通过PubTator进行PubMed文本挖掘

https://www.ncbi.nlm.nih.gov/research/pubtator-api/publications/export/[Format]?[Type]=[Identifiers]&concepts=[Bioconcepts]

注: 如仅需要对PubMed文献进行处理, 则无需搭建环境, 存在 `requests` 包即可. 可跳至本文"上传 `PMID` "部分继续观看. 

# conda run
conda create --name py36 python=3.6
conda env list
conda activate py36
conda install virtualenv

virtualenv -p python3.6 venv
source venv/bin/activate
pip install -r requirements.txt

ERROR: Could not find a version that satisfies the requirement en-core-sci-sm==0.2.4 (from versions: none)
ERROR: No matching distribution found for en-core-sci-sm==0.2.4

pip install https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.5.1/en_core_sci_sm-0.5.1.tar.gz

python SubmitPMIDList.py input_pmid/ex.pmid pubtator

$ python SubmitPMIDList.py [InputFile] [Format] [BioConcept]
[Inputfile]: a file with a pmid list
[Format]: 1) pubtator (PubTator)
			2) biocxml (BioC-XML)
			3) biocjson (JSON-XML)
			* Reference for format descriptions: https://www.ncbi.nlm.nih.gov/research/bionlp/APIs/format/
[Bioconcept]: Default (leave it blank) includes all bioconcepts. Otherwise, user can choose gene, disease, chemical, species, proteinmutation, dnamutation, snp, and cellline.

* All arguments are case sensitive.

	else:
		print(r.text.encode("utf-8"))

		with open('output_'+Inputfile+'.'+Format, 'wb') as f:
			f.write(r.text.encode("utf-8"))

# Submitting requests
python SubmitText_request.py input All SessionNumber.txt
# Retrieving results
python SubmitText_retrieve.py input SessionNumber.txt output

#!/bin/bash

# 每个文件的行数
LINES=1000

# 输入文件的名称
INPUT_FILE="ex.pmid"

# 文件名前缀
FILE_PREFIX="ex"

# 计数器
count=1

# 读取文件并将其拆分为多个小文件
split -l $LINES $INPUT_FILE $FILE_PREFIX

# 将小文件重命名为您想要的名称格式
for file in $FILE_PREFIX*
do
    mv "$file" "${FILE_PREFIX}_${count}.pmid"
    count=$((count+1))
done

# 输出文件列表到文件
ls $FILE_PREFIX* > file_names.txt

chmod +x split_and_list_to_file.sh
./split_and_list_to_file.sh

#!/bin/bash

# 读取文件列表
for file in $(sort -t_ -k2 -n file_names.txt)
do
  # 运行 SubmitPMIDList.py 脚本
  python ../SubmitPMIDList.py $file pubtator
done

chmod +x run_submit_pmid.sh
./run_submit_pmid.sh

cd input_pmid
./split_and_list_to_file.sh
./run_submit_pmid.sh

wget https://repo.continuum.io/miniconda/Miniconda3-latest-$(uname -s)-$(uname -m).sh
# exemple: wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh
bash ./Miniconda3-latest-$(uname -s)-$(uname -m).sh
# exemple: bash ./Miniconda3-latest-Linux-x86_64.sh
source ~/.bashrc

conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/bioconda
conda config --set show_channel_urls yes
conda config --show  # 查看新增channels

sudo apt-get install python
python -V
python3 -V

root@tenney:/www/wwwroot/mdreader.yeyeziblog.eu.org# whereis python
python: /usr/bin/python3.8-config /usr/bin/python2.7 /usr/bin/python3.8 /usr/lib/python2.7 /usr/lib/python3.8 /usr/lib/python3.9 /etc/python2.7 /etc/python3.8 /usr/local/lib/python2.7 /usr/local/lib/python3.8 /usr/include/python3.8 /usr/share/python
root@tenney:/www/wwwroot/mdreader.yeyeziblog.eu.org# rm /usr/bin/python
root@tenney:/www/wwwroot/mdreader.yeyeziblog.eu.org# ln -s /usr/bin/python3.8 /usr/bin/python

RuntimeError: failed to find interpreter for Builtin discover of python_spec='python3.6'
ERROR: Cannot uninstall 'certifi'. It is a distutils installed project and thus we cannot accurately determine which files belong to it which would lead to only a partial uninstall.