Skip to content

Instantly share code, notes, and snippets.

@maziyarpanahi
Last active October 22, 2017 13:49
Show Gist options
  • Save maziyarpanahi/c169e33b2c33b3f086604829ff912b09 to your computer and use it in GitHub Desktop.
Save maziyarpanahi/c169e33b2c33b3f086604829ff912b09 to your computer and use it in GitHub Desktop.
Results of LDA over PubMed dataset "Cancer" sub-corpora
Stanford CoreNLP (Sentence splitter and POS Tagging - extract noun phrases), StopWordsRemover, TF-IDF, word2vec and OnlineLDAOptimizer
==========
Query: "cancer"
Sample: 500K abstracts
Dataset: PubMed
==========
val numTopics: Int = 50
val maxIterations: Int = 100
val vocabSize: Int = 10000
val minDF: Int = 1
val minTF: Int = 1
val maxItems: Int = 10
// val embedding: Int = 50 // dimension fo embedding for Word2Vec representation of words
val embedding: Int = 50 // dimension fo embedding for Word2Vec representation of words
val energy : Double = .2 // threshold for cumulative probability deemed necessary for topic coherency
==========
Total number of unique phrases: 3389197
Top 100 phrases:
+--------------------+-----+ [12/9126]
| value|count|
+--------------------+-----+
| breast cancer|26585|
| cancer cells|18603|
| colorectal cancer|16739|
| lung cancer|14293|
| cell lines|13963|
| gastric cancer|13791|
| cancer patients|13125|
| prostate cancer|12895|
| present study|11832|
| ovarian cancer|11074|
| tumor cells|10430|
| overall survival| 9998|
| cervical cancer| 9720|
| pancreatic cancer| 8301|
| squamous cell| 6836|
| clinical trials| 6781|
| important role| 5947|
| nonsmall cell| 5569|
|multivariate anal...| 5426|
| human breast| 5159|
| tumor growth| 4932|
| high risk| 4636|
| cell proliferation| 4532|
| risk factors| 4386|
|breast cancer pat...| 4303|
|significant diffe...| 4290|
| epidermal growth| 4185|
| rectal cancer| 4090|
| human cancer| 3913|
| colon cancer| 3909|
| endometrial cancer| 3825|
| confidence interval| 3653|
| lymph nodes| 3598|
|confidence interv...| 3553|
| cell death| 3520|
| poor prognosis| 3467|
|significant diffe...| 3447|
| gene expression| 3438|
| peripheral blood| 3375|
| primary tumor| 3368|
| control group| 3360|
| bladder cancer| 3255|
| cancer cell lines| 3146|
| nude mice| 3128|
| high levels| 3111|
| early detection| 3063|
| breast cancer cells| 3060|
| first time| 3038|
| recent studies| 2918|
| radiation therapy| 2854|
| cell cycle| 2795|
| early stage| 2793|
| cancer therapy| 2742|
|hepatocellular ca...| 2741|
| t cells| 2709|
| relative risk| 2695|
|radical prostatec...| 2692|
| cell growth| 2628|
| median survival| 2592|
| cancer risk| 2588|
|adjuvant chemothe...| 2534|
|consecutive patients| 2530|
| previous studies| 2519|
| oxidative stress| 2505|
| oral cancer| 2504|
| cancer treatment| 2501|
| magnetic resonance| 2462|
| solid tumors| 2460|
| dna damage| 2420|
| metastatic disease| 2418|
| local recurrence| 2401|
| mcf7 cells| 2355|
|molecular mechanisms| 2353|
| epithelial cells| 2344|
| tumor progression| 2335|
| current study| 2317|
| general population| 2316|
| human cancers| 2277|
| anticancer drugs| 2259|
|vascular endothel...| 2258|
| metastatic breast| 2258|
| family history| 2255|
| small cell| 2254|
| side effects| 2250|
| ratio or| 2230|
|prostatespecific ...| 2213|
| normal tissues| 2205|
| cell line| 2172|
| other hand| 2168|
| expression levels| 2160|
| normal cells| 2157|
| renal cell| 2134|
| clinical practice| 2131|
| clinical stage| 2104|
|postmenopausal women| 2082|
| esophageal cancer| 2080|
|significant increase| 2076|
| normal tissue| 2066|
|human papillomavirus| 2065|
| reactive oxygen| 2062|
+--------------------+-----+
TOPIC: 30 - TOPIC SCORE: 0.8476564682732474
lung cancer 0.13845057898431662
nonsmall cell 0.06259561486508719
small cell 0.03094133958707408
human prostate 0.02844507552009765
complete response 0.021856482191307813
significant reduction 0.018573565217522667
malignant tumors 0.01729077087107646
gastric cancers 0.013750554150338127
prostate cancers 0.012537556929055995
advanced prostate 0.01232996514919678
==========
TOPIC: 27 - TOPIC SCORE: 0.6884355020952317
breast cancer 0.16056912204163817
human breast 0.053307886356763506
breast cancer cells 0.037020485875643556
cell growth 0.030969333758843542
cancer cells 0.01998242647217044
western blotting 0.01615054215417094
cell cycle arrest 0.015510840139912685
public health 0.014488262766118051
cell survival 0.014418354061685875
epithelial ovarian cancer 0.013930338686949059
==========
TOPIC: 40 - TOPIC SCORE: 0.5831249859876626
cancer patients 0.1464677636300192
clinical stage 0.03389561825127253
median age 0.024051056448969654
median followup 0.022499755402227407
multiple myeloma 0.019153598458509197
further study 0.017585664120282007
antitumor effect 0.016477593860300926
performance status 0.01584005653818513
clinical benefit 0.015345026283547834
small number 0.015108564481183867
==========
TOPIC: 9 - TOPIC SCORE: 0.5724783589249728
cervical cancer 0.12018220118900316
risk factors 0.05861707856702046
family history 0.03551419408451676
factor receptor 0.020599233666673575
risk factor 0.020406646566580772
incidence rates 0.018388660154977567
basal cell 0.017463035348360103
human epidermal growth 0.016159649600886998
genetic testing 0.015687824277258774
radical surgery 0.014339098221252698
==========
TOPIC: 25 - TOPIC SCORE: 0.5477698659614186
ovarian cancer 0.1347104392351164
poor prognosis 0.04125854811022281
retrospective study 0.031165160953528427
growth factors 0.023119675099120947
bone marrow 0.02226689295362343
nsclc patients 0.02126352863134205
cell surface 0.0164134838094147
stromal cells 0.015904597452613498
molecular basis 0.014390214415473182
papillary thyroid 0.01390077248295607
==========
TOPIC: 48 - TOPIC SCORE: 0.4738073420704046
colorectal cancer 0.15211240499836828
cancer therapy 0.03654594104475715
magnetic resonance 0.03364804744569887
solid tumors 0.03337948144215767
metastatic disease 0.031878329198085475
neoadjuvant chemotherapy 0.026238584470198202
extracellular matrix 0.023891227981740492
bone metastases 0.023166643104095483
anticancer agents 0.01949161883005604
imaging mri 0.01480240345376249
==========
TOPIC: 5 - TOPIC SCORE: 0.46866149528206774
prostate cancer 0.1329494422302325
adjuvant chemotherapy 0.04048303904897013
prospective study 0.025058693142823326
clinical data 0.02291380018673496
transgenic mice 0.016170210131467706
healthy subjects 0.013388837206330976
tumor response 0.01230205071732737
clinical setting 0.011864710189156006
active surveillance 0.01068798273885288
active site 0.010364950570336517
==========
TOPIC: 49 - TOPIC SCORE: 0.45956026259413213
gastric cancer 0.14551077910678897
breast cancers 0.029052850066276645
invasive breast 0.023258055847499615
local control 0.02312384125385959
long term 0.015998092273274832
survival time 0.015510759901194843
tumor suppressor genes 0.014751819587005633
invasive cancer 0.014485479328989987
nitric oxide 0.012139740209540084
casecontrol studies 0.01159502432168665
==========
TOPIC: 38 - TOPIC SCORE: 0.32731328342114385
breast cancer patients 0.05934556515711916
rectal cancer 0.0581851864305387
confidence interval 0.049929240912897764
primary tumor 0.04803981020351547
significant differences 0.047223186414071465
h pylori 0.020481882839394658
dosedependent manner 0.01827725493597441
univariate analysis 0.01789357203735552
immunohistochemical analysis 0.01514465969569096
relative risks 0.012604499345887293
==========
TOPIC: 44 - TOPIC SCORE: 0.3243047087749879
clinical trials 0.08884106946994014
hepatocellular carcinoma 0.04408286903655586
human cancers 0.03636180047396228
free survival 0.01739678200119424
epithelial cell 0.017299569685204044
recurrent disease 0.016375248088426688
standard treatment 0.014840276517110533
cancer methods 0.01475366784077592
cancerspecific survival 0.014614335261494657
animportant role 0.013778048927806028
==========
TOPIC: 17 - TOPIC SCORE: 0.3238880265041804
multivariate analysis 0.06328528229804985
significant increase 0.03609481945682823
lung cancer patients 0.03170254295797422
prognostic value 0.0313741125178178
multivariate analyses 0.021305079435449296
wildtype p53 0.014848586833840683
significant improvement 0.01482677245122327
nuclear factor 0.013938816178576646
epithelialmesenchymal transition 0.012931074344314364
residual disease 0.012918259366660094
==========
TOPIC: 39 - TOPIC SCORE: 0.30960693519250254
cancer cells 0.10262625932218586
human lung 0.029332397382489512
lung cancers 0.022602263215145257
liver cancer 0.022102784083048627
retrospective analysis 0.02115150381218353
high grade 0.02002458470660413
cancer incidence 0.01957748647572343
single agent 0.015917630322931642
mdamb231 cells 0.01518371541465734
total number 0.014673905490625706
==========
TOPIC: 13 - TOPIC SCORE: 0.3082244258789139
human cancer 0.05978400417143993
survival rate 0.02525053774244161
cell lines 0.022113913172225438
ic50 values 0.02123936278550741
a549 cells 0.01990076864208616
lncap cells 0.01957824934413536
factor vegf 0.01808457350046313
genomic dna 0.014858303425426943
mammalian cells 0.014728116933100137
transurethral resection 0.013629166749852572
==========
TOPIC: 31 - TOPIC SCORE: 0.30489885358307156
pancreatic cancer 0.09706923986947559
control group 0.046661158393270646
prostatespecific antigen 0.03048424405280925
tumor size 0.029316115305715873
advanced breast 0.0210398865799521
chemotherapeutic agents 0.01817930825451229
early breast 0.017722230388841187
early stages 0.01729555819557059
clear cell 0.014390178247821687
multivariate cox 0.013361407165351594
==========
TOPIC: 20 - TOPIC SCORE: 0.296421071357175
important role 0.058864996232835885
anticancer drugs 0.03575671144535993
further studies 0.029129249230063062
medical records 0.021347221029804055
several studies 0.020469817238263976
western blot 0.020386803806626302
several types 0.016752092104557085
lung cancer cells 0.016461662148857553
psa levels 0.015669335110822188
cancer mortality 0.015392758396132694
==========
TOPIC: 37 - TOPIC SCORE: 0.2860415746476063
epidermal growth 0.059883049899222496
critical role 0.027679678782947855
anticancer drug 0.026035237164210245
insulinlike growth 0.022121700449596292
transcription factors 0.01991809728934448
factor receptor egfr 0.017663127405303455
postoperative complications 0.017226621373253644
node dissection 0.01693177318943534
genomic instability 0.015275275443017646
lung cancer risk 0.013558481280956781
==========
TOPIC: 32 - TOPIC SCORE: 0.2707134641031502
cell lines 0.09442963730864111
side effects 0.035480515881602274
normal tissue 0.032860760642156976
immune response 0.026236719747512006
partial response 0.02089076518073533
single nucleotide 0.019465119723621402
various cancers 0.01658992249493931
progressive disease 0.01439946962639747
premenopausal women 0.013848015748626508
cardiovascular diseases 0.013711101522303449
==========
TOPIC: 7 - TOPIC SCORE: 0.2701962148373334 [304/9012]
squamous cell 0.078655964083346
tumor cells 0.050076110156166566
median survival 0.038414480593691305
human papillomavirus 0.031764700381959526
disease progression 0.026648766403081118
recent advances 0.024420590044916323
low levels 0.022185912410865396
different types 0.02051057084107411
high level 0.019429576566471818
immunohistochemical staining 0.018809688365588367
==========
TOPIC: 29 - TOPIC SCORE: 0.25135883254657143
cell proliferation 0.062321954250487636
normal cells 0.037746662868503686
breast cancer risk 0.033401817817081535
malignant cells 0.026147503140035392
multidrug resistance 0.02323409619947862
mortality rates 0.02309213991658235
control subjects 0.018118870782655325
pilot study 0.015924993780325834
cancer chemotherapy 0.014194812267033936
chronic inflammation 0.013988293470560914
==========
TOPIC: 8 - TOPIC SCORE: 0.2328459688982462
previous studies 0.04079729019904215
confidence intervals 0.027891445327896214
proportional hazards 0.027163628275752846
supportive care 0.01842216686916933
green tea 0.015913561945528686
melanoma cells 0.015703908940925177
life expectancy 0.015530814062554556
hazard ratios 0.014645997914787427
breast cancerpatients 0.013774351294822285
95confidence interval 0.013647204928937898
==========
TOPIC: 34 - TOPIC SCORE: 0.22332948844265235
lymph nodes 0.05361689241301311
cell cycle 0.04389114068513897
5year survival 0.032568687691553855
primary tumors 0.029880316410710185
same time 0.01863803888862814
soft tissue 0.018210198626092425
colorectal carcinoma 0.01723023913015326
weight loss 0.016147096117388796
age groups 0.01534263583867569
immune cells 0.01446820143762094
==========
TOPIC: 47 - TOPIC SCORE: 0.2233225615345069
peripheral blood 0.04923515818735687
esophageal cancer 0.03386808928691812
renal cell 0.03210248389519658
protein expression 0.02858858729746407
lymph node metastasis 0.027886997507939215
important roles 0.021194359478460746
tumor tissue 0.020927756448054856
metastatic colorectal cancer 0.016952495539401674
natural history 0.016300409875875888
combined treatment 0.016206986568078976
==========
TOPIC: 6 - TOPIC SCORE: 0.21508541172296178
clinical trial 0.03512881138061405
monoclonal antibody 0.03266636269700154
adjuvant therapy 0.03239538818398605
nonsmallcell lung 0.03173386972454389
flow cytometry 0.029613864915687883
drug resistance 0.029337444486057747
surgical treatment 0.025891481969729863
anticancer activity 0.024832059643801304
malignant transformation 0.019700455567681005
brain metastases 0.019620359100976658
==========
TOPIC: 42 - TOPIC SCORE: 0.2081269446171082
recent studies 0.043671421196443815
radical prostatectomy 0.04191845771235433
dna damage 0.03947924388901884
endothelial cells 0.03464791888382335
reactive oxygen 0.03313236872382482
healthy controls 0.03182839594459546
palliative care 0.02797652870807044
specific antigen 0.027041125979634144
liver metastases 0.023220743259302384
prostate cancer patients 0.01913052835240069
==========
TOPIC: 18 - TOPIC SCORE: 0.20805505788781953
cancer treatment 0.046091357599543616
consecutive patients 0.04338994604984704
stem cells 0.028910798691913105
survival rates 0.028845344728639585
diagnostic accuracy 0.020327236379355646
clinical use 0.018926190322487855
primary lung 0.018652102306174582
overall response 0.017672170626197328
response rates 0.01751077832965731
malignant disease 0.013282837964557686
==========
TOPIC: 22 - TOPIC SCORE: 0.20698146026215503
high risk 0.06981101381354342
t cells 0.04774897463215495
significant association 0.028353886966228693
recent findings 0.021539418459506136
cancer prevention 0.017189641103220334
ovarian cancers 0.017117070153712936
vitamin d 0.01674421794933062
histological grade 0.016378394489477928
high frequency 0.016141507510982176
previous study 0.01458116556184468
==========
TOPIC: 11 - TOPIC SCORE: 0.1980734759967912
gene expression 0.05242010835771469
early diagnosis 0.02584149843381739
cell migration 0.024317029620962285
localized prostate 0.023423554456004952
thepresent study 0.022189785747465544
cyclin d1 0.022037721393552114
effective treatment 0.018175779517327257
fatty acids 0.017651920550502704
fatty acid 0.016686235897125673
retinoic acid 0.015458680243600456
==========
TOPIC: 45 - TOPIC SCORE: 0.1979495177009727
colon cancer 0.05899312311319439
antitumor activity 0.03403217963156195
cancer stem cells 0.024938079934137544
wild type 0.020096884692999032
carcinoembryonic antigen 0.01833391040541782
clinical features 0.016605064343825103
renal cancer 0.016005471614679623
breast tumors 0.015592191995820223
life qol 0.015497525716431901
early gastric cancer 0.01545787324636892
==========
TOPIC: 1 - TOPIC SCORE: 0.19775027562105155
tumor growth 0.057715635799841375
high levels 0.04518240624279824
clinical practice 0.032062842926197634
physical activity 0.028792873819015765
cancer survivors 0.023791012913426383
response rate 0.0225461549183927
pc3 cells 0.017343704077459277
future studies 0.015574220823587965
ovarian carcinoma 0.014979376183381342
cytotoxic activity 0.014976908617592533
==========
TOPIC: 28 - TOPIC SCORE: 0.19323115582954234
bladder cancer 0.05233674276171279
cancer cell lines 0.0481639660751211
wide range 0.03266428297352827
skin cancer 0.027126554625847357
primary care 0.026404393599248784
wide variety 0.021373649463402155
mean age 0.021223104870500588
amino acids 0.02053416323978061
signaling pathways 0.01991472641458653
node metastases 0.014770623839067822
==========
TOPIC: 23 - TOPIC SCORE: 0.1926440882150571
endometrial cancer 0.0629973969973495
logistic regression 0.030291712905744665
inhibitory effect 0.024180209896303193
cell viability 0.023515998505461135
photodynamic therapy 0.018682758187326943
tumor development 0.01867274651125423
inhibitory effects 0.018037964144865956
coronary heart 0.01487176183006959
mouse models 0.014646180339690113
cancer pain 0.013832159128326207
==========
TOPIC: 0 - TOPIC SCORE: 0.19122924744757552
cancer risk 0.04365561592876321
metastatic breast 0.03856367211081143
expression levels 0.03510672803982253
clinical outcome 0.031012698439149947
primary breast 0.030653097558520616
testicular cancer 0.023844135166919127
clinical outcomes 0.02135759867255996
positive predictive value 0.020616874586405015
negative predictive value 0.01748756441411407
target cells 0.014865242530364888
==========
TOPIC: 35 - TOPIC SCORE: 0.18330126179918022
oral cancer 0.04100837759270243
local recurrence 0.035231202970040475
overall survival 0.03195374971682561
thyroid cancer 0.030174288672463384
vascular endothelial growth 0.024767513598202343
animal models 0.02353162484366136
adverse events 0.02143895017397162
computed tomography 0.01817160307381153
regional lymph 0.016954505670326213
advanced gastric cancer 0.016520049408151955
==========
TOPIC: 43 - TOPIC SCORE: 0.17795725103341747
current study 0.03861689208837456
neck cancer 0.03659203185988881
cardiovascular disease 0.03310484031688394
nk cells 0.0271447104504121
adverse effects 0.024359540798100397
tumor microenvironment 0.02098148306301457
family members 0.020207514278692277
natural killer 0.019951149075332512
social support 0.016828323834316754
metastatic cancer 0.016172265966645484
==========
TOPIC: 2 - TOPIC SCORE: 0.16996452770302584
prostate cancer cells 0.031668110985618655
high expression 0.027517358191761813
advanced stage 0.027438126662396787
independent predictor 0.015419046226696917
reverse transcriptase 0.014424695652684436
benign lesions 0.013301333711452432
african americans 0.013207636645542833
b cells 0.012745882647488514
laparoscopic surgery 0.012641461973971813
polymerase chain reaction 0.012635279872353439
==========
TOPIC: 10 - TOPIC SCORE: 0.1694913546936791
general population 0.04335105685602699
human colon 0.0366872034917232
elderly patients 0.03154233104368603
various types 0.025252309670416407
gastric carcinoma 0.023585286885818353
urinary bladder 0.02096818421351147
elevated levels 0.020437618811851306
tissue samples 0.017779899452741398
cigarette smoking 0.016891561782357692
ectopic expression 0.015798524321817234
==========
TOPIC: 12 - TOPIC SCORE: 0.16692569151811837
molecular mechanisms 0.041096522335334375
normal tissues 0.040455549727789065
cell line 0.039363033139868775
advanced cancer 0.02834063827157498
advanced disease 0.026572640293325
transcriptional activity 0.019081634897092224
lymph node 0.017691441108892418
liver metastasis 0.016844696584369323
other diseases 0.015174515091571564
low doses 0.014895479308074338
==========
TOPIC: 4 - TOPIC SCORE: 0.16239167102247953
nude mice 0.04544963498507365
early detection 0.04484422272130405
tumour cells 0.02545057529750835
protein levels 0.02535699800616801
axillary lymph 0.02267509449682127
gene therapy 0.019843751923595918
gleason score 0.01886460396436936
crucial role 0.017835933828188863
further investigation 0.017349411893611652
colon cancer cells 0.016993662192761542
==========
TOPIC: 16 - TOPIC SCORE: 0.14976219831528859
significant difference 0.05581639169031255
immune system 0.032700834139873236
large number 0.025447449224518106
prognostic significance 0.023305739249272414
dna repair 0.017066175892317813
small molecule 0.016851461043039848
central nervous system 0.016113474489672604
differential diagnosis 0.015433988622203477
intestinal metaplasia 0.014782314653398796
group b 0.014734695482641745
==========
TOPIC: 33 - TOPIC SCORE: 0.14898290333536
cell death 0.05906445213037029
surgical resection 0.03466710970541477
clinical studies 0.029718385189801296
laryngeal cancer 0.01840777526329671
other factors 0.018178852503565282
protective effect 0.018158595535868797
cell types 0.017617963784405156
possible role 0.01718599789166011
histological type 0.015607227317905436
squamous cellcarcinoma 0.01520203716535922
==========
TOPIC: 3 - TOPIC SCORE: 0.14485720820955478
epithelial cells 0.03964121818353677
distant metastasis 0.027430669847285087
cancer progression 0.02657550116270815
colorectal cancers 0.023199057518607836
high incidence 0.022689290116382245
hela cells 0.022437517323129003
cancer cases 0.01789554032899601
high rate 0.015484877696459417
therapeutic potential 0.013565237765343583
normal mucosa 0.013486997494623012
==========
TOPIC: 21 - TOPIC SCORE: 0.1442778482705391
early stage 0.04330143531404569
lung cancer nsclc 0.028008895764309587
cancer development 0.0242309629286751
hazard ratio 0.023185312627465725
adjuvant treatment 0.018627346921306923
epidemiological studies 0.016496457688265416
advanced nsclc 0.016216846738401142
central role 0.01510121422559139
cytotoxic effects 0.0145057529325854
urinary tract 0.014140218245270834
==========
TOPIC: 15 - TOPIC SCORE: 0.14125641576156275
other hand 0.04281861394452746
longterm survival 0.030758641678154598
cancer diagnosis 0.025716028759069656
curative resection 0.023862107027119345
many patients 0.021044379408432217
hepg2 cells 0.020220109163283085
breast carcinoma 0.017827292832416738
survival benefit 0.017029972398557133
tumor samples 0.016620120541508306
endoplasmic reticulum 0.016407938561312067
==========
TOPIC: 26 - TOPIC SCORE: 0.1329723221062735
radiation therapy 0.046825741368194215
tumor progression 0.037968624193072294
serum levels 0.024839803107159674
dna methylation 0.023755998676864346
lymph node metastases 0.021700545873959715
mammary gland 0.019514169770644227
controlled trials 0.0191526987812741
statistical significance 0.016268471217216585
western blot analysis 0.015821801424558926
combination therapy 0.015648565301631175
==========
TOPIC: 19 - TOPIC SCORE: 0.12870133365702838
mcf7 cells 0.04184711179268857
ratio or 0.03861593140881008
diseasefree survival 0.03680083405549083
recent years 0.03646467314739963
casecontrol study 0.026536118574848933
growth inhibition 0.020436208613231165
few studies 0.020155485069130712
ductal carcinoma 0.01865994203943431
age group 0.01717173929302333
cancer screening 0.014653839391664217
==========
TOPIC: 36 - TOPIC SCORE: 0.12479210463426968
confidence interval ci 0.0468849440018028
first time 0.04271718980164625
key role 0.02235652489524509
significant correlation 0.019637758530112365
crc patients 0.01866080204415066
stable disease 0.017198898486315787
retrospective review 0.01641144705312865
blood samples 0.01502473867624993
malignant melanoma 0.01422843462151835
metastatic lymph 0.013225417660525436
==========
TOPIC: 46 - TOPIC SCORE: 0.12239479459491899
relative risk 0.04312632404731693
oxidative stress 0.040317262146266575
distant metastases 0.028874577178933342
external beam 0.02163130085692433
mrna expression 0.01877875562890757
high dose 0.01797914544795384
mouse model 0.017381250426338975
mutant p53 0.015067770407128794
carcinoma cells 0.014842901771774096
low dose 0.014629007959799958
==========
TOPIC: 24 - TOPIC SCORE: 0.11492349702030173
tumor tissues 0.025658350371654138
potential role 0.02359435073861417
systematic review 0.02339481969532723
significant decrease 0.022335402755188357
therapeutic efficacy 0.021200887692310464
cancer tissues 0.018779573143627045
further research 0.017838611153715163
predictive value 0.01743623553939152
healthy individuals 0.01488532756532888
tumor volume 0.014752812849336161
==========
TOPIC: 41 - TOPIC SCORE: 0.10998448938693071
postmenopausal women 0.03589849582337777
dendritic cells 0.02262199322774567
other cancers 0.022123724038499333
clinical significance 0.02185197655482864
antitumor effects 0.018367051539391922
median time 0.017805478710276337
poor survival 0.014994720174331682
ofcolorectal cancer 0.01487633831635844
childhood cancer 0.01354661002261773
germline mutations 0.013523515236120024
==========
TOPIC: 14 - TOPIC SCORE: 0.10957447082067984
oral cavity 0.03484489720341778
monoclonal antibodies 0.03385889314132616
prognostic factors 0.0332367939687666
hormonal therapy 0.020721447308005903
molecular mechanism 0.019274031606714818
ulcerative colitis 0.01569981318987578
metastatic prostate 0.015605673358826183
clinicopathological features 0.014525442160893139
inhibitory activity 0.014385556370870922
cell invasion 0.012700707836844693
==========
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment