Martin Krzywinski / Genome Sciences Center / mkweb.bcgsc.ca Martin Krzywinski / Genome Sciences Center / mkweb.bcgsc.ca - contact me Martin Krzywinski / Genome Sciences Center / mkweb.bcgsc.ca on Twitter Martin Krzywinski / Genome Sciences Center / mkweb.bcgsc.ca - Lumondo Photography Martin Krzywinski / Genome Sciences Center / mkweb.bcgsc.ca - Pi Art Martin Krzywinski / Genome Sciences Center / mkweb.bcgsc.ca - Hilbertonians - Creatures on the Hilbert Curve
Trance opera—Spente le Stellebe dramaticmore quotes

words: meaningful


In Silico Flurries: Computing a world of snow. Scientific American. 23 December 2017


language + fiction

Dark Matter of the English Language—the unwords

Words are easy, like the wind;
Faithful friends are hard to find.
—William Shakespeare

These are London Underground station names generated by training on 622 actual London station names.

Public transit has never been this fun.

—8—
Aac Purk
Aad Hare
B Marrey
Balting
Calwinl
Cam Mary
D Carton
Dancon &
E Bralge
E Readen
Falsser
Feltham
Gatean S
Gay Park
H Canrey
Ham Roe
Iule ald
Janston
Ked uark
Kel Road
Lat Park
Lat oute
Mal Parl
Mal kary
Ne terlo
Neltolr
Oack Oek
Oad Gate
Pam Park
Par Btos
Queenas
Raa pale
Raywors
S Ceoley
S Digham
Tal Paln
Tat Park
Ubl Hall
Ues Wack
Wam prie
Wamdron
—9—
Aact Park
Aadon Hon
Baats Olk
Badin Eak
C Houncom
Caln Park
Da Halrey
Dack Cans
E penhalr
Each Hill
Farn Hill
Farn tale
Galb Wesr
Gane Hart
Hald Harf
Hald thel
Iach Hanm
Iali Park
Jace Eard
Japb Road
K Croydon
Kans Road
Lamen Oad
Lane Road
Maan Road
Maliford
N te Parl
Nar Breet
Oack Hinl
Oak Warte
Pallo Loy
Paok Hole
Qoeem amm
Qood ford
Ranchpal
Rayd Park
S Dsealey
S Evenham
Tath Hill
Tew Grice
Uad Surth
Udper Ead
Wackbury
Wal Crise
—10—
A ton Erst
Aak Ssreet
Back Green
Badne Road
C Palkbond
C syerrild
Daetp Mary
Dagton Mom
Eaad Ecton
Eaak Weast
Fais Grove
Fandham Le
Gaden Lane
Gadge Walt
H Hiclelay
Hadel Park
Iator Himp
Icton Down
Jambllean
Jichl Buck
KanOl Hanl
Kanan Town
LaHee Line
Labor Road
Mal Wathin
Maldon Oad
Nar untrig
Narth Park
Oaing Park
Oak Street
Paine Tiry
Pakor Hill
Qaom Ciwns
Qleew atte
Raad Cross
Raan Greet
S Celerons
S Janrwayd
Tanor Hark
Tead Jurns
Uamom Nort
Ucton Pilk
Vaoss Mroy
Veilh Bark
Waath Roas
Wack Canes
x Acesford
—11—
Aaast Green
Aach Saoret
Baants Park
Back Outham
C Haug Dell
Cabery Roat
Dadpel Herl
Dagton Hich
Eabcon Parn
Eacest Gaed
Fakden Sard
Falon Coutt
Gaades Wisl
Gacks Green
H cocnstort
H yanesting
Ianes Parke
Ianmon outt
Jannse Eath
Jarr' Greel
Kales Broad
Kanbor Ctos
Laddon Road
Lale Prrden
Madbad Hill
Madbon Hill
Nalton Park
Nardon Hall
Oader Green
Oadwe Coutt
P'vden Hall
Palder Cloy
Qharss Park
Qneene Park
Rabham uonb
Radal Croas
S Doungwort
S Wenherles
Tachyy Hark
Taddon Manf
Uadban Road
Uales Green
Veston Brad
Vinley Park
W Penk Town
Waadss Pord
—12—
Aakher Weath
Aanger Swark
Backham Hill
Backton West
C Nilsherton
Cachsoy Road
Dacbons Road
Dacknen Park
Eabpine Park
Eacens Green
Falnel Aales
Falnens Harl
Gack Eistie
Gaddens Wook
H Wemhalfoud
HaHdon Court
Iachwam Hick
Iaday Street
Jaldens Ipee
Jalwild Hood
Kadbinp Gare
Kalburn Park
Laange Torne
Ladgate High
Madrord Wood
Madsane Park
Naldhed Road
Naltham Road
Oadford Hols
Oadsram Hest
Paandon Park
Pabnick Mann
Qaapeam East
Qeanper Park
Raambon Town
Rac fordbond
S Govenbinll
S Hechertham
Tactham Hoxd
Talders Park
U link Green
Uackher Park
Vamptree tea
Vanbury Gate
Waanl Citray
Wackley Wick
x Abory Hoar
—13—
Abury Cerninl
Acherton Park
Baantley Road
Backbory Cown
C tenead Road
Ca onton Town
Daass Heltray
Dack iln Park
Ea Cton Sorte
Eaalfowe Pank
Facchary Road
Fadsare Touth
Gackbord Lone
Gadden Street
H Colney Park
H Hockiunh Ey
Ictamal Green
Icteron Arley
Jancham Hecle
Janens Strhet
Kalbowad Dark
Kanbury Green
Lachaut South
Laledon Sroed
Mady Jucnchee
Maels Angeran
Nagborr Green
Nalborte Park
Oadgeton Bale
Oadnston Loos
Packoon South
Packsens Town
Qarast Isters
Qoaden Stweet
Raanbhey Road
Rabrrigh urke
S Dheysonston
S Garees Groe
Tambern harth
Tantean' Cill
UBlenham Park
Uacerour Park
Varchley Park
Varcon Street
WackBes Park
Wackens Green

posh parks

—9—
Aact Park
Aats Park
Bale Park
Bane Park
Caln Park
Cear Park
Dest Park
Dham Park
Ead' Park
Eale Park
Gest Park
Gite Park
Hawe Park
Hene Park
Iali Park
Irle Park
KanOsPark
Keng Park
Lang Park
Layy Park
Mann Park
Maor Park
Nood Park
Nort Park
Oawe Park
Oess Park
Park Park
Pars Park
Rayd Park
Read Park
SouthPark
Syer Park
Tood Park
Toor Park
Uilp Park
Wast Park
Weel Park
—10—
Aales Park
Aalor Park
Balks Park
Balon Park
Calon Park
Carye Park
Danch Park
Ddans Park
Eador Park
Eadss Park
Fewel Park
Fiwey Park
Galee Park
Garte Park
Hadel Park
Halon Park
Ieder Park
Ildar Park
Junns Park
Kange Park
Kenle Park
Laner Park
Lenle Park
Mator Park
Mente Park
Narth Park
Nonth Park
Oaing Park
Oakon Park
Parlo Park
Parse Park
Quins Park
Reash Park
Reden Park
Samte Park
Sedde Park
Toore Park
Toott Park
Upgea Park
Uppan Park
Waigl Park
Walor Park
—11—
Aalang Park
Aalmla Park
Baants Park
Baldon Park
Calden Park
Calnon Park
Dapons Park
Dapten Park
Eacham Park
Eagtea Park
Falvel Park
Faodse Park
Gaders Park
Gafint Park
HaHass Park
Hailon Park
Idbrey Park
Idters Park
Julror Park
Kenbor Park
Kender Park
Lamere Park
Landoe Park
Malbar Park
Mallen Park
Nalton Park
Nenser Park
Oaltor Park
Oeddon Park
Palsay Park
Pandar Park
Qharss Park
Qneene Park
Rairyy Park
Ramens Park
Sauker Park
Sbount Park
Tarner Park
Tatlan Park
Uphilg Park
Vinley Park
Walley Park
Walpar Park
—12—
Aatgale Park
Adeondy Park
Bankres Park
Barcins Park
Cackdon Park
Cackton Park
Dacknen Park
Dalpewy Park
Eabpine Park
Eadsewe Park
Famesle Park
Faoving Park
Gaicong Park
Galbark Park
Hadbrey Park
Hallind Park
Iderily Park
Ikderse Park
Jasries Park
Jompher Park
Kalburn Park
Kambrey Park
Lagherh Park
Lalewon Park
Madsane Park
Malford Park
Narbery Park
Narbrey Park
Oakbote Park
Oakpute Park
Paandon Park
Palberl Park
Qeanper Park
Qoadens Park
Radburs Park
Raetham Park
S yamfe Park
Satbery Park
Talders Park
Tanping Park
Uackher Park
Updenle Park
Velting Park
Vlenton Park
Walford Park
Wampror Park
—13—
Acherton Park
Acteraud Park
Balkford Park
Banbford Park
Cal Oast Park
Calboune Park
Dack iln Park
Dameston Park
Eadswerd Park
Eagelnan Park
Falngich Park
Fansters Park
Gadturon Park
Gandland Park
H Colney Park
Halcourh Park
Ihfielsl Park
Ildendon Park
Jsterlip Park
Julsliwe Park
Kanbwrey Park
Kemblide Park
Lamerses Park
Landborn Park
Maleston Park
Mandan's Park
Nalborte Park
Nanblood Park
Oalesele Park
Oekernon Park
Parkfors Park
Parkorse Park
Qoidgeat Park
Qoidnell Park
Rayterle Park
Readbery Park
Saterxon Park
Satthame Park
Tawonton Park
Tebterle Park
UBlenham Park
Uacerour Park
Varchley Park
Vincerle Park
WackBes Park
Walborne Park
—14—
Achtelhan Park
Adgingame Park
Balingbou Park
Balperham Park
C Beysons Park
Calweldon Park
Dadniwone Park
Dalmetham Park
Ealinghen Park
Eals Bite Park
Falmonton Park
Falnsbury Park
Gadbtidge Park
Gan Surde Park
Hackyyham Park
Hambenrow Park
Ickichgon Park
Ilfuidgay Park
Jichlimin Park
Jutlilley Park
Kanpaloon Park
Kensiwale Park
Lakingdon Park
Larcenles Park
Manbondon Park
Manbord&e Park
Neetilrul Park
Nerhiogto Park
Oeethwate Park
Oek Eaton Park
Paln Stet Park
Paltingam Park
Qaenbends Park
Qoeenbner Park
Raralsaun Park
Rarmenton Park
S iskwark Park
SEdgerlol Park
Talfierdg Park
Tambonnne Park
Uwickston Park
Wamkshouk Park
Wannstind Park

the looss

—9—
Chillloon
Ciayblood
Lood Head
Lood Hill
Ropreyloo
Soudhlood
Weichloo
—10—
Bloodfeach
East Asloo
Harloordow
Lood Brove
Lood Soree
Nordhaloon
Perleslood
South Loon
Tow Haloon
Wichglooat
Wickilloon
—11—
Beonth Loon
Bornhamloou
Carnichlood
Gloog Aiton
Lood Gorder
Loode Green
Menpitloods
Woons Cloon
—12—
Elelham Lood
Gording Lood
Hilloor Loan
Loofor South
Loondan Dood
Maron Haloon
Moloond dane
Pallood Park
West Hallood
Westleblood
—13—
Bickh Hillloo
Eeltewon Lood
Elensgilblood
Hand Widceloo
Harkloos Lene
Laneting Loos
Lood Cronchey
Maolloon Park
Moinsouwiloon
Nanblood Park
Oadnston Loos
Ricghily Loon
Sevensinslood
—14—
Carnslood Lane
Galdondon Lood
Haringloo Park
Kanpaloon Park
Kenslood Green
Leumen Harloow
Linghlood Road
Slooath Morton
South Sloondon

the inges

—9—
Choyninge
Lemstinge
Nem Linge
Roletinge
Wiybringe
—10—
Binge Each
Calarminge
Cary Ginge
Firdylinge
Reyseringe
Wham Kinge
—11—
Boinge Hill
Bouse Binge
Cantinginge
Eanweytinge
Sheeretinge
—12—
Ciminge ford
Foringe Park
Lewinge Cich
Now Delninge
—13—
Admenty Binge
Barminge Lare
Bartinge Park
Calinge South
Canvinge Park
Demringe Road
Eystinge Park
Geryinge Wish
Merringe Gate
Mertinge Wesl
Nent Tomdinge
Oaleslordinge
Parlinge Park
Parvinge Park
Sulevey Linge
—14—
Beostinge Park
Bringe Eadbury
Calninge Harks
Chardinge Minl
Dawinge Street
Femtinge Crocd
Greeninge Palk
Jitch Cerninge
Paorxinge Park
Royle Herlinge
South Hillinge
South Kambinge
Uppinge Gareen

the tons

—5—
Acton
Adton
Caton
Citon
Eaton
Ecton
Gaton
Giton
Icton
Inton
Maton
Meton
Olton
Onton
Upton
Utton
—6—
Aaston
Acston
Balton
Bamton
Calton
Camton
Dagton
Daston
Eacton
Eadton
Falton
Fedton
Galton
Ganton
Hagton
Hapton
Ieston
Kanton
Katton
Lebton
Ledton
Manton
Marton
Nanton
Narton
Oigton
Parton
Paston
Rayton
Relton
Stiton
Surton
Tatton
Tenton
Udcton
Uenton
Wabton
Wafton
—7—
Adeston
Alepton
Backton
Barbton
Caauton
Ceaston
Dackton
Damcton
Eadston
Eddston
Famston
Feenton
Garyton
Geoston
Hackton
Halpton
Jemcton
Juncton
Kendton
Kenton
Lhiyton
Lington
Maryton
Mhoston
Newston
Nitston
Omenton
Osepton
Parkton
Pinston
Qoodton
Queyton
Rackton
Racpton
SKenton
Shedton
Tewyton
Thatton
Ulapton
Uoudton
Vectton
Wackton
Wampton
—8—
Achonton
Admelton
Baln'ton
Baronton
Camenton
Camerton
D Carton
Dagenton
Ealeston
Ealeyton
Faichton
Fertston
Grienton
Guteiton
HaKenton
Hammston
Icherton
Ilepston
Janston
Jorchton
Khampton
Kingston
Laleston
Laterton
Marbaton
Marnston
Nartston
Norbuton
Oacenton
Oakuston
Pamerton
Parkston
Quamcton
Quayston
Reventon
Reworton
Sentiton
Seventon
Tewelton
Thimston
Ucmenton
Uhmonton
Walbuton
Wamenton
—9—
Aakington
Aapington
Badmerton
Barimston
Cadonston
Calangton
Dadenston
Dectenton
Eacherton
Eadborton
Farbonton
Fealiton
Gadington
Garbiston
Halburton
Haldenton
Iakenston
Iakington
Jechcuton
Kambuston
Kenbouton
Lanborton
Lashelton
Manmonton
Masborton
Nedborton
Nemmonton
Oadborton
Ollington
Pachenton
Panciston
Qriangton
Queenston
Rasleyton
Rasserton
Samhatton
Setporton
Tarconton
Toldenton
Udnington
Uetington
Wackbuton
Wamilgton
—10—
A ton Erst
Aalimgeton
Baklington
Balcongton
Cackington
Cahbuctton
Dagton Mom
Daldington
Eaad Ecton
Eactton Le
Faldington
Falsington
Galdington
Ganbilgton
HaCrreston
Hackonston
Icton Down
Icton Holl
Jestington
Juldington
Kellington
Kencington
Landington
Lanhgetton
Maldington
Maleihgton
Nandonston
Narton Dow
Oadossyton
Oak Verton
Packington
Paesvelton
Qooyerston
Queysston
Raldington
Ranmington
S Jownaton
Satdington
Tarnington
Tedlington
Ucton Pilk
Upseadston
Varxington
Visdington
Wacton Hor
Waldington
—11—
Aanton Hill
Aaton Greet
Bagton Town
Balton Road
Cagton Hich
Calton Gare
Dackconcton
Dagongerton
Eagton Eald
Ealton Bauk
Falton Sint
Fanton Dant
Gacton Pird
Ganton Park
Haldsington
Halton Lane
Ias Hington
Ipeedington
Janningston
Jolton Mart
Karton Ciss
Kelton West
Lales Anton
Lanmingeton
Macklandton
Macklondton
Nalton Park
Nandstorton
Oals Auston
Oantimeaton
Pardingston
Parstington
Qadesesston
Qoachington
Racklington
Rapton East
Sank urston
Sarton Hoot
Tarnevelton
Tecton Cill
Uppingeaton
Veston Brad
Vonton Gree
Wadblry ton
Walton Cism

VIEW ALL

news + thoughts

Statistics vs Machine Learning

Tue 03-04-2018
We conclude our series on Machine Learning with a comparison of two approaches: classical statistical inference and machine learning. The boundary between them is subject to debate, but important generalizations can be made.

Inference creates a mathematical model of the datageneration process to formalize understanding or test a hypothesis about how the system behaves. Prediction aims at forecasting unobserved outcomes or future behavior. Typically we want to do both and know how biological processes work and what will happen next. Inference and ML are complementary in pointing us to biologically meaningful conclusions.

Martin Krzywinski @MKrzywinski mkweb.bcgsc.ca
Nature Methods Points of Significance column: Statistics vs machine learning. (read)

Statistics asks us to choose a model that incorporates our knowledge of the system, and ML requires us to choose a predictive algorithm by relying on its empirical capabilities. Justification for an inference model typically rests on whether we feel it adequately captures the essence of the system. The choice of pattern-learning algorithms often depends on measures of past performance in similar scenarios.

Bzdok, D., Krzywinski, M. & Altman, N. (2018) Points of Significance: Statistics vs machine learning. Nature Methods 15:233–234.

Background reading

Bzdok, D., Krzywinski, M. & Altman, N. (2017) Points of Significance: Machine learning: a primer. Nature Methods 14:1119–1120.

Bzdok, D., Krzywinski, M. & Altman, N. (2017) Points of Significance: Machine learning: supervised methods. Nature Methods 15:5–6.

...more about the Points of Significance column

Happy 2018 `\pi` Day—Boonies, burbs and boutiques of `\pi`

Wed 14-03-2018

Celebrate `\pi` Day (March 14th) and go to brand new places. Together with Jake Lever, this year we shrink the world and play with road maps.

Streets are seamlessly streets from across the world. Finally, a halva shop on the same block!

Martin Krzywinski @MKrzywinski mkweb.bcgsc.ca
A great 10 km run loop between Istanbul, Copenhagen, San Francisco and Dublin. Stop off for halva, smørrebrød, espresso and a Guinness on the way. (details)

Intriguing and personal patterns of urban development for each city appear in the Boonies, Burbs and Boutiques series.

Martin Krzywinski @MKrzywinski mkweb.bcgsc.ca
In the Boonies, Burbs and Boutiques of `\pi` we draw progressively denser patches using the digit sequence 159 to inform density. (details)

No color—just lines. Lines from Marrakesh, Prague, Istanbul, Nice and other destinations for the mind and the heart.

Martin Krzywinski @MKrzywinski mkweb.bcgsc.ca
Roads from cities rearranged according to the digits of `\pi`. (details)

The art is featured in the Pi City on the Scientific American SA Visual blog.

Check out art from previous years: 2013 `\pi` Day and 2014 `\pi` Day, 2015 `\pi` Day, 2016 `\pi` Day and 2017 `\pi` Day.

Machine learning: supervised methods (SVM & kNN)

Thu 18-01-2018
Supervised learning algorithms extract general principles from observed examples guided by a specific prediction objective.

We examine two very common supervised machine learning methods: linear support vector machines (SVM) and k-nearest neighbors (kNN).

SVM is often less computationally demanding than kNN and is easier to interpret, but it can identify only a limited set of patterns. On the other hand, kNN can find very complex patterns, but its output is more challenging to interpret.

Martin Krzywinski @MKrzywinski mkweb.bcgsc.ca
Nature Methods Points of Significance column: Machine learning: supervised methods (SVM & kNN). (read)

We illustrate SVM using a data set in which points fall into two categories, which are separated in SVM by a straight line "margin". SVM can be tuned using a parameter that influences the width and location of the margin, permitting points to fall within the margin or on the wrong side of the margin. We then show how kNN relaxes explicit boundary definitions, such as the straight line in SVM, and how kNN too can be tuned to create more robust classification.

Bzdok, D., Krzywinski, M. & Altman, N. (2018) Points of Significance: Machine learning: a primer. Nature Methods 15:5–6.

Background reading

Bzdok, D., Krzywinski, M. & Altman, N. (2017) Points of Significance: Machine learning: a primer. Nature Methods 14:1119–1120.

...more about the Points of Significance column

Human Versus Machine

Tue 16-01-2018
Balancing subjective design with objective optimization.

In a Nature graphics blog article, I present my process behind designing the stark black-and-white Nature 10 cover.

Nature 10, 18 December 2017

Machine learning: a primer

Thu 18-01-2018
Machine learning extracts patterns from data without explicit instructions.

In this primer, we focus on essential ML principles— a modeling strategy to let the data speak for themselves, to the extent possible.

The benefits of ML arise from its use of a large number of tuning parameters or weights, which control the algorithm’s complexity and are estimated from the data using numerical optimization. Often ML algorithms are motivated by heuristics such as models of interacting neurons or natural evolution—even if the underlying mechanism of the biological system being studied is substantially different. The utility of ML algorithms is typically assessed empirically by how well extracted patterns generalize to new observations.

Martin Krzywinski @MKrzywinski mkweb.bcgsc.ca
Nature Methods Points of Significance column: Machine learning: a primer. (read)

We present a data scenario in which we fit to a model with 5 predictors using polynomials and show what to expect from ML when noise and sample size vary. We also demonstrate the consequences of excluding an important predictor or including a spurious one.

Bzdok, D., Krzywinski, M. & Altman, N. (2017) Points of Significance: Machine learning: a primer. Nature Methods 14:1119–1120.

...more about the Points of Significance column

Snowflake simulation

Tue 16-01-2018
Symmetric, beautiful and unique.

Just in time for the season, I've simulated a snow-pile of snowflakes based on the Gravner-Griffeath model.

Martin Krzywinski @MKrzywinski mkweb.bcgsc.ca
A few of the beautiful snowflakes generated by the Gravner-Griffeath model. (explore)

The work is described as a wintertime tale in In Silico Flurries: Computing a world of snow and co-authored with Jake Lever in the Scientific American SA Blog.

Gravner, J. & Griffeath, D. (2007) Modeling Snow Crystal Growth II: A mesoscopic lattice map with plausible dynamics.