Introduction: Major depressive disorder (MDD) is a mental disorder characterized by alterations in mood, cognition, neurovegetative functions, and psychomotor activity. Millions of people worldwide suffer from this disease. There is no diagnosis based on laboratory tests for major depression. Even though there are varieties of treatments for MDD, antidepressants (ADs) are often used to treat the patients. There is a wide range of different responses to AD drugs. Treatment-resistant depression is a significant challenge in the treatment of this disease. This research aims to review our current knowledge of MDD and show the shortcomings in diagnosing and treating this disease. These gaps display the need for molecular studies to find new biomarkers related to this disease. 
Methods: This review uses two search strategies: A literature search using keywords (major depressive disorder or MDD) and articles on each study topic. Animal experiments, pediatric MDD, and postpartum depression are excluded. For parts requiring more study, specific keywords were used. 
Results: Biological approaches can help with a better understanding of the MDD pathogenesis mechanism, which is needed for diagnosis, treatment, and prediction of treatment response.
Conclusion: Although various treatments and diagnostic procedures exist for MDD, they are insufficient, and more investigations and research are needed. Finding a specific and sensitive panel of biomarkers is more helpful for accelerating the clinical development of new diagnoses and therapeutics for MDD.

Introduction: A major challenge today is personalizing the treatment for patients with major depressive disorder (MDD) to make it more efficient. To address this issue, we have proposed a novel approach based on machine learning (ML) models that utilize neural activity flow prior to treatment with selective serotonin reuptake inhibitor (SSRI) medication. 
Methods: The electroencephalogram signals of 30 patients were used to calculate the neural activity flow of each patient using the direct directed transfer function (dDTF). Then, based on the area under the curve (AUC) values, 30 important connections were identified for the delta, theta, alpha, beta, and gamma bands. To select the most critical neural activity flow, these neural activity flows were combined, and forward features, mRMR, and ReliefF methods were applied. Support vector machines (SVMs), decision tree, and random forest models are trained using selected neural activity flows. 
Results: Results showed that most connections originated from F8, Pz, T5, and P4, mainly from the frontal and parietal lobes. In addition, the SVM model showed 98% accuracy in classification using forward feature selection, where most of the neural activity flows were selected from alpha and beta. Finally, results indicate that patients who responded to treatment differed in their patterns of frontoparietal neural activity flows, implying that the frontoparietal network (FPN) is primarily involved in treatment response at alpha and beta frequencies.
Conclusion: Therefore, the proposed method can accurately detect responders in MDD patients. It can reduce costs for both patients and medical facilities.