fixes and improvements

main.bib

@@ -2214,10 +2214,11 @@ Based on {WST} and {HR} data from the wearable device, the algorithms demonstrat
 	file = {PDF:/home/alex/Zotero/storage/SQCGXH4T/Albertson and Zinaman - 1987 - The prediction of ovulation and monitoring of the fertile period.pdf:application/pdf},
 }
 
-@article{owen_physiology_nodate,
+@article{owen_physiology_1975,
 	title = {Physiology of the menstrual cycle},
 	abstract = {Modern techniques of bioassay have permitted correlation of hormonal secretion with genital tissue changes during the normal menstrual cycle. During the follicular phase, estrogen secretion rises while other hormone levels are low. At ovulation luteinizing hormone and follicle-stimulating hormone surges are associated with falling estrogen levels. Secretions of progesterone and estrogen again are characteristic of the lutea! phase ending with menstruation. Gonadotrophin-releasing hormones are detectable just before the luteinizing hormone and follicle-stimulating hormone surges. Basal body temperature rises with ovulation and is still the most reliable clinical indicator, although ferning and spinnbarkeit (when present) are also quite helpful. Vaginal smears are probably less useful except in the hands of experienced observers. Am. J. Clin. Nutr. 28: 333-338, 1975.},
 	author = {Owen, A},
+	date = {1975},
 	langid = {english},
 	file = {PDF:/home/alex/Zotero/storage/J9ITWN5R/Owen - Physiology of the menstrual cycle.pdf:application/pdf},
 }
@@ -2558,3 +2559,78 @@ Conclusions Motivations for fertility app use are varied, overlap and change ove
 	langid = {english},
 	file = {PDF:/home/alex/Zotero/storage/JCQLD5GG/Lecun - Gradient-Based Learning Applied to Document Recognition.pdf:application/pdf},
 }
+
+@article{smoley_natural_nodate,
+	title = {Natural Family Planning},
+	author = {Smoley, Brian A},
+	langid = {english},
+	file = {PDF:/home/alex/Zotero/storage/WGENM9D3/Smoley - Natural Family Planning.pdf:application/pdf},
+}
+
+@article{elman_finding_nodate,
+	title = {Finding Structure in Time},
+	author = {Elman, Jeffrey L},
+	langid = {english},
+	file = {PDF:/home/alex/Zotero/storage/EDNNYH7G/Elman - Finding Structure in Time.pdf:application/pdf},
+}
+
+@misc{pascanu_difficulty_2013,
+	title = {On the difficulty of training Recurrent Neural Networks},
+	url = {http://arxiv.org/abs/1211.5063},
+	doi = {10.48550/arXiv.1211.5063},
+	abstract = {There are two widely known issues with properly training Recurrent Neural Networks, the vanishing and the exploding gradient problems detailed in Bengio et al. (1994). In this paper we attempt to improve the understanding of the underlying issues by exploring these problems from an analytical, a geometric and a dynamical systems perspective. Our analysis is used to justify a simple yet effective solution. We propose a gradient norm clipping strategy to deal with exploding gradients and a soft constraint for the vanishing gradients problem. We validate empirically our hypothesis and proposed solutions in the experimental section.},
+	number = {{arXiv}:1211.5063},
+	publisher = {{arXiv}},
+	author = {Pascanu, Razvan and Mikolov, Tomas and Bengio, Yoshua},
+	urldate = {2025-09-08},
+	date = {2013-02-16},
+	eprinttype = {arxiv},
+	eprint = {1211.5063 [cs]},
+	keywords = {Computer Science - Machine Learning},
+	file = {Full Text PDF:/home/alex/Zotero/storage/DSVXLCYM/Pascanu et al. - 2013 - On the difficulty of training Recurrent Neural Networks.pdf:application/pdf;Snapshot:/home/alex/Zotero/storage/95QFYD7E/1211.html:text/html},
+}
+
+@article{tsukiyama_lstm-phv_2021,
+	title = {{LSTM}-{PHV}: prediction of human-virus protein–protein interactions by {LSTM} with word2vec},
+	volume = {22},
+	rights = {https://creativecommons.org/licenses/by-nc/4.0/},
+	issn = {1467-5463, 1477-4054},
+	url = {https://academic.oup.com/bib/article/doi/10.1093/bib/bbab228/6308200},
+	doi = {10.1093/bib/bbab228},
+	shorttitle = {{LSTM}-{PHV}},
+	abstract = {Viral infection involves a large number of protein–protein interactions ({PPIs}) between human and virus. The {PPIs} range from the initial binding of viral coat proteins to host membrane receptors to the hijacking of host transcription machinery. However, few interspecies {PPIs} have been identified, because experimental methods including mass spectrometry are time-consuming and expensive, and molecular dynamic simulation is limited only to the proteins whose 3D structures are solved. Sequence-based machine learning methods are expected to overcome these problems. We have first developed the {LSTM} model with word2vec to predict {PPIs} between human and virus, named {LSTM}-{PHV}, by using amino acid sequences alone. The {LSTM}-{PHV} effectively learnt the training data with a highly imbalanced ratio of positive to negative samples and achieved {AUCs} of 0.976 and 0.973 and accuracies of 0.984 and 0.985 on the training and independent datasets, respectively. In predicting {PPIs} between human and unknown or new virus, the {LSTM}-{PHV} learned greatly outperformed the existing state-of-the-art {PPI} predictors. Interestingly, learning of only sequence contexts as words is sufficient for {PPI} prediction. Use of uniform manifold approximation and projection demonstrated that the {LSTM}-{PHV} clearly distinguished the positive {PPI} samples from the negative ones. We presented the {LSTM}-{PHV} online web server and support data that are freely available at http://kurata35.bio.kyutech.ac.jp/{LSTM}-{PHV}.},
+	pages = {bbab228},
+	number = {6},
+	journaltitle = {Briefings in Bioinformatics},
+	author = {Tsukiyama, Sho and Hasan, Md Mehedi and Fujii, Satoshi and Kurata, Hiroyuki},
+	urldate = {2025-09-08},
+	date = {2021-11-05},
+	langid = {english},
+	file = {PDF:/home/alex/Zotero/storage/JBK85458/Tsukiyama et al. - 2021 - LSTM-PHV prediction of human-virus protein–protein interactions by LSTM with word2vec.pdf:application/pdf},
+}
+
+@article{min_deep_2016,
+	title = {Deep learning in bioinformatics},
+	issn = {1467-5463, 1477-4054},
+	url = {https://academic.oup.com/bib/article-lookup/doi/10.1093/bib/bbw068},
+	doi = {10.1093/bib/bbw068},
+	abstract = {In the era of big data, transformation of biomedical big data into valuable knowledge has been one of the most important challenges in bioinformatics. Deep learning has advanced rapidly since the early 2000s and now demonstrates state-of-theart performance in various fields. Accordingly, application of deep learning in bioinformatics to gain insight from data has been emphasized in both academia and industry. Here, we review deep learning in bioinformatics, presenting examples of current research. To provide a useful and comprehensive perspective, we categorize research both by the bioinformatics domain (i.e. omics, biomedical imaging, biomedical signal processing) and deep learning architecture (i.e. deep neural networks, convolutional neural networks, recurrent neural networks, emergent architectures) and present brief descriptions of each study. Additionally, we discuss theoretical and practical issues of deep learning in bioinformatics and suggest future research directions. We believe that this review will provide valuable insights and serve as a starting point for researchers to apply deep learning approaches in their bioinformatics studies.},
+	pages = {bbw068},
+	journaltitle = {Brief Bioinform},
+	author = {Min, Seonwoo and Lee, Byunghan and Yoon, Sungroh},
+	urldate = {2025-09-08},
+	date = {2016-07-29},
+	langid = {english},
+	file = {PDF:/home/alex/Zotero/storage/CLI454YK/Min et al. - 2016 - Deep learning in bioinformatics.pdf:application/pdf},
+}
+
+@incollection{lecun_convolutional_1998,
+	title = {Convolutional networks for images, speech, and time series},
+	url = {https://hal.science/hal-05083427},
+	booktitle = {The handbook of brain theory and neural networks},
+	author = {Lecun, Yann and Bengio, Yoshua},
+	urldate = {2025-09-08},
+	date = {1998-10},
+	doi = {10.5555/303568.303704},
+	file = {Full Text PDF:/home/alex/Zotero/storage/7VFH99SR/Lecun and Bengio - 1998 - Convolutional networks for images, speech, and time series.pdf:application/pdf},
+}