Press n or j to go to the next uncovered block, b, p or k for the previous block.
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 | 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 2x 1871x 1871x 2x 1636x 1636x | /**
* What each task re-implements, as the Analysis column's `?` names it (§18.1,
* §18.9).
*
* One line per task whose code follows a published method or package: the
* method, the paper it is cited by, and how it came out against it in
* `notebooks/validation.qmd` — **identical** or **equivalent** there, or
* **untested** for a task the notebook does not run yet. A task whose code
* names no reference has no line, and its row no `?`: an implementation written
* from first principles, or reading biology rather than following an
* algorithm — the arms' alignment, the origin and terminus, the metagenome's
* tables, the model against the map, the dot plot — is not a re-implementation
* of anything, and a citation on it would be a claim the code does not make.
*
* Kept as a table rather than a field on each descriptor so that the whole
* list can be read, and checked, at once: `test/unit/references.test.ts` holds
* every id to a task, every DOI to its shape, and every validated line to a
* section of the notebook's own table. The DOIs are the papers' own, checked
* against Europe PMC when they were written down.
*/
/** How a task came out against its reference in `notebooks/validation.qmd`. */
export type Agreement = 'identical' | 'equivalent' | 'untested'
/** What a task re-implements. */
export interface TaskReference {
/** The method, as one would cite it: what it is, whose it is, and the year. */
method: string
/** The paper's DOI, bare: `10.1038/nature14450`. */
doi: string
agreement: Agreement
/** Its section of `notebooks/validation.qmd`; absent while it is untested. */
section?: number
}
const BIOFRAME = '10.1093/bioinformatics/btae088'
const COOLTOOLS = '10.1371/journal.pcbi.1012067'
const DEEPTOOLS = '10.1093/nar/gkw257'
export const TASK_REFERENCES: Readonly<Record<string, TaskReference>> = {
coverage: {
method: 'Coverage as cooltools computes it (Open2C 2024).',
doi: COOLTOOLS,
agreement: 'identical',
section: 9,
},
cistrans: {
method: 'Cis and trans sums as cooltools’ expected_cis and expected_trans make them (Open2C 2024).',
doi: COOLTOOLS,
agreement: 'identical',
section: 20,
},
cellqc: {
method: 'The near and mitotic contact shares of Nagano et al. 2017.',
doi: '10.1038/nature23001',
agreement: 'untested',
},
expected: {
method: 'The expected contact by separation, as cooltools’ expected_cis computes it (Open2C 2024).',
doi: COOLTOOLS,
agreement: 'identical',
section: 4,
},
pairsqc: {
method: 'The pairs’ statistics and fragments, as pairtools’ stats and restrict count them (Open2C 2024).',
doi: '10.1371/journal.pcbi.1012164',
agreement: 'identical',
section: 27,
},
// The resolution ladder counts what Rao et al.'s map resolution is read off,
// held in § 29 to cooler's own coarsening at every stored resolution.
mapreport: {
method: 'The map resolution of Rao et al. 2014, its counts at every bin size.',
doi: '10.1016/j.cell.2014.11.021',
agreement: 'identical',
section: 29,
},
scalogram: {
method: 'The scalogram of Lioy et al. 2018.',
doi: '10.1016/j.cell.2017.12.027',
agreement: 'untested',
},
fourc: {
method: 'Virtual 4C as cooltools’ virtual4c computes it (Open2C 2024).',
doi: COOLTOOLS,
agreement: 'identical',
section: 10,
},
insulation: {
method: 'Diamond insulation (Crane et al. 2015), as cooltools computes it.',
doi: '10.1038/nature14450',
agreement: 'identical',
section: 1,
},
di: {
method: 'The directionality index of Dixon et al. 2012, as domaincaller computes it.',
doi: '10.1038/nature11082',
agreement: 'identical',
section: 2,
},
hicscore: {
method: 'The HiC score of Bignaud et al. 2024, after their R script.',
doi: '10.1038/s41594-023-01178-2',
agreement: 'untested',
},
arrowhead: {
method: 'Contact domains by Arrowhead (Rao et al. 2014), as juicer_tools arrowhead calls them.',
doi: '10.1016/j.cell.2014.11.021',
agreement: 'identical',
section: 28,
},
compartments: {
method: 'The first eigenvector (Lieberman-Aiden et al. 2009), as cooltools’ eigs_cis takes it.',
doi: '10.1126/science.1181369',
agreement: 'equivalent',
section: 3,
},
loops: {
method: 'HiCCUPS (Rao et al. 2014), as cooltools.dots computes it.',
doi: '10.1016/j.cell.2014.11.021',
agreement: 'identical',
section: 19,
},
chromosight: {
method: 'Chromosight’s template matching (Matthey-Doret et al. 2020).',
doi: '10.1038/s41467-020-19562-7',
agreement: 'identical',
section: 6,
},
hicrep: {
method: 'HiCRep’s stratum-adjusted correlation (Yang et al. 2017).',
doi: '10.1101/gr.220640.117',
agreement: 'identical',
section: 7,
},
apa: {
method: 'Coolpup.py’s pile-ups (Flyamer et al. 2020), and chromosight’s score.',
doi: '10.1093/bioinformatics/btaa073',
agreement: 'identical',
section: 11,
},
reconstruct3d: {
method: 'pastis-NB, a negative binomial fit (Varoquaux et al. 2023).',
doi: '10.1093/bioinformatics/btac838',
agreement: 'equivalent',
section: 8,
},
motif: {
method: 'A motif scan as seqkit locate makes it (Shen et al. 2016).',
doi: '10.1371/journal.pone.0163962',
agreement: 'identical',
section: 17,
},
restriction: {
method: 'Restriction sites as bioframe’s digest finds them, each 2 bp earlier (Open2C 2024).',
doi: BIOFRAME,
agreement: 'identical',
section: 26,
},
peaks: {
method: 'yapc’s concave regions (Jänes et al. 2018), with IDR across replicates.',
doi: '10.7554/eLife.37344',
agreement: 'identical',
section: 5,
},
composition: {
method: 'GC content and skews, as bioframe and Biopython compute them (Open2C 2024).',
doi: BIOFRAME,
agreement: 'identical',
section: 16,
},
metaplot: {
method: 'deepTools’ computeMatrix and plotProfile (Ramírez et al. 2016).',
doi: DEEPTOOLS,
agreement: 'identical',
section: 14,
},
trackcorr: {
method: 'deepTools’ multiBigwigSummary and plotCorrelation (Ramírez et al. 2016), on exact window means.',
doi: DEEPTOOLS,
agreement: 'equivalent',
section: 18,
},
frip: {
method: 'FRiP, as the ENCODE guidelines define it (Landt et al. 2012).',
doi: '10.1101/gr.136184.111',
agreement: 'identical',
section: 22,
},
groupsignal: {
method: 'Mann–Whitney and Kruskal–Wallis tests as SciPy computes them (Virtanen et al. 2020).',
doi: '10.1038/s41592-019-0686-2',
agreement: 'identical',
section: 23,
},
overlap: {
method: 'bedtools’ intersect and jaccard, with a shuffle null (Quinlan and Hall 2010).',
doi: '10.1093/bioinformatics/btq033',
agreement: 'identical',
section: 15,
},
}
/** The task's reference, or `null` for a task that re-implements none. */
export function referenceOf(taskId: string): TaskReference | null {
return TASK_REFERENCES[taskId] ?? null
}
/** Whether the validation has shown it to agree: identical or equivalent, not untested. */
export function isValidated(reference: TaskReference): boolean {
return reference.agreement !== 'untested'
}
|