Addressing Imbalanced Classification Problems in Drug Discovery and Development Using Random Forest, Support Vector Machine, AutoGluon-Tabular, and H2O AutoML by Ayush Garg (21090944)

“…The important findings of our studies are as follows: (i) there is no effect of threshold optimization on ranking metrics such as AUC and AUPR, but AUC and AUPR get affected by class-weighting and SMOTTomek; (ii) for ML methods RF and SVM, significant percentage improvement up to 375, 33.33, and 450 over all the data sets can be achieved, respectively, for F1 score, MCC, and balanced accuracy, which are suitable for performance evaluation of imbalanced data sets; (iii) for AutoML libraries AutoGluon-Tabular and H2O AutoML, significant percentage improvement up to 383.33, 37.25, and 533.33 over all the data sets can be achieved, respectively, for F1 score, MCC, and balanced accuracy; (iv) the general pattern of percentage improvement in balanced accuracy is that the percentage improvement increases when the class ratio is systematically decreased from 0.5 to 0.1; in the case of F1 score and MCC, maximum improvement is achieved at the class ratio of 0.3; (v) for both ML and AutoML with balancing, it is observed that any individual class-balancing technique does not outperform all other methods on a significantly higher number of data sets based on F1 score; (vi) the three external balancing techniques combined outperformed the internal balancing methods of the ML and AutoML; (vii) AutoML tools perform as good as the ML models and in some cases perform even better for handling imbalanced classification when applied with imbalance handling techniques. …”

Relative expression of hub genes. by Ziyang Liu (242055)

Relationships between clay and quartz content, TOC, 2D-NMR solid OM, S₁, 2D-NMR light oil and fractal dimensions. by Changjun Ji (18285907)

“…This results in the formation of larger dissolution pores within the carbonated minerals [<a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0309346#pone.0309346.ref043" target="_blank">43</a>], leading to a decrease in the fractal dimensions D₁ and D₂. …”

LULC proportion from 2040 to 2060. by Muse Wldmchel (20642444)

“…The study highlighted significant land-use changes, with increased agriculture and built-up areas at the expense of forests and pasturelands. …”

Global sensitive flow parameters [84]. by Muse Wldmchel (20642444)

“…The study highlighted significant land-use changes, with increased agriculture and built-up areas at the expense of forests and pasturelands. …”

Gene expression omnibus datasets. by Xinyi Xia (7516694)

“…<div><p>Although the link between ischemia-reperfusion injury (IRI) and T cell-mediated rejection (TCMR) in kidney transplantation (KT) is well known, the mechanism remains unclear. We investigated essential genes and biological processes involved in interactions between IRI and TCMR. …”

Calycosin Inhibit PANoptosis and Alleviate Brain Damage: A Bioinformatics and Experimental Verification Approach by Huiyan An (20959966)

“…Numerous studies have highlighted the significance of PANoptosis in brain ischemia–reperfusion (I/R) injury. …”

Basic characteristics of the afforested land. by Yao Zhong (280645)

“…The results revealed that land use significantly altered the distribution of carbon fractions. …”

Effect of contraction mode on pH. by Luke R. Arieta (10517126)

Heterotrophic cell growth and dry cell yield of <i>Rhodovulum sulfidophilum</i> in artificial seawater (ASW) based growth medium of different salinities, wherein 100% corresponds t... by Shamitha Rao Morey-Yagi (19779981)

Detailed information of the observation datasets. by Weidong Ji (129916)

“…Understanding spatial-temporal characteristics of wind speed is significant in meteorology, coastal engineering design and maritime industries. …”

General technical specification for GW154/6700. by Weidong Ji (129916)

“…Understanding spatial-temporal characteristics of wind speed is significant in meteorology, coastal engineering design and maritime industries. …”

Flow chart of research object screening. by Wenyao Xie (21567889)

“…</p><p>Results</p><p>Cancer patients had higher mean age (68.70 ± 11.85 vs. 48.36 ± 17.00 years), lower testosterone levels (377.35 ± 204.26 vs. 415.02 ± 183.92 ng/dL, P < 0.001), and lower ALI values (64.86 ± 118.61 vs. 72.68 ± 185.25, P = 0.053) than non-cancer controls. …”

Data file without outliers. by Helena Wallin (6103205)

“…At follow-up, the increase in KYN and KYN/TRP was related to a decrease in ExCap in CKD 2–3. After adjusting for GFR, increase in KYN/TRP remained an independent significant predictor of a decline in ExCap in CKD 2–3.…”

Supplementary Table 1–9. by Yu Wang (12152)

“…To gain further insight, expression quantitative trait loci (eQTL) data were used to investigate the significant drug targets for lipid-lowering.</p><p>Results</p><p>Increasing ApoA-1 levels was associated with a diminished risk of sepsis (under 75) (OR 0.927, 95% CI 0.861–0.999; p = 0.047). …”

STROBE-MR checklist. by Yu Wang (12152)

“…To gain further insight, expression quantitative trait loci (eQTL) data were used to investigate the significant drug targets for lipid-lowering.</p><p>Results</p><p>Increasing ApoA-1 levels was associated with a diminished risk of sepsis (under 75) (OR 0.927, 95% CI 0.861–0.999; p = 0.047). …”

Instrumental Variables details of lipids. by Yu Wang (12152)

“…To gain further insight, expression quantitative trait loci (eQTL) data were used to investigate the significant drug targets for lipid-lowering.</p><p>Results</p><p>Increasing ApoA-1 levels was associated with a diminished risk of sepsis (under 75) (OR 0.927, 95% CI 0.861–0.999; p = 0.047). …”

Relative abundance (%) of the main coccolithophore species between 1854.6–1820.4 cm (74.353–73.505 ka) of core SO130-289KL. by Jose Dominick Guballa (19739909)

Osteoporosis screening among study participants. by Surakshya Khanal (19949745)

“…<div><p>Osteoporosis is a major public health problem that can lead to physical disability, working performance limitations, decreased self-sufficiency, and increased hospitalization and mortality rates. …”

Box-whisker plots of the relative abundances (%) of coccolithophore species characteristic for the “pseudo-stadial” (PS; 1854.6–1852.8 cm), the interstadial before the YTT eruption... by Jose Dominick Guballa (19739909)