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
Safe, fallen down this way, I want to be just what I am.Cocteau Twinssafe at lastmore quotes

EMBO Practical Course: Bioinformatics and Genome Analysis, 5–17 June 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

unnames

These are names generated from the US Census list of names using a char-rnn recurrent neural network.

The names generated by the network appear neither in the list of names nor in a 479,000 list of English words. The names may be words or names in another language, however.

female first names that don't exist

Your friends discouraged you from naming your first daughter "Ginavietta Xilly Anganelel" but you didn't listen. When you named your second daughter "Nabule Yama Janda" everyone wanted to know what your secret to having such successful children was.

Below are the alphabetically first 3–10 letter female unnames for each letter. In some cases, no names of a given length were generated for a given letter.

—3—
Bei
Cac
Cau
Daa
Deu
Edz
Ele
Fea
Fri
Hea
Hhi
Ied
Ien
Jea
Kau
Kec
Ldo
Leb
Maz
Mec
Nie
Nin
Oro
Ota
Reu
Ric
Seu
Sia
Tix
Tuu
Uan
Uid
Vad
Vea
Wie
Wil
Xai
Xon
Yka
Yra
—4—
Aaya
Abal
Bbhy
Beli
Cani
Caro
Daee
Dayn
Eann
Ebha
Gori
Guda
Hael
Hari
Idek
Idla
Joga
Joon
Kace
Kade
Laan
Laha
Mada
Madi
Nado
Nian
Olce
Olly
Phry
Pide
Qisy
Qoly
Rari
Rary
Sabi
Saes
Tany
Tary
Ucte
Uida
Vatt
Vean
Wada
Waid
Xiem
Yama
Yamn
Zibi
Ziun
—5—
Adree
Adyla
Babyl
Balbo
Caccy
Cadda
Dadel
Dader
Eddra
Ededr
Fibee
Fleei
Gelan
Guita
Hacie
Haela
Idale
Idena
Janda
Jerly
Kaaly
Kacee
Laala
Lacee
Maala
Mabie
Nayle
Nelli
Olako
Olise
Payna
Phaci
Qinsy
Qolee
Raane
Racey
Sacti
Sacul
Tabbr
Tabuy
Uanga
Uayda
Vaale
Vadia
Wagwa
Walyg
Xilly
Xiwda
Yabuy
Yahye
—6—
Adeley
Alelee
Babela
Bajbie
Caccye
Cacell
Dadela
Dakith
Edalla
Edelah
Feliey
Felike
Garlee
Geldie
Haishe
Haline
Idelig
Idelle
Jaccey
Jatqie
Kaceey
Kacele
Laceie
Ladira
Maarae
Maarla
Nabule
Nadera
Olchee
Olisha
Pamber
Parell
Qoesha
Qoleen
Rabina
Rabymi
Sachie
Sacola
Tafbie
Tamima
Ulieta
Ullena
Vadeta
Vandie
Waghel
Wandie
Xaique
Xillia
Yaketo
Yameka
—7—
Alenlis
Alissea
Barelah
Barmeta
Cacalla
Caccayc
Dalecee
Dalleer
Ebeccii
Eeenera
Farleen
Ferreda
Ganalel
Griagne
Harlean
Hayceda
Iellina
Ienetka
Jadquen
Jaqquil
Kaariko
Kabjine
Labelle
Labrice
Maadite
Maadrae
Nachlee
Naqoena
Ollisha
Oralore
Panelte
Paricel
Qilonga
Qlianna
Rabette
Racelie
Sacelie
Sacelle
Tamarie
Tamarke
Ualacie
Uibelle
Valerte
Vanelte
Waylena
Wazlein
Yadalie
Yakkina
—8—
Aleretha
Allalera
Bamberah
Battynkb
Caccelle
Cacellen
Dacheele
Dameline
Eetenere
Eethelie
Feairice
Gaannele
Gelneria
Hacylone
Hecticie
Iachelie
Ilabetth
Jacquine
Jaqqueyn
Kabrenee
Kacalyne
Laloytha
Langella
Maarmila
Mabylere
Nadalena
Nadmelle
Orotenne
Parleeta
Parmicia
Quettine
Rachilde
Racierda
Saaleych
Saccelle
Tasharia
Tathrika
Uuguetta
Uussuida
Valtonda
Vassicha
Wapreida
Willenee
Yaumette
Yeholaki
—9—
Anganelel
Bathueyna
Bealyakha
Caccalren
Caleniqsa
Dalerisha
Dannerele
Eferwrace
Elaberosh
Genelnice
Helmarita
Hemaricia
Ieanerise
Ilbebette
Jatquelyn
Kacalenne
Kacelynen
Lasheudde
Laverethe
Macarelze
Macbalica
Nompterla
Porpencia
Ramancina
Rarashera
Saccellne
Sanelline
Thashinda
Tizkiqhie
Ususuista
Uussautti
Velletita
Vellotina
—10—
Camalincia
Ccarleetta
Deliqheeda
Elatoresha
Elisamerie
Ginavietta
Iimameline
Ilollinina
Karestanet
Kariamarie
Lelagrelie
Lelerateta
Maccelline
Maceannica
Retaqyelle
Saraquetta
Shelolesne
—11—
Cciccinelda
Cclarleette
Elisazetlie
Elisebethle
Ikekzikeina
Ilizeblelle
Kimbhrresty
Lichiabetta
Liebetreide
Mamiammalan
Marianceran
Sherleenene
Sisselletta

male first names that don't exist

You name your first child "Babton Laarco Tabrit". You name your second "Ferandulde Hommanloco Kictortick". Both see infinite success in life and you wonder why you haven't discovered neural networks sooner.

Below are the alphabetically first 3–10 letter male unnames for each letter. In some cases, no names of a given length were generated for a given letter.

—3—
Aad
Aan
Bil
Bre
Cas
Ces
Daa
Dax
Ede
Eey
Har
Hhe
Ial
Iir
Jac
Jal
Kel
Kib
Lal
Lel
Mah
Meh
Nal
Nas
Oid
Oon
Phy
Pys
Roz
Ruf
Sas
Sih
Tes
Tey
Vay
Ven
Wal
Wil
Zes
Zin
—4—
Aado
Admo
Baan
Badl
Cald
Calg
Daad
Daal
Eard
Ebax
Farn
Felb
Gaht
Gart
Haan
Haco
Iane
Idae
Jaan
Jace
Kaan
Khen
Laad
Laan
Maab
Madi
Nald
Nall
Obby
Odan
Peit
Piar
Qide
Raal
Rady
Saag
Saan
Tacy
Tany
Vaen
Vaes
Waci
Waco
Ytih
—5—
Aanle
Aaton
Baane
Baart
Cabis
Cailh
Daamo
Daano
Eamon
Earis
Famry
Fandy
Gacon
Gahey
Hadel
Hagre
Idail
Idris
Jacer
Jadio
Karry
Keris
Laale
Laber
Maaro
Mabin
Naado
Naalo
Oaris
Ohale
Palio
Paric
Qebin
Qikel
Rabey
Radey
Sacon
Sadne
Tacie
Talet
Uusse
Vaeld
Valen
Wacer
Wadle
Zilal
Zloyn
—6—
Aabird
Aareno
Babton
Badunt
Cadlor
Cadron
Daapis
Dabron
Earrel
Earrre
Fabery
Faicey
Gaarrh
Gadano
Haares
Habide
Ienlir
Igamar
Jaalil
Jabron
Kebitt
Kelmar
Laarco
Laarin
Maccel
Maccol
Nablan
Nacell
Ohepto
Olerrh
Paciul
Pakdon
Qicias
Qrekon
Rabwin
Raciad
Saando
Saddon
Tabrit
Tactan
Ulande
Uoseol
Vachon
Vacors
Waaren
Wabton
Xiklel
Zesian
—7—
Aabrado
Aarsado
Balnend
Barcick
Caduuse
Caliulo
Daalius
Daarrol
Eanondo
Earesle
Falbeus
Faloric
Ganunle
Garlard
Haameno
Habrenc
Icoolse
Idonald
Jaendie
Jajuian
Kodavio
Korgell
Laarnel
Laarrec
Maccalo
Machual
Nabtumo
Nachale
Oimolan
Ollisee
Paberto
Palducb
Quitius
Radlond
Radullo
Sacholh
Saconad
Tadrine
Tahinte
Vacelle
Vagallo
Wabbent
Wacivey
Zewrave
—8—
Aarnounf
Aarruleu
Balibhat
Baravile
Carelcic
Carkocce
Dalevice
Danilian
Earrinto
Eberepto
Fadonocf
Farricco
Gaurlnih
Gegirald
Handerus
Harelcce
Januipan
Jarcebph
Korancin
Laleaddo
Lalenicd
Maccelce
Macchely
Nachaane
Nalaneil
Parlicco
Parreico
Randlold
Rantozer
Sachasce
Sactonae
Talentin
Tavintey
Vernilve
Vernnche
Wacellio
Waldrand
Ziliasen
—9—
Aldanoldf
Aldresdis
Barrkimad
Berganton
Carlercca
Carmencan
Darriscce
Dauguslus
Edgaronte
Eeletento
Flandinco
Flilnendy
Galrinand
Gerarmovo
Hefarordo
Helaphhey
Jeenforue
Jeffersol
Lannendan
Lanuullan
Marricice
Marridcce
Nathanaal
Oberverto
Qoaberucc
Rallisten
Rardusler
Salcieley
Salvinten
Teliberel
Tewraslel
Wiccelele
Willofvis
—10—
Alfandrone
Atthaaneel
Brantisard
Castushart
Caucerucce
Eeverielti
Elerdrolde
Ferandulde
Flarericco
Hommanloco
Kictortick
Licoonicio
Llenelvind
Nattonanal
Oriccoomon
Rarvondard
Renaldordo
Sawvarcsas
Wengortwen
—11—
Cadrielccar
Ccrickuctof
Llantonlolm
Lunuslinzus
Micckelammy
Triddatrerd
Waldinawwan

VIEW ALL

news + thoughts

Machine learning: a primer

Tue 05-12-2017
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 14-11-2017
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)

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

Genes that make us sick

Thu 02-11-2017
Where disease hides in the genome.

My illustration of the location of genes in the human genome that are implicated in disease appears in The Objects that Power the Global Economy, a book by Quartz.

Martin Krzywinski @MKrzywinski mkweb.bcgsc.ca
The location of genes implicated in disease in the human genome, shown here as a spiral. (more...)

Ensemble methods: Bagging and random forests

Mon 16-10-2017
Many heads are better than one.

We introduce two common ensemble methods: bagging and random forests. Both of these methods repeat a statistical analysis on a bootstrap sample to improve the accuracy of the predictor. Our column shows these methods as applied to Classification and Regression Trees.

Martin Krzywinski @MKrzywinski mkweb.bcgsc.ca
Nature Methods Points of Significance column: Ensemble methods: Bagging and random forests. (read)

For example, we can sample the space of values more finely when using bagging with regression trees because each sample has potentially different boundaries at which the tree splits.

Random forests generate a large number of trees by not only generating bootstrap samples but also randomly choosing which predictor variables are considered at each split in the tree.

Krzywinski, M. & Altman, N. (2017) Points of Significance: Ensemble methods: bagging and random forests. Nature Methods 14:933–934.

Background reading

Krzywinski, M. & Altman, N. (2017) Points of Significance: Classification and regression trees. Nature Methods 14:757–758.

...more about the Points of Significance column

Classification and regression trees

Mon 16-10-2017
Decision trees are a powerful but simple prediction method.

Decision trees classify data by splitting it along the predictor axes into partitions with homogeneous values of the dependent variable. Unlike logistic or linear regression, CART does not develop a prediction equation. Instead, data are predicted by a series of binary decisions based on the boundaries of the splits. Decision trees are very effective and the resulting rules are readily interpreted.

Trees can be built using different metrics that measure how well the splits divide up the data classes: Gini index, entropy or misclassification error.

Martin Krzywinski @MKrzywinski mkweb.bcgsc.ca
Nature Methods Points of Significance column: Classification and decision trees. (read)

When the predictor variable is quantitative and not categorical, regression trees are used. Here, the data are still split but now the predictor variable is estimated by the average within the split boundaries. Tree growth can be controlled using the complexity parameter, a measure of the relative improvement of each new split.

Individual trees can be very sensitive to minor changes in the data and even better prediction can be achieved by exploiting this variability. Using ensemble methods, we can grow multiple trees from the same data.

Krzywinski, M. & Altman, N. (2017) Points of Significance: Classification and regression trees. Nature Methods 14:757–758.

Background reading

Lever, J., Krzywinski, M. & Altman, N. (2016) Points of Significance: Logistic regression. Nature Methods 13:541-542.

Altman, N. & Krzywinski, M. (2015) Points of Significance: Multiple Linear Regression Nature Methods 12:1103-1104.

Lever, J., Krzywinski, M. & Altman, N. (2016) Points of Significance: Classifier evaluation. Nature Methods 13:603-604.

Lever, J., Krzywinski, M. & Altman, N. (2016) Points of Significance: Model Selection and Overfitting. Nature Methods 13:703-704.

Lever, J., Krzywinski, M. & Altman, N. (2016) Points of Significance: Regularization. Nature Methods 13:803-804.

...more about the Points of Significance column

Personal Oncogenomics Program 5 Year Anniversary Art

Wed 26-07-2017

The artwork was created in collaboration with my colleagues at the Genome Sciences Center to celebrate the 5 year anniversary of the Personalized Oncogenomics Program (POG).

Martin Krzywinski @MKrzywinski mkweb.bcgsc.ca
5 Years of Personalized Oncogenomics Program at Canada's Michael Smith Genome Sciences Centre. The poster shows 545 cancer cases. (left) Cases ordered chronologically by case number. (right) Cases grouped by diagnosis (tissue type) and then by similarity within group.

The Personal Oncogenomics Program (POG) is a collaborative research study including many BC Cancer Agency oncologists, pathologists and other clinicians along with Canada's Michael Smith Genome Sciences Centre with support from BC Cancer Foundation.

The aim of the program is to sequence, analyze and compare the genome of each patient's cancer—the entire DNA and RNA inside tumor cells— in order to understand what is enabling it to identify less toxic and more effective treatment options.