COMPASS
Quick actions
Impact Factor Distribution 2026 JCR
Recent reports
🔬 COMPASS Keywords
Click to select · Type above
| # | Title ↕ | PMID | Journal | Year ↕ | IF ↕ | Status |
|---|
Papers PharosDBIF source: 2026 JCR
| # | Title | PMID | Journal | IF | Cit. | Topics | Type | Pub Date | Source | Score | OA |
|---|
BioMind 生物智研
Research TrendsAvg IF source: 2026 JCR
📈 Publication Volume by Year
📊 Avg Impact Factor by Year
🔬 Publications by Topic
⭐ IF Distribution Trend
🏆 Top High-IF Journals (2024-2026)
| # | Journal | Papers | Avg IF |
|---|
🔍 Cross-Topic Intersections
🌱 Emerging Keywords (2025-2026)
📈 Topic Growth & Gap Analysis
Author & Institution NetworkAvg IF source: 2026 JCR
👤 Top Authors
🏛 Top Institutions
🔗 Co-Authorship Network (Top Authors)
Research Teams & Rising StarsIF source: 2026 JCR
Knowledge Explorer
Cross-dimensional literature mining. Filter by one dimension, see relationships to another. Click any result to drill down to papers.
Disease × Pipeline Stage
Reports
Subscribe & custom search
Email subscription
Subscriber overview
Check / Unsubscribe
Settings
API services powering this platform — and how to bring your own keys.
Service Status
Use Your Own API Key
By default, this platform uses server-configured keys. Keys are stored per-session, never persisted.
Apply & Test will verify your key. If it fails, the platform falls back to the server default.
Usage
| Service | When Used |
|---|---|
| LLM API | Report generation, Q&A AI |
| NCBI E-utilities | Paper search & metadata |
| Semantic Scholar | Citation tracking |
| Embedding Model | Knowledge base indexing (local) |
| SMTP Email | Report delivery (server-managed) |
SMTP email uses the platform's server-configured account — users cannot override this.
Help & Guide
What is this platform?这是什么平台？
COMPASS (COMPutational biology Agent for Pharmaceutical Sciences) — an automated pipeline that continuously monitors the intersection of computational biology and pharmaceutical R&D. It searches PubMed daily, downloads papers, builds a searchable knowledge base, generates bilingual review reports, and delivers them to subscribers via email.
Built on PharosDB (structured DB) and AetherBase (vector KB). Full statistics report →
COMPASS（COMPutational biology Agent for Pharmaceutical Sciences，面向药物科学的计算生物学智能体）—— 一条自动化流水线，持续监测计算生物学与药物研发的交汇领域。它每日检索 PubMed、下载论文、构建可检索的知识库、生成双语综述报告，并通过邮件推送给订阅者。
构建于 PharosDB（结构化数据库）与 AetherBase（向量知识库）之上。完整统计报告 →
Page Guide页面导览
Dashboard
Global overview: paper trends, hot topics, recent reports, and an AI-powered Ask KB Q&A panel.
Papers
Browse and search all 69,000+ papers in PharosDB. Filter by year, impact factor, topic, or free text. Click any paper for full details.
Knowledge Explorer
Cross-dimensional mining: pick two dimensions (e.g. Disease × Method) to see distribution, sparklines, and heatmaps. Click any cell to drill into papers.
Network
Interactive co-authorship graph showing top researchers and their collaborations. Filter by topic, click nodes to explore connections.
Teams
Top 30 research teams globally, detected via co-authorship community analysis. Rising stars, research series, and team-level collaboration networks.
Reports
AI-generated bilingual review reports. Filter by type (weekly/monthly/trends), preview in-browser, download as .md/.html/.pdf.
Subscribe
Sign up for weekly or monthly email reports. Check your subscription status or unsubscribe anytime. No email addresses are publicly visible.
Settings
View platform service status. Bring your own LLM or NCBI API key — apply & test, and the key will only be used for your session.
总览 Dashboard
全局概览：论文趋势、热点主题、最新报告，以及 AI 驱动的知识库问答面板。
论文库 Papers
浏览并检索 PharosDB 中的 69,000+ 篇论文。可按年份、影响因子、主题或自由文本筛选。点击任意论文查看详情。
知识图谱探索 Explorer
跨维度挖掘：选择两个维度（如 疾病 × 方法），查看分布、迷你趋势图与热力图。点击任意单元格可下钻到论文。
网络 Network
交互式共著网络图，展示顶尖研究者及其合作关系。可按主题筛选，点击节点探索关联。
团队 Teams
基于共著社区分析发现的全球 Top 30 研究团队，含新星、研究系列与团队级合作网络。
报告 Reports
AI 生成的双语综述报告。可按类型（周报 / 月报 / 趋势）筛选，在线预览，下载 .md / .html / .pdf。
订阅 Subscribe
订阅周报或月报邮件，随时查询订阅状态或退订。邮箱地址不会公开显示。
设置 Settings
查看平台服务状态。可使用自己的 LLM 或 NCBI API Key —— 应用并测试后，密钥仅用于你的会话。
📊 Ranking & Scoring (Network)排名与评分（网络）
Top Authors and Top Institutions are ranked by a composite score that weighs the author's role in each paper, together with the paper's impact factor and its citation count.
Contribution = Weight × (1 + 0.1 × IF) × (1 + 0.5 × log₁₀(1 + Citations))
Co-author papers (weight 0.3, no citation boost):
Contribution = Weight × (1 + 0.1 × IF)
Role Weight:
• First author / corresponding author — 1.0 (lead)
• Co-first author — 0.8 (lead)
• Other co-author — 0.3 (no citation boost)
IF = journal impact factor of the paper, sourced from the 2026 JCR (Journal Citation Reports).
Citations = total citations, log-scaled (log₁₀) to dampen outliers. The citation boost applies only to lead papers — citations reflect the contribution of the leading authors, so a 0-lead co-author cannot outrank a first/corresponding author via high citations alone.
Author disambiguation & quality control. Authors are merged across name variants and ORCIDs; institutions are normalized to parent entities (e.g. Harvard-affiliated hospitals → Harvard University; Max Planck institutes → Max Planck Society) so scores are not diluted by fragmentation. Papers classified as News / Interview / Editorial are excluded from ranking, so journal staff writers do not appear as researchers. An author's primary institution follows the same platform-wide rule as Teams (see below): ORCID-first, then the mode of the first-listed affiliation across research papers from the last two calendar years.
Topic view. When a domain (topic) filter is active, the Score is re-computed from the author's/institution's papers in that domain only (same formula above, over that topic's papers), so the same author shows a different score in each topic, and the list is ranked by that domain score (descending). Authors with no lead contribution in the domain get score 0 and sink. The all-topics view shows the overall composite score.
顶尖作者与顶尖机构按综合评分排序；该评分同时考量作者在每篇论文中的角色，以及论文的影响因子和被引次数。
贡献值 = 权重 × (1 + 0.1 × IF) × (1 + 0.5 × log₁₀(1 + 被引次数))
合著论文（权重 0.3，不放大引用）：
贡献值 = 权重 × (1 + 0.1 × IF)
角色权重：
• 第一作者 / 通讯作者 —— 1.0（主导）
• 共同第一作者 —— 0.8（主导）
• 其他合著者 —— 0.3（不放大引用）
IF = 论文所在期刊的影响因子，取自 2026 JCR（Journal Citation Reports）。
被引次数 = 总被引次数，取对数（log₁₀）以抑制离群值。引用放大仅对主导论文生效 —— 引用反映的是主导作者的贡献，因此零主导贡献的合著者无法仅凭高被引超越第一 / 通讯作者。
作者消歧与质量控制。平台跨姓名变体与 ORCID 合并同一作者；机构归一到上级实体（如 哈佛附属医院 → 哈佛大学；马克斯·普朗克各研究所 → 马克斯·普朗克学会），避免评分被碎片化稀释。被归类为新闻 / 访谈 / 社论的论文不计入排名，以免期刊编辑与撰稿人被当作研究者。作者的主要单位遵循与「团队」一致的平台级规则（见下）：ORCID 优先，其次取近两个自然年度研究论文中第一署名单位的众数。
主题视图。当启用领域（主题）筛选时，评分仅基于该作者 / 机构在该领域下的论文重新计算（公式同上，只是作用域变为该主题论文），因此同一作者在不同主题下显示不同评分，榜单按该领域评分降序排列。在该领域无主导贡献的作者评为 0 分并沉底；全部主题视图显示综合评分。
🏛 Team Scoring (Research Teams)团队评分（研究团队）
Teams are detected from the co-authorship graph with a two-level split: Louvain communities first, then large communities (≥50 members, institution-level collaboration circles) are re-split into PI-centric research groups. Each team is ranked by its composite score, which rewards papers where the team holds lead authorship and weights in the journal impact factor.
Paper Weight:
• Paper has a team lead (first / corresponding author among team members) — 1.0
• Team members appear only as regular co-authors — 0.3
IF = journal impact factor of the paper (0 when unknown), sourced from the 2026 JCR (Journal Citation Reports).
Lead papers = papers where at least one team member holds first or corresponding authorship.
Total papers = all papers involving any team member.
Team discovery (two-level split). ① Level 1 — run Louvain community detection on the co-authorship graph (edges = ≥2 shared papers), keep communities with ≥3 members and ≥5 papers. ② Level 2 — for each large community (≥50 members), split it into PI-centric groups: PI candidates are members with ≥5 lead papers (first / corresponding); each other member joins the PI with whom they share the most co-authored papers, requiring ≥3 shared papers; members without a ≥3-paper link merge into the nearest PI (highest co-authorship, fallback = PI with most lead papers); groups with fewer than 3 members after splitting are dropped; communities with no clear PI core are kept whole. Teams are named "<Lead Author> Group". All qualified groups are written to the JSON artifacts under data/teams/ (teams.json plus the per-level teams_*.json), which the platform reads directly, while this page displays the top 30 by Team Score.
Teams are displayed in descending Team Score order. Under a domain (topic) filter, the Team Score is re-computed over that domain's papers only (same formula), paper / lead counts are rewritten to domain-level numbers, and teams are ranked by the domain score. Teams with no papers in the domain are hidden. Note: unlike the author score, the team score does not yet include a citation term.
Author institution labeling. ① Authors with an ORCID — institution is resolved from the papers under that ORCID identity (the platform stores no separate ORCID registry, so the ORCID's own research papers are the authoritative source, merging across name variants); ② Authors without affiliation info — institution comes from their research-paper affiliations; ③ When multiple institutions exist — take the mode of the first-listed affiliation across papers published in the last two calendar years, falling back to all papers when no papers fall in that window; ties are broken by the most recent year, then alphabetically. This prevents a single recent joint affiliation (e.g. a co-supervised paper) from overriding an author's primary institution.
团队从共著网络中识别，采用两级切分：先做 Louvain 社区发现，再把大型社区（≥50 人，属机构级合作圈）重新切分为以 PI 为核心的研究组。每个团队按其综合评分排序；该评分奖励团队持有主导署名的论文，并计入期刊影响因子。
论文权重：
• 论文有团队主导作者（团队成员中的第一 / 通讯作者）—— 1.0
• 团队成员仅以普通合著者身份出现 —— 0.3
IF = 论文所在期刊的影响因子（未知时按 0），取自 2026 JCR（Journal Citation Reports）。
主导论文 = 至少有一位团队成员担任第一或通讯作者的论文。
论文总数 = 涉及任一团队成员的全部论文。
团队发现（两级切分）。① 第一级 —— 在共著网络（边 = 共同署名 ≥2 篇）上运行 Louvain 社区发现，保留成员 ≥3 且论文 ≥5 的社区。② 第二级 —— 对每个大型社区（≥50 人）切分为以 PI 为核心的研究组：PI 候选为拥有 ≥5 篇主导论文（第一 / 通讯）的成员；其余成员加入与其共同署名论文最多的 PI，要求共同署名 ≥3 篇；不足 3 篇链接的成员并入最近的 PI（共同署名最多者，兜底为拥有最多主导论文的 PI）；切分后成员少于 3 人的组被丢弃；没有明确 PI 核心的社区整体保留。团队命名为 "<主导作者> Group"。所有合格团队写入 data/teams/ 下的 JSON 产物（teams.json 及分档 teams_*.json），由平台直接读取，本页展示按团队评分排序的 Top 30。
团队按团队评分降序展示。启用领域（主题）筛选时，团队评分仅基于该领域的论文重新计算（公式相同），论文 / 主导论文数量改写为该领域口径，并按领域评分排序；在该领域无论文的团队隐藏。注意：与作者评分不同，团队评分目前尚未包含引用项。
作者单位标注规则。① 有 ORCID 的作者 —— 单位取自该 ORCID 名下的论文（平台不单独维护 ORCID 注册表，故以该 ORCID 自身的研究论文为准，并跨姓名变体合并）；② 无单位信息的作者 —— 单位取自其研究论文的署名单位；③ 存在多个单位时 —— 取近两个自然年度论文中第一署名单位的众数，若该窗口内无论文则回退到全部论文；平局按最近年份、再按字典序。这可避免单篇近期联合署名（如共同指导的论文）覆盖作者的主要单位。
Bring Your Own Key (BYOK)使用你自己的密钥（BYOK）
On the Settings page, you can enter your own API keys for:
在设置页面，你可以填入自己的 API Key，用于：
- LLM API — enter provider, model, and key. Click Apply & Test. If the key works, your LLM calls will use your account. If it fails, the platform falls back to the server default.
- NCBI API — increases PubMed search speed from 3 req/s to 10 req/s. Free from NCBI account settings.
- LLM API —— 填写服务商、模型与密钥，点击「应用并测试」。若密钥可用，你的 LLM 调用将走你自己的账号；若失败，平台自动回退到服务器默认配置。
- NCBI API —— 将 PubMed 检索速度从 3 次/秒提升到 10 次/秒。可在 NCBI 账号设置 免费获取。
Keys are stored per-browser-session and never persisted to disk. They are cleared when you close the browser or click Clear.
密钥按浏览器会话存储，绝不写入磁盘；关闭浏览器或点击「清空」即被清除。
Automation Schedule自动化调度
| Task | Schedule | What |
|---|---|---|
| Citation Tracking | Mon 6:00 AM | Update citation counts for tracked papers |
| Author Extraction + Fulltext KB | Mon 6:30 AM | Extract authors, rebuild knowledge base |
| Weekly Pipeline (Windows Task Scheduler) | Mon 7:00 AM | Search new papers + generate bilingual review report + send to weekly subscribers (search → report → email chained in one task) |
| Team Discovery & Rising Stars | Mon 7:45 AM | Recompute teams / rising stars / research series |
| Monthly Report Generate | 1st Mon 7:30 AM | 30-day search + trend analysis + monthly report |
| Monthly Email | paused | Monthly report delivery is paused — send manually if needed |
| 任务 | 调度 | 内容 |
|---|---|---|
| 引用追踪 | 周一 06:00 | 更新受追踪论文的被引次数 |
| 作者抽取 + 全文知识库 | 周一 06:30 | 抽取作者信息、重建知识库 |
| 周报流水线（Windows 任务计划程序） | 周一 07:00 | 检索新论文 + 生成双语综述报告 + 推送给周报订阅者（检索 → 报告 → 邮件在同一任务内串联） |
| 团队发现与新星 | 周一 07:45 | 重算团队 / 新星 / 研究系列 |
| 月报生成 | 每月第一个周一 07:30 | 30 天检索 + 趋势分析 + 月报 |
| 月报邮件 | 已暂停 | 月报推送已暂停 —— 如需请手动发送 |
Rising Stars Detection新星发现机制
Rising Stars surface new researchers and emerging teams. Candidates are drawn from 14,000+ disambiguated authors using multi-dimensional growth metrics, with a deliberate emphasis on true first authorship and recent career start rather than senior corresponding-author status. Only original research papers are counted — Review / Editorial / News / Interview / Comment / Letter / Guideline / Case Report / Meta-Analysis / Retracted papers are excluded (matched on raw PubMed types, since PubMed often tags a review as both "Journal Article" and "Review"), so journal staff writers, editors and review-heavy authors do not appear as researchers. Top 50 are selected each run.
Authorship Credit (per paper)
| Role | Weight |
|---|---|
| True first author (position 1) | 1.0 — full credit |
| True last/senior corresponding (corresponding & last-listed) | 1.0 — full credit |
| Co-first author (shared first) | 0.4 — down-weighted |
| Co-corresponding (corresponding but not last-listed) | 0.4 — down-weighted |
Weighted lead score = 1.0×(first + last-corresponding) + 0.4×(co-first + co-corresponding). Co-first / co-corresponding roles no longer inflate a researcher's standing.
Admission Thresholds
| Criterion | Threshold |
|---|---|
| Minimum papers | ≥ 3 |
| Average IF | ≥ 2 |
| Active years | ≥ 2 distinct years |
| Recent activity | ≥ 1 paper in 2025-2026 |
| Recent IF | ≥ 5 |
| True lead authorship | ≥ 1 first-authored or last-corresponding paper (co-first/co-corresponding alone does not qualify) |
Growth Scoring
| Metric | Formula |
|---|---|
| Paper growth | recent (2024+) ≥ early (<2024) × 0.5 |
| IF trajectory | recent_avg_if ≥ early_avg_if × 0.8 |
| Growth rate | recent_papers / max(early_papers, 1) |
Ranking Priority (descending)
- True first-author papers (emphasis on hands-on new researchers)
- Growth rate (faster rising = higher)
- Career start recency (later first publication = newer)
- Weighted lead score (co-first / co-corresponding already down-weighted)
- Recent average IF (quality gate, not the primary driver)
新星用于发掘新锐研究者与新兴团队。候选来自 14,000+ 位已消歧作者，采用多维成长指标筛选，刻意强调真实的第一次署名与职业生涯起步较晚近，而非资深通讯作者身份。只统计原创研究论文 —— 综述 / 社论 / 新闻 / 访谈 / 评论 / 通信 / 指南 / 病例报告 / 荟萃分析 / 已撤稿论文均被排除（按 PubMed 原始类型匹配，因为 PubMed 常把综述同时标注为 "Journal Article" 与 "Review"），因此期刊编辑、撰稿人与高产综述作者不会以研究者身份出现。每轮选出 Top 50。
署名贡献（单篇）
| 角色 | 权重 |
|---|---|
| 真实第一作者（第 1 位） | 1.0 —— 全额计入 |
| 真实末位 / 资深通讯（是通讯且列在最后） | 1.0 —— 全额计入 |
| 共同第一作者（并列第一） | 0.4 —— 降权 |
| 共同通讯（是通讯但不在末位） | 0.4 —— 降权 |
加权主导分 = 1.0×(第一 + 末位通讯) + 0.4×(共同第一 + 共同通讯)。共同第一 / 共同通讯不再抬高研究者的排位。
入选门槛
| 标准 | 阈值 |
|---|---|
| 最少论文数 | ≥ 3 |
| 平均 IF | ≥ 2 |
| 活跃年数 | ≥ 2 个不同年份 |
| 近期活跃度 | 2025-2026 年 ≥ 1 篇 |
| 近期 IF | ≥ 5 |
| 真实主导署名 | ≥ 1 篇第一作者或末位通讯论文（仅共同第一 / 共同通讯不合格） |
成长评分
| 指标 | 公式 |
|---|---|
| 论文增长 | 近期（2024+）≥ 早期（<2024）× 0.5 |
| 影响因子走势 | recent_avg_if ≥ early_avg_if × 0.8 |
| 增长率 | recent_papers / max(early_papers, 1) |
排序优先级（降序）
- 真实第一作者论文（侧重亲自动手的新锐研究者）
- 增长率（上升越快排位越高）
- 职业起步的晚近程度（首次发表越晚越新）
- 加权主导分（共同第一 / 共同通讯已降权）
- 近期平均 IF（质量门槛，不是主要驱动）
Paper Relevance论文相关性
Every paper is scored on how strongly it connects computational biology methods to drug discovery applications.
| Rule | Score |
|---|---|
| Keyword match in title | +2 each |
| Keyword match in abstract | +1 each |
| Cross-domain: method + industry keywords both present | +2 ~ +5 |
| Open Access paper | +1 |
Filter threshold: ≥2. Score 0 papers are excluded from the knowledge base.
每篇论文都会按「计算生物学方法」与「药物发现应用」之间的连接强度进行打分。
| 规则 | 得分 |
|---|---|
| 关键词命中标题 | 每个 +2 |
| 关键词命中摘要 | 每个 +1 |
| 跨领域：方法类与产业类关键词同时出现 | +2 ~ +5 |
| 开放获取论文 | +1 |
筛选阈值：≥2。得分为 0 的论文不入知识库。
📚 Data Sources & Metrics数据来源与指标口径
| Metric | Source & Version |
|---|---|
| Impact Factor (IF) | 2026 JCR (Journal Citation Reports) — every impact-factor value on the platform (paper-level IF, Avg IF, Recent IF, and the IF term inside the author / institution / team scoring formulas) is taken from the 2026 JCR and matched to journals by ISSN. Journals not covered by JCR are shown as “—” or counted as 0 in scoring. |
| Papers & metadata | PubMed (NCBI E-utilities) — title, abstract, MeSH terms, publication types, journal, year |
| Citation counts | Semantic Scholar (primary) + OpenAlex (fallback) |
| Open-access full text | PMC OA Subset (open-access full text only) |
| Knowledge base dimensions | LLM-structured extraction from paper abstracts — 8 dimensions |
On the impact-factor convention (important): the platform does not compute impact factors itself — it adopts journal-level values from the authoritative external source and binds them to each paper. Papers published in different years in the same journal therefore share one and the same 2026 JCR value, which keeps cross-paper comparison consistent; it also means the IF shown for an older paper reflects the journal's current standing rather than its standing in the year of publication. When JCR publishes a new edition, the platform replaces all values in one pass and the year label on this page is updated accordingly.
| 指标 | 数据来源与版本 |
|---|---|
| 影响因子（IF） | 2026 JCR（Journal Citation Reports）—— 平台全部影响因子数值（论文 IF、Avg IF、Recent IF，以及作者 / 机构 / 团队评分公式中的 IF 项）统一取自 2026 年 JCR，按期刊 ISSN 匹配后写入数据库；期刊未被 JCR 收录时显示 “—” 或在评分中按 0 计。 |
| 论文与元数据 | PubMed（NCBI E-utilities）—— 标题、摘要、MeSH 主题词、公开类型、期刊、年份 |
| 被引次数 | Semantic Scholar（主）+ OpenAlex（兜底） |
| 开放获取全文 | PMC OA Subset（仅收录开放获取全文） |
| 知识库维度 | 由论文摘要经 LLM 结构化抽取，共 8 个维度 |
关于影响因子口径（重要）：平台不自行计算 IF，而是采用外部权威来源的期刊级数值并绑定到每篇论文。因此同一期刊在不同年份发表的论文使用的是同一套 2026 JCR 数值，便于横向比较；这也意味着历史论文所显示的 IF 反映的是该期刊的当前水平，而非其发表当年的水平。若 JCR 后续发布新版数据，平台将在同步更新后统一替换，届时本页标注的年份会同步调整。
💬 Feedback问题反馈
Found a problem, or have a suggestion for the platform? Tell us directly — anyone can submit, no registration required.
使用中遇到问题，或对平台有任何建议？欢迎直接告诉我们 —— 任何用户均可提交，无需注册。
Please describe the problem or suggestion you have; if you leave an email or phone number, we can get back to you quickly.
Your message is delivered straight to the platform's working mailbox compbioagent@163.com.
请描述你遇到的问题或建议；若能留下邮箱或电话，我们会尽快与你联系。
提交后将直接送达平台工作邮箱 compbioagent@163.com。
If you left contact details, we will get back to you soon.