | 41591 | `41591_{year}_{article_num}_Fig{N}_HTML.png` |
| Nat Commun | s41467-026-73538-7 | 41467 | `41467_{year}_{article_num}_Fig{N}_HTML.png` |
- article_num 提取规则:从DOI中提取期刊ID后的倒数第二段(年份后的数字段),去前导零。如 `s41591-026-04393-8` → 编号段为 `04393` → 去前导零 → `4393`;`s41586-026-10480-0` → `10480`(无前导零即可直接使用) → `10480`;`s41593-026-02317-w` → `02317` → `2317`
- 参考 `references/figure-download-patterns.md` 获取各期刊的详细URL模式
### Step 6: 制作公众号风格HTML深度解读 — Python Builder模式
HTML文件要求:
1. 所有图片用base64 data URI嵌入,不使用file://协议
2. 仿公众号排版(简洁卡片风格)
3. 每条结果配"复现建议"(🔬 复现建议:...)
4. 包含论文原图 + 逐图解读 + 文章小结
5. 保存到桌面,文件命名规范:`{主题关键词}_文献解读.html`
**实现方法**(大文件HTML必须用此方式):
由于HTML含多张base64图片(5-7张原图≈10MB),不能直接用`write_file`写入。
```python
# 1. 先读取base64数据(terminal工具写入的文件)
# ⚠️ 重要:Windows Python不识别 MSYS 路径 /c/Users/,必须用 C:/Users/ 格式
# ⚠️ 不硬编码range(1,8):读取所有fig{N}_b64.txt文件
import os, glob
fig_b64 = {}
for f_path in glob.glob("C:/Users/forgase/fig*_b64.txt"):
i = os.path.basename(f_path).replace('fig', '').replace('_b64.txt', '')
with open(f_path, "r") as f:
fig_b64[f"fig{i}"] = f.read().strip()
print(f"Loaded Fig{i}: {len(fig_b64[f'fig{i}'])} bytes")
# 2. 构建HTML字符串(用f-string嵌入base64)
html = f'''...<img src="data:image/png;base64,{fig_b64['fig1']}">...'''
# 3. 写入文件(使用正斜杠路径,Windows Python可识别)
with open("C:/Users/forgase/Desktop/主题_文献解读.html", "w", encoding="utf-8") as f:
f.write(html)
```
⚠️ **重要:f-string与JavaScript花括号冲突**:当用Python f-string构建HTML时,JS代码中的花括号(如`img.onload = function() { }`)会与f-string语法冲突。推荐将HTML拆分为多个部分(parts列表),用字符串拼接代替f-string:
```python
# ✅ 推荐:字符串列表拼接,避免f-string花括号冲突
def build_html(fig_b64, captions):
parts = []
parts.append('<!DOCTYPE html>')
parts.append('<html>')
parts.append('<script>')
# ⚠️ 可检测实际图数,不硬编码range(1,8);先统计fig_b64中的键数量
fig_count = max([int(k.replace('fig', '')) for k in fig_b64.keys()])
for i in range(1, fig_count + 1):
parts.append(f'const fig{i}_b64 = "{fig_b64.get(f"fig{i}", "")}";')
parts.append('''
function loadImage(id, b64) {
var canvas = document.getElementById(id);
if (!canvas || !b64) return;
...
}
''')
parts.append('</script>')
return '\n'.join(parts)
html = build_html(fig_b64, captions)
```
详见 `references/html-template-structure.md` 获取完整模板框架。
**流程总结**(4步):
1. terminal中`curl | base64 -w 0 > /c/Users/forgase/fig{N}_b64.txt` 下载所有图片(保存到用户目录,/tmp/在沙箱中不可用)
2. 用`write_file`将Python builder脚本写入磁盘(不含base64数据,仅模板)
3. terminal中执行该Python脚本(`python C:/Users/forgase/build_html.py` — 读取base64文件 + 构建完整HTML + 写入桌面)
4. 验证文件存在:`ls -la /c/Users/forgase/Desktop/`
**HTML模板风格指南**:
- 头部:渐变深蓝背景 + 白色文字 + 标签徽章
- 评分卡片:flex网格布局,5维度评分条
- 图文解读:Fig依次排列,每个配caption+复现建议
- 文章小结:渐变紫色卡片
- 参考 `references/html-template-structure.md` 获取模板框架
### Step 7: 微信推送(⚠️ 关键:必须附上HTML文件)
**格式要求**(最终消息末尾必须加上 `MEDIA:路径` 发送HTML文件):
```
🔥 {时间} {主题} 论文推荐
🏆 标题...
📅 日期 | 📰 期刊
⭐ Claude评分:X/50
💡 推荐理由:...
MEDIA:C:\Users\forgase\Desktop\{文件名}.html
```
**如果当天没有好论文**:
```
📭 {时间} {主题}
今天这个方向没有找到特别适合你的论文,下次继续关注。
```
**⚠️ 不做这个动作等于白做**:最终推送消息的末尾必须包含 `MEDIA:C:\Users\forgase\Desktop\{文件名}.html` 这一行,这样微信才会把HTML文件当作附件发送给用户。只发文字说"已生成"用户收不到文件。
## 核心原则
- **只推1篇** —— 不要让用户从多个候选中选择
- **宁缺毋滥** —— 没有好论文就不推,不强塞
- **Hermes + Claude 双重把关** —— 都确认完美适合才推
- **不推荐综述**(除非极高价值)
- **不推荐与用户研究方向无关的论文**(即使评分高)
- **推送语言用中文**,但保留英文标题和期刊名
- **⚠️ 必须将HTML文件附在消息中一起发送** — 在最终消息末尾加上 `MEDIA:/path/to/file`,确保用户直接收到文件,不是只发文字
## 参考文件
- `references/pubmed-API-patterns.md` — PubMed E-utilities API详细笔记
- `references/figure-download-patterns.md` — Nature/Cell/Elsevier等期刊的图片URL提取模式
- `references/github-access-patterns.md` — 国内网络环境下载GitHub资源的优先级策略
The user has provided the following instruction alongside the skill invocation: [IMPORTANT: You are running as a scheduled cron job. DELIVERY: Your final response will be automatically delivered to the user — do NOT use send_message or try to deliver the output yourself. Just produce your report/output as your final response and the system handles the rest. SILENT: If there is genuinely nothing new to report, respond with exactly "[SILENT]" (nothing else) to suppress delivery. Never combine [SILENT] with content — either report your findings normally, or say [SILENT] and nothing more.]
你是Hermes,用户的科研助手。加载 paper-recommender skill。
**今日任务**:搜索细胞死亡机制方向论文,经过Hermes+Claude双重评判后**只推最优的1篇**,做成HTML深度解读并**必须在消息末尾用MEDIA:路径附上HTML文件**。
**主题关键词**:cell death, mitoxyperiosis, ferroptosis, pyroptosis, ubiquitination, necroptosis
**⚠️ 🎯 此方向与用户博一课题直接相关,优先推送以下内容**:
- **Mitoxyperiosis相关**(最优先):线粒体-质膜接触/线粒体动力学/细胞膜裂解
- **乳酸化与细胞死亡交叉**:新型修饰(Kla)调控死亡通路
- **RhoA / 细胞骨架与细胞死亡**:RhoA GTPase调控细胞命运
- **代谢与细胞死亡**:Warburg效应如何影响死亡敏感性
- **铁死亡与能量代谢交叉**(次优先)
日期范围:最近3个月内发表
期刊要求:IF > 10 或领域顶刊
遵循 paper-recommender skill 的完整6步流程。
**⚠️ 必须:最终微信消息末尾加上 `MEDIA:C:\Users\forgase\Desktop\{文件名}.html`**
论文推荐-13-细胞死亡 · Jun 14 13:05
2026-06-14 13:00 · 46 条 · deepseek-v4-flash
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"success": true, "name": "paper-recommender", "file": "references/pubmed-API-patterns.md", "content": "# PubMed E-utilities API 实战笔记\n\n## 搜索API (esearch)\n\n### 基础结构\n```\nbase: https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi\nparams:\n db=pubmed\n term=<查询表达式>\n mindate/maxdate — 日期范围\n datetype=pdat (publication date)\n retmax=N — 最大返回数\n retmode=json\n```\n\n### 已验证的关键查询模式\n\n**1. 主题搜索 + 高影响因子期刊过滤**\n```python\nquery = 'Parkinson AND (\"Nat Neurosci\"[Journal] OR \"Neuron\"[Journal] OR \"Nat Med\"[Journal])'\n```\n- 期刊名必须用 `\"全称\"[Journal]` 格式\n- 不加 `[Journal]` 标签时,`Neuron` 被翻译为 MeSH 的 neurons(神经元)\n- `Brain` 被翻译为 MeSH 的 brain(大脑解剖结构)\n\n**2. 细胞死亡方向搜索(已验证)**\n```python\nquery = '(ferroptosis[Title/Abstract] OR pyroptosis[Title/Abstract] OR ' + \\\n 'necroptosis[Title/Abstract] OR PANoptosis[Title/Abstract] OR ' + \\\n 'cuproptosis[Title/Abstract] OR mitophagy[Title/Abstract]) ' + \\\n 'AND (Nature[Journal] OR \"Cell\"[Journal] OR \"Nat Cell Biol\"[Journal] OR ' + \\\n '\"Cell Death Differ\"[Journal] OR \"Nat Commun\"[Journal])'\n```\n这个模式成功返回了 Nature 的精胺/铁死亡论文。\n\n**3. 已测试的有效期刊标签**\n| 期刊 | 标签 |\n|------|------|\n| Nature | `\"Nature\"[Journal]` |\n| Nature Communications | `\"Nat Commun\"[Journal]` |\n| Nature Medicine | `\"Nat Med\"[Journal]` |\n| Neuron | `\"Neuron\"[Journal]` |\n| Nature Neuroscience | `\"Nat Neurosci\"[Journal]` |\n| Science Advances | `\"Sci Adv\"[Journal]` |\n| Cell | `\"Cell\"[Journal]` |\n| Cell Reports | `\"Cell Rep\"[Journal]` |\n| Cell Death & Differentiation | `\"Cell Death Differ\"[Journal]` |\n| EMBO Journal | `\"EMBO J\"[Journal]` |\n| Molecular Neurodegeneration | `\"Mol Neurodegener\"[Journal]` |\n| EBioMedicine | `\"EBioMedicine\"[Journal]` |\n| Acta Neuropathologica | `\"Acta Neuropathol\"[Journal]` |\n| Brain | `\"Brain\"[Journal]` |\n| Lancet Neurology | `\"Lancet Neurol\"[Journal]` |\n| Developmental Cell | `\"Dev Cell\"[Journal]` |\n| Nature Structural & Molecular Biology | `\"Nat Struct Mol Biol\"[Journal]` |\n| Cell Metabolism | `\"Cell Metab\"[Journal]` |\n| Molecular Cell | `\"Mol Cell\"[Journal]` |\n| Nature Cell Biology | `\"Nat Cell Biol\"[Journal]` |\n\n### 已验证无用的参数\n- `sort=date` — 返回 warning \"Unknown sort schema 'date' ignored\",无效果\n\n## 获取详情API (esummary)\n\n```python\nurl = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=pubmed&id=<PMID列表>&retmode=json'\n```\n\n关键字段:\n- `pubtype` — 文章类型(含 \"Review\" 则为综述)\n- `source` — 期刊缩写名\n- `articleids[].idtype == 'doi'` — DOI\n- `attributes` — 包含 \"Has Abstract\" 则有摘要\n- `pubdate` — 发表日期\n- `title` — 标题\n\n⚠️ JSON的id列表键名是小写 `idlist`(如 `data['esearchresult']['idlist']`),不是驼峰的 `IdList`。\n\n## 获取摘要API (efetch)\n\n```python\n# XML模式(含结构化信息)\nurl = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=<PMIDs>&retmode=xml'\n\n# 文本模式(纯文本)\nurl = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=<PMIDs>&retmode=text&rettype=abstract'\n```\n\nXML模式返回结构化数据,适合用正则提取:\n- `<ArticleTitle>` → 标题(需要去除XML标签+解码HTML实体)\n- `<AbstractText>` → 摘要段落(可以有多段,Label属性区分BACKGROUND/METHODS/RESULTS/CONCLUSIONS)\n- `<ELocationID EIdType=\"doi\">` → DOI\n- `<Journal><Title>` → 期刊全名\n- `<PubDate><Year>` + `<Month>` → 发表日期\n\nXML转义字符需要手动替换:`α`=α, `β`=β, `γ`=γ, ` `=空格, `⁠`='', `&`=&, `<`=<, `>`=>\n\n## 获取文章元数据(XML完整模式)\n\n```python\nurl = 'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=<PMIDs>&retmode=xml'\n```\n此模式返回完整XML,包含:\n- 所有作者的 `<LastName>` 和 `<ForeName>`\n- 所有 `<Keyword>`\n- 完整 `<AbstractText>`(含多个Label段落)\n- `<PublicationTypeList>` 用于排除Review/Letter\n\n## 已知环境陷阱\n\n### 1. SSL连接失败(exit code 35)\n某些环境(git-bash/MSYS2)的 curl SSL 版本与 NCBI 服务器不兼容。\n- 修复1:`curl -k`(跳过证书验证)\n- 修复2:改用 Python 的 `urllib.request`(在本环境中工作可靠)\n- 修复3:更新 curl CA bundle\n\n### 2. URL编码问题\ncurl 命令行中包含 `()\"[]` 等特殊字符时容易解析失败(exit code 3)。\n- 修复:用 Python 的 `urllib.parse.urlencode(params)` 构建查询串\n\n### 3. `sort=date` 无效\nPubMed API 不支持 sort=date,搜索结果的顺序按默认相关性排序。\n\n### 4. `mindate`/`maxdate` + `datetype` 日期过滤可能返回0结果(2026-06发现)\n使用 `mindate` + `maxdate` + `datetype=pdat/ppub/edat` 参数组合对常见查询(如 `ferroptosis[Title/Abstract]`)返回 Count=0,不返回任何PMID。PubMed API的日期参数在此环境下不可靠。\n- **修复**:改用 `dp` (Date - Publication) 范围语法直接在查询串中限定日期:\n ```python\n query = 'ferroptosis[Title/Abstract] AND (\"2026/03/01\"[dp] : \"2026/06/12\"[dp])'\n params = {'db': 'pubmed', 'term': query, 'retmax': 20, 'retmode': 'json'}\n ```\n `dp` 语法格式:`\"YYYY/MM/DD\"[dp] : \"YYYY/MM/DD\"[dp]`(日期之间需加空格、冒号、空格)。此方式已验证可靠(2026-06-12),可与其他搜索条件自由组合(如 AND 期刊过滤)。\n\n### 5. execute_code 中 PubMed API 不稳定\n在 `execute_code` 沙箱中连续调用 PubMed API 时,部分请求返回空结果(即使同一查询在前一个调用中返回了完整的 count 和 idlist)。推测与沙箱环境的连接复用或速率限制有关。\n- 修复:将 PubMed API 调用移至 `terminal(\"python -c \\\"...\\\"\")` 中执行。terminal 中的 Python 连接更稳定,返回结果一致。\n- 如果结果仍然为空,在两次 API 调用之间添加 `time.sleep(0.5)` 避免速率限制。\n\n### 6. Cell/Elsevier 付费墙\nCell Press(www.cell.com、linkinghub.elsevier.com)对脚本访问严格限制,返回403/超时。Nature系列(www.nature.com)通常可正常访问。\n- 但 Cell Press 的 Figure 图片通过 `ars.els-cdn.com` CDN 分发,可直接通过 curl 下载(详见 figure-download-patterns.md)。\n- PII 中的括号和连字符需要清理:`tr -d '()-'`\n\n### 7. esummary hascreator 字段不可靠(2026-06发现)\n`esummary` 返回的 `hascreator` 字段对所有高IF期刊论文均显示 `'N'`,即使论文明确有多位作者。\n```json\n// 示例:Nat Med 2026 phase 1 clinical trial,真实作者8人,但:\n\"hascreator\": \"N\" // ❌ 错误\n```\n**对策**:改用 efetch XML 确认作者——统计 `<Author>` 标签数。不要因 `hascreator='N'` 排除论文。\n\n### 8. esummary HasAbstract 字段同样不可靠(2026-06-13发现)\n高IF期刊论文(Nat Neurosci, Cell Rep, Brain, Nat Commun等)的 esummary `attributes` 数组均不包含 `HasAbstract`(即使论文明确有完整摘要)。\n- ❌ 不要用 `HasAbstract in attributes` 做初筛条件——这会导致几乎所有高IF论文被误排除\n- ✅ 改用 efetch XML 的 `<AbstractText>` 标签计数来确认:`len(re.findall(r'<AbstractText', xml_text)) > 0`\n\n### 9. efetch XML 批取污染(2026-06-14新发现)\n当一次efetch调用传入**多个PMID**时,XML响应可能返回**所有PMID共享同一篇文章数据**(而非各自独立的元数据)。2026-06-14在35个PMID批取调用中,所有16篇高IF论文均返回了同一篇的标题和摘要(GPNMB Neuron论文)。\n\n**现象**:不同PMID的efetch返回相同的`<ArticleTitle>`和`<AbstractText>`,即使已知这些是不同论文。\n\n**修复**:逐篇单独fetech,每篇之间加延迟避免速率限制:\n```python\nfocus_pmids = ['42127911', '42140967', '42191733'] # 逐篇取\nfor pmid in focus_pmids:\n time.sleep(0.4) # 关键:避免速率限制\n url = f'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id={pmid}&retmode=xml'\n req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0'})\n resp = urllib.request.urlopen(req)\n xml_text = resp.read().decode('utf-8')\n # 每篇独立处理,结果可靠\n```\n**原因推测**:PubMed API在批取时可能复用连接或缓存,导致高并发下返回错位数据。\n\n## 搜索策略(两阶段工作流)\n\n### 阶段A:主题搜索\n```python\n# 方式A: mindate/maxdate(可能不可靠)\nparams = {\n 'db': 'pubmed', 'term': query,\n 'mindate': '<3月前>', 'maxdate': '<今天>',\n 'datetype': 'pdat', 'retmax': 10, 'retmode': 'json'\n}\n# 方式B: [dp] 语法(推荐,已验证可靠)\nquery = 'Parkinson disease AND (\"2026/03/01\"[dp] : \"2026/06/12\"[dp])'\nparams = {\n 'db': 'pubmed', 'term': query,\n 'retmax': 10, 'retmode': 'json'\n}\n```\n目的:了解该时段总论文数,获取基础PMID列表。\n\n### 阶段B:高影响力期刊过滤\n```python\njournal_tags = '\"Nature\"[Journal] OR \"Cell\"[Journal] OR \"Nat Neurosci\"[Journal] OR ...'\nquery = f'({topic_keywords}) AND ({journal_tags}) AND (\"<3月前>\"[dp] : \"<今天>\"[dp])'\n```\n目的:直接命中IF>10的高质量论文。\n\n### 初筛要点\n1. `pubtype` 不含 \"Review\" → 原创研究\n2. `attributes` 含 \"Has Abstract\" → 有摘要\n3. 检查 DOI 是否存在\n4. 排除 \"No authors listed\" → 通常是 News & Views\n5. 从XML提取时注意HTML实体和Unicode转义符的处理\n\n## 评分标准(Claude评估用,5维度各1-10分)\n\n| 维度 | 评分要点 | 满分 |\n|------|---------|------|\n| 逻辑完整性 | gain+loss of function, KO/KI, 正反验证 | 10 |\n| 方法学水平 | 单细胞测序, 冷冻电镜, 活细胞成像, TurboID等 | 10 |\n| 创新性 | 新概念/新机制/新方法 | 10 |\n| 可借鉴性 | 实验设计可迁移到神经科学 **←最重要维度** | 10 |\n| 临床转化潜力 | 体内验证, 治疗靶点, 生物标志物 | 10 |\n\n总分 >= 30 且各维度 >= 5 → 候选。再经Hermes确认相关性后,只选最优1篇。", "file_type": ".md"}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"success": true, "name": "paper-recommender", "file": "references/figure-download-patterns.md", "content": "# 学术期刊Figure下载模式速查\n\n## Nature 系列\n**已验证模式(2026年6月)**\n\n### URL结构\n```\n文章页: https://www.nature.com/articles/{article_id}\nFigure URL: https://media.springernature.com/{size}/springer-static/image/\n art%3A10.1038%2F{article_id}/MediaObjects/\n {journal_id}_{year}_{article_num}_Fig{N}_HTML.png\n```\n\n### 关键参数\n- `{article_id}`: DOI中`/`后面的部分,如 `s41586-026-10597-2` 或 `s41593-026-02317-w`\n- `{journal_id}`: 期刊对应数字ID,如 Nature=41586, Nat Neurosci=41593\n- `{year}`: 4位年份\n- `{article_num}`: 文章编号(DOI中期刊ID后的数字部分,去连字符)\n- `{N}`: Figure编号(1-7)\n\n### 实例1 (Nature — 已验证 2026-06)\n```\narticle_id = s41586-026-10597-2\njournal_id = 41586\nyear = 2026\narticle_num = 10597\n\nFig1 全尺寸:\nhttps://media.springernature.com/full/springer-static/image/art%3A10.1038%2Fs41586-026-10597-2/MediaObjects/41586_2026_10597_Fig1_HTML.png\n\nFig2 中等尺寸:\nhttps://media.springernature.com/lw1200/springer-static/image/art%3A10.1038%2Fs41586-026-10597-2/MediaObjects/41586_2026_10597_Fig2_HTML.png\n```\n\n### 实例2 (Nature Neuroscience — 已验证 2026-06)\n```\narticle_id = s41593-026-02317-w\njournal_id = 41593\nyear = 2026\narticle_num = 2317\n\nFig1 全尺寸:\nhttps://media.springernature.com/full/springer-static/image/art%3A10.1038%2Fs41593-026-02317-w/MediaObjects/41593_2026_2317_Fig1_HTML.png\n\nFig4 中等尺寸:\nhttps://media.springernature.com/lw1200/springer-static/image/art%3A10.1038%2Fs41593-026-02317-w/MediaObjects/41593_2026_2317_Fig4_HTML.png\n```\n\n### 实例4 (Nature Neuroscience — 新验证 2026-06-12, PMID: 42151483)\n```\narticle_id = s41593-026-02267-3\njournal_id = 41593\nyear = 2026\narticle_num = 2267 # 从DOI \"02267\" 去前导零 → 2267\n\nFig1-Fig7 (lw1200): 全部 HTTP 200 ✅\nFig1-Fig3 (full): 全部 HTTP 200 ✅\nPDF: https://www.nature.com/articles/s41593-026-02267-3.pdf → HTTP 200, 26.7MB ✅\n```\n\n### 实例5 (Nature Communications — 新验证 2026-06-13, PMID: 42140967)\n```\narticle_id = s41467-026-73136-7\njournal_id = 41467\nyear = 2026\narticle_num = 73136 # 从DOI \"73136\" 无前导零 → 73136\n\nFig1 (full): HTTP 200 ✅ (1.5MB)\nFig2-Fig7 (lw1200): 全部 HTTP 200 ✅ (1.4-2.5MB each)\nPDF: https://www.nature.com/articles/s41467-026-73136-7.pdf → HTTP 200 ⚠️ 但返回的是HTML! file命令显示为\"HTML document\",非真实PDF\n\n关键发现:该文章为\"unedited version\"(预印本版),HTML页面仅含Abstract,\n不含<figcaption>标签。Figure图片通过CDN可正常下载,但caption无法从HTML提取。\n```\n\n### 实例3 (Nature Medicine — 已验证 2026-06-11)\n```\narticle_id = s41591-026-04393-8\njournal_id = 41591\nyear = 2026\narticle_num = 4393\n\nFig1 全尺寸:\nhttps://media.springernature.com/full/springer-static/image/art%3A10.1038%2Fs41591-026-04393-8/MediaObjects/41591_2026_4393_Fig1_HTML.png\n\nFig2-Fig5 中等尺寸:\nhttps://media.springernature.com/lw1200/springer-static/image/art%3A10.1038%2Fs41591-026-04393-8/MediaObjects/41591_2026_4393_Fig2_HTML.png\n...\nhttps://media.springernature.com/lw1200/...41591_2026_4393_Fig5_HTML.png\n\narticle_num提取: DOI \"s41591-026-04393-8\" → 取s41591后的两段 \"026\"+\"04393\" → 截取最终段的数字部分去前导零 → 4393\n```\n\n### 快速提取命令(curl + grep)\n```bash\n# 1. 从HTML提取所有Figure URL(通用模式,匹配所有s415XX系列期刊)\ncurl -s -L -H \"User-Agent: Mozilla/5.0\" \\\n \"https://www.nature.com/articles/{article_id}\" \\\n | grep -oP 'https://media\\.springernature\\.com/[^\"'\"'\"'<>]+s415\\d\\d[^\"'\"'\"'<>]*\\.(?:png|jpg|webp)' \\\n | sort -u\n\n# 2. 下载某张Figure为base64(用于HTML嵌入)\nFIG_URL=\"https://media.springernature.com/lw1200/springer-static/image/art%3A10.1038%2F{article_id}/MediaObjects/{journal_id}_{year}_{article_num}_Fig{N}_HTML.png\"\ncurl -s \"$FIG_URL\" -H \"User-Agent: Mozilla/5.0\" | base64 -w 0 > /c/Users/<user>/fig{N}_b64.txt\n```\n\n### 分辨率控制\n| 前缀 | 尺寸 | 说明 |\n|------|------|------|\n| `/full/` | 全尺寸 | 最高分辨率,推荐用于Fig1。**注意:Nature系列通常在`/full/`下所有Figure都可用,非仅Fig1**(已验证:Nature s41586-026-10480-0, Fig1-Fig6全部200) |\n| `/lw1200/` | 宽1200px | 中等尺寸,适用于其余Figures。备选方案——若`/full/`偶有404,降级到此 |\n| `/m685/` | 宽685px | 小尺寸 |\n| `/w215h120/` | 215x120px | 缩略图 |\n\n### 已测试的期刊ID\n| 期刊 | ID | DOI前缀 | 验证状态 |\n|------|----|---------|---------|\n| Nature | 41586 | s41586 | ✅ 2026-06 (Fig1-Fig6 all HTTP 200 full/) |\n| **Nature Medicine** | **41591** | **s41591** | **✅ 2026-06** |\n| **Nature Neuroscience** | **41593** | **s41593** | **✅ 2026-06 (两篇独立验证)** |\n| Nature Communications | 41467 | s41467 | 🟢 已验证 |\n| Cell Death & Differentiation | 41418 | s41418 | 🟢 已验证 |\n| Scientific Reports | 41598 | s41598 | 🟢 已验证 |\n| Cell Discovery | 41420 | s41420 | 🟢 已验证 |\n\n## Figure Caption Extraction (Nature系列 — HTML解析)\n\n### 为什么需要提取caption\nStep 6的HTML深度解读需要为每张Figure配caption文字。直接从Nature文章页HTML中提取比手动编写更准确、更快速。\n\n### 方法:Python regex解析 `<figcaption>`\n\nNature系列文章将figure caption放在 `<figcaption>` 标签内,可通过Python regex可靠提取:\n\n```bash\ncurl -s -L -H \"User-Agent: Mozilla/5.0\" \"https://www.nature.com/articles/{article_id}\" \\\n | python -c \"\nimport sys, re\nhtml = sys.stdin.read()\nfigs = re.findall(r'<fig[^>]*>.*?<figcaption[^>]*>(.*?)</figcaption>', html, re.DOTALL)\nfor i, fig in enumerate(figs):\n clean = re.sub(r'<[^>]+>', '', fig).strip()\n print(f'Figure {i+1}: {clean}')\n print()\n\"\n```\n\n### 已验证(2026-06-12,Nat Neurosci s41593-026-02267-3)\n所有7张Figure的caption均正确提取,如:\n```\nFigure 1: Fig. 1: CODEX workflow for neuroscience applications.\nFigure 2: Fig. 2: Multicellular characterization of the Aβ plaque microenvironment at the proteomic level.\nFigure 3: Fig. 3: CODEX-CNS reveals specific cellular interactions in human AD brain.\n...\n```\n\n### 在Builder脚本中使用captions\n将提取到的captions以Python变量形式嵌入builder脚本:\n```python\ncaptions = {\n 1: \"CODEX workflow for neuroscience applications.\",\n 2: \"Multicellular characterization of the Aβ plaque microenvironment at the proteomic level.\",\n # ...\n}\n```\n\n### 已知注意事项\n- Nature系列的 `<figcaption>` 目前为纯文本加少量 `<sup>` 标签,清理 `<sup>` 后即可得到干净文本\n- Cell Press系列因Cloudflare防护,页面HTML不可直接解析→caption需从PDF或手动输入\n- 部分文章可能有Extended Data Figures(Fig S1, S2等),主文章通常只含Fig1-Fig7,**但Nat Commun可能有Fig8、Fig9**(已验证:PMID 42098118,9张Figures)\n- **关键**:不要硬编码 `for fig in 1 2 3 4 5 6 7`,应先通过HTML提取或CDN枚举(到Fig9或Fig10)动态检测实际图数。若枚举只到Fig7,会漏掉Fig8/Fig9(图片数据不完整,HTML解读会缺失关键图)\n\n### Pre-print / Unedited Version Caption 降级策略\n**场景**:Nature Communications等期刊有时发布\"unedited version\"(未编辑预印本),HTML页面可能不含 `<figcaption>` 标签(regex提取返回空)。**但并非所有unedited version都无caption**——2026-06-14验证发现Nat Commun unedited version (s41467-026-72783-0) 可正常提取9条figcaptions。\n\n**检测方法**:查看文章HTML中是否有 \"unedited version\" 或 \"preprint\" 字样。然后尝试提取figcaptions:\n```bash\n# 先尝试提取——可能成功也可能失败\nfigs=$(curl -s -L -H \"User-Agent: Mozilla/5.0\" \"https://www.nature.com/articles/${ARTICLE_ID}\" \\\n | python -c \"\nimport sys, re\nhtml = sys.stdin.read()\nfigs = re.findall(r'<fig[^>]*>.*?<figcaption[^>]*>(.*?)</figcaption>', html, re.DOTALL)\nprint(len(figs))\n\")\necho \"Found ${figs} figcaptions\"\nif [ \"$figs\" -gt 0 ]; then\n echo \"Captions available — use them directly\"\nelse\n echo \"No captions — enter pre-print fallback\"\nfi\n```\n\n**降级流程**(仅在regex提取返回空时触发):\n1. **手动构建**:基于abstract和论文结构合理推断各Figure内容(推荐,已验证可行)。将描述写为Python字典嵌入builder脚本。\n2. **PDF提取**:尝试 pdftotext 从PDF中提取captions。但⚠️预印本PDF有时也返回HTML(部分nat commun),此时跳过。\n3. **浏览器工具**:用browser工具导航到文章页 → Accept cookies → 滚动查看是否有JS渲染的figure captions。部分预印本也未渲染。\n\n**手动构建模板**(适用于机制类论文):\n```python\ncaptions = {\n 1: \"Fig. 1: [主要发现,通常为表型]。[技术手段+关键结果1-2句]\",\n 2: \"Fig. 2: [机制研究,通常为通路验证]。[上游调控+下游效应]\",\n 3: \"Fig. 3: [分子机制细节]。[蛋白互作/修饰/定位数据]\",\n 4: \"Fig. 4: [细胞/体内功能验证]。[表型恢复/功能实验]\",\n 5: \"Fig. 5: [深入机制或转化研究]。[治疗/干预结果]\",\n 6: \"Fig. 6: [补充机制或模型验证]。[定量/统计支持]\",\n 7: \"Fig. 7: [整体工作模型示意图]。\"\n}\n```\n\n## Cell Press / Elsevier 系列(Cell Metabolism, Cell, Neuron, Cell Reports 等)\n**已验证模式(2026年6月)**\n\n### 关键发现:主页面有Cloudflare防护,但CDN图片可直接访问\nCell Press 主页面(www.cell.com)使用 Cloudflare 防护,curl/browser 直接访问被拦截。\n但图片通过 `ars.els-cdn.com` CDN 分发,**可以直接通过 curl 下载**。\n\n### URL结构(已成功用于 Cell Metabolism)\n```\nFigure N (大尺寸):\nhttps://ars.els-cdn.com/content/image/1-s2.0-{PII}-gr{N}_lrg.jpg\n\nFigure N (小尺寸):\nhttps://ars.els-cdn.com/content/image/1-s2.0-{PII}-gr{N}.jpg\n\nGraphical Abstract (大尺寸):\nhttps://ars.els-cdn.com/content/image/1-s2.0-{PII}-fx1_lrg.jpg\n```\n\n### 关键参数\n- `{PII}`: 文章的PII(Publisher Item Identifier),可从PubMed esummary结果中获取(idtype='pii'),或从DOI对应的ScienceDirect URL中提取\n- `{N}`: Figure编号(1-7),Cell Press系列使用 `gr1, gr2, ..., gr7` 格式(非 `Fig1`)\n- `fx1`: Graphical Abstract的固定标识\n\n### 实例(Neuron — 已验证 2026-06-12)\n```bash\nPMID: 42127911\nDOI: 10.1016/j.neuron.2026.04.033\nPII: S0896-6273(26)00328-4 # 含有括号和连字符,需全部去除\nURL-PII: S0896627326003284 # 去除括号和连字符后的实际URL用PII\n\n# Figure URL (CDN直接访问,无防护):\n# 核心:去除PII中的括号,替换 gr{N}_lrg 和 fx1_lrg\nFig1: https://ars.els-cdn.com/content/image/1-s2.0-S0896627326003284-gr1_lrg.jpg\nFig2: https://ars.els-cdn.com/content/image/1-s2.0-S0896627326003284-gr2_lrg.jpg\nFig3: https://ars.els-cdn.com/content/image/1-s2.0-S0896627326003284-gr3_lrg.jpg\nFig4: https://ars.els-cdn.com/content/image/1-s2.0-S0896627326003284-gr4_lrg.jpg\nFig5: https://ars.els-cdn.com/content/image/1-s2.0-S0896627326003284-gr5_lrg.jpg\nFig6: https://ars.els-cdn.com/content/image/1-s2.0-S0896627326003284-gr6_lrg.jpg\nFig7: https://ars.els-cdn.com/content/image/1-s2.0-S0896627326003284-gr7_lrg.jpg\nGraphical Abstract: https://ars.els-cdn.com/content/image/1-s2.0-S0896627326003284-fx1_lrg.jpg\n\n# PII括号去除规则\n# ⚠️ 必须同时去除括号和连字符:tr -d '()-'\n# \"S0896-6273(26)00328-4\" → tr -d '()-' → \"S0896627326003284\"\nPII_URL=$(echo \"$PII\" | tr -d '()-')\necho \"$PII_URL\" # → S0896627326003284\n\n```\n\n### 实例3(Neuron — 新验证 2026-06-13, PMID: 42263678 — 8张Figures!)\n```bash\nPMID: 42263678\nDOI: 10.1016/j.neuron.2026.05.015\nPII: S0896-6273(26)00386-7\nURL-PII: S0896627326003867 # 经 tr -d '()-' 处理\n\n# gr1-gr8 _lrg.jpg 全部 HTTP 200 ✅(共8张,不是通常的7张!)\n# Fig1: 3.5MB, Fig4: 3.2MB, Fig7: 3.1MB, Fig8: 1.2MB (高清原图)\n# fx1 (Graphical Abstract): HTTP 404 ❌ (本文章无Graphical Abstract)\n\n# ⚠️ 关键教训:枚举范围必须 ≥ 8!不要假设所有论文都是7张Figs\n\n# Cell Press页面有Cloudflare防护,无法提取figcaptions\n# -> 需要手动构建captions(基于abstract和论文结构推断)\n```\n```bash\nPMID: 42263678\nDOI: 10.1016/j.neuron.2026.05.015\nPII: S0896-6273(26)00386-7\nURL-PII: S0896627326003867 # 经 tr -d '()-' 处理\n\n# gr1-gr7 全部 HTTP 200 ✅ (含 _lrg 和无 _lrg 两种尺寸均可用)\ncurl -s \"https://ars.els-cdn.com/content/image/1-s2.0-S0896627326003867-gr1_lrg.jpg\" | base64 -w 0 > fig1_b64.txt\n# fx1: HTTP 404(非所有Cell Press文章都有Graphical Abstract)\n```\n\n### 实例4(Cell Metabolism — 首次验证 2026-06-11,PMID: 42049021,7 figures)\n```bash\nPMID: 42049021\nDOI: 10.1016/j.cmet.2026.04.001\nPII: S1550-4131(26)00139-7 # 注意:PII可能不同于全文URL中的pii\n# ⚠️ 同样需要 tr -d '()-' 去除括号和连字符\n\n# ScienceDirect URL (有Cloudflare防护,curl会失败):\n# https://www.sciencedirect.com/science/article/pii/S1550413126001397\n\n# Figure URL (CDN直接访问,无防护):\nFig1-Fig7: gr1_lrg.jpg ~ gr7_lrg.jpg 全部 HTTP 200 ✅\nGraphical Abstract (fx1): HTTP 200 ✅\n```\n\n### 实例5(Cell Metabolism — 再验证 2026-06-13,PMID: 42235511,仅6 figures)\n```bash\nPMID: 42235511\nDOI: 10.1016/j.cmet.2026.05.005\nPII: S1550-4131(26)00190-7\nURL-PII: S1550413126001907 # 经 tr -d '()-' 处理\n\n# gr1-gr6 _lrg.jpg 全部 HTTP 200 ✅\n# gr7: HTTP 404 ❌ (本文章只有6张Figures,不是7张)\n# fx1 (Graphical Abstract): HTTP 404 ❌ (无Graphical Abstract)\n\n# 关键发现:同一期刊的不同论文,Figure数量可能不同(6张vs7张)。\n# 暴力枚举法从gr1试到gr7即可自动处理,404的跳过。\n```\n\n### 快速提取命令(修复版)\n```bash\n# 1. 从PubMed esummary中获取PII\n# PII字段: idtype='pii', value='S1550-4131(26)00139-7'\n# 或从DOI的ScienceDirect重定向URL中提取:/pii/{PII}\n\n# 2. ⚠️ 关键:清理PII中的括号和连字符,否则CDN URL会404\nPII_CLEAN=$(echo \"$PII\" | tr -d '()-')\n\n# 3. 暴力枚举法:从gr1试到gr9(⚠️ 不要只用7!Neuron已验证8张,Nat Commun已验证9张)\nfor fig in $(seq 1 9); do\n url=\"https://ars.els-cdn.com/content/image/1-s2.0-${PII_CLEAN}-gr${fig}_lrg.jpg\"\n code=$(curl -s -o /dev/null -w \"%{http_code}\" -L \"$url\" -H \"User-Agent: Mozilla/5.0\")\n echo \"gr${fig}: HTTP ${code}\"\n if [ \"$code\" != \"404\" ]; then\n curl -s \"$url\" -H \"User-Agent: Mozilla/5.0\" | base64 -w 0 > fig${fig}_b64.txt\n fi\ndone\n\n# 4. 下载Graphical Abstract (可能不存在→404,正常)\ncurl -s \"https://ars.els-cdn.com/content/image/1-s2.0-${PII_CLEAN}-fx1_lrg.jpg\" \\\n -H \"User-Agent: Mozilla/5.0\" | base64 -w 0 > fig_fx1_b64.txt\n```\n\n### 已验证的Cell Press期刊\n| 期刊 | 验证状态 | 备注 |\n|------|---------|------|\n| Cell Metabolism | ✅ 已验证(2026-06) | gr1-gr6/7全部通过,HTTP 200;⚠️ figure数因论文而异(已见6张和7张两种) |\n| **Neuron** | **✅ 已验证(2026-06-12)** | **gr1-gr7全部通过,HTTP 200;PMID 42127911 + PMID 42263678** |\n| Cell Reports | ✅ 已验证(2026-06-13) | gr1-gr7 _lrg.jpg全部HTTP 200;PMID 42275213, PII S2211-1247(26)00628-5 → S2211124726006285;fx1 无(404) |\n\n### 实例7 (Nature Communications — 新验证 2026-06-14, PMID: 42098118 — 9 figures!)\n```\narticle_id = s41467-026-72783-0\njournal_id = 41467\nyear = 2026\narticle_num = 72783 # 从DOI \"72783\" 无前导零 → 72783\n\nFig1-Fig9 (lw1200): 全部 HTTP 200 ✅ (单张0.4-1.3MB each)\nFig8: HTTP 200 ✅ (650KB)\nFig9: HTTP 200 ✅ (402KB)\nPDF: https://www.nature.com/articles/s41467-026-72783-0.pdf → HTTP 200 ✅\n file命令: \"PDF document, version 1.4, 20 page(s)\" ✅ (2.5MB真实PDF)\n\n关键发现1:⚠️ 主文章有9张Figures(非通常的7张!),枚举范围应增加到9或动态检测\n关键发现2:该文章虽为\"unedited version\",但CDN可下载Fig1-Fig9全部,且<html>中<figcaption>标签可提取(9条全部命中)\n关键发现3:⚠️ 暴力枚举法硬编码 `for fig in 1 2 3 4 5 6 7` 会漏掉Fig8、Fig9\n```\n```\narticle_id = s41467-026-72779-w\njournal_id = 41467\nyear = 2026\narticle_num = 72779 # 从DOI \"72779\" 无前导零 → 72779\n\nFig1 (lw1200): HTTP 200 ✅ (1.8MB)\nFig2-Fig6 (lw1200): 全部 HTTP 200 ✅ (0.8-3.7MB each)\nFig7 (lw1200): HTTP 200 ✅ (1.2MB)\n\n验证要点:\n- 另一篇Nat Commun unedited version,无<figcaption>标签\n- ⚠️ 图中的fig7在批量下载循环中报告\"Saved\"但实际文件未写入磁盘\n → 需在循环后增加文件存在性验证 + 单独重下载缺失的图\n- Article_num = 72779 (直接取\"72779\"即可)\n```\n| Cell | 🟡 大概率可用 | 同属Cell Press,URL模式相同 |\n| Developmental Cell | 🟡 大概率可用 | 同属Cell Press,URL模式相同 |\n| Molecular Cell | 🟡 大概率可用 | 同属Cell Press,URL模式相同 |\n\n### 已知限制\n- PDF下载:ScienceDirect有强防护,PDF无法直接通过curl下载(需订阅或机构访问)\n- 主页面HTML:Cloudflare拦截,无法直接从页面解析figure列表\n- PII格式因期刊而异,需从PubMed API或DOI重定向中获取\n- **Figure数量因论文而异**:同一期刊的不同论文,Figures数量可能不同(Cell Metabolism 6或7张;Neuron 7或8张;Nat Commun 7-9张)。暴力枚举法从gr1→gr9(共9轮)能自适应处理——返回200的保持,404的跳过。不要假设所有论文都有7张Figures。\n\n## PMC / PubMed Central 开放获取\n```\nhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC{pmcid}/bin/{filename}\n```\n- 仅对开放获取文章有效\n\n## 通用最佳实践\n\n1. **先获取文章HTML页面**,从中提取Figure图片链接\n2. **优先使用全尺寸版本**(替换路径中的尺寸限定词)\n3. **base64嵌入**到HTML中,避免file://协议被浏览器拦截\n4. **文件命名**:`Figure{N}_{简短描述}.png`\n5. **注意付费墙**:3xx/4xx响应 → 放弃,不要反复重试\n6. **Nature/Nature Neuroscience/Nature Medicine PDF下载**:`https://www.nature.com/articles/{article_id}.pdf` — 已验证可下载(2026-06),Nature Medicine实例如 `s41591-026-04393-8`(7.8MB)\n7. **Nature Communications PDF ⚠️**:同为nature.com子域,但部分文章的PDF可能返回HTML(反爬),部分返回真实PDF。已验证双向并存:\n - PMID 42140967 (s41467-026-73136-7) → PDF返回HTML ⚠️\n - PMID 42098118 (s41467-026-72783-0) → PDF返回真实PDF (20页, 2.5MB) ✅\n - 下载后必须检查:`file article.pdf` → 若输出\"HTML document\"而非\"PDF document\",则非真实PDF。此时跳过PDF,仅下载Figure图片。\n\n## ⚠️ Windows 路径注意事项\n\n在 git-bash 中执行 `curl` + `base64` 保存图文件时,路径用 `/c/Users/<user>/` 形式(如 `/c/Users/forgase/fig1_b64.txt`)。但在 **Python 脚本** 中读取这些文件时,必须用 Windows 原生路径格式(`C:/Users/<user>/fig1_b64.txt`),因为 Python on Windows 不认识 MSYS 路径 `/c/Users/...`。\n\n**错误做法:**\n```python\nopen(\"/c/Users/forgase/fig1_b64.txt\", \"r\") # ❌ FileNotFoundError\n```\n\n**正确做法:**\n```python\nopen(\"C:/Users/forgase/fig1_b64.txt\", \"r\") # ✅ 正斜杠在Windows Python中可识别\n# 或\nopen(r\"C:\\Users\\forgase\\fig1_b64.txt\", \"r\") # ✅ 原始字符串\n```\n", "file_type": ".md"}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"success": true, "name": "paper-recommender", "file": "references/html-template-structure.md", "content": "# 公众号风格HTML解读 — 模板结构\n\n## 文件架构\n\n```\n<!DOCTYPE html>\n├── <head>\n│ ├── 字符集/视口\n│ └── 样式(全部内联<style>)\n│ ├── 全局重置\n│ ├── .header — 渐变深蓝背景\n│ ├── .card — 白色圆角卡片\n│ ├── .section-title — 左边框强调标题\n│ ├── .score-bar / .score-item — 评分网格\n│ ├── .figure-box — 图片容器\n│ ├── .reproduce-tip — 蓝色复现建议\n│ ├── .highlight — 黄色高亮框\n│ └── .summary-box — 紫色渐变结论卡\n├── <body>\n│ ├── .header\n│ │ ├── 标签徽章(🔥 今日推荐 + 主题标签)\n│ │ ├── h1 中文标题\n│ │ ├── p 英文标题\n│ │ └── p 📅日期 | 📰期刊 | IF\n│ ├── .container\n│ │ ├── .card (评分) — 5维度×flex网格\n│ │ ├── .card (速览) — 摘要+高亮框\n│ │ ├── .card (团队) — 作者信息\n│ │ ├── .card (图文) — Figure×5 含canvas+caption+🔬复现建议\n│ │ ├── .card (评述) — ✅优势/⚠️缺憾/🔬借鉴\n│ │ ├── .summary-box (小结)\n│ │ └── .card (元数据) — DOI/关键词/时间\n│ └── <script>\n│ ├── const fig1_b64 = \"...\" (base64数据)\n│ └── function loadImage() → canvas渲染\n```\n\n## 评分部分(5维度flex网格)\n\n```html\n<div class=\"score-bar\">\n <div class=\"score-item\">\n <div class=\"label\">逻辑完整性</div>\n <div class=\"value\">9</div>\n <div class=\"stars\">★★★★★</div>\n </div>\n <!-- 重复 ×5 -->\n</div>\n<!-- 总分 -->\n<div style=\"text-align:center;font-size:24px;font-weight:700;color:#e94560;\">\n 总分:41 / 50 ⭐\n</div>\n```\n\n## 图文解读(每个Figure的结构)\n\n```html\n<div class=\"figure-box\">\n <canvas id=\"fig{N}-canvas\" style=\"max-width:100%\"></canvas>\n <div class=\"caption\">\n <b>Figure {N} | 标题</b><br>\n 解读文字...\n <div style=\"margin-top:8px;\">\n <b>🔬 复现建议:</b>具体建议...\n </div>\n </div>\n</div>\n<div class=\"divider\"></div>\n```\n\n## 图片嵌入方案\n\n### 方案A:直接 `<img>` 标签(推荐,更简单)\n\n当HTML仅需展示静态图片(不需要缩放/交互)时,直接使用 `<img>` 标签最简洁,无需JavaScript:\n\n```html\n<!-- 直接嵌入base64到img标签 -->\n<img class=\"fig-image\" src=\"data:image/png;base64,{fig_b64['fig1']}\" alt=\"Fig1\">\n\n<!-- 在Python builder脚本中可用字符串拼接实现 -->\nparts.append(f'<img class=\"fig-image\" src=\"data:image/png;base64,{fig_b64[\"fig1\"]}\" alt=\"Fig1\">')\n```\n\n**优点**:代码最少,无需canvas/JS,兼容性最好。\n**缺点**:无法编程控制渲染尺寸(但CSS的 `max-width: 100%` 即可解决)。\n**⚠️ 注意**:Nature系列用PNG格式(base64以 `iVBOR` 开头),Cell Press系列用JPEG(base64以 `/9j/` 开头)。直接使用 `data:image/png;base64,` 对PNG有效;若下载的是JPEG需改为 `data:image/jpeg;base64,`。\n\n### 方案B:Canvas渲染(当需要编程控制图片时)\n\n当需要对图片做交互(局部放大、叠加标注、过滤等)时使用:\n\n```javascript\n// 1. base64数据存为JS变量(在<script>开头)\nconst fig1_b64 = \"iVBORw0KGgo...\"; // PNG格式\nconst fig2_b64 = \"/9j/4AAQSkZJRg...\"; // JPEG格式(以/9j/开头)\n\n// 2. canvas渲染(onload时自适应尺寸,自动检测PNG/JPEG)\nfunction loadImage(canvasId, b64) {\n var canvas = document.getElementById(canvasId);\n var ctx = canvas.getContext(\"2d\");\n var img = new Image();\n img.onload = function() {\n canvas.width = img.width;\n canvas.height = img.height;\n ctx.drawImage(img, 0, 0);\n };\n // 自动判断格式:PNG头部为\"iVBOR\",JPEG头部为\"/9j/\"\n var mime = b64.startsWith(\"iVBOR\") ? \"image/png\" : \"image/jpeg\";\n img.src = \"data:\" + mime + \";base64,\" + b64;\n}\n```\n\n**⚠️ 重要**:Canvas方案在Python builder脚本中要注意f-string与JS花括号的冲突(详见SKILL.md的\"Python f-string与JavaScript花括号冲突\"节)。\n\n### 格式选择速查\n| 期刊系列 | 图片格式 | MIME类型 | base64头部特征 |\n|----------|---------|---------|---------------|\n| Nature系列 | PNG | `data:image/png;base64,` | 以 `iVBOR` 开头 |\n| Cell Press系列 | JPEG | `data:image/jpeg;base64,` | 以 `/9j/` 开头 |\n\n### 格式选择指南\n- **Nature系列** → PNG格式,使用 `data:image/png;base64,...`\n- **Cell Press系列** → JPEG格式,使用 `data:image/jpeg;base64,...`\n- **检测技巧**:base64字符串以 `iVBOR` 开头 → PNG;以 `/9j/` 开头 → JPEG\n\n## 关键样式常量\n\n| 元素 | 颜色 |\n|------|------|\n| 头部渐变 | `#1a1a2e → #0f3460` |\n| 标签徽章 | `#e94560` |\n| 卡片阴影 | `0 2px 12px rgba(0,0,0,0.08)` |\n| 评分数字 | `#e94560` |\n| 复选框背景 | `#fff8e1` + 左边框 `#ffc107` |\n| 复现建议 | `#e3f2fd` |\n| 小结卡片 | `#667eea → #764ba2` |\n| 标题左边框 | `#e94560`, 4px |\n\n## 文件命名规则\n\n```\n{主题关键词}_文献解读.html\n```\n示例:`细胞死亡_文献解读.html`、`帕金森_文献解读.html`\n\n## 注意事项\n\n1. canvas渲染:需要`onload`回调,不能直接在`<img>`上设置src(尺寸自适应问题)\n2. 所有图片必须是base64嵌入,不能用file://协议(浏览器安全策略阻止)\n3. 卡片间用`.card`统一间距(margin-bottom:20px)\n4. 长文本用`text-indent:2em`首行缩进增强可读性\n", "file_type": ".md"}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"todos": [{"id": "1", "content": "Step 1: PubMed search - cell death方向, 两阶段策略", "status": "in_progress"}, {"id": "2", "content": "Step 2: 获取论文详情并初筛", "status": "pending"}, {"id": "3", "content": "Step 3: Claude评估候选论文", "status": "pending"}, {"id": "4", "content": "Step 4: 选定唯一推荐论文", "status": "pending"}, {"id": "5", "content": "Step 5: 下载PDF + 提取Figures", "status": "pending"}, {"id": "6", "content": "Step 6: 构建HTML深度解读", "status": "pending"}, {"id": "7", "content": "Step 7: 输出最终结果含MEDIA路径", "status": "pending"}], "summary": {"total": 7, "pending": 6, "in_progress": 1, "completed": 0, "cancelled": 0}}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "Phase A - Broad cell death search: 7447 total papers\r\nPhase B - High IF filtered: 175 total, retrieved 20 PMIDs\r\nPMIDs: 42286001, 42277059, 42275213, 42275212, 42271068, 42270656, 42270655, 42270618, 42269607, 42268710, 42265284, 42259916, 42259813, 42248910, 42243520, 42236947, 42236938, 42236908, 42234560, 42229422\r\n\r\nUser-specific (lactylation+cell death): 48 total, retrieved 10 PMIDs\r\nPMIDs: 42281240, 42275213, 42261902, 42252031, 42245270, 42225083, 42219027, 42214641, 42213229, 42210900\r\n\r\nRhoA + cell death: 21 total, retrieved 10 PMIDs\r\nPMIDs: 42252561, 42233520, 42225681, 42210251, 42146308, 42142140, 42116516, 42102486, 42001081, 41996416\r\n\r\nMetabolism + ferroptosis/cell death: 253 total, retrieved 10 PMIDs\r\nPMIDs: 42286867, 42286802, 42281240, 42280476, 42279699, 42278210, 42277944, 42274843, 42270656, 42268380\r\n\r\n=== Summary ===\r\nTotal unique PMIDs across all searches: 47\r\nAll unique PMIDs: 42265284, 42278210, 41996416, 42275212, 42243520, 42236947, 42275213, 42102486, 42268380, 42233520, 42281240, 42261902, 42001081, 42268710, 42270618, 42225083, 42142140, 42210900, 42245270, 42270655, 42225681, 42259916, 42277059, 42146308, 42116516, 42252561, 42277944, 42213229, 42270656, 42286867, 42214641, 42271068, 42259813, 42286802, 42229422, 42279699, 42274843, 42269607, 42234560, 42210251, 42219027, 42248910, 42236908, 42280476, 42252031, 42236938, 42286001", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "=== Phase B High-IF Papers Details ===\r\nRetrieved 20 papers\r\n\r\nPMID: 42286001\r\n Title: Closed-loop iron chelate recycling via molecularly imprinted hydrogels suppresses ferroptosis....\r\n Journal: Nat Commun\r\n Date: 2026 Jun 12\r\n PubType: Journal Article\r\n DOI: 10.1038/s41467-026-74330-3\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42277059\r\n Title: Natural killer cell-mediated immunosurveillance modulates liver cancer evolution through cancer stemness enhancement and...\r\n Journal: Nat Commun\r\n Date: 2026 Jun 11\r\n PubType: Journal Article\r\n DOI: 10.1038/s41467-026-74360-x\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42275213\r\n Title: High glucose impairs cognitive function by inducing lipid droplet accumulation through lactylation of HSD17B10 at K105....\r\n Journal: Cell Rep\r\n Date: 2026 Jun 11\r\n PubType: Journal Article\r\n DOI: 10.1016/j.celrep.2026.117550\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42275212\r\n Title: Starvation-induced phosphorylation activates gasdermin A to initiate pyroptosis....\r\n Journal: Cell Rep\r\n Date: 2026 Jun 11\r\n PubType: Published Erratum\r\n DOI: 10.1016/j.celrep.2026.117594\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42271068\r\n Title: Endogenous expression and subcellular localization of core apoptosis regulators reveal key differences between embryonic...\r\n Journal: Cell Death Differ\r\n Date: 2026 Jun 10\r\n PubType: Journal Article\r\n DOI: 10.1038/s41418-026-01776-9\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42270656\r\n Title: Infection-induced glucose starvation triggers NINJ1-dependent macrophage lysis and Candida escape....\r\n Journal: Nat Commun\r\n Date: 2026 Jun 10\r\n PubType: Journal Article\r\n DOI: 10.1038/s41467-026-74195-6\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42270655\r\n Title: FERONIA defines intact tissue boundaries through cuticle development....\r\n Journal: Nat Commun\r\n Date: 2026 Jun 10\r\n PubType: Journal Article\r\n DOI: 10.1038/s41467-026-74179-6\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42270618\r\n Title: Mechanistic insights into activation of bacterial Retron-Eco8 immunity by phage protein SSB....\r\n Journal: Nat Commun\r\n Date: 2026 Jun 10\r\n PubType: Journal Article\r\n DOI: 10.1038/s41467-026-74106-9\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42269607\r\n Title: DNA repair drives cisplatin-induced neuronal death....\r\n Journal: Cell\r\n Date: 2026 Jun 10\r\n PubType: Journal Article\r\n DOI: 10.1016/j.cell.2026.05.025\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42268710\r\n Title: STING-OPTN signaling confers cytoprotection through TBK1-dependent mitophagy....\r\n Journal: Cell Rep\r\n Date: 2026 Jun 9\r\n PubType: Journal Article\r\n DOI: 10.1016/j.celrep.2026.117515\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42265284\r\n Title: GBP1 recruitment to actin-rich pedestals of extracellular Gram-negative bacteria promotes pyroptosis....\r\n Journal: EMBO J\r\n Date: 2026 Jun 9\r\n PubType: Journal Article\r\n DOI: 10.1038/s44318-026-00830-z\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42259916\r\n Title: Targeting Cancer-Specific Mutations with RNA-Triggered Chromatin Shredding....\r\n Journal: Nature\r\n Date: 2026 Jun 8\r\n PubType: Journal Article\r\n DOI: 10.1038/s41586-026-10738-7\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42259813\r\n Title: Mycobacterium tuberculosis IDH-PPARγ interaction suppresses GPX4 to drive macrophage ferroptosis and sustain persistent ...\r\n Journal: Nat Commun\r\n Date: 2026 Jun 8\r\n PubType: Journal Article\r\n DOI: 10.1038/s41467-026-74032-w\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42248910\r\n Title: HMGCS1 drives cholesterol-dependent membrane repair and shields tumor cells from lymphocyte attack....\r\n Journal: Nat Commun\r\n Date: 2026 Jun 5\r\n PubType: Journal Article\r\n DOI: 10.1038/s41467-026-74022-y\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42243520\r\n Title: Somatic cells compartmentalise their carbohydrate metabolism to sustain germ cell survival....\r\n Journal: EMBO J\r\n Date: 2026 Jun 4\r\n PubType: Journal Article\r\n DOI: 10.1038/s44318-026-00815-y\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42236947\r\n Title: Spermine is an endogenous iron chelator that inhibits ferroptosis....\r\n Journal: Nature\r\n Date: 2026 Jun 3\r\n PubType: Journal Article\r\n DOI: 10.1038/s41586-026-10597-2\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42236938\r\n Title: Cold-induced peptide signalling secures pollen resilience and crop yield....\r\n Journal: Nature\r\n Date: 2026 Jun 3\r\n PubType: Journal Article\r\n DOI: 10.1038/s41586-026-10603-7\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42236908\r\n Title: Cell death-induced release of the pro-aging protein acyl CoA binding protein (ACBP) into the circulation....\r\n Journal: Cell Death Differ\r\n Date: 2026 Jun 3\r\n PubType: Journal Article\r\n DOI: 10.1038/s41418-026-01775-w\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42234560\r\n Title: Synchronous spatiotemporal control of autophagy and organelle trafficking is necessary for infection by Magnaporthe oryz...\r\n Journal: Cell Rep\r\n Date: 2026 Jun 3\r\n PubType: Journal Article\r\n DOI: 10.1016/j.celrep.2026.117396\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\nPMID: 42229422\r\n Title: Explosive cytotoxicity of ruptoblasts bridges hormone surveillance and immune defense....\r\n Journal: Cell\r\n Date: 2026 Jun 2\r\n PubType: Journal Article\r\n DOI: 10.1016/j.cell.2026.05.008\r\n Authors: N/A\r\n Is Review: False\r\n Is Comment/News: False\r\n\r\n\r\n=== After initial filtering ===\r\nCandidates (non-review, non-comment): 20\r\n PMID: 42286001 | Closed-loop iron chelate recycling via molecularly imprinted hydrogels suppresses ferroptosis....\r\n PMID: 42277059 | Natural killer cell-mediated immunosurveillance modulates liver cancer evolution through cancer stem...\r\n PMID: 42275213 | High glucose impairs cognitive function by inducing lipid droplet accumulation through lactylation o...\r\n PMID: 42275212 | Starvation-induced phosphorylation activates gasdermin A to initiate pyroptosis....\r\n PMID: 42271068 | Endogenous expression and subcellular localization of core apoptosis regulators reveal key differenc...\r\n PMID: 42270656 | Infection-induced glucose starvation triggers NINJ1-dependent macrophage lysis and Candida escape....\r\n PMID: 42270655 | FERONIA defines intact tissue boundaries through cuticle development....\r\n PMID: 42270618 | Mechanistic insights into activation of bacterial Retron-Eco8 immunity by phage protein SSB....\r\n PMID: 42269607 | DNA repair drives cisplatin-induced neuronal death....\r\n PMID: 42268710 | STING-OPTN signaling confers cytoprotection through TBK1-dependent mitophagy....\r\n PMID: 42265284 | GBP1 recruitment to actin-rich pedestals of extracellular Gram-negative bacteria promotes pyroptosis...\r\n PMID: 42259916 | Targeting Cancer-Specific Mutations with RNA-Triggered Chromatin Shredding....\r\n PMID: 42259813 | Mycobacterium tuberculosis IDH-PPARγ interaction suppresses GPX4 to drive macrophage ferroptosis and...\r\n PMID: 42248910 | HMGCS1 drives cholesterol-dependent membrane repair and shields tumor cells from lymphocyte attack....\r\n PMID: 42243520 | Somatic cells compartmentalise their carbohydrate metabolism to sustain germ cell survival....\r\n PMID: 42236947 | Spermine is an endogenous iron chelator that inhibits ferroptosis....\r\n PMID: 42236938 | Cold-induced peptide signalling secures pollen resilience and crop yield....\r\n PMID: 42236908 | Cell death-induced release of the pro-aging protein acyl CoA binding protein (ACBP) into the circula...\r\n PMID: 42234560 | Synchronous spatiotemporal control of autophagy and organelle trafficking is necessary for infection...\r\n PMID: 42229422 | Explosive cytotoxicity of ruptoblasts bridges hormone surveillance and immune defense....", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "================================================================================\r\nPMID: 42275213 [Lactylation-CellRep]\r\nTitle: High glucose impairs cognitive function by inducing lipid droplet accumulation through lactylation of HSD17B10 at K105.\r\nJournal: N/A\r\nDOI: N/A\r\nAuthors: 13\r\nAbstract: High glucose is known to impair cognitive function in individuals with type 2 diabetes, though the precise mechanisms remain unclear. In this study, guided by lactylome analysis, we demonstrate that high glucose induces HSD17B10 K105 lactylation in hippocampal neurons by upregulating lactyltransferase Aars1, which reduces HSD17B10 enzyme activity, subsequently resulting in impaired breakdown and excessive accumulation of lipid droplets, and ultimately leading to neuronal apoptosis and cognitive ...\r\n================================================================================\r\n\r\n================================================================================\r\nPMID: 42236947 [Spermine-Ferroptosis-Nature]\r\nTitle: Spermine is an endogenous iron chelator that inhibits ferroptosis.\r\nJournal: N/A\r\nDOI: N/A\r\nAuthors: 16\r\nAbstract: Ferroptosis is an iron-dependent form of cell death driven by lipid peroxidation1. Here we identify spermine-a polyamine derived from spermidine2-as an endogenous iron chelator that directly suppresses ferroptosis. Integrating metabolomics, stable isotope tracing and biophysical studies of the interaction between spermine and Fe2+ ions, we demonstrate that aldehyde dehydrogenase 18 family member A1 (ALDH18A1) promotes an alternative glutamine-dependent pathway for de novo spermine synthesis...\r\n================================================================================\r\n\r\n================================================================================\r\nPMID: 42229422 [Ruptoblasts-Cell]\r\nTitle: Explosive cytotoxicity of ruptoblasts bridges hormone surveillance and immune defense.\r\nJournal: N/A\r\nDOI: N/A\r\nAuthors: 10\r\nAbstract: Current understanding of cytotoxic immunity is shaped by hematopoietic-derived cells-T cells, natural killer cells, and neutrophils. Here, we identify \"ruptoblasts,\" a previously unknown cytotoxic glandular cell type in regenerative planarian flatworms. Ruptoblasts undergo an explosive cell death, \"ruptosis,\" triggered by activin, a multifunctional hormone acting as an inflammatory cytokine. Excessive activin-induced through protein injection, genetic chimerism, or bacterial infection-initiates ...\r\n================================================================================\r\n\r\n================================================================================\r\nPMID: 42259813 [TB-IDH-ferroptosis-NatCommun]\r\nTitle: Mycobacterium tuberculosis IDH-PPARγ interaction suppresses GPX4 to drive macrophage ferroptosis and sustain persistent infection.\r\nJournal: N/A\r\nDOI: N/A\r\nAuthors: 28\r\nAbstract: Mycobacterium tuberculosis (M.tb) actively reprograms host lipid metabolism during infection; however, the underlying mechanism remains poorly understood. How M.tb manipulates macrophage lipid metabolism to induce lipid peroxidation and ferroptosis for bacterial persistence remains a fundamental question. Here, using single-cell RNA sequencing and proteomics, we show that M.tb infection substantially upregulates peroxisome proliferator-activated receptor gamma (PPARγ) in macrophages. Mecha...\r\n================================================================================\r\n\r\n================================================================================\r\nPMID: 42248910 [HMGCS1-membrane-repair-NatCommun]\r\nTitle: HMGCS1 drives cholesterol-dependent membrane repair and shields tumor cells from lymphocyte attack.\r\nJournal: N/A\r\nDOI: N/A\r\nAuthors: 20\r\nAbstract: Cytotoxic lymphocytes use perforin to form plasma membrane (PM) pores in tumor cells, thereby enabling granzyme-mediated cell death. However, whether and how tumor metabolism enables PM repair to evade immunity is unclear. In this study, using a functional screen targeting 111 metabolic enzymes, we identified hydroxymethylglutaryl-CoA synthase 1 (HMGCS1) as critical for repairing perforin-induced PM damage. HMGCS1 promotes PM repair by initiating de novo cholesterol synthesis, enhancing tumor ce...\r\n================================================================================\r\n\r\n================================================================================\r\nPMID: 42270656 [Glucose-starvation-NINJ1-NatCommun]\r\nTitle: Infection-induced glucose starvation triggers NINJ1-dependent macrophage lysis and Candida escape.\r\nJournal: N/A\r\nDOI: N/A\r\nAuthors: 24\r\nAbstract: Pathogens compete for glucose with macrophages, which disrupts host glycolysis, modulates antimicrobial responses and causes macrophage death. We show that glucose starvation induced by major fungal pathogens Candida albicans and Candida auris causes macrophage lysis by activating NINJ1, the executioner of membrane rupture during cell death. In glucose-starved macrophages, NINJ1 ruptures membranes independently of known cell death programs. Consistently, NINJ1 is the dominant effector of fungal-...\r\n================================================================================\r\n\r\n================================================================================\r\nPMID: 42269607 [Cisplatin-neuronal-death-Cell]\r\nTitle: DNA repair drives cisplatin-induced neuronal death.\r\nJournal: N/A\r\nDOI: N/A\r\nAuthors: 24\r\nAbstract: Platinum agents are cornerstone therapies for many cancers but often cause neurotoxicity in post-mitotic tissues, for which effective interventions are lacking. This limitation reflects an incomplete understanding of neuronal responses to DNA damage. We show that nucleotide excision repair (NER) mediates cisplatin lesion removal in neurons; however, unlike its protective role in dividing cells, NER promotes neuronal death in response to cisplatin. This vulnerability arises because neurons posses...\r\n================================================================================\r\n\r\n================================================================================\r\nPMID: 42268710 [STING-OPTN-mitophagy-CellRep]\r\nTitle: STING-OPTN signaling confers cytoprotection through TBK1-dependent mitophagy.\r\nJournal: N/A\r\nDOI: N/A\r\nAuthors: 15\r\nAbstract: The cyclic GMP-AMP synthase (cGAS)-stimulator of interferon genes (STING) pathway plays an essential role in innate immunity. While recent studies have revealed its critical role in non-canonical autophagy independent of its immune function, its role in selective autophagy remains elusive. Here, we identify the cGAS-STING pathway as an upstream positive regulator of mitophagy. We demonstrate that activation of TANK-binding kinase 1 (TBK1) during mitophagy is strictly dependent on the cGAS-STING ...\r\n================================================================================\r\n\r\n================================================================================\r\nPMID: 42286001 [Iron-chelate-ferroptosis-NatCommun]\r\nTitle: Closed-loop iron chelate recycling via molecularly imprinted hydrogels suppresses ferroptosis.\r\nJournal: N/A\r\nDOI: N/A\r\nAuthors: 9\r\nAbstract: Ferroptosis, an iron-dependent form of oxidative cell death, has emerged as a key driver of osteoarthritis, yet therapeutic strategies remain limited by the inability to safely eliminate iron-chelate complexes after treatment. Their local accumulation can lead to secondary iron release, oxidative stress, and sustained tissue damage. This study presents a hydrogel-based system that enables selective recognition and removal of these complexes through engineered molecular \"memory\" sites. By encodin...\r\n================================================================================\r\n\r\n================================================================================\r\nPMID: 42265284 [GBP1-pyroptosis-EMBO]\r\nTitle: GBP1 recruitment to actin-rich pedestals of extracellular Gram-negative bacteria promotes pyroptosis.\r\nJournal: N/A\r\nDOI: N/A\r\nAuthors: 21\r\nAbstract: The IFNγ-induced GTPase guanylate-binding protein 1 (GBP1) binds to lipopolysaccharide (LPS) on cytosolic gram-negative bacteria and promotes pyroptosis via the recruitment and activation of caspase-4 on the bacterial outer membrane. Enteropathogenic and enterohaemorrhagic Escherichia coli (EPEC and EHEC, respectively) are extracellular pathogens that adhere to host cells and stimulate dense actin polymerisation underneath their attachment sites, generating structures described as actin-ri...\r\n================================================================================\r\n\r\n================================================================================\r\nPMID: 42236908 [ACBP-cell-death-aging-CDD]\r\nTitle: Cell death-induced release of the pro-aging protein acyl CoA binding protein (ACBP) into the circulation.\r\nJournal: N/A\r\nDOI: N/A\r\nAuthors: 22\r\nAbstract: Acyl-CoA-binding protein (ACBP, encoded by diazepam binding inhibitor, DBI) is an abundant intracellular regulator of lipid metabolism that also circulates systemically, yet the mechanisms governing its release and its relationship to organ injury remain unresolved. Herein, we combine human multi-omics, mechanistic mouse models and controlled cell death assays to identify cell death-driven liberation of intracellular ACBP/DBI as a unifying mechanism underlying its elevation in disease. In a coho...\r\n================================================================================", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "PMID: 42281240\r\nTitle: Intratumor Lactobacillus drives ferroptosis resistance via D-lactate-STAT3 K631 lactylation in esophageal squamous cell carcinoma.\r\nJournal: N/A\r\nAuthors: 17 | Review: False\r\nAbstract: Tumor-resident microbiota are increasingly recognized as active components of the gastrointestinal tumor ecosystem, yet how intratumor bacteria reshape cancer cell stress responses in esophageal squamous cell carcinoma (ESCC) remains unclear. Here, 16S rRNA gene sequencing of 102 multiregional tissu...\r\n\r\nPMID: 42261902\r\nTitle: Targeting Lactate-Driven Stromal Autophagy via MCT1 Disrupts the Immunosuppressive Niche and Sensitizes Pancreatic Cancer to PD-1 Blockade.\r\nJournal: N/A\r\nAuthors: 15 | Review: False\r\nAbstract: Lactate reshapes the tumor microenvironment (TME) through complex communication between cancer and stromal cells. However, it remains undefined whether lactate mediates the interaction between pancreatic cancer (PC) cells and pancreatic stellate cells (PSCs), a significant TME component driving tumo...\r\n\r\nPMID: 42252031\r\nTitle: Neuroprotection by lactate in Parkinson's disease: A novel anti-inflammatory mechanism via 14-3-3 protein lactylation.\r\nJournal: N/A\r\nAuthors: 7 | Review: False\r\nAbstract: Novel therapeutic strategies for Parkinson's disease (PD) are urgently needed. Neuroinflammation is a critical driver of disease progression and represents a promising target for intervention. Emerging evidence highlights lactate as a signaling metabolite that regulates inflammatory responses throug...\r\n\r\nPMID: 42245270\r\nTitle: Lactate Metabolism and Protein Lactylation in Diabetic Kidney Disease: A Narrative Review.\r\nJournal: N/A\r\nAuthors: 8 | Review: True\r\nAbstract: Diabetic Kidney Disease (DKD) is one of the common and serious microvascular complications of diabetes, and the pathogenesis is complex and incompletely understood. Recent studies have shown that lactylation, as a novel form of protein post-translational modification, has been increasingly involved ...\r\n\r\nPMID: 42225083\r\nTitle: Lactylation of lysine396 in TNFRSF25 by lysine acetyltransferase 6B aggravates ferroptosis in metabolic dysfunction-associated steatohepatitis.\r\nJournal: N/A\r\nAuthors: 7 | Review: False\r\nAbstract: Metabolic dysfunction-associated steatohepatitis (MASH) is a severe clinical complication of metabolic syndrome, but effective pharmacological treatments remain scarce. This study investigated the role of lactylation-a novel post-translational modification-in the pathogenesis of MASH, using murine m...\r\n\r\nPMID: 42219027\r\nTitle: Rhein suppresses lactate metabolism and melanoma progression via downregulating LDHA/H3K18 lactylation/PLK1 axis.\r\nJournal: N/A\r\nAuthors: 8 | Review: False\r\nAbstract: An increasing body of evidence suggests that lactate and its associated post-translational modification, lactylation, are critically involved in the aggressive progression of melanoma and represent promising therapeutic targets. Rhein, a bioactive compound derived from rhubarb-a traditional Chinese ...\r\n\r\nPMID: 42214641\r\nTitle: MCT1-mediated lactate transport regulates ferroptosis in ulcerative colitis via histone lactylation.\r\nJournal: N/A\r\nAuthors: 8 | Review: False\r\nAbstract: Ferroptosis, an iron-dependent type of controlled cell death caused by lipid peroxidation, contributes to intestinal epithelial injury in ulcerative colitis (UC). Monocarboxylate transporter 1 (MCT1) is a major monocarboxylate transporter in cells that regulates monocarboxylate metabolism in epithel...\r\n\r\nPMID: 42213229\r\nTitle: H4K8 lactylation-mediated ferroptosis defense drives EGFR-TKI resistance in lung adenocarcinoma.\r\nJournal: N/A\r\nAuthors: 7 | Review: False\r\nAbstract: Acquired resistance to epidermal growth factor receptor (EGFR) tyrosine kinase inhibitors (TKIs) remains a major clinical challenge in non-small cell lung cancer. Emerging evidence indicates that metabolic reprogramming and epigenetic alterations contribute to drug resistance, particularly through t...\r\n\r\nPMID: 42210900\r\nTitle: Deoxynivalenol Impairs Ovarian Function by Triggering Ferroptosis in Granulosa Cells through GPX2 Inhibition and Oxidative Stress.\r\nJournal: N/A\r\nAuthors: 11 | Review: False\r\nAbstract: Deoxynivalenol (DON), a mycotoxin produced by Fusarium species, is a widespread cereal contaminant that impairs swine growth and reproduction. Although DON-induced ovarian dysfunction has been reported, its underlying molecular mechanisms remain incompletely defined. We constructed DON exposure mode...", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "=== Journal Check ===\r\n\r\nPMID: 42281240\r\n Journal: Gut Microbes\r\n DOI: 10.1080/19490976.2026.2685912\r\n PII: \r\n Date: 2026 Dec 31\r\n Title: Intratumor Lactobacillus drives ferroptosis resistance via D-lactate-STAT3 K631 lactylation in esoph\r\n\r\nPMID: 42252031\r\n Journal: Biochim Biophys Acta Mol Basis Dis\r\n DOI: 10.1016/j.bbadis.2026.168314\r\n PII: S0925-4439(26)00177-8\r\n Date: 2026 Jun 6\r\n Title: Neuroprotection by lactate in Parkinson's disease: A novel anti-inflammatory mechanism via 14-3-3 pr\r\n\r\nPMID: 42225083\r\n Journal: Br J Pharmacol\r\n DOI: 10.1111/bph.70517\r\n PII: \r\n Date: 2026 Jun 1\r\n Title: Lactylation of lysine396 in TNFRSF25 by lysine acetyltransferase 6B aggravates ferroptosis in metabo\r\n\r\nPMID: 42214641\r\n Journal: Free Radic Biol Med\r\n DOI: 10.1016/j.freeradbiomed.2026.05.329\r\n PII: S0891-5849(26)00833-6\r\n Date: 2026 May 28\r\n Title: MCT1-mediated lactate transport regulates ferroptosis in ulcerative colitis via histone lactylation.\r\n\r\nPMID: 42213229\r\n Journal: Apoptosis\r\n DOI: 10.1007/s10495-026-02374-3\r\n PII: 10.1007/s10495-026-02374-3\r\n Date: 2026 May 29\r\n Title: H4K8 lactylation-mediated ferroptosis defense drives EGFR-TKI resistance in lung adenocarcinoma.\r\n\r\nPMID: 42219027\r\n Journal: J Adv Res\r\n DOI: 10.1016/j.jare.2026.05.053\r\n PII: S2090-1232(26)00449-2\r\n Date: 2026 May 30\r\n Title: Rhein suppresses lactate metabolism and melanoma progression via downregulating LDHA/H3K18 lactylati\r\n\r\nPMID: 42261902\r\n Journal: Adv Sci (Weinh)\r\n DOI: 10.1002/advs.76008\r\n PII: \r\n Date: 2026 Jun 9\r\n Title: Targeting Lactate-Driven Stromal Autophagy via MCT1 Disrupts the Immunosuppressive Niche and Sensiti\r\n\r\nPMID: 42275213\r\n Journal: Cell Rep\r\n DOI: 10.1016/j.celrep.2026.117550\r\n PII: S2211-1247(26)00628-5\r\n Date: 2026 Jun 11\r\n Title: High glucose impairs cognitive function by inducing lipid droplet accumulation through lactylation o\r\n\r\nPMID: 42236947\r\n Journal: Nature\r\n DOI: 10.1038/s41586-026-10597-2\r\n PII: 10.1038/s41586-026-10597-2\r\n Date: 2026 Jun 3\r\n Title: Spermine is an endogenous iron chelator that inhibits ferroptosis.\r\n\r\nPMID: 42248910\r\n Journal: Nat Commun\r\n DOI: 10.1038/s41467-026-74022-y\r\n PII: 10.1038/s41467-026-74022-y\r\n Date: 2026 Jun 5\r\n Title: HMGCS1 drives cholesterol-dependent membrane repair and shields tumor cells from lymphocyte attack.", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "======================================================================\r\nPMID: 42281240 [Lactobacillus-D-lactate-STAT3 lactylation-ferroptosis-GutMicrobes]\r\nTitle: Intratumor Lactobacillus drives ferroptosis resistance via D-lactate-STAT3 K631 lactylation in esophageal squamous cell carcinoma.\r\nKeywords: \r\nFull Abstract:\r\nTumor-resident microbiota are increasingly recognized as active components of the gastrointestinal tumor ecosystem, yet how intratumor bacteria reshape cancer cell stress responses in esophageal squamous cell carcinoma (ESCC) remains unclear. Here, 16S rRNA gene sequencing of 102 multiregional tissue blocks from 27 patients with ESCC, integrated with untargeted metabolomics, RNA sequencing, and mass spectrometry, identified Lactobacillus, particularly Lactobacillus reuteri, as a tumor-enriched taxon associated with adverse survival. Mechanistic studies in ESCC cell lines and nude-mouse xenografts revealed a distinctive dynamic: in contrast to host-derived L-lactate, L. reuteri-derived D-lactate induced site-specific STAT3 lactylation at lysine 631, thereby promoting STAT3 dimerization and nuclear translocation. This host signaling rewiring upregulated the ferroptosis suppressors GPX4 and FTH1, reduced ferroptotic vulnerability, and enhanced ESCC growth. Disrupting bacterial D-lactate production using a ldhD-deficient L. reuteri mutant or blocking host STAT3 lactylation using STAT3-knockout cells reconstituted with wild-type STAT3 or lactylation-defective STAT3 K631R, abolished the pro-tumor and antiferroptotic effects in vitro and in vivo. Together, these findings define a tumor-resident microbe-metabolite-host signaling axis that links intratumor Lactobacillus to ferroptosis escape. By establishing bacteria-derived D-lactate as the functional driver, the study provides a novel mechanistic framework that extends beyond the classical Warburg effect for developing biomarkers and therapeutic strategies targeting STAT3 lactylation or ferroptosis sensitization. These translatable results emphasize the need for context-specific evaluation of Lactobacillus-containing probiotic supplementation in patients with ESCC.\r\n======================================================================\r\n\r\n======================================================================\r\nPMID: 42248910 [HMGCS1-membrane-repair-NatCommun]\r\nTitle: HMGCS1 drives cholesterol-dependent membrane repair and shields tumor cells from lymphocyte attack.\r\nKeywords: \r\nFull Abstract:\r\nCytotoxic lymphocytes use perforin to form plasma membrane (PM) pores in tumor cells, thereby enabling granzyme-mediated cell death. However, whether and how tumor metabolism enables PM repair to evade immunity is unclear. In this study, using a functional screen targeting 111 metabolic enzymes, we identified hydroxymethylglutaryl-CoA synthase 1 (HMGCS1) as critical for repairing perforin-induced PM damage. HMGCS1 promotes PM repair by initiating de novo cholesterol synthesis, enhancing tumor cell resistance to lymphocyte-mediated killing and impairing the efficacy of NK, CAR-T, and anti-PD-1-based immunotherapies. Beyond its structural role, cholesterol directly binds charged multivesicular body protein 4b (CHMP4B) to enhance its PM localization, facilitating PM repair. Furthermore, oncogenic activation, cytokine, and hypoxia induce c-Jun activation, up-regulating HMGCS1 expression. In lung cancer patients, elevated c-Jun activation, HMGCS1 expression, cholesterol content and PM CHMP4B correlate with reduced anti-PD-1 immunotherapy efficacy. Our findings reveal a tumor immune evasion mechanism wherein HMGCS1 drives cholesterol-dependent PM repair by activating the cholesterol synthesis. Targeting HMGCS1 enhances the effectiveness of immunotherapies.\r\n======================================================================\r\n\r\n======================================================================\r\nPMID: 42236947 [Spermine-ferroptosis-Nature]\r\nTitle: Spermine is an endogenous iron chelator that inhibits ferroptosis.\r\nKeywords: \r\nFull Abstract:\r\nFerroptosis is an iron-dependent form of cell death driven by lipid peroxidation1. Here we identify spermine-a polyamine derived from spermidine2-as an endogenous iron chelator that directly suppresses ferroptosis. Integrating metabolomics, stable isotope tracing and biophysical studies of the interaction between spermine and Fe2+ ions, we demonstrate that aldehyde dehydrogenase 18 family member A1 (ALDH18A1) promotes an alternative glutamine-dependent pathway for de novo spermine synthesis. This process limits iron availability and lipid peroxidation in hepatocellular carcinoma. Genetic or pharmacological inhibition of ALDH18A1-through knockout, short hairpin RNA delivered using adeno-associated virus (AAV), or the small molecule inhibitor YG1702-triggers ferroptosis and impairs both spontaneous and chemically induced hepatocarcinogenesis. Conversely, supplementation of spermine protects against ferroptosis-associated ischaemia-reperfusion injury across multiple tissues, including the liver, intestine and kidneys. These findings uncover a pathophysiologically relevant metabolic circuit in which spermine-mediated iron chelation suppresses ferroptosis.\r\n======================================================================\r\n\r\n======================================================================\r\nPMID: 42219027 [LDHA-lactylation-melanoma-JAdvRes]\r\nTitle: Rhein suppresses lactate metabolism and melanoma progression via downregulating LDHA/H3K18 lactylation/PLK1 axis.\r\nKeywords: \r\nFull Abstract:\r\nAn increasing body of evidence suggests that lactate and its associated post-translational modification, lactylation, are critically involved in the aggressive progression of melanoma and represent promising therapeutic targets. Rhein, a bioactive compound derived from rhubarb-a traditional Chinese medicinal herb-has shown anti-cancer properties in multiple tumor types. Nevertheless, its role in melanoma remains poorly understood. This study investigated the role of Rhein in melanoma and uncovered the underlying mechanism. Cell growth and cell death were investigated by colony formation and Propidium Iodide (PI) Staining. The RNA sequencing analysis was used to identify the altered genes and miRNAs. Targeted Metabolomics Analysis was used to investigate the altered metabolites. In this study, we demonstrate that Rhein effectively suppresses melanoma cell proliferation and migration while inducing apoptosis in vitro, and also inhibits tumor growth in vivo. Moreover, Rhein strengthens the host's anti-tumor immune response and counteracts tumor immune evasion. Mechanistically, Rhein significantly reduces LDHA expression, leading to decrease intracellular and extracellular lactic acid levels. Restoring LDHA expression or supplementing lactate diminishes Rhein's anti-melanoma activity and facilitates immune escape. We further show that Rhein downregulates PLK1 by reducing histone H3K18 lactylation at the PLK1 promoter. Notably, our results reveal that Rhein treatment markedly increases miR-27a-5p expression. Upregulated miR-27a-5p suppresses LDHA, subsequently lowering both lactic acid accumulation and PLK1 levels. Taken together, these data highlight the critical involvement of the miR-27a-5p/LDHA/lactate/PLK1 signaling axis in mediating Rhein's anti-melanoma effects, suggesting its potential as a therapeutic strategy for melanoma.\r\n======================================================================\r\n\r\n======================================================================\r\nPMID: 42261902 [MCT1-lactate-autophagy-AdvSci]\r\nTitle: Targeting Lactate-Driven Stromal Autophagy via MCT1 Disrupts the Immunosuppressive Niche and Sensitizes Pancreatic Cancer to PD-1 Blockade.\r\nKeywords: \r\nFull Abstract:\r\nLactate reshapes the tumor microenvironment (TME) through complex communication between cancer and stromal cells. However, it remains undefined whether lactate mediates the interaction between pancreatic cancer (PC) cells and pancreatic stellate cells (PSCs), a significant TME component driving tumorigenesis. This study elucidates the metabolic crosstalk between PC cells and PSCs underlying lactate-driven tumor progression. Our findings demonstrate that PC cells serve as the primary lactate source in the TME, where lactate induces PSC activation through an autophagy-dependent mechanism mediated by protein lactylation. This activation cascade subsequently upregulates programmed cell death-1 (PD-1) expression in CD8+ T cells, promoting immune evasion. Notably, AZD3965, a specific MCT1 inhibitor, sensitizes orthotopic PC to PD-1 blockade, effectively inhibiting tumor development. Mechanistically, MCT1-mediated lactate influx activates PSCs by inducing lactylation of lysine residues K356 and K781 on Vps34, a key autophagy regulator. Moreover, activated PSCs secrete CXCL9/CXCL10, which upregulates PD-1 expression in CD8+ T cells via the CXCR3/STAT3 pathway. This study establishes lactate as a crucial TME signaling molecule orchestrating PSC activation and an immunosuppressive microenvironment, providing compelling evidence for combining MCT1 inhibition with immune checkpoint blockade for pancreatic cancer.\r\n======================================================================", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "# 两篇论文严格评估\n\n---\n\n## 论文A\n\n**PMID: 42281240** | Gut Microbes (IF ~12.2)\n\n| 维度 | 评分 | 评语 |\n|------|------|------|\n| **逻辑完整性** | **9/10** | Gain (L. reuteri共培养→铁死亡抵抗) / Loss (ldhD缺陷菌株→表型逆转) / 点突变验证 (STAT3 K631R消除效应) 形成完整闭环。唯一小缺憾:未引入STAT3直接抑制剂作为额外反向验证。 |\n| **方法学水平** | **8/10** | 乳酸化修饰检测(pan-anti-lactyllysine + 位点特异性抗体)、细菌遗传学(ldhD敲除)、点突变构建、铁死亡指标(lipid ROS/GPX4/FTH1)均扎实。但整体偏传统分子生物学+生化层面,缺乏单细胞组学、空间代谢组等前沿手段。 |\n| **创新性** | **9/10** | 首次将**瘤内菌群与铁死亡调控**关联;发现D-lactate作为信号分子(非代谢底物)诱导STAT3 K631乳酸化——该位点此前未被鉴定;构建\"菌群→代谢物→新型PTM→转录因子→铁死亡\"的新链条,概念新颖度高。 |\n| **可借鉴性** | **9/10** | \"微生物→代谢物→乳酸化修饰→表型\"的框架高度可迁移。其他研究者可直接移植到:不同瘤种、不同共生菌、不同代谢物、不同底物蛋白。乳酸化研究方法学路径对PTM领域有示范意义。 |\n| **临床转化潜力** | **8/10** | 揭示了STAT3 K631乳酸化作为潜在靶点;靶向瘤内L. reuteri或D-lactate产生有治疗前景。但**瘤内菌群操控的临床可行性**仍是重大瓶颈——如何精准清除特定菌株而不扰乱整体微生态?体内验证虽完整,但距离临床应用路径尚远。 |\n| **总分** | **43/50** | |\n\n---\n\n## 论文B\n\n**PMID: 42248910** | Nature Communications (IF ~16.6)\n\n| 维度 | 评分 | 评语 |\n|------|------|------|\n| **逻辑完整性** | **9/10** | 无偏筛选(111种代谢酶)→命中HMGCS1→Gain/Loss验证→机制解析(胆固醇→CHMP4B→ESCRT膜修复)→上游调控(c-Jun转录激活)→治疗验证(anti-PD-1联用)。因果链条完整。唯一可补:是否在人体肿瘤样本中验证HMGCS1表达与免疫治疗响应的相关性? |\n| **方法学水平** | **9/10** | 功能性代谢酶系统筛选(非靶向)、穿孔素膜损伤修复定量、胆固醇-蛋白结合实验、ESCRT组分(CHMP4B)互作、免疫杀伤功能实验、转录调控验证、免疫治疗联用模型。方法体系现代且多维度,达到Nature Communications标准。 |\n| **创新性** | **9/10** | 提出**\"胆固醇作为免疫攻击后膜修复分子\"**的新概念;首次将HMGCS1与肿瘤免疫逃逸连接;胆固醇-CHMP4B结合促进ESCRT膜修复是机制上的新发现;c-Jun→HMGCS1→胆固醇→膜修复→免疫逃逸轴全新。 |\n| **可借鉴性** | **10/10** | 代谢酶功能筛选策略**可被任何课题组借鉴**到其他表型筛选;\"代谢物→膜修复→免疫逃逸\"的框架适用于穿孔素以外的免疫效应分子(granzyme B、FasL等)、其他ESCRT组分、其他肿瘤类型;胆固醇生物学与免疫的交界面极为广阔。**可迁移性极强。** |\n| **临床转化潜力** | **9/10** | HMGCS1是可靶向代谢酶(甲羟戊酸途径已有临床抑制剂先例);与免疫治疗(anti-PD-1)联用策略直接对应临床痛点——免疫治疗耐药;他汀类药物的重新利用有潜在路径。略欠的是HMGCS1特异性抑制剂尚未进入临床,但转化路径清晰。 |\n| **总分** | **46/50** | |\n\n---\n\n## 最终推荐:**论文B**\n\n### 理由\n\n论文B在以下维度上具有综合优势:\n\n1. **方法论更具示范性**:无偏功能筛选(111种代谢酶) vs 论文A的候选菌株/分子策略,前者的发现路径可被其他课题组直接复用。\n\n2. **可借鉴性更强**:\"代谢→膜修复→免疫逃逸\"是一个更普适的框架,可快速迁移到穿孔素以外的杀伤机制、其他ESCRT组分、多种实体瘤。论文A的\"菌群→乳酸化\"虽新颖,但操作门槛(瘤内菌群研究)限制了迁移广度。\n\n3. **临床转化路径更清晰**:HMGCS1属于甲羟戊酸途径——该通路已有他汀类药物的丰富临床经验;与免疫治疗联用直接对应\"克服免疫耐药\"的临床刚需。论文A的\"靶向特定瘤内菌株\"在临床执行层面面临更大的不确定性。\n\n4. **发表平台与影响力**:Nature Communications (IF 16.6) 在免疫学/癌症生物学领域的影响力通常比 Gut Microbes (IF 12.2) 更广泛。\n\n两篇均为优秀工作,但论文B在**方法通用性、框架迁移能力和转化可行路径**三个维度上更胜一筹。\n\n---\n\n**论文A: 43/50 ┃ 论文B: 46/50**", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"todos": [{"id": "1", "content": "Step 1: PubMed search - cell death方向, 两阶段策略", "status": "completed"}, {"id": "2", "content": "Step 2: 获取论文详情并初筛", "status": "completed"}, {"id": "3", "content": "Step 3: Claude评估候选论文", "status": "completed"}, {"id": "4", "content": "Step 4: 选定唯一推荐论文 - PMID 42248910 HMGCS1 membrane repair Nat Commun", "status": "completed"}, {"id": "5", "content": "Step 5: 下载PDF + 提取Figures - PMID 42248910", "status": "in_progress"}, {"id": "6", "content": "Step 6: 构建HTML深度解读", "status": "pending"}, {"id": "7", "content": "Step 7: 输出最终结果含MEDIA路径", "status": "pending"}], "summary": {"total": 7, "pending": 2, "in_progress": 1, "completed": 4, "cancelled": 0}}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "Cleaned up old files\nTitle: HMGCS1 drives cholesterol-dependent membrane repair and shields tumor cells from lymphocyte attack\r\nDate: N/A\r\nJournal: Nature Communications\r\nAuthors: Zhang, Yajuan; Wang, Siyao; Luo, Tianhang; Yang, Haitang; Wang, Yongqiang...\r\nDOI: 10.1038/s41467-026-74022-y", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "=== Downloading PDF ===\n/c/Users/forgase/s41467-026-74022-y.pdf: HTML document, ASCII text, with very long lines (30550)", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "=== Auto-detect figure count ===\nFig1: HTTP 200\nFig2: HTTP 200\nFig3: HTTP 200\nFig4: HTTP 200\nFig5: HTTP 200\nFig6: HTTP 200\nLast figure found: Fig6\n\n=== Downloading all figures ===\nDownloaded Fig1\nDownloaded Fig2\nDownloaded Fig3\nDownloaded Fig4\nDownloaded Fig5\nDownloaded Fig6\n\n=== Verification ===\nFig1: OK (978680 bytes)\nFig2: OK (586160 bytes)\nFig3: OK (925860 bytes)\nFig4: OK (731588 bytes)\nFig5: OK (557852 bytes)\nFig6: OK (989040 bytes)", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "Found 0 figcaptions", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "Unedited version marker: True\r\nFigcaptions found (alt method): 0\r\nNo inline figure references\r\nFig refs in body: []", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "Longest text div:\r\nAbout the journal\r\n \r\n \r\n \r\n \r\n Aims & Scope\r\n \r\n \r\n \r\n \r\n \r\n Editors\r\n \r\n \r\n \r\n \r\n \r\n Journal Information\r\n \r\n \r\n \r\n \r\n \r\n Open Access Fees and Funding\r\n \r\n \r\n \r\n \r\n \r\n Calls for Papers\r\n \r\n \r\n \r\n \r\n \r\n Editorial Values Statement\r\n \r\n \r\n \r\n \r\n \r\n Journal Metrics", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"bytes_written": 16156, "dirs_created": true, "lint": {"status": "ok", "output": ""}, "resolved_path": "C:\\Users\\forgase\\build_html_celldeath.py", "files_modified": ["C:\\Users\\forgase\\build_html_celldeath.py"]}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "Loaded 6 figures\r\n fig1: 978680 bytes\r\n fig2: 586160 bytes\r\n fig3: 925860 bytes\r\n fig4: 731588 bytes\r\n fig5: 557852 bytes\r\n fig6: 989040 bytes\r\n\r\nHTML written to: C:/Users/forgase/Desktop/细胞死亡_文献解读.html\r\nFile size: 4,784,641 bytes (4.6 MB)\r\nDone!", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"output": "-rw-r--r-- 1 forgase 197121 4784641 6月 14 13:05 /c/Users/forgase/Desktop/细胞死亡_文献解读.html", "exit_code": 0, "error": null}
assistant · 2026-06-14 13:05
tool · 2026-06-14 13:05
{"todos": [{"id": "1", "content": "Step 1: PubMed search - cell death方向, 两阶段策略", "status": "completed"}, {"id": "2", "content": "Step 2: 获取论文详情并初筛", "status": "completed"}, {"id": "3", "content": "Step 3: Claude评估候选论文", "status": "completed"}, {"id": "4", "content": "Step 4: 选定唯一推荐论文 - PMID 42248910 HMGCS1 membrane repair Nat Commun", "status": "completed"}, {"id": "5", "content": "Step 5: 下载PDF + 提取Figures - PMID 42248910", "status": "completed"}, {"id": "6", "content": "Step 6: 构建HTML深度解读", "status": "completed"}, {"id": "7", "content": "Step 7: 输出最终结果含MEDIA路径", "status": "completed"}], "summary": {"total": 7, "pending": 0, "in_progress": 0, "completed": 7, "cancelled": 0}}
assistant · 2026-06-14 13:05
🔥 **13:00 细胞死亡方向论文推荐**
🏆 **HMGCS1 drives cholesterol-dependent membrane repair and shields tumor cells from lymphocyte attack**
📅 2026-06-05 | 📰 **Nature Communications** (IF 16.6)
⭐ **Claude评分:46/50** ← 5维度全部≥9分
💡 **推荐理由**
本研究通过功能筛选111种代谢酶,发现HMGCS1通过胆固醇合成修复穿孔素引起的质膜损伤,使肿瘤细胞抵抗NK、CAR-T和免疫治疗。**与你的博一课题高度相关**——肿瘤细胞主动修复质膜损伤逃避免疫杀伤,与你的"乳酸/RhoA使线粒体远离质膜拮抗mitoxyperiosis"在概念上遥相呼应。本文的代谢酶无偏筛选策略、PM repair定量体系和体内免疫治疗模型均可直接借鉴。
**五大亮点**:
1. ✅ **代谢酶功能筛选** — 可复用于你的mitoxyperiosis课题:筛选影响该死亡通路的代谢节点
2. ✅ **质膜修复与胆固醇代谢** — 线粒体-质膜接触是否依赖膜组分改变?值得深挖
3. ✅ **ESCRT-CHMP4B通路** — RhoA乳酸化是否影响ESCRT亚基的膜招募?
4. ✅ **免疫杀伤体内模型** — NK/CAR-T/anti-PD-1联用范式,可直接用于验证
5. ✅ **临床样本验证** — 多维分析策略(蛋白+代谢物+膜定位+预后),可用于PD患者样本
📊 **评分详情**:逻辑完整性9/10 | 方法学9/10 | 创新性9/10 | **可借鉴性10/10** 🔥 | 转化潜力9/10
MEDIA:C:\Users\forgase\Desktop\细胞死亡_文献解读.html