@sjcrh/proteinpaint-rust 2.40.6 → 2.49.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/src/indel.rs CHANGED
@@ -848,7 +848,7 @@ fn main() {
848
848
  let remainder: usize = iter % max_threads; // Calculate remainder of read number divided by max_threads to decide which thread parses this read
849
849
  //println!("iter:{}", iter);
850
850
  if remainder == thread_num {
851
- // Thread analyzing a particular read must have the same remainder as the thread_num, this avoids multiple reads from parsing the same read. Also checking if the read length > 0
851
+ // Thread analyzing a particular read must have the same remainder as the thread_num, this avoids multiple threads from parsing the same read. Also checking if the read length > 0
852
852
 
853
853
  //println!(
854
854
  // "start_positions_list:{}",
@@ -141,274 +141,274 @@ fn chi_square_test(
141
141
  }
142
142
  }
143
143
 
144
- //#[allow(dead_code)]
145
- //pub fn wilcoxon_rank_sum_test(
146
- // mut group1: Vec<f64>,
147
- // mut group2: Vec<f64>,
148
- // threshold: usize,
149
- // alternative: char,
150
- // correct: bool,
151
- //) -> f64 {
152
- // // Check if there are any ties between the two groups
153
- //
154
- // let mut combined = group1.clone();
155
- // combined.extend(group2.iter().cloned());
156
- // combined.sort_by(|a, b| a.partial_cmp(b).unwrap());
157
- // //println!("combined:{:?}", combined);
158
- //
159
- // group1.sort_by(|a, b| a.partial_cmp(b).unwrap());
160
- // group2.sort_by(|a, b| a.partial_cmp(b).unwrap());
161
- // //println!("group1:{:?}", group1);
162
- // //println!("group2:{:?}", group2);
163
- //
164
- // let mut group1_iter = 0;
165
- // let mut group2_iter = 0;
166
- // let mut xy: Vec<char> = Vec::with_capacity(combined.len()); // Stores X-Y classification
167
- // let mut ranks: Vec<f64> = Vec::with_capacity(combined.len()); // Stores the rank of each element
168
- // let mut is_repeat = false;
169
- // let mut repeat_present = false;
170
- // let mut frac_rank: f64 = 0.0;
171
- // let mut num_repeats: f64 = 1.0;
172
- // let mut repeat_iter: f64 = 1.0;
173
- // #[allow(unused_variables)]
174
- // let mut weight_x: f64 = 0.0;
175
- // let mut weight_y: f64 = 0.0;
176
- // let mut group_char: char = 'X';
177
- // let mut rank_frequencies: Vec<f64> = Vec::with_capacity(combined.len());
178
- // for i in 0..combined.len() {
179
- // //println!("group1_iter:{}", group1_iter);
180
- // //println!("group2_iter:{}", group2_iter);
181
- // //println!("item1:{}", combined[i]);
182
- // //println!("is_repeat:{}", is_repeat);
183
- // if group1_iter < group1.len() && combined[i] == group1[group1_iter] {
184
- // xy.push('X');
185
- // group1_iter += 1;
186
- // group_char = 'X';
187
- // } else if group2_iter < group2.len() && combined[i] == group2[group2_iter] {
188
- // xy.push('Y');
189
- // group2_iter += 1;
190
- // group_char = 'Y';
191
- // }
192
- //
193
- // // Computing ranks
194
- // if is_repeat == false {
195
- // // Check if current element has other occurences
196
- // num_repeats = 1.0;
197
- // for j in i + 1..combined.len() {
198
- // if combined[i] == combined[j] {
199
- // is_repeat = true;
200
- // repeat_present = true;
201
- // repeat_iter = 1.0;
202
- // num_repeats += 1.0;
203
- // } else {
204
- // break;
205
- // }
206
- // }
207
- // //println!("num_repeats:{}", num_repeats);
208
- // if is_repeat == false {
209
- // ranks.push(i as f64 + 1.0);
210
- // if group_char == 'X' {
211
- // weight_x += i as f64 + 1.0;
212
- // } else if group_char == 'Y' {
213
- // weight_y += i as f64 + 1.0;
214
- // }
215
- // //rank_frequencies.push(RankFreq {
216
- // // rank: i as f64 + 1.0,
217
- // // freq: 1,
218
- // //});
219
- // rank_frequencies.push(1.0);
220
- // } else {
221
- // frac_rank = calculate_frac_rank(i as f64 + 1.0, num_repeats);
222
- // ranks.push(frac_rank);
223
- // if group_char == 'X' {
224
- // weight_x += frac_rank;
225
- // } else if group_char == 'Y' {
226
- // weight_y += frac_rank
227
- // }
228
- // //rank_frequencies.push(RankFreq {
229
- // // rank: frac_rank,
230
- // // freq: num_repeats as usize,
231
- // //});
232
- // rank_frequencies.push(num_repeats);
233
- // }
234
- // } else if repeat_iter < num_repeats {
235
- // // Repeat case
236
- // ranks.push(frac_rank);
237
- // repeat_iter += 1.0;
238
- // if group_char == 'X' {
239
- // weight_x += frac_rank;
240
- // } else if group_char == 'Y' {
241
- // weight_y += frac_rank
242
- // }
243
- // if repeat_iter == num_repeats {
244
- // is_repeat = false;
245
- // }
246
- // } else {
247
- // //println!("i:{}", i);
248
- // ranks.push(i as f64 + 1.0);
249
- // repeat_iter = 1.0;
250
- // num_repeats = 1.0;
251
- // if group_char == 'X' {
252
- // weight_x += i as f64 + 1.0;
253
- // } else if group_char == 'Y' {
254
- // weight_y += i as f64 + 1.0;
255
- // }
256
- // }
257
- // }
258
- // //println!("rank_frequencies:{:?}", rank_frequencies);
259
- // //println!("xy:{:?}", xy);
260
- // //println!("ranks:{:?}", ranks);
261
- // //println!("weight_x:{}", weight_x);
262
- // //println!("weight_y:{}", weight_y);
263
- //
264
- // //u_dash (calculated below) calculates the "W Statistic" in wilcox.test function in R
265
- //
266
- // let u_y = weight_y - (group2.len() as f64 * (group2.len() as f64 + 1.0) / 2.0) as f64;
267
- // let u_dash_y = (u_y - (group1.len() * group2.len()) as f64).abs();
268
- // //println!("u_dash_y:{}", u_dash_y);
269
- //
270
- // let u_x = weight_x - (group1.len() as f64 * (group1.len() as f64 + 1.0) / 2.0) as f64;
271
- // let _u_dash_x = (u_x - (group1.len() * group2.len()) as f64).abs();
272
- // //println!("u_dash_x:{}", u_dash_x);
273
- //
274
- // // Calculate test_statistic
275
- //
276
- // //let t1 = weight_x - ((group1.len() as f64) * (group1.len() as f64 + 1.0)) / 2.0;
277
- // //let t2 = weight_y - ((group2.len() as f64) * (group2.len() as f64 + 1.0)) / 2.0;
278
- // //
279
- // //let mut test_statistic = t1;
280
- // //if t2 < t1 {
281
- // // test_statistic = t2;
282
- // //}
283
- //
284
- // //println!("test_statistic:{}", test_statistic);
285
- //
286
- // if group1.len() < threshold && group2.len() < threshold && repeat_present == false {
287
- // // Compute exact p-values
288
- //
289
- // // Calculate conditional probability for weight_y
290
- //
291
- // if alternative == 'g' {
292
- // // Alternative "greater"
293
- // //if group1.len() <= low_cutoff && group2.len() <= low_cutoff {
294
- // // iterate_exact_p_values(ranks, weight_y, group2.len())
295
- // //} else {
296
- // calculate_exact_probability(u_dash_y, group1.len(), group2.len(), alternative)
297
- // //}
298
- // } else if alternative == 'l' {
299
- // // Alternative "lesser"
300
- // //if group1.len() <= low_cutoff && group2.len() <= low_cutoff {
301
- // // iterate_exact_p_values(ranks, weight_x, group1.len())
302
- // //} else {
303
- // calculate_exact_probability(u_dash_y, group1.len(), group2.len(), alternative)
304
- // //}
305
- // } else {
306
- // // Two-sided distribution
307
- // calculate_exact_probability(u_dash_y, group1.len(), group2.len(), alternative)
308
- // }
309
- // } else {
310
- // // Compute p-values from a normal distribution
311
- // //println!("group1 length:{}", group1.len());
312
- // //println!("group2 length:{}", group2.len());
313
- //
314
- // let mut z = u_dash_y - ((group1.len() * group2.len()) as f64) / 2.0;
315
- // //println!("z_original:{}", z);
316
- // let mut nties_sum: f64 = 0.0;
317
- // for i in 0..rank_frequencies.len() {
318
- // nties_sum += rank_frequencies[i] * rank_frequencies[i] * rank_frequencies[i]
319
- // - rank_frequencies[i];
320
- // }
321
- //
322
- // let sigma = (((group1.len() * group2.len()) as f64) / 12.0
323
- // * ((group1.len() + group2.len() + 1) as f64
324
- // - nties_sum
325
- // / (((group1.len() + group2.len()) as f64)
326
- // * ((group1.len() + group2.len() - 1) as f64))))
327
- // .sqrt();
328
- // //println!("sigma:{}", sigma);
329
- // let mut correction: f64 = 0.0;
330
- // if correct == true {
331
- // if alternative == 'g' {
332
- // // Alternative "greater"
333
- // correction = 0.5;
334
- // } else if alternative == 'l' {
335
- // // Alternative "lesser"
336
- // correction = -0.5;
337
- // } else {
338
- // // Alternative "two-sided"
339
- // if z > 0.0 {
340
- // correction = 0.5;
341
- // } else if z < 0.0 {
342
- // correction = -0.5;
343
- // } else {
344
- // // z=0
345
- // correction = 0.0;
346
- // }
347
- // }
348
- // }
349
- // z = (z - correction) / sigma;
350
- // //println!("z:{}", z);
351
- // if alternative == 'g' {
352
- // // Alternative "greater"
353
- // //println!("greater:{}", n.cdf(weight_y));
354
- // //1.0 - n.cdf(z) // Applying continuity correction
355
- // r_mathlib::normal_cdf(z, 0.0, 1.0, false, false)
356
- // } else if alternative == 'l' {
357
- // // Alternative "lesser"
358
- // //println!("lesser:{}", n.cdf(weight_x));
359
- // //n.cdf(z) // Applying continuity coorection
360
- // r_mathlib::normal_cdf(z, 0.0, 1.0, true, false)
361
- // } else {
362
- // // Alternative "two-sided"
363
- // let p_g = r_mathlib::normal_cdf(z, 0.0, 1.0, false, false); // Applying continuity correction
364
- // let p_l = r_mathlib::normal_cdf(z, 0.0, 1.0, true, false); // Applying continuity correction
365
- // let mut p_value;
366
- // if p_g < p_l {
367
- // p_value = 2.0 * p_g;
368
- // } else {
369
- // p_value = 2.0 * p_l;
370
- // }
371
- // //println!("p_value:{}", p_value);
372
- // if p_value > 1.0 {
373
- // p_value = 1.0;
374
- // }
375
- // p_value
376
- // }
377
- // }
378
- //}
144
+ #[allow(dead_code)]
145
+ pub fn wilcoxon_rank_sum_test(
146
+ mut group1: Vec<f64>,
147
+ mut group2: Vec<f64>,
148
+ threshold: usize,
149
+ alternative: char,
150
+ correct: bool,
151
+ ) -> f64 {
152
+ // Check if there are any ties between the two groups
153
+
154
+ let mut combined = group1.clone();
155
+ combined.extend(group2.iter().cloned());
156
+ combined.sort_by(|a, b| a.partial_cmp(b).unwrap());
157
+ //println!("combined:{:?}", combined);
158
+
159
+ group1.sort_by(|a, b| a.partial_cmp(b).unwrap());
160
+ group2.sort_by(|a, b| a.partial_cmp(b).unwrap());
161
+ //println!("group1:{:?}", group1);
162
+ //println!("group2:{:?}", group2);
163
+
164
+ let mut group1_iter = 0;
165
+ let mut group2_iter = 0;
166
+ let mut xy: Vec<char> = Vec::with_capacity(combined.len()); // Stores X-Y classification
167
+ let mut ranks: Vec<f64> = Vec::with_capacity(combined.len()); // Stores the rank of each element
168
+ let mut is_repeat = false;
169
+ let mut repeat_present = false;
170
+ let mut frac_rank: f64 = 0.0;
171
+ let mut num_repeats: f64 = 1.0;
172
+ let mut repeat_iter: f64 = 1.0;
173
+ #[allow(unused_variables)]
174
+ let mut weight_x: f64 = 0.0;
175
+ let mut weight_y: f64 = 0.0;
176
+ let mut group_char: char = 'X';
177
+ let mut rank_frequencies: Vec<f64> = Vec::with_capacity(combined.len());
178
+ for i in 0..combined.len() {
179
+ //println!("group1_iter:{}", group1_iter);
180
+ //println!("group2_iter:{}", group2_iter);
181
+ //println!("item1:{}", combined[i]);
182
+ //println!("is_repeat:{}", is_repeat);
183
+ if group1_iter < group1.len() && combined[i] == group1[group1_iter] {
184
+ xy.push('X');
185
+ group1_iter += 1;
186
+ group_char = 'X';
187
+ } else if group2_iter < group2.len() && combined[i] == group2[group2_iter] {
188
+ xy.push('Y');
189
+ group2_iter += 1;
190
+ group_char = 'Y';
191
+ }
192
+
193
+ // Computing ranks
194
+ if is_repeat == false {
195
+ // Check if current element has other occurences
196
+ num_repeats = 1.0;
197
+ for j in i + 1..combined.len() {
198
+ if combined[i] == combined[j] {
199
+ is_repeat = true;
200
+ repeat_present = true;
201
+ repeat_iter = 1.0;
202
+ num_repeats += 1.0;
203
+ } else {
204
+ break;
205
+ }
206
+ }
207
+ //println!("num_repeats:{}", num_repeats);
208
+ if is_repeat == false {
209
+ ranks.push(i as f64 + 1.0);
210
+ if group_char == 'X' {
211
+ weight_x += i as f64 + 1.0;
212
+ } else if group_char == 'Y' {
213
+ weight_y += i as f64 + 1.0;
214
+ }
215
+ //rank_frequencies.push(RankFreq {
216
+ // rank: i as f64 + 1.0,
217
+ // freq: 1,
218
+ //});
219
+ rank_frequencies.push(1.0);
220
+ } else {
221
+ frac_rank = calculate_frac_rank(i as f64 + 1.0, num_repeats);
222
+ ranks.push(frac_rank);
223
+ if group_char == 'X' {
224
+ weight_x += frac_rank;
225
+ } else if group_char == 'Y' {
226
+ weight_y += frac_rank
227
+ }
228
+ //rank_frequencies.push(RankFreq {
229
+ // rank: frac_rank,
230
+ // freq: num_repeats as usize,
231
+ //});
232
+ rank_frequencies.push(num_repeats);
233
+ }
234
+ } else if repeat_iter < num_repeats {
235
+ // Repeat case
236
+ ranks.push(frac_rank);
237
+ repeat_iter += 1.0;
238
+ if group_char == 'X' {
239
+ weight_x += frac_rank;
240
+ } else if group_char == 'Y' {
241
+ weight_y += frac_rank
242
+ }
243
+ if repeat_iter == num_repeats {
244
+ is_repeat = false;
245
+ }
246
+ } else {
247
+ //println!("i:{}", i);
248
+ ranks.push(i as f64 + 1.0);
249
+ repeat_iter = 1.0;
250
+ num_repeats = 1.0;
251
+ if group_char == 'X' {
252
+ weight_x += i as f64 + 1.0;
253
+ } else if group_char == 'Y' {
254
+ weight_y += i as f64 + 1.0;
255
+ }
256
+ }
257
+ }
258
+ //println!("rank_frequencies:{:?}", rank_frequencies);
259
+ //println!("xy:{:?}", xy);
260
+ //println!("ranks:{:?}", ranks);
261
+ //println!("weight_x:{}", weight_x);
262
+ //println!("weight_y:{}", weight_y);
263
+
264
+ //u_dash (calculated below) calculates the "W Statistic" in wilcox.test function in R
265
+
266
+ let u_y = weight_y - (group2.len() as f64 * (group2.len() as f64 + 1.0) / 2.0) as f64;
267
+ let u_dash_y = (u_y - (group1.len() * group2.len()) as f64).abs();
268
+ //println!("u_dash_y:{}", u_dash_y);
269
+
270
+ let u_x = weight_x - (group1.len() as f64 * (group1.len() as f64 + 1.0) / 2.0) as f64;
271
+ let _u_dash_x = (u_x - (group1.len() * group2.len()) as f64).abs();
272
+ //println!("u_dash_x:{}", u_dash_x);
273
+
274
+ // Calculate test_statistic
275
+
276
+ //let t1 = weight_x - ((group1.len() as f64) * (group1.len() as f64 + 1.0)) / 2.0;
277
+ //let t2 = weight_y - ((group2.len() as f64) * (group2.len() as f64 + 1.0)) / 2.0;
278
+ //
279
+ //let mut test_statistic = t1;
280
+ //if t2 < t1 {
281
+ // test_statistic = t2;
282
+ //}
283
+
284
+ //println!("test_statistic:{}", test_statistic);
285
+
286
+ if group1.len() < threshold && group2.len() < threshold && repeat_present == false {
287
+ // Compute exact p-values
288
+
289
+ // Calculate conditional probability for weight_y
290
+
291
+ if alternative == 'g' {
292
+ // Alternative "greater"
293
+ //if group1.len() <= low_cutoff && group2.len() <= low_cutoff {
294
+ // iterate_exact_p_values(ranks, weight_y, group2.len())
295
+ //} else {
296
+ calculate_exact_probability(u_dash_y, group1.len(), group2.len(), alternative)
297
+ //}
298
+ } else if alternative == 'l' {
299
+ // Alternative "lesser"
300
+ //if group1.len() <= low_cutoff && group2.len() <= low_cutoff {
301
+ // iterate_exact_p_values(ranks, weight_x, group1.len())
302
+ //} else {
303
+ calculate_exact_probability(u_dash_y, group1.len(), group2.len(), alternative)
304
+ //}
305
+ } else {
306
+ // Two-sided distribution
307
+ calculate_exact_probability(u_dash_y, group1.len(), group2.len(), alternative)
308
+ }
309
+ } else {
310
+ // Compute p-values from a normal distribution
311
+ //println!("group1 length:{}", group1.len());
312
+ //println!("group2 length:{}", group2.len());
313
+
314
+ let mut z = u_dash_y - ((group1.len() * group2.len()) as f64) / 2.0;
315
+ //println!("z_original:{}", z);
316
+ let mut nties_sum: f64 = 0.0;
317
+ for i in 0..rank_frequencies.len() {
318
+ nties_sum += rank_frequencies[i] * rank_frequencies[i] * rank_frequencies[i]
319
+ - rank_frequencies[i];
320
+ }
379
321
 
380
- //// To be used only when there are no ties in the input data
381
- //#[allow(dead_code)]
382
- //fn calculate_exact_probability(weight: f64, x: usize, y: usize, alternative: char) -> f64 {
383
- // //println!("Using Wilcoxon CDF");
384
- // let mut p_value;
385
- // if alternative == 't' {
386
- // if weight > ((x * y) as f64) / 2.0 {
387
- // p_value = 2.0 * r_mathlib::wilcox_cdf(weight - 1.0, x as f64, y as f64, false, false);
388
- // } else {
389
- // p_value = 2.0 * r_mathlib::wilcox_cdf(weight, x as f64, y as f64, true, false);
390
- // }
391
- // if p_value > 1.0 {
392
- // p_value = 1.0;
393
- // }
394
- // } else if alternative == 'g' {
395
- // p_value = r_mathlib::wilcox_cdf(weight - 1.0, x as f64, y as f64, false, false);
396
- // } else if alternative == 'l' {
397
- // p_value = r_mathlib::wilcox_cdf(weight, x as f64, y as f64, true, false);
398
- // } else {
399
- // // Should not happen
400
- // panic!("Unknown alternative option given, please check!");
401
- // }
402
- // //println!("p_value:{}", p_value);
403
- // p_value
404
- //}
405
- //
406
- //#[allow(dead_code)]
407
- //pub fn calculate_frac_rank(current_rank: f64, num_repeats: f64) -> f64 {
408
- // let mut sum = 0.0;
409
- // for i in 0..num_repeats as usize {
410
- // let rank = current_rank + i as f64;
411
- // sum += rank;
412
- // }
413
- // sum / num_repeats
414
- //}
322
+ let sigma = (((group1.len() * group2.len()) as f64) / 12.0
323
+ * ((group1.len() + group2.len() + 1) as f64
324
+ - nties_sum
325
+ / (((group1.len() + group2.len()) as f64)
326
+ * ((group1.len() + group2.len() - 1) as f64))))
327
+ .sqrt();
328
+ //println!("sigma:{}", sigma);
329
+ let mut correction: f64 = 0.0;
330
+ if correct == true {
331
+ if alternative == 'g' {
332
+ // Alternative "greater"
333
+ correction = 0.5;
334
+ } else if alternative == 'l' {
335
+ // Alternative "lesser"
336
+ correction = -0.5;
337
+ } else {
338
+ // Alternative "two-sided"
339
+ if z > 0.0 {
340
+ correction = 0.5;
341
+ } else if z < 0.0 {
342
+ correction = -0.5;
343
+ } else {
344
+ // z=0
345
+ correction = 0.0;
346
+ }
347
+ }
348
+ }
349
+ z = (z - correction) / sigma;
350
+ //println!("z:{}", z);
351
+ if alternative == 'g' {
352
+ // Alternative "greater"
353
+ //println!("greater:{}", n.cdf(weight_y));
354
+ //1.0 - n.cdf(z) // Applying continuity correction
355
+ r_mathlib::normal_cdf(z, 0.0, 1.0, false, false)
356
+ } else if alternative == 'l' {
357
+ // Alternative "lesser"
358
+ //println!("lesser:{}", n.cdf(weight_x));
359
+ //n.cdf(z) // Applying continuity coorection
360
+ r_mathlib::normal_cdf(z, 0.0, 1.0, true, false)
361
+ } else {
362
+ // Alternative "two-sided"
363
+ let p_g = r_mathlib::normal_cdf(z, 0.0, 1.0, false, false); // Applying continuity correction
364
+ let p_l = r_mathlib::normal_cdf(z, 0.0, 1.0, true, false); // Applying continuity correction
365
+ let mut p_value;
366
+ if p_g < p_l {
367
+ p_value = 2.0 * p_g;
368
+ } else {
369
+ p_value = 2.0 * p_l;
370
+ }
371
+ //println!("p_value:{}", p_value);
372
+ if p_value > 1.0 {
373
+ p_value = 1.0;
374
+ }
375
+ p_value
376
+ }
377
+ }
378
+ }
379
+
380
+ // To be used only when there are no ties in the input data
381
+ #[allow(dead_code)]
382
+ fn calculate_exact_probability(weight: f64, x: usize, y: usize, alternative: char) -> f64 {
383
+ //println!("Using Wilcoxon CDF");
384
+ let mut p_value;
385
+ if alternative == 't' {
386
+ if weight > ((x * y) as f64) / 2.0 {
387
+ p_value = 2.0 * r_mathlib::wilcox_cdf(weight - 1.0, x as f64, y as f64, false, false);
388
+ } else {
389
+ p_value = 2.0 * r_mathlib::wilcox_cdf(weight, x as f64, y as f64, true, false);
390
+ }
391
+ if p_value > 1.0 {
392
+ p_value = 1.0;
393
+ }
394
+ } else if alternative == 'g' {
395
+ p_value = r_mathlib::wilcox_cdf(weight - 1.0, x as f64, y as f64, false, false);
396
+ } else if alternative == 'l' {
397
+ p_value = r_mathlib::wilcox_cdf(weight, x as f64, y as f64, true, false);
398
+ } else {
399
+ // Should not happen
400
+ panic!("Unknown alternative option given, please check!");
401
+ }
402
+ //println!("p_value:{}", p_value);
403
+ p_value
404
+ }
405
+
406
+ #[allow(dead_code)]
407
+ pub fn calculate_frac_rank(current_rank: f64, num_repeats: f64) -> f64 {
408
+ let mut sum = 0.0;
409
+ for i in 0..num_repeats as usize {
410
+ let rank = current_rank + i as f64;
411
+ sum += rank;
412
+ }
413
+ sum / num_repeats
414
+ }