From af575f7d2ab5539cbef305a3e793772b0373c01a Mon Sep 17 00:00:00 2001
From: "Jochens, Florian" <fj@andaco.de>
Date: Wed, 10 Nov 2021 12:31:41 +0100
Subject: [PATCH] example urls

---
 input/__pycache__/input_fj.cpython-39.pyc | Bin 0 -> 4300 bytes
 input/example_urls                        |   2 +
 input/test.py                             |   2 +-
 input/x                                   | 234 ++++++++++++++++++++++
 4 files changed, 237 insertions(+), 1 deletion(-)
 create mode 100644 input/__pycache__/input_fj.cpython-39.pyc
 create mode 100644 input/example_urls
 create mode 100644 input/x

diff --git a/input/__pycache__/input_fj.cpython-39.pyc b/input/__pycache__/input_fj.cpython-39.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..a3e6099f4ab4c56400b2698c812d4b5fc9a9a7aa
GIT binary patch
literal 4300
zcmYe~<>g{vU|_KS)RDMLh=JiTh=Yuo85kHG7#J9eI~W)kQW&BbQW&EcQ<$QdQkbKd
zQ&>`1b69d&qu3Z3Qdm;ha@eCdz%*wRX9`OSdk$AFcN8}xgF8bCM+#>PLkedzQxuOo
zLkd?4cMC%bcQaEIZwgNeZwo^dUkYCee+xqte~LhgU<*T(K#EX`a0^3}V2VhJXbVG>
zP>NWJcnd?6a0**6gQi5450_hMUUErheqOOcT7Hp2W?ou;QEnngK%pqLq$o4BEHOtR
zKTRRAs3bEvC$(51ttdZNp(G<!!O=NbAuGSMC@(Qb!OPjxmy4^4-z_J<C^Ion!7D#G
zBQ>wMiYG10Au%r{F*#o^B{hmGpeR436l~i|P~d1X-r{viO)M?ROe@U^&Mz(S(`3BG
z5|CJukqnYX#!RsAlVD(ANM(p(Oks#(N@s{-PGL-8YGH_CNns9V&}6yA9Z;H-lbH<m
zKr%a$2_QDe5NA*%XfQA^)G*dC#52?|)iA^})-cyF#52{f)G)*|*Ra+w#Iw|})iA`f
zrZ5CEtYq}lWV^*$l39|IdP|@HVSIc_VoB;Pp5*+zlA_F{(vtk5;#=$~`I+&hMLD-P
zic6ESQj<%HZ}H}p=Ef&ymVlj9tjT_hr8qSwt%!|*fuRWGs3Hy!ixWhEl28#h0|UcK
zh9X`D28Lfc`WgATsrqSI`bDV)`NjIlnZ>#VMfq8&*(Lg!c?G3VGCnO!ub}c4M|^x{
zUS>&ryd=nvJRr|AvoXS8l?YPM=)siwX|jU!<t65(#>d~{ijU9DPbtj-v3cU-3riDo
z;4*M86!C-H3UVLVkr09pB*wzPz#s~;8^qvXVqq!*F>uGF2vS@^<B=H}j~vd>5KCqS
z`2&hUY<MKf;E6;~#1(;5YqEet`W8Dhr6NLGleGvGL}2M6kgE|=5HEp!2=*7q!zv(u
zfuf258lqK#Fef4fCQFe3C?Etugb;`TX+<&)VJ67$${;gA{^4LO0`Zd>q5cF>Af2G}
z0Zy<lKz?P&VgQ9w3Ue=0En^L17O1RX1@W>NYnh;YHYlGN%x6qt2k~7PV)<%WYFHL9
zrEn}{tYs~<fy#1%WNX>d8EV;U*cLFSa4lqXVTcu}<)~p_z*57pfGLH0A>%?uMux%+
zunwLSUa$_%bcR~48qO?G$;Af}abbuRsO7HVTEJ4nodwY`53GYRg&!ne%TvRX#aetS
zMWB{9j|0TcVyxvYVXI-PVXon-VXa}W;caHC<*VTfX3!M$yTzQ6Sym+rEpy^CQWH~B
zi*$2R(@GQyN^^3+td)#WY{@x^#l`WrSc(f0^QyQra@=xKbVEQHwTiExG)WhfL3PU#
zb4pXIMA6Jj$<G93Q<jXP)U+ybG|7_0iu}C%+{#;wiQwcB#Z;OT#hjC$SS1Xx!x@t2
z9ZO3x@{6KGpxS*w<z;eld~$wiUP%!sE<w3HEi*6W7E4KLMaeDZ^wg4D93X-C#GIU4
zY>5R0sd*_yQlNwa$|;)sw^)kvOABtXL3|v=3pF_&T>5~Ei(4!?nR(eooD2*MQ7px!
zNySB=QsWkLacNQ%OLBf*F*q4VF(>EeMX}_S<|cy+lv~UNrAbKX5R|NM38bf%#KUX=
z75rMD^avst82K0l7zG%G7<m}^7+Dzk7=^$zh~xvMe<ltlE=HFBEKEhJ3=9k?IUH2e
zfpQ)=-Fh)FFqAN4F~ZX=LkdeRV-3RsrW96iT2rWHs$p8doWiz{F@-&wsYs@V5zOaU
z$Y{<`%UCE=!cxQ7%*e=4!x+q<$>~=l#=yW(C7YaCqMMRmo|luKn4+6flwSbi#Dj|B
z)Vz`+agZ93jFOUqVk>?9g3_d7y~N~Vz5JqdNLYi)-YRie_EkvCOHn9FO-n6G%}Y)#
zE|O$mV9;bOQUJw@G>DJ`5wZ*n47XSdiZb&`G?}B=QY#Abi%M=Wmlov|DS_m{IU7tM
z!WQHxkPAUIf)glgK~kWw1%)UmggF?CKvfY+z6XULC^3M;&jp<C7citSE@Ui{s$p0F
z4#|Z~DNK?KwTvZ9Da<vD;tb88{Li$2c_BlQMF~p^3n;wuI7(PjSV1gMS*Xe8_lwc?
zB`8f+ap>u%W#*(7>sJZ8W#*(RB<2*QCZ<#>q*i1WmlQ(<Q}R=b74q^+AflSAMWB$l
z#a2{Ykds+b1ajjo_RQjVkU>Ripa5eoQU`?)2S@}|XWU{bNG!=fPjVcvAn^tT2dMmI
zVB}&HVB}%sVB}&d(g!6bkl~;L5QISi3QFqWz<9;Lz>v-WskM=k6mvR5ElUk^789r$
z1uAS@7-A)AS!-ApFxRkVu`FOsVM}3O$OJCN)Y2Jh*`R7UplSsmg<lPO77JKSP&z{`
zM-B4=rW8(a5*4ZCtl?O|T*JA54OBpa)f9mXK!}~(aC1NfAae~j)SOu*>?u4Y9H8Xe
z%;drlt5wTW!;r<WfVqUThNXr_lA(qTOmcxq4iMQ4altNdl=1pSG3Dn}NhW8Oq^9UX
z({_AvQY9?mg41~ss6kYvj#CjVgX@BekXwv;w-~C_aI1z^le(ZNgk%;_cBs<Btpi$s
zfE@^H2SExyt|DPj&H$yHB5)p(2XR5w_AU0J)PkJE<kTWawkk@@OHaMUoS9bwt_L-F
zi$K*axa0!o!zlKY)RM%^oZ=`pus4b!#WF9{wecX=7T;n4QBfSwCRi~zK|)GHc2MXQ
zWhUKX%tTL-f}lbW*0zZUm4YFlq-g+3eT;12Qjd+1=|2~f7$XZKgas=R5qu#=5k{W>
zMdqO73(8|4%^(b_+d=I)aPmC{E(=o_YZ$T^XEUTQ)i7i+&1Ohpu3^Yxp3RWLGM62c
zTT2*f7_wMWSX0<C8T%L+8A=#Z5aO&z;%qexS?tY>DID1>MY~F1JkD&UqJk2J6fTfi
zc|s)&Dcm4+vl&u&<}!oCY8bLOTo_{YY8guyQg~|^vp{a)t6|LIoXwEJU&ENiI-4Oy
zpoS6bCc(L!AU%a0c^oASDMBDNIB5#|RS7vlIs^*f2(eO7P*A86=0a*>Du8NVE0Caz
zzo%|!kPlc5NS%U06*m`GFtmYeb&I(;wV;YgN1=+33tF*)8`D<cR8$12kE$%WLNYRo
z6_8rr3Yo<U;6$mAR0-~mq~+)2<d<jWr6a4d;;PaiMQas5vhHFlt}0<JkdwiU3b+TL
zf?kl$4^$W`h~fi~??Kv8L!gQmY$iwogsUvDx)4<O!abOnSE-O+l95`3>^wb9E^yfk
z&J5tj0k~NJZV-UeeUS+$!+{bYBqxGextdJiycNX(OY`U%f)8BB#TS$&fpbG9C^zVV
z5;G$YxW;Gs$HgkZ$iXPU#K*|T$i*bY$i>J4m0@9K`OCt>@`sPT$Pzs-fa)|52ImD(
zZCJvvfU$;QA!8O(En^9D4Py#pGgB>72}=!AGh;1t32O~=7F#o83R5;qkzEOU4P2y#
zshOFPp$637WA>}!&M3*v(JM$SDo!l|Cm2nRTg*kNh2WB<2wd1OB^864DM-Nq%Bh+x
z;1VK=6J$a>sDTD9Yrw&S9w@Bf-c}PREFhH@4<i>72e@5SWCN=HL~gOi$EV~cLpo83
z;D%v*d=zJVd}?lDW=?#36jywFaY<rHX>ojf6mwFsNfD@UD6$5%<2Z^^3rkarONxuE
zKy@f{ab@u>c2M=1lbHmrYr*{}aM1|y2&mBjt}MYt4mhmA&OmZDsOBsJwKr~Y*yMuy
nbao&Mi$Mi33o8pK%Gg1*E(aqI6CWQRJBI`ZCkH2oD2F5fLQw>G

literal 0
HcmV?d00001

diff --git a/input/example_urls b/input/example_urls
new file mode 100644
index 0000000..96ac680
--- /dev/null
+++ b/input/example_urls
@@ -0,0 +1,2 @@
+https://pubs.acs.org/doi/10.1021/acs.jcim.5b00332
+https://pubs.acs.org/doi/10.1021/acs.jcim.6b00709
diff --git a/input/test.py b/input/test.py
index bdd12e8..dc623ca 100755
--- a/input/test.py
+++ b/input/test.py
@@ -4,7 +4,7 @@ from input_fj import input, print_pub_info
 import sys
 
 if len(sys.argv) != 3:
-    sys.stderr.write('Usage: {} <url>\n'.format(sys.argv[0]))
+    sys.stderr.write('Usage: {} <url> <url>\n'.format(sys.argv[0]))
     exit(1)
 url = sys.argv[1]
 url2 = sys.argv[2]
diff --git a/input/x b/input/x
new file mode 100644
index 0000000..c8ade9d
--- /dev/null
+++ b/input/x
@@ -0,0 +1,234 @@
+Article title:    Feasibility of Active Machine Learning for Multiclass Compound Classification
+Publication date: January 7, 2016
+DOI-URL:          https://doi.org/10.1021/acs.jcim.5b00332
+
+Subjects:
+Algorithms, Molecules, Drug discovery, Screening assays, Receptors
+
+Contributors:
+Tobias Lang, Florian Flachsenberg, Ulrike von Luxburg, Matthias Rarey
+
+This publication is cited by the following 30 publications:
+
+
+    Title:        Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery 
+    Journal:      Chemical Reviews
+    Contributors: Xin Yang, Yifei Wang, Ryan Byrne, Gisbert Schneider, Shengyong Yang. 
+    DOI-URL:      https://doi.org/10.1021/acs.chemrev.8b00728
+            
+
+    Title:        De Novo Molecule Design by Translating from Reduced Graphs to SMILES 
+    Journal:      Journal of Chemical Information and Modeling
+    Contributors: Peter Pogány, Navot Arad, Sam Genway, Stephen D. Pickett. 
+    DOI-URL:      https://doi.org/10.1021/acs.jcim.8b00626
+            
+
+    Title:        Designing Algorithms To Aid Discovery by Chemical Robots 
+    Journal:      ACS Central Science
+    Contributors: Alon B. Henson, Piotr S. Gromski, Leroy Cronin. 
+    DOI-URL:      https://doi.org/10.1021/acscentsci.8b00176
+            
+
+    Title:        Modeling Kinase Inhibition Using Highly Confident Data Sets 
+    Journal:      Journal of Chemical Information and Modeling
+    Contributors: Sorin Avram, Alina Bora, Liliana Halip, Ramona Curpăn. 
+    DOI-URL:      https://doi.org/10.1021/acs.jcim.7b00729
+            
+
+    Title:        Predictive Models for Fast and Effective Profiling of Kinase Inhibitors 
+    Journal:      Journal of Chemical Information and Modeling
+    Contributors: Alina  Bora, Sorin  Avram, Ionel  Ciucanu, Marius  Raica, and Stefana  Avram  . 
+    DOI-URL:      https://doi.org/10.1021/acs.jcim.5b00646
+            
+
+    Title:        Evaluation of categorical matrix completion algorithms: toward improved active learning for drug discovery 
+    Journal:      Bioinformatics
+    Contributors: Huangqingbo  Sun, Robert F  Murphy, . 
+    DOI-URL:      https://doi.org/10.1093/bioinformatics/btab322
+            
+
+    Title:        An Artificial Intelligence Approach Based on Hybrid CNN-XGB Model to Achieve High Prediction Accuracy through Feature Extraction, Classification and Regression for Enhancing Drug Discovery in Biomedicine 
+    Journal:      International Journal of Biology and Biomedical Engineering
+    Contributors: Mukesh  Madanan, Biju T.  Sayed, Nurul Akhmal  Mohd Zulkefli, Nitha C.  Velayudhan. 
+    DOI-URL:      https://doi.org/10.46300/91011.2021.15.22
+            
+
+    Title:        Artificial Intelligence in Medicinal Chemistry 
+    Journal:      
+    Contributors: Edward  Griffen, Alexander  Dossetter, Andrew  Leach, Shane  Montague. 
+    DOI-URL:      https://doi.org/10.1002/0471266949.bmc267
+            
+
+    Title:        Practical Chemogenomic Modeling and Molecule Discovery Strategies Unveiled by Active Learning 
+    Journal:      
+    Contributors: J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.1016/B978-0-12-801238-3.11533-8
+            
+
+    Title:        Machine learning phases and criticalities without using real data for training 
+    Journal:      Physical Review B
+    Contributors: D.-R.  Tan, F.-J.  Jiang. 
+    DOI-URL:      https://doi.org/10.1103/PhysRevB.102.224434
+            
+
+    Title:        Active learning effectively identifies a minimal set of maximally informative and asymptotically performant cytotoxic structure–activity patterns in NCI-60 cell lines 
+    Journal:      RSC Medicinal Chemistry
+    Contributors: Takumi  Nakano, Shunichi  Takeda, J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.1039/D0MD00110D
+            
+
+    Title:        Active learning efficiently converges on rational limits of toxicity prediction and identifies patterns for molecule design 
+    Journal:      Computational Toxicology
+    Contributors: Ahsan  Habib Polash, Takumi  Nakano, Christin  Rakers, Shunichi  Takeda, J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.1016/j.comtox.2020.100129
+            
+
+    Title:        Practical considerations for active machine learning in drug discovery 
+    Journal:      Drug Discovery Today: Technologies
+    Contributors: Daniel  Reker. 
+    DOI-URL:      https://doi.org/10.1016/j.ddtec.2020.06.001
+            
+
+    Title:        Designing compact training sets for data-driven molecular property prediction through optimal exploitation and exploration 
+    Journal:      Molecular Systems Design & Engineering
+    Contributors: Bowen  Li, Srinivas  Rangarajan. 
+    DOI-URL:      https://doi.org/10.1039/C9ME00078J
+            
+
+    Title:        Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification 
+    Journal:      Molecules
+    Contributors: Ahsan Habib  Polash, Takumi  Nakano, Shunichi  Takeda, J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.3390/molecules24152716
+            
+
+    Title:        Capturing and applying knowledge to guide compound optimisation 
+    Journal:      Drug Discovery Today
+    Contributors: Matthew  Segall, Tamsin  Mansley, Peter  Hunt, Edmund  Champness. 
+    DOI-URL:      https://doi.org/10.1016/j.drudis.2019.02.004
+            
+
+    Title:        A novel graph kernel on chemical compound classification 
+    Journal:      Journal of Bioinformatics and Computational Biology
+    Contributors: Qiangrong  Jiang, Jiajia  Ma. 
+    DOI-URL:      https://doi.org/10.1142/S0219720018500269
+            
+
+    Title:        Accelerating Drug Discovery Using Convolution Neural Network Based Active Learning 
+    Journal:      
+    Contributors: Pengfei  Liu, Kwong-Sak  Leung. 
+    DOI-URL:      https://doi.org/10.1109/TENCON.2018.8650298
+            
+
+    Title:        An Adaptive Lightweight Security Framework Suited for IoT 
+    Journal:      
+    Contributors: Menachem  Domb. 
+    DOI-URL:      https://doi.org/10.5772/intechopen.73712
+            
+
+    Title:        Adaptive mining and model building of medicinal chemistry data with a multi-metric perspective 
+    Journal:      Future Medicinal Chemistry
+    Contributors: JB  Brown. 
+    DOI-URL:      https://doi.org/10.4155/fmc-2018-0188
+            
+
+    Title:        Chemogenomic Active Learning's Domain of Applicability on Small, Sparse qHTS Matrices: A Study Using Cytochrome P450 and Nuclear Hormone Receptor Families 
+    Journal:      ChemMedChem
+    Contributors: Christin  Rakers, Rifat Ara  Najnin, Ahsan Habib  Polash, Shunichi  Takeda, J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.1002/cmdc.201700677
+            
+
+    Title:        Automating drug discovery 
+    Journal:      Nature Reviews Drug Discovery
+    Contributors: Gisbert  Schneider. 
+    DOI-URL:      https://doi.org/10.1038/nrd.2017.232
+            
+
+    Title:        Classifiers and their Metrics Quantified 
+    Journal:      Molecular Informatics
+    Contributors: J. B.  Brown. 
+    DOI-URL:      https://doi.org/10.1002/minf.201700127
+            
+
+    Title:        Active Search for Computer-aided Drug Design 
+    Journal:      Molecular Informatics
+    Contributors: Dino  Oglic, Steven A.  Oatley, Simon J. F.  Macdonald, Thomas  Mcinally, Roman  Garnett, Jonathan D.  Hirst, Thomas  Gärtner. 
+    DOI-URL:      https://doi.org/10.1002/minf.201700130
+            
+
+    Title:        Selection of Informative Examples in Chemogenomic Datasets 
+    Journal:      
+    Contributors: Daniel  Reker, J. B.  Brown. 
+    DOI-URL:      https://doi.org/10.1007/978-1-4939-8639-2_13
+            
+
+    Title:        The value of prior knowledge in machine learning of complex network systems 
+    Journal:      Bioinformatics
+    Contributors: Dana  Ferranti, David  Krane, David  Craft, . 
+    DOI-URL:      https://doi.org/10.1093/bioinformatics/btx438
+            
+
+    Title:        Lightweight adaptive Random-Forest for IoT rule generation and execution 
+    Journal:      Journal of Information Security and Applications
+    Contributors: Menachem  Domb, Elisheva  Bonchek-Dokow, Guy  Leshem. 
+    DOI-URL:      https://doi.org/10.1016/j.jisa.2017.03.001
+            
+
+    Title:        Active learning for computational chemogenomics 
+    Journal:      Future Medicinal Chemistry
+    Contributors: Daniel  Reker, Petra  Schneider, Gisbert  Schneider, JB  Brown. 
+    DOI-URL:      https://doi.org/10.4155/fmc-2016-0197
+            
+
+    Title:        Small Random Forest Models for Effective Chemogenomic Active Learning 
+    Journal:      Journal of Computer Aided Chemistry
+    Contributors: Christin  Rakers, Daniel  Reker, J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.2751/jcac.18.124
+            
+
+    Title:        Large-Scale Off-Target Identification Using Fast and Accurate Dual Regularized One-Class Collaborative Filtering and Its Application to Drug Repurposing 
+    Journal:      PLOS Computational Biology
+    Contributors: Hansaim  Lim, Aleksandar  Poleksic, Yuan  Yao, Hanghang  Tong, Di  He, Luke  Zhuang, Patrick  Meng, Lei  Xie, . 
+    DOI-URL:      https://doi.org/10.1371/journal.pcbi.1005135
+            
+Article title:    Matched Molecular Series: Measuring SAR Similarity
+Publication date: May 1, 2017
+DOI-URL:          https://doi.org/10.1021/acs.jcim.6b00709
+
+Subjects:
+Substituents, Mathematical methods, Structure activity relationship, Biological databases
+
+Contributors:
+Emanuel S. R. Ehmki, Christian Kramer
+
+This publication is cited by the following 5 publications:
+
+
+    Title:        Matched Molecular Series Analysis for ADME Property Prediction 
+    Journal:      Journal of Chemical Information and Modeling
+    Contributors: Mahendra Awale, Sereina Riniker, Christian Kramer. 
+    DOI-URL:      https://doi.org/10.1021/acs.jcim.0c00269
+            
+
+    Title:        Approaches using AI in medicinal chemistry 
+    Journal:      
+    Contributors: Christian  Tyrchan, Eva  Nittinger, Dea  Gogishvili, Atanas  Patronov, Thierry  Kogej. 
+    DOI-URL:      https://doi.org/10.1016/B978-0-12-822249-2.00002-5
+            
+
+    Title:        Bioactivity Prediction Based on Matched Molecular Pair and Matched Molecular Series Methods 
+    Journal:      Current Pharmaceutical Design
+    Contributors: Xiaoyu  Ding, Chen  Cui, Dingyan  Wang, Jihui  Zhao, Mingyue  Zheng, Xiaomin  Luo, Hualiang  Jiang, Kaixian  Chen. 
+    DOI-URL:      https://doi.org/10.2174/1381612826666200427111309
+            
+
+    Title:        BRADSHAW: a system for automated molecular design 
+    Journal:      Journal of Computer-Aided Molecular Design
+    Contributors: Darren V. S.  Green, Stephen  Pickett, Chris  Luscombe, Stefan  Senger, David  Marcus, Jamel  Meslamani, David  Brett, Adam  Powell, Jonathan  Masson. 
+    DOI-URL:      https://doi.org/10.1007/s10822-019-00234-8
+            
+
+    Title:        The use of matched molecular series networks for cross target structure activity relationship translation and potency prediction 
+    Journal:      MedChemComm
+    Contributors: Christopher E.  Keefer, George  Chang. 
+    DOI-URL:      https://doi.org/10.1039/C7MD00465F
+            
-- 
GitLab