The inherent heterogeneity of cancer contributes to highly variable responses to any anticancer treatments. This underscores the need to first identify precise biomarkers through complex multi-omics datasets that are now available. Although much research has focused on this aspect, identifying biomarkers associated with distinct drug responders still remains a major challenge. Here, we develop MOMLIN, a multi-modal and -omics machine learning integration framework, to enhance drug-response prediction. MOMLIN jointly utilizes sparse correlation algorithms and class-specific feature selection algorithms, which identifies multi-modal and -omics-associated interpretable components. MOMLIN was applied to 147 patients\' breast cancer datasets (clinical, mutation, gene expression, tumor microenvironment cells and molecular pathways) to analyze drug-response class predictions for non-responders and variable responders. Notably, MOMLIN achieves an average AUC of 0.989, which is at least 10% greater when compared with current state-of-the-art (data integration analysis for biomarker discovery using latent components, multi-omics factor analysis, sparse canonical correlation analysis). Moreover, MOMLIN not only detects known individual biomarkers such as genes at mutation/expression level, most importantly, it correlates multi-modal and -omics network biomarkers for each response class. For example, an interaction between ER-negative-HMCN1-COL5A1 mutations-FBXO2-CSF3R expression-CD8 emerge as a multimodal biomarker for responders, potentially affecting antimicrobial peptides and FLT3 signaling pathways. In contrast, for resistance cases, a distinct combination of lymph node-TP53 mutation-PON3-ENSG00000261116 lncRNA expression-HLA-E-T-cell exclusions emerged as multimodal biomarkers, possibly impacting neurotransmitter release cycle pathway. MOMLIN, therefore, is expected advance precision medicine, such as to detect context-specific multi-omics network biomarkers and better predict drug-response classifications.

Conventional breeding techniques for crop improvement have reached their full potential, and hence, alternative routes are required to ensure a sustained genetic gain in lentils. Although high-throughput omics technologies have been effectively employed in major crops, less-studied crops such as lentils have primarily relied on conventional breeding. Application of genomics and transcriptomics in lentils has resulted in linkage maps and identification of QTLs and candidate genes related to agronomically relevant traits and biotic and abiotic stress tolerance. Next-generation sequencing (NGS) complemented with high-throughput phenotyping (HTP) technologies is shown to provide new opportunities to identify genomic regions and marker-trait associations to increase lentil breeding efficiency. Recent introduction of image-based phenotyping has facilitated to discern lentil responses undergoing biotic and abiotic stresses. In lentil, proteomics has been performed using conventional methods such as 2-D gel electrophoresis, leading to the identification of seed-specific proteome. Metabolomic studies have led to identifying key metabolites that help differentiate genotypic responses to drought and salinity stresses. Independent analysis of differentially expressed genes from publicly available transcriptomic studies in lentils identified 329 common transcripts between heat and biotic stresses. Similarly, 19 metabolites were common across legumes, while 31 were common in genotypes exposed to drought and salinity stress. These common but differentially expressed genes/proteins/metabolites provide the starting point for developing high-yielding multi-stress-tolerant lentils. Finally, the review summarizes the current findings from omic studies in lentils and provides directions for integrating these findings into a systems approach to increase lentil productivity and enhance resilience to biotic and abiotic stresses under changing climate.