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. …”

Fig 5 - by Torsten Schober (20485754)

Fig 4 - by Torsten Schober (20485754)

Scatter plots of the linear regression for the relationship between the duration of the vegetative phase and the average mass of single inflorescences. by Torsten Schober (20485754)

Fig 6 - by Torsten Schober (20485754)

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

PoAce1 enrichment in the specific regions of (hemi)cellulase genes assayed by ChIP-qPCR. by Zhongjiao Liu (11877464)

The effect of PoFbx23 on the protein abundance, transcription level, and DNA binding ability of PoAce1 under glucose signal. by Zhongjiao Liu (11877464)

Initial RBC dominant clot compaction in the <i>in vitro</i> MCA model without and with collateral with alteplase applied at clinically relevant concentration (1.3 mg L^-1... by Sandra Thalerová (11434762)

Serum metabolomic response to aging. by Gwangho Yoon (5771678)

“…<b>(B)</b> Metabolites that decreased with aging. Statistical significance is indicated in the heatmap with asterisks. …”

Fig 9 - by Torsten Schober (20485754)

Reaction time and peak velocity across four cognitive-motor integration conditions during a youth soccer season across all athletes in the study. by Rachel S. Watson (21864061)

The CYP7B1 inhibitor, clotrimazole, and the EBI2 receptor antagonist, NIBR189, attenuate LPS-induced astrocyte migration <i>in vitro.</i> by Fionä Caratis (12759506)

Pediatric CPP with Praat and ADSV (Joshi et al., 2025) by Ashwini Joshi (21594817)

“…Age and <i>F</i>0 are significant predictors of CPP; however, the observed increase in CPP with increasing age in males is primarily due to the substantial decrease in <i>F</i>0 postpuberty. …”

Tight junction and adhesion proteins in the brain are downregulated during systemic inflammation. by Fionä Caratis (12759506)

“…Expression of the adhesion molecule N-cadherin significantly decreased after 12 hours (12 h: 49% + /- 5% vs. vehicle) and 24 h (3% + /- 1% vs. vehicle) of LPS treatment. …”

I.p. injection of LPS induces inflammation in the brain A. by Fionä Caratis (12759506)

Effect of <i>T. oliverianum</i> extracts on liver enzymes and total bilirubin. by Rania F. Ahmed (10032039)

Effect of <i>T. olivarium</i> extracts on hepatic content of TNF-<i>α.</i> by Rania F. Ahmed (10032039)

Effects of <i>T. oliverianum</i> extracts on hepatic content of GSH and MDA. by Rania F. Ahmed (10032039)

The oxysterol 7α, 25OHC synthesising and degrading enzymes are expressed in the mouse brain microvessels. by Fionä Caratis (12759506)