Imbalance deep multi‐instance learning for predicting isoform–isoform interactions

Abstract

Multi‐instance learning (MIL) can model complex bags (samples) that are further made of diverse instances (subsamples). In typical MIL, the labels of bags are known while those of individual instances are unknown and to be specified. In this paper we propose an imbalanced deep multi‐instance learning approach (IDMIL‐III) and apply it to predict genome‐wide isoform–isoform interactions (IIIs). This prediction task is crucial for precisely understanding the interactome between proteoforms and to reveal their functional diversity. The current solutions typically formulate the prediction of IIIs as a MIL problem by pairing two genes as a “bag” and any two isoforms spliced from these two genes as “instances.” The key instances (interacting isoform pairs) trigger the label of the positive (interacting) gene bags, which is important for identifying the IIIs. Furthermore, the prediction task was simplified as a balanced classification problem, which in practice is a rather imbalanced one. To address these issues, IDMIL‐III fuses RNA‐seq, nucleotide sequence, amino acid sequence and exon array data, and further introduces a novel loss function to separately model the loss of positive pairs and of negative pairs, and thus to avoid the expected loss dominated by majority negative pairs. In addition, it includes an attention strategy to identify positive isoform pairs from a positive gene bag. Extensive experimental results prove the effectiveness of IDMIL‐III on predicting IIIs. Particularly, IDMIL‐III achieves an F1 value as 95.4%, at least 3.8% higher than those of competitive methods at the gene‐level; and obtains an F1 as 29.8%, at least 2.4% higher than the state‐of‐the‐art methods at the isoform‐level. The code of IDMIL‐III is available at http://mlda.swu.edu.cn/codes.php?name=IDMIL-III.

An intelligent system of pelvic lymph node detection

“…Since 2012, when AlexNet 13 won the 2012 ILSVRC competition, 14 numerous important breakthroughs in computer vision have been achieved using DCNNs 15‐20 . Benefit from the development of DCNNs, continuous optimization of object detection algorithms in natural images, and the release of open‐source medical image datasets, the studies on object detection in medical images have made significant progress.…”

“…Since 2012, when AlexNet 13 won the 2012 ILSVRC competition, 14 numerous important breakthroughs in computer vision have been achieved using DCNNs. [15][16][17][18][19][20] Benefit from the development of DCNNs, continuous optimization of object detection algorithms in natural images, and the release of open-source medical image datasets, the studies on object detection in medical images have made significant progress. According to the different dimensions of the medical data used in them, these studies can be divided into two-dimensional (2D) detection and three-dimensional (3D) detection.…”

SLNL: A novel method for gene selection and phenotype classification

“…The sample reweighting process is a typical strategy against the high noise problem 20,21 . The sample weights are generally calculated according to training loss.…”

SPLSN: An efficient tool for survival analysis and biomarker selection

“…28,29 The sample reweighting process is a typical strategy against the robust learning problem. 30,31 The sample weights are normally calculated according to training loss. However, there are two contradictory viewpoints in the method of training loss: one is to rank samples according to the greater values of training loss because they tend to be complex and more uncertain locating at the classification boundary, for example, AdaBoost, 32 and focal loss 33 ; Another method is to select samples based on small training loss as simple samples like self-paced learning (SPL) 34 along with its variants.…”