update performance chart (6e6f1e8e) · Commits · 钟慕尧 / deepchem

README.md

+58 −20

Original line number	Diff line number	Diff line
		@@ -215,36 +215,43 @@ Index splitting
		\|-----------\|--------------------\|-------------------\|-------------------\|
		\|tox21 \|logistic regression \|0.903 \|0.705 \|
		\| \|Random Forest \|0.999 \|0.733 \|
		\| \|XGBoost \|0.891 \|0.753 \|
		\| \|IRV \|0.811 \|0.767 \|
		\| \|Multitask network \|0.856 \|0.763 \|
		\| \|robust MT-NN \|0.857 \|0.767 \|
		\| \|graph convolution \|0.872 \|0.798 \|
		\|muv \|logistic regression \|0.963 \|0.766 \|
		\| \|XGBoost \|0.895 \|0.714 \|
		\| \|Multitask network \|0.904 \|0.764 \|
		\| \|robust MT-NN \|0.934 \|0.781 \|
		\| \|graph convolution \|0.840 \|0.823 \|
		\|pcba \|logistic regression \|0.809 \|0.776 \|
		\| \|XGBoost \|0.931 \|0.847 \|
		\| \|Multitask network \|0.826 \|0.802 \|
		\| \|robust MT-NN \|0.809 \|0.783 \|
		\| \|graph convolution \|0.876 \|0.852 \|
		\|sider \|logistic regression \|0.933 \|0.620 \|
		\| \|Random Forest \|0.999 \|0.670 \|
		\| \|XGBoost \|0.829 \|0.639 \|
		\| \|IRV \|0.649 \|0.642 \|
		\| \|Multitask network \|0.775 \|0.634 \|
		\| \|robust MT-NN \|0.803 \|0.632 \|
		\| \|graph convolution \|0.708 \|0.594 \|
		\|toxcast \|logistic regression \|0.721 \|0.575 \|
		\| \|XGBoost \|0.738 \|0.621 \|
		\| \|Multitask network \|0.830 \|0.678 \|
		\| \|robust MT-NN \|0.825 \|0.680 \|
		\| \|graph convolution \|0.821 \|0.720 \|
		\|clintox \|logistic regression \|0.967 \|0.676 \|
		\| \|Random Forest \|0.995 \|0.776 \|
		\| \|XGBoost \|0.879 \|0.890 \|
		\| \|IRV \|0.763 \|0.814 \|
		\| \|Multitask network \|0.934 \|0.830 \|
		\| \|robust MT-NN \|0.949 \|0.827 \|
		\| \|graph convolution \|0.946 \|0.860 \|
		\|hiv \|logistic regression \|0.864 \|0.739 \|
		\| \|Random Forest \|0.999 \|0.720 \|
		\| \|XGBoost \|0.917 \|0.745 \|
		\| \|IRV \|0.841 \|0.724 \|
		\| \|Multitask network \|0.761 \|0.652 \|
		\| \|robust MT-NN \|0.780 \|0.708 \|
		@@ -256,11 +263,13 @@ Random splitting
		\|-----------\|--------------------\|-------------------\|-------------------\|
		\|tox21 \|logistic regression \|0.902 \|0.715 \|
		\| \|Random Forest \|0.999 \|0.764 \|
		\| \|XGBoost \|0.874 \|0.773 \|
		\| \|IRV \|0.808 \|0.767 \|
		\| \|Multitask network \|0.844 \|0.795 \|
		\| \|robust MT-NN \|0.855 \|0.773 \|
		\| \|graph convolution \|0.865 \|0.827 \|
		\|muv \|logistic regression \|0.957 \|0.719 \|
		\| \|XGBoost \|0.874 \|0.696 \|
		\| \|Multitask network \|0.902 \|0.734 \|
		\| \|robust MT-NN \|0.933 \|0.732 \|
		\| \|graph convolution \|0.860 \|0.730 \|
		@@ -270,22 +279,26 @@ Random splitting
		\| \|graph convolution \|0.872 \|0.844 \|
		\|sider \|logistic regression \|0.929 \|0.656 \|
		\| \|Random Forest \|0.999 \|0.665 \|
		\| \|XGBoost \|0.824 \|0.635 \|
		\| \|IRV \|0.648 \|0.596 \|
		\| \|Multitask network \|0.777 \|0.655 \|
		\| \|robust MT-NN \|0.804 \|0.630 \|
		\| \|graph convolution \|0.705 \|0.618 \|
		\|toxcast \|logistic regression \|0.725 \|0.586 \|
		\| \|XGBoost \|0.738 \|0.633 \|
		\| \|Multitask network \|0.836 \|0.684 \|
		\| \|robust MT-NN \|0.822 \|0.681 \|
		\| \|graph convolution \|0.820 \|0.717 \|
		\|clintox \|logistic regression \|0.972 \|0.725 \|
		\| \|Random Forest \|0.997 \|0.670 \|
		\| \|XGBoost \|0.886 \|0.731 \|
		\| \|IRV \|0.809 \|0.846 \|
		\| \|Multitask network \|0.951 \|0.834 \|
		\| \|robust MT-NN \|0.959 \|0.830 \|
		\| \|graph convolution \|0.975 \|0.876 \|
		\|hiv \|logistic regression \|0.860 \|0.806 \|
		\| \|Random Forest \|0.999 \|0.850 \|
		\| \|XGBoost \|0.933 \|0.841 \|
		\| \|IRV \|0.839 \|0.809 \|
		\| \|Multitask network \|0.742 \|0.715 \|
		\| \|robust MT-NN \|0.753 \|0.727 \|
		@@ -297,11 +310,13 @@ Scaffold splitting
		\|-----------\|--------------------\|-------------------\|-------------------\|
		\|tox21 \|logistic regression \|0.900 \|0.650 \|
		\| \|Random Forest \|0.999 \|0.629 \|
		\| \|XGBoost \|0.881 \|0.703 \|
		\| \|IRV \|0.823 \|0.708 \|
		\| \|Multitask network \|0.863 \|0.703 \|
		\| \|robust MT-NN \|0.861 \|0.710 \|
		\| \|graph convolution \|0.885 \|0.732 \|
		\|muv \|logistic regression \|0.947 \|0.767 \|
		\| \|XGBoost \|0.875 \|0.705 \|
		\| \|Multitask network \|0.899 \|0.762 \|
		\| \|robust MT-NN \|0.944 \|0.726 \|
		\| \|graph convolution \|0.872 \|0.795 \|
		@@ -311,22 +326,26 @@ Scaffold splitting
		\| \|graph convolution \|0.874 \|0.817 \|
		\|sider \|logistic regression \|0.926 \|0.592 \|
		\| \|Random Forest \|0.999 \|0.619 \|
		\| \|XGBoost \|0.796 \|0.560 \|
		\| \|IRV \|0.639 \|0.599 \|
		\| \|Multitask network \|0.776 \|0.557 \|
		\| \|robust MT-NN \|0.797 \|0.560 \|
		\| \|graph convolution \|0.722 \|0.583 \|
		\|toxcast \|logistic regression \|0.716 \|0.492 \|
		\| \|XGBoost \|0.741 \|0.587 \|
		\| \|Multitask network \|0.828 \|0.617 \|
		\| \|robust MT-NN \|0.830 \|0.614 \|
		\| \|graph convolution \|0.832 \|0.638 \|
		\|clintox \|logistic regression \|0.960 \|0.803 \|
		\| \|Random Forest \|0.993 \|0.735 \|
		\| \|XGBoost \|0.873 \|0.850 \|
		\| \|IRV \|0.793 \|0.718 \|
		\| \|Multitask network \|0.947 \|0.862 \|
		\| \|robust MT-NN \|0.953 \|0.890 \|
		\| \|graph convolution \|0.957 \|0.823 \|
		\|hiv \|logistic regression \|0.858 \|0.798 \|
		\| \|Random Forest \|0.946 \|0.562 \|
		\| \|XGBoost \|0.927 \|0.830 \|
		\| \|IRV \|0.847 \|0.811 \|
		\| \|Multitask network \|0.775 \|0.765 \|
		\| \|robust MT-NN \|0.785 \|0.748 \|
		@@ -337,27 +356,36 @@ Scaffold splitting
		\|Dataset \|Model \|Splitting \|Train score/R2\|Valid score/R2\|
		\|----------------\|--------------------\|------------\|--------------\|--------------\|
		\|delaney \|Random Forest \|Index \|0.953 \|0.626 \|
		\| \|XGBoost \|Index \|0.898 \|0.664 \|
		\| \|NN regression \|Index \|0.868 \|0.578 \|
		\| \|graphconv regression\|Index \|0.967 \|0.790 \|
		\| \|Random Forest \|Random \|0.951 \|0.684 \|
		\| \|XGBoost \|Random \|0.927 \|0.727 \|
		\| \|NN regression \|Random \|0.865 \|0.574 \|
		\| \|graphconv regression\|Random \|0.964 \|0.782 \|
		\| \|Random Forest \|Scaffold \|0.953 \|0.284 \|
		\| \|XGBoost \|Scaffold \|0.890 \|0.316 \|
		\| \|NN regression \|Scaffold \|0.866 \|0.342 \|
		\| \|graphconv regression\|Scaffold \|0.967 \|0.606 \|
		\|sampl \|Random Forest \|Index \|0.968 \|0.736 \|
		\| \|XGBoost \|Index \|0.884 \|0.784 \|
		\| \|NN regression \|Index \|0.917 \|0.764 \|
		\| \|graphconv regression\|Index \|0.982 \|0.864 \|
		\| \|Random Forest \|Random \|0.967 \|0.752 \|
		\| \|XGBoost \|Random \|0.906 \|0.745 \|
		\| \|NN regression \|Random \|0.908 \|0.830 \|
		\| \|graphconv regression\|Random \|0.987 \|0.868 \|
		\| \|Random Forest \|Scaffold \|0.966 \|0.473 \|
		\| \|XGBoost \|Scaffold \|0.918 \|0.439 \|
		\| \|NN regression \|Scaffold \|0.891 \|0.217 \|
		\| \|graphconv regression\|Scaffold \|0.985 \|0.666 \|
		\|nci \|NN regression \|Index \|0.171 \|0.062 \|
		\|nci \|XGBoost \|Index \|0.441 \|0.066 \|
		\| \|NN regression \|Index \|0.171 \|0.062 \|
		\| \|graphconv regression\|Index \|0.123 \|0.048 \|
		\| \|XGBoost \|Random \|0.409 \|0.106 \|
		\| \|NN regression \|Random \|0.168 \|0.085 \|
		\| \|graphconv regression\|Random \|0.117 \|0.076 \|
		\| \|XGBoost \|Scaffold \|0.445 \|0.046 \|
		\| \|NN regression \|Scaffold \|0.180 \|0.052 \|
		\| \|graphconv regression\|Scaffold \|0.131 \|0.046 \|
		\|pdbbind(core) \|Random Forest \|Random \|0.969 \|0.445 \|
		@@ -418,36 +446,43 @@ Time needed for benchmark test(~20h in total)
		\|Dataset \|Model \|Time(loading)/s \|Time(running)/s\|
		\|----------------\|--------------------\|----------------\|---------------\|
		\|tox21 \|logistic regression \|30 \|60 \|
		\| \|XGBoost \|30 \|1500 \|
		\| \|Multitask network \|30 \|60 \|
		\| \|robust MT-NN \|30 \|90 \|
		\| \|random forest \|30 \|6000 \|
		\| \|IRV \|30 \|650 \|
		\| \|graph convolution \|40 \|160 \|
		\|muv \|logistic regression \|600 \|450 \|
		\| \|XGBoost \|600 \|3492 \|
		\| \|Multitask network \|600 \|400 \|
		\| \|robust MT-NN \|600 \|550 \|
		\| \|graph convolution \|800 \|1800 \|
		\|pcba \|logistic regression \|1800 \|10000 \|
		\| \|XGBoost \|1800 \|470521 \|
		\| \|Multitask network \|1800 \|9000 \|
		\| \|robust MT-NN \|1800 \|14000 \|
		\| \|graph convolution \|2200 \|14000 \|
		\|sider \|logistic regression \|15 \|80 \|
		\| \|XGBoost \|15 \|660 \|
		\| \|Multitask network \|15 \|75 \|
		\| \|robust MT-NN \|15 \|150 \|
		\| \|random forest \|15 \|2200 \|
		\| \|IRV \|15 \|150 \|
		\| \|graph convolution \|20 \|50 \|
		\|toxcast \|logistic regression \|80 \|2600 \|
		\| \|XGBoost \|80 \|30000 \|
		\| \|Multitask network \|80 \|2300 \|
		\| \|robust MT-NN \|80 \|4000 \|
		\| \|graph convolution \|80 \|900 \|
		\|clintox \|logistic regression \|15 \|10 \|
		\| \|XGBoost \|15 \|33 \|
		\| \|Multitask network \|15 \|20 \|
		\| \|robust MT-NN \|15 \|30 \|
		\| \|random forest \|15 \|200 \|
		\| \|IRV \|15 \|10 \|
		\| \|graph convolution \|20 \|130 \|
		\|hiv \|logistic regression \|180 \|40 \|
		\| \|XGBoost \|180 \|1062 \|
		\| \|Multitask network \|180 \|350 \|
		\| \|robust MT-NN \|180 \|450 \|
		\| \|random forest \|180 \|2800 \|
		@@ -456,11 +491,14 @@ Time needed for benchmark test(~20h in total)
		\|delaney \|MT-NN regression \|10 \|40 \|
		\| \|graphconv regression\|10 \|40 \|
		\| \|random forest \|10 \|30 \|
		\| \|XGBoost \|10 \|51 \|
		\|sampl \|MT-NN regression \|10 \|30 \|
		\| \|graphconv regression\|10 \|40 \|
		\| \|random forest \|10 \|20 \|
		\| \|XGBoost \|10 \|18 \|
		\|nci \|MT-NN regression \|400 \|1200 \|
		\| \|graphconv regression\|400 \|2500 \|
		\| \|XGBoost \|400 \|28096 \|
		\|pdbbind(core) \|MT-NN regression \|0(featurized) \|30 \|
		\|pdbbind(refined)\|MT-NN regression \|0(featurized) \|40 \|
		\|pdbbind(full) \|MT-NN regression \|0(featurized) \|60 \|

Admin message